CN113555132A

Movatterモバイル変換

Info

Publication number: CN113555132A
Application number: CN202010330890.8A
Authority: CN
Inventors: 张慧; 许培达; 李靖; 马闪闪
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2020-04-24
Filing date: 2020-04-24
Publication date: 2021-10-26
Anticipated expiration: 2040-04-24
Also published as: CN113555132B; WO2021213165A1

Abstract

Translated fromChinese

本申请实施例公开了一种多源数据处理方法、电子设备和计算机可读存储介质，方法包括：获取第一电子设备采集的第一生理数据和第二电子设备采集的第二生理数据；确定相似度满足预设条件的第一目标数据片段和第二目标数据片段，该第一目标数据片段是从第一生理数据中截取的预设时间长度的信号片段，该第二目标数据片段是从第二生理数据中截取的预设时间长度的信号片段；根据第一目标数据片段对应的时间戳信息和第二目标数据片段对应的时间戳信息，确定第一电子设备和第二电子设备之间的时间偏差；根据时间偏差，对第一生理数据和第二生理数据进行数据对齐操作。本申请实施例不用预先记录电子设备之间的时间偏差，也能将多源数据进行对齐。

The embodiments of the present application disclose a multi-source data processing method, an electronic device, and a computer-readable storage medium. The method includes: acquiring first physiological data collected by a first electronic device and second physiological data collected by a second electronic device; determining The first target data segment and the second target data segment whose similarity satisfies the preset condition, the first target data segment is a signal segment of a preset time length intercepted from the first physiological data, and the second target data segment is from the first target data segment. A signal segment of a preset time length intercepted from the second physiological data; according to the time stamp information corresponding to the first target data segment and the time stamp information corresponding to the second target data segment, determine the distance between the first electronic device and the second electronic device time deviation; according to the time deviation, perform a data alignment operation on the first physiological data and the second physiological data. This embodiment of the present application can also align multi-source data without pre-recording the time offset between electronic devices.

Description

Translated fromChinese

多源数据处理方法、电子设备和计算机可读存储介质Multi-source data processing method, electronic device and computer-readable storage medium

技术领域technical field

本申请涉及数据处理领域，尤其涉及一种多源数据处理方法、电子设备和计算机可读存储介质。The present application relates to the field of data processing, and in particular, to a multi-source data processing method, an electronic device and a computer-readable storage medium.

背景技术Background technique

多源数据是指存在多个数据源的数据，即同一个数据对象存在多个数据源。例如，来源于多个不同网络设备的日志数据，来源于多个健康监测设备的同一个人的生理数据。Multi-source data refers to data with multiple data sources, that is, there are multiple data sources for the same data object. For example, log data from multiple different network devices, and physiological data from the same person from multiple health monitoring devices.

一般情况下，通过数据时间戳表征数据产生时间，而数据的时间戳是跟设备时间是保持一致的。但是，不同电子设备的时钟经常会出现偏差，即同一个时刻，不同电子设备上的时间会存在偏差。例如，同一个时刻，手机和电脑的时钟会存在几秒到几十秒的偏差。因此，在对多源数据进行数据融合之前，一般需要根据不同电子设备之间的时间偏差进行多源数据对齐，然后再进行数据融合。In general, the data generation time is represented by the data timestamp, and the data timestamp is consistent with the device time. However, the clocks of different electronic devices often deviate, that is, at the same moment, the time on different electronic devices deviates. For example, at the same moment, the clocks of mobile phones and computers will have a deviation of several seconds to tens of seconds. Therefore, before performing data fusion on multi-source data, it is generally necessary to align multi-source data according to the time deviation between different electronic devices, and then perform data fusion.

目前，多源数据对齐需要先记录两个电子设备的时间差，再根据预先记录的时间差进行数据对齐。例如，主站和各个子站需要预先进行网络对时，记录子站和主站之间的时间差。对于没有预先记录时间差的数据无法进行对齐，另外，电子设备之间的时间差并不是恒定不变的，也会随之时间的变化而变化，故需要不断地更新预先记录的时间差。Currently, multi-source data alignment needs to record the time difference between two electronic devices first, and then perform data alignment according to the pre-recorded time difference. For example, the master station and each slave station need to perform network time synchronization in advance, and record the time difference between the slave station and the master station. Data without pre-recorded time difference cannot be aligned. In addition, the time difference between electronic devices is not constant and changes with time, so it is necessary to continuously update the pre-recorded time difference.

发明内容SUMMARY OF THE INVENTION

本申请提供一种多源数据处理方法、电子设备和计算机可读存储介质，以解决现有多源数据对齐方案中需要预先记录设备间的时间差才能进行数据对齐的问题。The present application provides a multi-source data processing method, an electronic device and a computer-readable storage medium to solve the problem that the time difference between devices needs to be pre-recorded in the existing multi-source data alignment scheme before data alignment can be performed.

第一方面，本申请实施例提供一种多源数据处理方法，该方法首先获取第一电子设备采集的第一生理数据和第二电子设备采集的第二生理数据，其中，上述第一生理数据和第二生理数据均包括用于表征数据产生时间的时间戳信息，而第一生理数据和第二生理数据是同一个生理参数在预设时间段内的数据；然后，确定相似度满足预设条件的第一目标数据片段和第二目标数据片段，该第一目标数据片段是从第一生理数据中截取的预设时间长度的信号片段，该第二目标数据片段是从第二生理数据中截取的预设时间长度的信号片段；接着，根据第一目标数据片段对应的时间戳信息和第二目标数据片段对应的时间戳信息，确定第一电子设备和第二电子设备之间的时间偏差；最后，根据时间偏差，对第一生理数据和第二生理数据进行数据对齐操作。In a first aspect, an embodiment of the present application provides a multi-source data processing method. The method first acquires first physiological data collected by a first electronic device and second physiological data collected by a second electronic device, wherein the above-mentioned first physiological data and the second physiological data both include timestamp information used to characterize the time when the data is generated, and the first physiological data and the second physiological data are data of the same physiological parameter within a preset time period; then, it is determined that the similarity satisfies the preset The first target data segment and the second target data segment of the condition, the first target data segment is a signal segment of a preset time length intercepted from the first physiological data, and the second target data segment is obtained from the second physiological data. The intercepted signal segment of the preset time length; then, according to the time stamp information corresponding to the first target data segment and the time stamp information corresponding to the second target data segment, determine the time offset between the first electronic device and the second electronic device ; Finally, according to the time offset, a data alignment operation is performed on the first physiological data and the second physiological data.

可以看出，本申请实施例提供的多源数据处理方法基于每个个体的生理学参数随时间变化的唯一性，通过从第一生理数据和第二生理数据中确定出相似度满足预设条件的第一目标数据片段和第二目标数据片段，根据这两个目标数据片段的时间戳信息得到两个电子设备之间的时间偏差，再根据时间偏差进行数据对齐，不用预先记录两个电子设备之间的时间偏差，也能将多源数据进行对齐，保证了对于时间依赖性很强的且没有预先记录设备时间偏差的数据也能正常使用。It can be seen that the multi-source data processing method provided by the embodiment of the present application is based on the uniqueness of the physiological parameters of each individual changing with time, and determines the similarity from the first physiological data and the second physiological data that satisfies the preset condition. The first target data segment and the second target data segment obtain the time offset between the two electronic devices according to the timestamp information of the two target data segments, and then perform data alignment according to the time offset, without pre-recording the difference between the two electronic devices. It can also align multi-source data, ensuring that data with strong time dependence and no pre-recorded device time deviation can also be used normally.

作为示例而非限定，上述生理参数为心率，此时，第一生理数据可以是智能手环采集的心率数据，第二生理数据可以是多导睡眠监测设备(Polysomnography，PSG)采集的心率数据。一般情况下，每个时刻同一个人的心率数据是唯一的，在不考虑采集精度和设备间时间偏差等原因，智能手环和PSG采集到的心率数据和对应的时间戳是一样的。但是，不同电子设备之间由于采集精度和设备间时间偏差等原因，采集到的心率数据和对应的时间戳可能不完全相同。虽然每个智能手环和PSG设备的采集精度和设备时间是不相同，但是可以根据心率数据的相似度来找出同一个时刻(非智能手环和PSG设备的设备时间)的心率数据，即当相似度满足预设条件时的第一目标数据片段和第二目标数据片段是同一时刻对应的心率数据。然后再根据这两个第一目标数据片段和第二目标数据片段的时间戳，得到智能手环和PSG设备的时间偏差。By way of example and not limitation, the above physiological parameter is heart rate. In this case, the first physiological data may be heart rate data collected by a smart bracelet, and the second physiological data may be heart rate data collected by polysomnography (PSG). In general, the heart rate data of the same person at each moment is unique. Regardless of the acquisition accuracy and the time deviation between devices, the heart rate data collected by the smart bracelet and the PSG is the same as the corresponding time stamp. However, the collected heart rate data and the corresponding time stamps may not be exactly the same between different electronic devices due to the acquisition accuracy and the time deviation between the devices. Although the acquisition accuracy and device time of each smart bracelet and PSG device are different, the heart rate data at the same moment (device time of non-smart bracelet and PSG device) can be found according to the similarity of heart rate data, that is, When the similarity satisfies the preset condition, the first target data segment and the second target data segment are heart rate data corresponding to the same moment. Then, according to the timestamps of the two first target data segments and the second target data segment, the time offset between the smart bracelet and the PSG device is obtained.

例如，第一目标数据片段对应的时间戳信息为10s～15s，第二目标数据片段对应的时间戳信息为12s～17s，此时，智能手环和PSG设备之间的时间偏差为2s。For example, the timestamp information corresponding to the first target data segment is 10s to 15s, and the timestamp information corresponding to the second target data segment is 12s to 17s. At this time, the time offset between the smart bracelet and the PSG device is 2s.

在第一方面的一种可能的实现方式中，确定相似度满足预设条件的第一目标数据片段和第二目标数据片段可以包括但不限于以下两种方式。In a possible implementation manner of the first aspect, determining the first target data segment and the second target data segment whose similarity satisfies a preset condition may include, but is not limited to, the following two manners.

第一种方式：The first way:

分别在第一生理数据中设置预设时间长度的第一时间滑动窗口和在第二生理数据中设置预设时间长度的第二时间滑动窗口；respectively setting a first time sliding window with a preset time length in the first physiological data and a second time sliding window with a preset time length in the second physiological data;

计算第一时间滑动窗口对应的第一数据片段和第二时间滑动窗口对应的第二数据片段之间的相似度评估指标；calculating the similarity evaluation index between the first data segment corresponding to the first time sliding window and the second data segment corresponding to the second time sliding window;

根据相似度评估指标，确定第一数据片段和第二数据片段之间的相似度是否满足预设条件；According to the similarity evaluation index, determine whether the similarity between the first data segment and the second data segment satisfies a preset condition;

若相似度满足预设条件，将第一数据片段作为第一目标数据片段，第二数据片段作为第二目标数据片段；If the similarity satisfies the preset condition, the first data segment is used as the first target data segment, and the second data segment is used as the second target data segment;

若相似度不满足预设条件，滑动其中一个时间滑动窗口后，返回计算第一时间滑动窗口对应的第一数据片段和第二时间滑动窗口对应的第二数据片段之间的相似度评估指标，根据相似度评估指标确定第一数据片段和第二数据片段之间的相似度是否满足预设条件的步骤，直到遍历完第一生理数据和第二生理数据或者找到相似度满足预设条件的数据片段为止；If the similarity does not meet the preset condition, after sliding one of the time sliding windows, return to calculate the similarity evaluation index between the first data segment corresponding to the first time sliding window and the second data segment corresponding to the second time sliding window, The step of determining whether the similarity between the first data segment and the second data segment meets the preset condition according to the similarity evaluation index, until the first physiological data and the second physiological data are traversed or data whose similarity meets the preset condition is found until the fragment;

第二种方式：The second way:

从第一生理数据中截取预设时间长度的至少一个第一数据片段，从第二生理数据中截取预设时间长度的至少一个第二数据片段；intercepting at least one first data segment of a preset time length from the first physiological data, and intercepting at least one second data segment of a preset time length from the second physiological data;

分别计算每个第一数据片段和每个第二数据片段之间的相似性评估指标；Calculate the similarity evaluation index between each first data segment and each second data segment respectively;

根据相似性评估指标，确定第一数据片段和第二数据片段之间的相似度是否满足预设条件；According to the similarity evaluation index, determine whether the similarity between the first data segment and the second data segment satisfies a preset condition;

将相似度满足预设条件对应的第一数据片段作为第一目标数据片段，对应的第二数据片段作为第二目标数据片段。The first data segment corresponding to which the similarity satisfies the preset condition is used as the first target data segment, and the corresponding second data segment is used as the second target data segment.

需要指出的是，在计算第一数据片段和第二数据片段之间的相似度评估指标时，可以先对第一数据片段和第二数据片段先进行数据预处理，例如，滤波和傅里叶变换等，再根据预处理之后的数据片段计算相似度评估指标；也可以先对第一数据片段和第二数据片段进行数据预处理，生成第一数据片段对应的第一曲线和第二数据片段对应的第二曲线，再计算第一曲线和第二曲线之间的相似度评估指标。第一曲线和第二曲线均为生理参数随着原设备的时间变化的曲线，例如，第一曲线是心率随着第一电子设备的时间变化的曲线。It should be pointed out that when calculating the similarity evaluation index between the first data segment and the second data segment, data preprocessing can be performed on the first data segment and the second data segment, for example, filtering and Fourier transform. transformation, etc., and then calculate the similarity evaluation index according to the preprocessed data segment; it is also possible to perform data preprocessing on the first data segment and the second data segment to generate the first curve and the second data segment corresponding to the first data segment. For the corresponding second curve, the similarity evaluation index between the first curve and the second curve is calculated. Both the first curve and the second curve are curves of physiological parameters changing with time of the original device, for example, the first curve is a curve of heart rate changing with time of the first electronic device.

该相似度评估指标是指用于评估设两个数据片段之间的相似性高低的指标，包括但不限于相关系数，欧氏距离、曼哈顿距离等距离度量指标中的一种或多种。The similarity evaluation index refers to an index used to evaluate the similarity between two data segments, including but not limited to correlation coefficient, one or more of distance metrics such as Euclidean distance and Manhattan distance.

进一步地，若相似度评估指标包括相关系数和距离度量指标，距离度量指标用于表征样本间距离，例如，欧氏距离和曼哈顿距离等；Further, if the similarity evaluation index includes a correlation coefficient and a distance metric index, the distance metric index is used to characterize the distance between samples, such as Euclidean distance and Manhattan distance, etc.;

此时，根据相似性度量指标，确定第一数据片段和第二数据片段之间的相似度是否满足预设条件的过程可以包括：At this time, according to the similarity measurement index, the process of determining whether the similarity between the first data segment and the second data segment satisfies a preset condition may include:

若第一数据片段和第二数据片段之间的相关系数大于第一预设阈值，且距离度量指标小于第二预设阈值，确定第一数据片段和第二数据片段之间的相似度满足预设条件；If the correlation coefficient between the first data segment and the second data segment is greater than the first preset threshold, and the distance metric is less than the second preset threshold, it is determined that the similarity between the first data segment and the second data segment satisfies the predetermined set conditions;

若第一数据片段和第二数据片段之间的相关系数小于或等于第一预设阈值，和/或距离度量指标大于或等于第二预设阈值，确定第一数据片段和第二数据片段之间的相似度不满足预设条件。If the correlation coefficient between the first data segment and the second data segment is less than or equal to the first preset threshold, and/or the distance metric is greater than or equal to the second preset threshold, determine the relationship between the first data segment and the second data segment. The similarity between them does not meet the preset conditions.

在第一方面的一种可能的实现方式中，还可以通过能不能找到相似度满足预设条件的两个目标数据片段来确定第一生理数据和第二生理数据是否来源于同一个个体。即上述方法还可以包括：若存在相似度满足预设条件的第一目标数据片段和第二目标数据片段，确定第一生理数据和第二生理数据属于同一个个体；若不存在相似度满足预设条件的第一目标数据片段和第二目标数据片段，确定第一生理数据和第二生理数据不属于同一个个体。In a possible implementation manner of the first aspect, whether the first physiological data and the second physiological data originate from the same individual may also be determined by whether two target data segments whose similarity satisfies a preset condition can be found. That is, the above method may further include: if there is a first target data segment and a second target data segment whose similarity satisfies a preset condition, determining that the first physiological data and the second physiological data belong to the same individual; The first target data segment and the second target data segment of the condition are set, and it is determined that the first physiological data and the second physiological data do not belong to the same individual.

举例来说，第一生理数据是智能手环采集的心率数据，第二生理数据是PSG设备采集的心率数据，若能找到相似度满足预设条件的两个目标数据片段，则认为智能手环和PSG设备采集的是同一个个人的心率数据。反之，认为智能手环和PSG设备采集的两个人的心率数据。For example, the first physiological data is the heart rate data collected by the smart bracelet, and the second physiological data is the heart rate data collected by the PSG device. If two target data segments whose similarity satisfies the preset condition can be found, the smart bracelet is considered to be. The heart rate data of the same individual is collected by the PSG device. On the contrary, consider the heart rate data of two people collected by the smart bracelet and the PSG device.

需要指出的是，在该实现方式中，在计算第一生理数据和第二生理数据之间的时间偏差之前，假设两个生理数据是来源于同一个个体。在不能找到相似度满足预设条件的两个目标数据片段时认为两个生理数据不是来源于同一个个体。It should be noted that, in this implementation manner, before calculating the time offset between the first physiological data and the second physiological data, it is assumed that the two physiological data originate from the same individual. When two target data segments whose similarity satisfies a preset condition cannot be found, it is considered that the two physiological data do not originate from the same individual.

在另一些实施例中，可以先确定出两个生理数据是否来源于同一个个体，若两个生理数据来源于同一个个体，再计算两个设备之间的时间偏差。In other embodiments, it may be first determined whether the two physiological data originate from the same individual, and if the two physiological data originate from the same individual, then the time offset between the two devices is calculated.

也就是说，在第一方面的一种可能的实现方式中，在确定相似度满足预设条件的第一目标数据片段和第二目标数据片段之前，上述方法可以还包括：That is, in a possible implementation manner of the first aspect, before determining the first target data segment and the second target data segment whose similarity satisfies a preset condition, the above method may further include:

计算第一生理数据和第二生理数据中重叠时间段对应的数据的相似度度量特征；calculating the similarity measure feature of the data corresponding to the overlapping time periods in the first physiological data and the second physiological data;

提取第一生理数据和第二生理数据的线性特征、非线性特征和离散型特征；extracting linear features, nonlinear features and discrete features of the first physiological data and the second physiological data;

根据相似度度量特征、线性特征、非线性特征和离散型特征进行线性回归分析，得到第一生理数据和第二生理数据的差异性评估结果；Perform linear regression analysis according to the similarity measure feature, linear feature, nonlinear feature and discrete feature to obtain the difference evaluation result between the first physiological data and the second physiological data;

若差异性评估结果小于第三预设阈值，确定第一生理数据和第二生理数据属于同一个个体；If the difference evaluation result is less than the third preset threshold, it is determined that the first physiological data and the second physiological data belong to the same individual;

若差异性评估结果大于第三预设阈值，确定第一生理数据和第二生理数据不属于同一个个体。If the difference evaluation result is greater than the third preset threshold, it is determined that the first physiological data and the second physiological data do not belong to the same individual.

在该实现方式中，不仅计算两个生理数据之间的相似度度量特征，还引入了数据的线性、非线性和离散型特征等。然后，再通过对这些特征进行线性回归分析，得到用于评估两个生理数据的差异性大小的评估结果，若差异性较大，则认为两个数据不属于同一个个体，反之，差异性较小，则认为两个数据属于同一个个体。该相似度度量特征可以包括但不限于欧氏距离等，该线性相关特征可以包括但不限于向量长度指标(vector lengthindex,VLI)和向量角度指标(vector angle index,VAI)等，该离散型特征包括但不限于数据的整体方差和均值等。In this implementation, not only the similarity measurement feature between the two physiological data is calculated, but also the linear, nonlinear and discrete features of the data are introduced. Then, by performing linear regression analysis on these features, the evaluation results for evaluating the difference between the two physiological data are obtained. If the difference is large, it is considered that the two data do not belong to the same individual. is small, the two data are considered to belong to the same individual. The similarity measure feature may include, but is not limited to, Euclidean distance, etc. The linear correlation feature may include, but is not limited to, a vector length index (VLI) and a vector angle index (VAI), etc. The discrete feature Including but not limited to the overall variance and mean of the data.

在第一方面的一种可能的实现方式中，若确定出第一生理数据和第二生理数据属于同一个个体，可以对两个生理数据进行数据融合，得到数据融合后的生理数据。也就是说，在根据时间偏差，对第一生理数据和第二生理数据进行数据对齐操作之后，方法还包括：对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据。In a possible implementation manner of the first aspect, if it is determined that the first physiological data and the second physiological data belong to the same individual, data fusion of the two physiological data may be performed to obtain physiological data after data fusion. That is, after performing a data alignment operation on the first physiological data and the second physiological data according to the time offset, the method further includes: performing data fusion on the first physiological data and the second physiological data to obtain the fused physiological data.

需要指出的是，若需要对多个生理数据进行数据对齐和数据融合操作，可以根据上述数据对齐方案，先进行两两数据对齐。再将所有生理数据进行数据对齐之后，再将多个生理数据进行数据融合，得到融合后的生理数据。It should be pointed out that, if data alignment and data fusion operations need to be performed on multiple physiological data, pairwise data alignment may be performed first according to the above data alignment scheme. After aligning all the physiological data, data fusion of multiple physiological data is performed to obtain the fused physiological data.

数据融合的过程可以是：通过数据质量比对，保留数据质量较高的数据片段；而对于一些缺少的数据段，可以使用其它生理数据的相应时间段的数据段进行多源补偿。具体地，在第一方面的一种可能的实现方式中，对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据可以包括：通过数据质量评价指标对第一生理数据和第二生理数据进行质量对比，获得相同时间段内质量较高的第三数据段；若第一生理数据和第二生理数据中的其中一个生理数据存在缺失的数据段，获得另外一个生理数据中相应时间段对应的第四数据段，按照时间顺序将第三数据段和第四数据段进行合并，得到融合后的生理数据。The process of data fusion can be as follows: through data quality comparison, data segments with higher data quality are retained; for some missing data segments, data segments corresponding to time periods of other physiological data can be used for multi-source compensation. Specifically, in a possible implementation manner of the first aspect, performing data fusion on the first physiological data and the second physiological data, and obtaining the fused physiological data may include: using a data quality evaluation index to compare the first physiological data and the second physiological data. The quality of the second physiological data is compared, and a third data segment with higher quality in the same time period is obtained; if there is a missing data segment in one of the first physiological data and the second physiological data, the other physiological data is obtained. For the fourth data segment corresponding to the corresponding time segment, the third data segment and the fourth data segment are merged in time sequence to obtain the fused physiological data.

上述数据质量评价指标可以包括但不限于数据的完整性、一致性、准确性和冗余性等。另外，也可以通过数据可用性和数据量等来评价数据质量。The above-mentioned data quality evaluation indicators may include, but are not limited to, data integrity, consistency, accuracy, and redundancy. In addition, data quality can also be evaluated by data availability and data volume.

在第一方面的一种可能的实现方式中，在得到融合后的生理数据之后，还可以生成对应的生理数据分析报告，进一步地，还可以将该生理数据分析报告显示给用户终端。也就是说，在得到融合后的生理数据之后，上述方法还可以包括：根据融合后的生理数据，生成对应的生理数据分析报告。In a possible implementation manner of the first aspect, after obtaining the fused physiological data, a corresponding physiological data analysis report may be generated, and further, the physiological data analysis report may be displayed to the user terminal. That is, after obtaining the fused physiological data, the above method may further include: generating a corresponding physiological data analysis report according to the fused physiological data.

举例来说，第一生理数据是智能手环采集的心率数据，第二生理数据是PSG设备采集的心率数据，智能手环和PSG设备采集的心率数据均传输到用户手机。用户手机可以再将智能手环和PSG设备采集的心率数据进行数据对齐后，再进行数据融合，然后根据数据融合后的心率数据生成心率数据分析报告，并将该报告显示给用户。For example, the first physiological data is the heart rate data collected by the smart bracelet, the second physiological data is the heart rate data collected by the PSG device, and the heart rate data collected by the smart bracelet and the PSG device are both transmitted to the user's mobile phone. The user's mobile phone can align the heart rate data collected by the smart bracelet and the PSG device, and then perform data fusion, and then generate a heart rate data analysis report based on the heart rate data after data fusion, and display the report to the user.

在第一方面的一种可能的实现方式中，在进行数据对齐之后，数据融合之前，还可以根据数据对齐之后的生理数据进行二次相似度匹配，再根据相似度匹配结果来选择生成一份生理数据分析报告，还是多份生理数据分析报告。也就是说，在对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据之前，上述方法还可以包括：In a possible implementation manner of the first aspect, after data alignment and before data fusion, secondary similarity matching may be performed according to the physiological data after data alignment, and then a copy of the similarity matching result may be selected and generated. Physiological data analysis report, or multiple physiological data analysis reports. That is to say, before data fusion is performed on the first physiological data and the second physiological data to obtain the fused physiological data, the above method may further include:

对数据对齐后的第一生理数据和第二生理数据进行相似度计算，得到目标相似度；Perform similarity calculation on the first physiological data and the second physiological data after data alignment to obtain the target similarity;

若目标相似度大于第四预设阈值，进入对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据的步骤；If the target similarity is greater than the fourth preset threshold, enter the step of performing data fusion on the first physiological data and the second physiological data to obtain the fused physiological data;

若目标相似度小于第四预设阈值，分别生成第一生理数据的生理数据分析报告和第二生理数据的生理分析报告。If the target similarity is less than the fourth preset threshold, a physiological data analysis report of the first physiological data and a physiological analysis report of the second physiological data are respectively generated.

在该实现方式中，对数据对齐之后的生理数据进行二次相似度匹配，可以进一步提高数据融合和所生成的数据分析报告的准确性。In this implementation manner, secondary similarity matching is performed on the physiological data after data alignment, which can further improve the accuracy of data fusion and the generated data analysis report.

在第一方面的一种可能的实现方式中，生理参数为心率、呼吸率、体温或血氧。In a possible implementation manner of the first aspect, the physiological parameter is heart rate, respiration rate, body temperature or blood oxygen.

第二方面，本申请实施例提供一种多源数据处理装置，该装置可以包括：In a second aspect, an embodiment of the present application provides a multi-source data processing apparatus, and the apparatus may include:

生理数据获取模块，用于获取第一电子设备采集的第一生理数据和第二电子设备采集的第二生理数据，第一生理数据和第二生理数据均包括用于表征数据产生时间的时间戳信息，第一生理数据和第二生理数据是同一个生理参数在预设时间段内的数据；A physiological data acquisition module, configured to acquire the first physiological data collected by the first electronic device and the second physiological data collected by the second electronic device, both the first physiological data and the second physiological data include a time stamp for characterizing the time when the data was generated information, the first physiological data and the second physiological data are data of the same physiological parameter within a preset time period;

目标数据片段确定模块，用于确定相似度满足预设条件的第一目标数据片段和第二目标数据片段，第一目标数据片段是从第一生理数据中截取的预设时间长度的信号片段，第二目标数据片段是从第二生理数据中截取的预设时间长度的信号片段；a target data segment determination module, configured to determine a first target data segment and a second target data segment whose similarity satisfies a preset condition, where the first target data segment is a signal segment of a preset time length intercepted from the first physiological data, The second target data segment is a signal segment of a preset time length intercepted from the second physiological data;

设备间时间偏差确定模块，用于根据第一目标数据片段对应的时间戳信息和第二目标数据片段对应的时间戳信息，确定第一电子设备和第二电子设备之间的时间偏差；an inter-device time deviation determination module, configured to determine the time deviation between the first electronic device and the second electronic device according to the time stamp information corresponding to the first target data segment and the time stamp information corresponding to the second target data segment;

数据对齐模块，用于根据时间偏差，对第一生理数据和第二生理数据进行数据对齐操作。The data alignment module is configured to perform a data alignment operation on the first physiological data and the second physiological data according to the time offset.

在第二方面的一种可能的实现方式中，目标数据片段确定模块具体用于：In a possible implementation manner of the second aspect, the target data segment determination module is specifically configured to:

或者，or,

在第二方面的一种可能的实现方式中，若相似度评估指标包括相关系数和距离度量指标，距离度量指标用于表征样本间距离；In a possible implementation manner of the second aspect, if the similarity evaluation index includes a correlation coefficient and a distance metric index, the distance metric index is used to represent the distance between samples;

目标数据片段确定模块具体用于：The target data segment determination module is specifically used for:

在第二方面的一种可能的实现方式中，该装置还可以包括：In a possible implementation manner of the second aspect, the apparatus may further include:

第一判断模块，用于若存在相似度满足预设条件的第一目标数据片段和第二目标数据片段，确定第一生理数据和第二生理数据属于同一个个体；若不存在相似度满足预设条件的第一目标数据片段和第二目标数据片段，确定第一生理数据和第二生理数据不属于同一个个体。The first judgment module is used to determine that the first physiological data and the second physiological data belong to the same individual if there are first target data segments and second target data segments whose similarity satisfies the preset condition; if there is no similarity satisfying the preset condition; The first target data segment and the second target data segment of the condition are set, and it is determined that the first physiological data and the second physiological data do not belong to the same individual.

第二判断模块，用于计算第一生理数据和第二生理数据中重叠时间段对应的数据的相似度度量特征；提取第一生理数据和第二生理数据的线性特征、非线性特征和离散型特征；根据相似度度量特征、线性特征、非线性特征和离散型特征进行线性回归分析，得到第一生理数据和第二生理数据的差异性评估结果；若差异性评估结果小于第三预设阈值，确定第一生理数据和第二生理数据属于同一个个体；若差异性评估结果大于第三预设阈值，确定第一生理数据和第二生理数据不属于同一个个体。The second judgment module is used to calculate the similarity measurement feature of the data corresponding to the overlapping time periods in the first physiological data and the second physiological data; extract the linear features, nonlinear features and discrete features of the first physiological data and the second physiological data feature; perform linear regression analysis according to the similarity measure feature, linear feature, nonlinear feature and discrete feature to obtain the difference evaluation result of the first physiological data and the second physiological data; if the difference evaluation result is less than the third preset threshold , it is determined that the first physiological data and the second physiological data belong to the same individual; if the difference evaluation result is greater than the third preset threshold, it is determined that the first physiological data and the second physiological data do not belong to the same individual.

在第二方面的一种可能的实现方式中，若确定出第一生理数据和第二生理数据属于同一个个体，该装置还可以包括：In a possible implementation manner of the second aspect, if it is determined that the first physiological data and the second physiological data belong to the same individual, the apparatus may further include:

数据融合模块，用于对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据。The data fusion module is used for data fusion of the first physiological data and the second physiological data to obtain the fused physiological data.

在第二方面的一种可能的实现方式中，数据融合模块具体用于：In a possible implementation manner of the second aspect, the data fusion module is specifically used for:

通过数据质量评价指标对第一生理数据和第二生理数据进行质量对比，获得相同时间段内质量较高的第三数据段；Comparing the quality of the first physiological data and the second physiological data through the data quality evaluation index to obtain a third data segment with higher quality within the same time period;

若第一生理数据和第二生理数据中的其中一个生理数据存在缺失的数据段，获得另外一个生理数据中相应时间段对应的第四数据段，If there is a missing data segment in one of the first physiological data and the second physiological data, obtain a fourth data segment corresponding to the corresponding time period in the other physiological data,

按照时间顺序将第三数据段和第四数据段进行合并，得到融合后的生理数据。The third data segment and the fourth data segment are combined in time sequence to obtain the fused physiological data.

报告生成模块，用于根据融合后的生理数据，生成对应的生理数据分析报告。The report generation module is used to generate a corresponding physiological data analysis report according to the fused physiological data.

二次相似度匹配模块，用于对数据对齐后的第一生理数据和第二生理数据进行相似度计算，得到目标相似度；若目标相似度大于第四预设阈值，进入对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据的步骤；若目标相似度小于第四预设阈值，分别生成第一生理数据的生理数据分析报告和第二生理数据的生理分析报告。The secondary similarity matching module is used to calculate the similarity between the first physiological data and the second physiological data after data alignment to obtain the target similarity; if the target similarity is greater than the fourth preset threshold, enter the first physiological data The step of data fusion with the second physiological data to obtain the fused physiological data; if the target similarity is less than the fourth preset threshold, a physiological data analysis report of the first physiological data and a physiological analysis report of the second physiological data are respectively generated.

在第二方面的一种可能的实现方式中，生理参数可以为但不限于心率、呼吸率、体温或血氧等。In a possible implementation manner of the second aspect, the physiological parameter may be, but not limited to, heart rate, respiration rate, body temperature, blood oxygen, and the like.

第三方面，本申请实施例提供一种电子设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如上述第一方面任一项所述的方法。In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, which is implemented when the processor executes the computer program The method of any one of the first aspects above.

第四方面，本申请实施例提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现如上述第一方面任一项所述的方法。In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any one of the above-mentioned first aspect is implemented. method.

第五方面，本申请实施例提供一种芯片系统，所述芯片系统包括处理器，所述处理器与存储器耦合，所述处理器执行存储器中存储的计算机程序，以实现如上述第一方面任一项所述的方法。所述芯片系统可以为单个芯片，或者多个芯片组成的芯片模组。In a fifth aspect, an embodiment of the present application provides a chip system, the chip system includes a processor, the processor is coupled to a memory, and the processor executes a computer program stored in the memory, so as to implement any of the above-mentioned first aspect. one of the methods described. The chip system may be a single chip, or a chip module composed of multiple chips.

第六方面，本申请实施例提供一种计算机程序产品，当计算机程序产品在电子设备上运行时，使得电子设备执行上述第一方面中任一项所述的方法。In a sixth aspect, an embodiment of the present application provides a computer program product that, when the computer program product runs on an electronic device, causes the electronic device to execute the method described in any one of the first aspects above.

可以理解的是，上述第二方面至第六方面的有益效果可以参见上述第一方面中的相关描述，在此不再赘述。It can be understood that, for the beneficial effects of the foregoing second aspect to the sixth aspect, reference may be made to the relevant descriptions in the foregoing first aspect, and details are not described herein again.

附图说明Description of drawings

图1为本申请实施例提供的一种可能的场景示意图；FIG. 1 is a schematic diagram of a possible scenario provided by an embodiment of the present application;

图2为本申请实施例提供的另一种可能的场景示意图；FIG. 2 is a schematic diagram of another possible scenario provided by an embodiment of the present application;

图3为本申请实施例提供的一种多源数据处理方法的一种流程示意框图；3 is a schematic block diagram of a flow of a multi-source data processing method provided by an embodiment of the present application;

图4为本申请实施例提供的相似度匹配过程的流程示意框图；4 is a schematic block diagram of the flow of a similarity matching process provided by an embodiment of the present application;

图5为本申请实施例提供的多源数据处理方法的又一种流程示意框图；FIG. 5 is another schematic flow diagram of a multi-source data processing method provided by an embodiment of the present application;

图6(a)为本申请实施例提供的S₁(t)的示意图；Fig. 6(a) is a schematic diagram of S₁ (t) provided by the embodiment of the present application;

图6(b)为本申请实施例提供的S₂(t)的示意图；FIG. 6(b) is a schematic diagram of S₂ (t) provided in the embodiment of the present application;

图7为本申请实施例提供的信号未对齐时的示意图；FIG. 7 is a schematic diagram when signals provided in an embodiment of the present application are not aligned;

图8为本申请实施例提供的信号对齐时的示意图；8 is a schematic diagram of a signal alignment provided by an embodiment of the present application;

图9为本申请实施例提供的多源数据处理方法的一种示意图FIG. 9 is a schematic diagram of a multi-source data processing method provided by an embodiment of the present application

图10为本申请实施例提供的多源数据处理装置的结构框图；10 is a structural block diagram of a multi-source data processing apparatus provided by an embodiment of the present application;

图11为本申请实施例提供的电子设备的硬件结构示意框图。FIG. 11 is a schematic block diagram of a hardware structure of an electronic device provided by an embodiment of the present application.

具体实施方式Detailed ways

以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、技术之类的具体细节，以便透彻理解本申请实施例。In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are set forth in order to provide a thorough understanding of the embodiments of the present application.

下面首先对本申请实施例可能涉及的系统架构和可能涉及的场景进行示例性说明。The following first exemplarily describes the system architecture and possible scenarios involved in the embodiments of the present application.

参见图1示出的一种可能的场景示意图，如图1所示，电子设备11和多个具备生理数据采集功能的电子设备12通信连接。电子设备11可以是但不限于手机、平板或者电脑等。而电子设备12是指具备生理数据采集功能的电子设备，该电子设备12的数量可以是任意的。生理数据可以包括但不限于人体的心率、体温、呼吸率和血氧中的一种或多种，即电子设备12可以采集心率、体温、呼吸率和血氧中的一种或多种数据。电子设备12可以是可穿戴式设备，例如，智能手环；也可以是非可穿戴式设备，例如，PSG设备。作为示例而非限定，电子设备12可以包括但不限于智能手环、PSG设备、智能手表和可穿戴衣物中的一种或多种，可穿戴衣物可以例如为设置有心率采集传感器和血氧采集传感器的背心。Referring to the schematic diagram of a possible scenario shown in FIG. 1 , as shown in FIG. 1 , theelectronic device 11 is connected in communication with a plurality ofelectronic devices 12 having the function of collecting physiological data. Theelectronic device 11 may be, but not limited to, a mobile phone, a tablet, or a computer. Theelectronic device 12 refers to an electronic device with a function of collecting physiological data, and the number of theelectronic device 12 can be arbitrary. Physiological data may include, but not limited to, one or more of human heart rate, body temperature, respiration rate, and blood oxygen, ie, theelectronic device 12 may collect one or more of heart rate, body temperature, breathing rate, and blood oxygen. Theelectronic device 12 may be a wearable device, such as a smart bracelet, or a non-wearable device, such as a PSG device. As an example and not limitation, theelectronic device 12 may include, but is not limited to, one or more of a smart bracelet, a PSG device, a smart watch, and wearable clothing. The wearable clothing may, for example, be provided with a heart rate sensor and a blood oxygen sensor. Sensor vest.

作为示例而非限定，图1中示出的电子设备11为手机，电子设备12包括智能手环和PSG设备。此时，智能手环和PSG设备具备心率采集、体温采集、呼吸率采集和血氧采集等功能，智能手环和PSG设备还可以对用户的睡眠质量进行监测等。智能手环和PSG设备采集的生理数据可以通过短距离无线通信方式传输至手机，手机接收到智能手环和PSG设备传输的生理数据，对生理数据进行相应处理。该短距离无线通信方式可以是但不限于蓝牙、低功耗蓝牙、红外和Wi-Fi点对点等。当然，在其它一些情况下，PSG设备也可以通过无线路由器将所采集的生理数据传输至手机，比如，在智能家居场景下，PSG设备和手机均与家中的无线路由器连接，PSG设备可以将采集的生理数据通过无线路由器转发给手机。也就是说，在不同应用场景下，电子设备11和电子设备12之间的通信方式可能会有所不同。By way of example and not limitation, theelectronic device 11 shown in FIG. 1 is a mobile phone, and theelectronic device 12 includes a smart bracelet and a PSG device. At this time, the smart bracelet and PSG device have functions such as heart rate collection, body temperature collection, respiration rate collection, and blood oxygen collection. The smart bracelet and PSG device can also monitor the user's sleep quality. The physiological data collected by the smart bracelet and the PSG device can be transmitted to the mobile phone through short-range wireless communication, and the mobile phone receives the physiological data transmitted by the smart bracelet and the PSG device, and processes the physiological data accordingly. The short-range wireless communication method may be, but is not limited to, Bluetooth, Bluetooth low energy, infrared, and Wi-Fi point-to-point. Of course, in other cases, the PSG device can also transmit the collected physiological data to the mobile phone through the wireless router. For example, in the smart home scenario, the PSG device and the mobile phone are both connected to the wireless router at home, and the PSG device can transfer the collected physiological data to the mobile phone. The physiological data is forwarded to the mobile phone through the wireless router. That is to say, in different application scenarios, the communication modes between theelectronic device 11 and theelectronic device 12 may be different.

智能手环和PSG设备均有各自对应的设备时间，且一般情况下智能手环和PSG设备各自的设备时间并不是完全同步的。比如，同一个时刻，智能手环上的设备时间为2020年1月1号12时00分30秒，而PSG设备上的设备时间为2020年1月1号12时00分35秒。也就是说，不同电子设备上的时间是不同步的。另外，随着时间的推移，不同电子设备之间的时间偏差也不是固定不变的。比如，当前时刻，智能手环和PSG设备之间的时间偏差是5s；由于智能手环和PSG设备上的时钟精度不一样，随着时间地不断推移，智能手环和PSG设备的时间累积偏差也不一样，在3个月后，智能手环和PSG设备之间的时间偏差变为7s。Both the smart bracelet and the PSG device have their own corresponding device times, and in general, the respective device times of the smart bracelet and the PSG device are not completely synchronized. For example, at the same moment, the device time on the smart bracelet is 12:00:30 on January 1, 2020, and the device time on the PSG device is 12:00:35 on January 1, 2020. That is, the time on different electronic devices is not synchronized. In addition, the time offset between different electronic devices is not constant over time. For example, at the current moment, the time offset between the smart bracelet and the PSG device is 5s; because the clocks on the smart bracelet and the PSG device have different precisions, as time goes on, the time deviation between the smart bracelet and the PSG device accumulates. It is also different. After 3 months, the time offset between the smart bracelet and the PSG device becomes 7s.

智能手环和PSG设备在采集生理数据时，会根据自身的设备时间为生理数据设置一个时间戳，该时间戳用于表征该生理数据的产生时间。时间戳一般是一串字符序列，用于唯一地标识某一个时刻的时间。例如，2020年1月1日14时54分28秒所对应的时间戳为1577861668。即如果智能手环在自身设备时间为2020年1月1日14时54分28秒所产生的生理数据，为该生理数据打上的时间戳为1577861668。When collecting physiological data, the smart bracelet and PSG device will set a timestamp for the physiological data according to its own device time, and the timestamp is used to represent the generation time of the physiological data. A timestamp is generally a sequence of characters used to uniquely identify the time at a certain moment. For example, the timestamp corresponding to 14:54:28 on January 1, 2020 is 1577861668. That is, if the physiological data generated by the smart bracelet at 14:54:28 on January 1, 2020, the time stamp for the physiological data is 1577861668.

由于智能手环和PSG设备的设备时间是不同步的，对于同一时刻的生理数据的时间戳是不一致的。因此，手机在接收到智能手环和PSG设备采集的生理数据时，需要先确定出智能手环和PSG设备之间的时间偏差。然后手机再根据设备之间的时间偏差，将两个设备所采集的生理数据的时间戳调整至同步，以将两个设备之间的生理数据进行数据对齐，最后可以根据数据对齐之后的生理数据进行数据融合等操作。Since the device time of the smart bracelet and the PSG device are not synchronized, the time stamps of the physiological data at the same time are inconsistent. Therefore, when the mobile phone receives the physiological data collected by the smart bracelet and the PSG device, it is necessary to first determine the time offset between the smart bracelet and the PSG device. Then, according to the time deviation between the devices, the mobile phone adjusts the time stamps of the physiological data collected by the two devices to be synchronized, so as to align the physiological data between the two devices, and finally the physiological data can be aligned according to the data. Perform data fusion and other operations.

基于个体生理数据随时间变化的唯一性，可以根据生理数据的相似度高低，从两个设备的生理数据中找出同一个时刻(该时刻不是设备时间)的数据片段，然后再根据该时刻的生理数据对应的时间戳，确定两个设备之间的时间偏差。Based on the uniqueness of individual physiological data over time, the data segments at the same time (this time is not the device time) can be found from the physiological data of the two devices according to the similarity of the physiological data, and then based on the Timestamps corresponding to physiological data to determine the time offset between the two devices.

举例来说，生理数据为心率数据，对于同一个个体来说，同一个时刻(该时刻不是设备时间)的心率数据是一样的。换句话说，如果不考虑设备之间的时间偏差和采集精度差异等因素，即假设智能手环和PSG设备的时间同步，且采集精度也是一样的，智能手环和PSG设备采集的心率数据是一样的，即此时心率数据随着原始设备(例如智能手环和PSG设备)的设备时间变化的曲线是一样的。但是，实际应用中，设备之间的时间会存在偏差，不是同步的，且采集精度也会有高低之分，所以会导致智能手环和PSG设备采集到的心率数据是不一样的，即心率数据随着原始设备的设备时间变化的曲线是不一样的。For example, the physiological data is heart rate data, and for the same individual, the heart rate data at the same moment (the moment is not the device time) are the same. In other words, if factors such as the time deviation between devices and the difference in acquisition accuracy are not considered, that is, assuming that the time of the smart bracelet and the PSG device is synchronized, and the acquisition accuracy is the same, the heart rate data collected by the smart bracelet and the PSG device is The same, that is, the curve of the heart rate data changing with the device time of the original device (such as a smart bracelet and a PSG device) is the same. However, in practical applications, the time between devices will be biased, not synchronized, and the acquisition accuracy will be different, so the heart rate data collected by the smart bracelet and the PSG device will be different, that is, the heart rate. The curve of the data as a function of the device time of the original device is not the same.

电子设备之间的时间不同步可能会导致同一时刻的心率数据所对应的时间戳不相同，例如，实际时刻为12时12分30秒，此时，智能手环上的设备时间为12时12分35秒，故在该实际时刻下的智能手环采集的心率数据对应的时间戳信息为12时12分35秒。而PSG设备上的设备时间为12时12分33秒，故在该实际时刻下的PSG设备采集的心率数据对应的时间戳信息为12时12分33秒。实际上，智能手环上12时12分35秒对应的心率数据和PSG设备上12时12分33秒对应的心率数据是同一个时刻的心率数据，但由于两个设备之间的时间偏差，导致同一个时刻的心率数据对应的时间戳是不一样的，或者说，两个设备的时间戳相同时，心率数据不是同一时刻的数据。The time synchronization between electronic devices may lead to different time stamps corresponding to heart rate data at the same time. For example, the actual time is 12:12:30. At this time, the device time on the smart bracelet is 12:12 Therefore, the time stamp information corresponding to the heart rate data collected by the smart bracelet at this actual moment is 12:12:35. The device time on the PSG device is 12:12:33, so the timestamp information corresponding to the heart rate data collected by the PSG device at this actual moment is 12:12:33. In fact, the heart rate data corresponding to 12:12:35 on the smart bracelet and the heart rate data corresponding to 12:12:33 on the PSG device are the heart rate data at the same moment, but due to the time deviation between the two devices, As a result, the time stamps corresponding to the heart rate data at the same time are different, or in other words, when the time stamps of the two devices are the same, the heart rate data are not data at the same time.

而电子设备之间的采集精度高低可能会导致即使是同一个实际时刻的心率数据，智能手环和PSG设备所采集的心率数据也不是完全相同的。虽然由于采集精度的影响，智能手环和PSG设备所采集的同一个时刻的心率数据也不是完全相同的，但是，两个设备所采集的同一个时刻的心率数据的相似度是满足一定的条件的。The acquisition accuracy between electronic devices may result in that the heart rate data collected by the smart bracelet and the PSG device are not exactly the same even if it is the heart rate data at the same actual moment. Although the heart rate data collected by the smart bracelet and the PSG device at the same time are not exactly the same due to the influence of the collection accuracy, the similarity of the heart rate data collected by the two devices at the same time meets certain conditions. of.

基于此，可以先根据两个设备所采集的心率数据的相似度高低，找到同一个实际时刻范围的心率数据片段，然后再基于上文提及的设备间的时间偏差，即根据两个数据片段的时间戳来确定出两个设备之间的时间偏差。比如，根据相似度高低，找到的两个心率数据分别为：智能手环上12时12分33秒～12时12分38秒的心率数据，以及PSG设备上12时12分35秒～12时12分40秒的心率数据。然后，可以根据这两个心率数据片段中的任意一个数据，来得到智能手环和PSG设备之间的时间偏差。具体地，智能手环上12时12分38秒的心率数据和PSG设备上12时12分40秒的心率数据是同一个实际时刻的心率数据，故可以得到智能手环和PSG设备之间的时间偏差为2s。Based on this, it is possible to first find the heart rate data segments in the same actual time range based on the similarity of the heart rate data collected by the two devices, and then based on the time deviation between the devices mentioned above, that is, according to the two data segments time stamp to determine the time offset between the two devices. For example, according to the similarity, the two heart rate data found are: the heart rate data from 12:12:33 to 12:12:38 on the smart bracelet, and the heart rate data from 12:12:35 to 12:00 on the PSG device. Heart rate data for 12 minutes and 40 seconds. Then, the time offset between the smart bracelet and the PSG device can be obtained according to any one of the two pieces of heart rate data. Specifically, the heart rate data of 12:12:38 on the smart bracelet and the heart rate data of 12:12:40 on the PSG device are the heart rate data at the same actual moment, so the relationship between the smart bracelet and the PSG device can be obtained. The time offset is 2s.

需要说明的是，如果需要确定出多个电子设备12之间的时间偏差时，可以依次按照上文提及的方式进行两两计算，直到确定出多个电子设备之间的时间偏差。比如，电子设备12包括智能手环、PSG设备和智能手表时，先确定智能手环和PSG设备之间的时间偏差，再确定智能手环或者PSG设备与智能手表之间的时间偏差，从而得到智能手环、PSG设备和智能手表三者之间的时间偏差。It should be noted that, if the time offset between multipleelectronic devices 12 needs to be determined, two-by-two calculations can be performed sequentially in the manner mentioned above until the time offset between multiple electronic devices is determined. For example, when theelectronic device 12 includes a smart bracelet, a PSG device and a smart watch, first determine the time offset between the smart bracelet and the PSG device, and then determine the time offset between the smart bracelet or the PSG device and the smart watch, thereby obtaining Time offset between smartbands, PSG devices, and smartwatches.

另外，还需要指出的是，上文所列举的时间数值和时间戳信息等仅仅是为了描述方便和计算方便，并不是对具体的时间数值和时间戳等进行限定。In addition, it should also be pointed out that the time value and time stamp information, etc. listed above are only for convenience of description and calculation, and do not limit the specific time value and time stamp.

手机依据上述原理和过程确定出智能手环和PSG设备之间的时间偏差之后，可以再根据该时间偏差将两个设备采集的生理数据进行数据对齐，以将两个生理数据的时间戳调整至同步。After the mobile phone determines the time deviation between the smart bracelet and the PSG device according to the above principles and processes, it can then align the physiological data collected by the two devices according to the time deviation, so as to adjust the time stamps of the two physiological data to Synchronize.

此外，手机从两个设备的生理数据中找相似度满足预设条件的数据片段时，可以根据是否能找到相似度满足预设条件的两个数据片段，来确定这两个设备采集的生理数据是否来源于同一个个体。具体地，当找不到相似度满足预设条件的数据片段时，则认为智能手环采集的生理数据和PSG设备采集的生理数据不是同一个人的。反之，当能找到相似度满足预设条件的数据片段，则认为智能手环采集的生理数据和PSG设备采集的生理数据是同一个人的。In addition, when the mobile phone finds data segments whose similarity satisfies a preset condition from the physiological data of two devices, it can determine the physiological data collected by the two devices according to whether two data segments whose similarity satisfies the preset condition can be found. originate from the same individual. Specifically, when no data segment whose similarity satisfies the preset condition cannot be found, it is considered that the physiological data collected by the smart bracelet and the physiological data collected by the PSG device are not of the same person. Conversely, when a data segment whose similarity satisfies the preset conditions can be found, it is considered that the physiological data collected by the smart bracelet and the physiological data collected by the PSG device belong to the same person.

手机将智能手环和PSG设备采集的生理数据进行数据对齐之后，如果智能手环和PSG设备采集的生理数据是同一个人的，则将智能手环采集的生理数据和PSG设备采集的生理数据进行数据融合，得到融合后的生理数据，再根据融合后的生理数据生成对应的数据分析报告，并将该数据分析报告显示给用户。而如果智能手环和PSG设备采集的生理数据不是同一个人的，则可以分别生成两份数据分析报告。After the mobile phone aligns the physiological data collected by the smart bracelet and the PSG device, if the physiological data collected by the smart bracelet and the PSG device belong to the same person, the physiological data collected by the smart bracelet and the PSG device will be compared. After data fusion, the fused physiological data is obtained, and then a corresponding data analysis report is generated according to the fused physiological data, and the data analysis report is displayed to the user. If the physiological data collected by the smart bracelet and the PSG device are not from the same person, two data analysis reports can be generated respectively.

需要指出的是，在上述根据能否找到满足预设条件的数据片段来确定两个设备所采集的生理数据是否属于同一个体的方案中，需要预先假设两个设备采集的生理数据是属于同一个个体的。而在另一些实施例中，也可以先确定出两个设备采集的生理数据是否属于同一个个体，在确定属于同一个个体之后，再从两个设备的生理数据中满足相似度满足预设条件的两个数据片段。此时，可以根据两个设备采集的生理数据的相似度度量特征、线性特征、非线性特征和离散型特征等，进行线性回归分析，得到差异化评估结果。如果两个生理数据之间的差异化小于预设阈值，则认为两个设备采集的生理数据来源于同一个个体，反之，如果差异化大于预设阈值，则认为两个设备采集的生理数据不是来源于同一个个体。It should be pointed out that, in the above scheme of determining whether the physiological data collected by the two devices belong to the same individual based on whether the data fragments that meet the preset conditions can be found, it needs to be pre-assumed that the physiological data collected by the two devices belong to the same individual. individual. In other embodiments, it is also possible to first determine whether the physiological data collected by the two devices belong to the same individual, and after it is determined that the physiological data belong to the same individual, the similarity satisfies the preset condition from the physiological data of the two devices. of the two data segments. At this time, a linear regression analysis can be performed according to the similarity measurement features, linear features, nonlinear features, discrete features, etc. of the physiological data collected by the two devices, and a differentiated evaluation result can be obtained. If the difference between the two physiological data is less than the preset threshold, it is considered that the physiological data collected by the two devices comes from the same individual. On the contrary, if the difference is greater than the preset threshold, it is considered that the physiological data collected by the two devices are not from the same individual.

手机将智能手环和PSG设备采集的生理数据进行数据对齐和数据融合等操作之后，可以再生成生理数据分析报告，将该报告显示给用户。例如，智能手环和PSG设备采集的是心率数据，手机最终可以显示该心率数据随时间变化的曲线，以及该心率数据对应的分析报告。After the mobile phone performs data alignment and data fusion operations on the physiological data collected by the smart bracelet and the PSG device, it can generate a physiological data analysis report and display the report to the user. For example, the smart bracelet and PSG device collect heart rate data, and the mobile phone can finally display the curve of the heart rate data over time, as well as the analysis report corresponding to the heart rate data.

至此，基于图1，以手机、智能手环和PSG设备作为示例，介绍了手机、智能手环和PSG设备之间的生理数据处理过程。So far, based on Figure 1, taking a mobile phone, a smart bracelet, and a PSG device as examples, the physiological data processing process between the mobile phone, the smart bracelet, and the PSG device has been introduced.

而在具体应用中，电子设备11还可以为电脑或者平板等，而电子设备12还可以包括可穿戴衣物和智能手表等。如果需要确定三个以上的电子设备采集的生理数据的时间偏差时，可以根据上文提及的过程进行两两计算，得到三个以上的电子设备之间的时间偏差。此外，不同电子设备采集的生理数据是同一个生理参数的数据，该生理参数可以是心率、体温、呼吸率或者血氧。例如，智能手环和PSG设备所采集的生理数据均为心率数据。In a specific application, theelectronic device 11 may also be a computer or a tablet, and theelectronic device 12 may also include wearable clothing, a smart watch, and the like. If it is necessary to determine the time offset of the physiological data collected by more than three electronic devices, a pairwise calculation can be performed according to the above-mentioned process to obtain the time offset between the three or more electronic devices. In addition, the physiological data collected by different electronic devices are data of the same physiological parameter, and the physiological parameter may be heart rate, body temperature, respiration rate or blood oxygen. For example, the physiological data collected by smart bracelets and PSG devices are heart rate data.

在上述图1对应的场景中，智能手环和PSG等设备采集的生理数据通过短距离无线通信技术传输至用户终端，或者通过无线路由器传输至用户终端。在另一些场景下，智能手环和PSG等设备采集的生理数据可以上传至云端服务器，由云端服务器对生理数据进行数据对齐和数据融合等操作，下面将通过图2示出的另一种可能的场景示意图进行示例性介绍。In the scenario corresponding to FIG. 1 above, the physiological data collected by devices such as the smart bracelet and PSG are transmitted to the user terminal through short-range wireless communication technology, or to the user terminal through a wireless router. In other scenarios, the physiological data collected by devices such as smart bracelets and PSG can be uploaded to the cloud server, and the cloud server will perform operations such as data alignment and data fusion on the physiological data. Another possibility shown in Figure 2 will be shown below. Schematic diagram of the scene for an exemplary introduction.

如图2所示，云端服务器21可以通过互联网等方式与电子设备22通信连接，而电子设备22可以通过短距离无线通信方式与电子设备23通信连接。例如，电子设备22可以为手机，电子设备23可以包括但不限于可穿戴设备和非可穿戴设备，这些设备均具备健康或者生理参数检测功能。作为示例而非限定，电子设备23包括智能手环和PSG设备。此时，智能手环和PSG等设备可以先将所采集的生理数据传输至手机，再由手机将这些生理数据传输至云端服务器。As shown in FIG. 2 , thecloud server 21 can communicate with theelectronic device 22 through the Internet, and theelectronic device 22 can communicate with theelectronic device 23 through short-range wireless communication. For example, theelectronic device 22 may be a mobile phone, and theelectronic device 23 may include, but is not limited to, wearable devices and non-wearable devices, all of which have the function of detecting health or physiological parameters. By way of example and not limitation, theelectronic device 23 includes a smart bracelet and a PSG device. At this time, devices such as smart bracelets and PSGs can first transmit the collected physiological data to the mobile phone, and then the mobile phone transmits the physiological data to the cloud server.

在其它一些情况下，云端服务器21也可以直接与电子设备23通信连接。例如，在智能家居场景下，智能手环和PSG设备均可以与无线路由器连接，智能手环和PSG设备所采集的生理数据可以通过无线路由器上传至云端服务器。In some other cases, thecloud server 21 may also be directly connected to theelectronic device 23 for communication. For example, in a smart home scenario, both the smart bracelet and the PSG device can be connected to a wireless router, and the physiological data collected by the smart bracelet and the PSG device can be uploaded to the cloud server through the wireless router.

需要指出的是，随着全场景的应用，每个用户可能会有多种形态的终端设备，多源数据和多源数据融合的场景也会越来越多。在一些场景下，如果不对多源数据进行数据对齐，而是直接对来源于多个设备的数据进行数据融合，多源数据的有益效果可能会相互抵消，导致后续特征提取、模型建立和模型预测等都会与实际情况存在严重偏差。It should be pointed out that with the application of all scenarios, each user may have various forms of terminal devices, and there will be more and more scenarios of multi-source data and multi-source data fusion. In some scenarios, if the multi-source data is not aligned, but data from multiple devices is directly fused, the beneficial effects of the multi-source data may cancel each other out, resulting in subsequent feature extraction, model building and model prediction. There will be serious deviations from the actual situation.

在移动健康领域，健康监测设备越来越智能化，智能穿戴设备越来越普及，用户可以使用穿戴式设备和家用健康监测设备采集人体生理参数。此时，用户可能需要查看多个个体的生理参数，例如，某个用户需要关注多个家人的身体健康情况，这种情况下，每个家人的生理数据可能都需要传输至该用户的手机，或者传输至云端服务器，由云端服务器对多个家人的生理数据进行处理后再推送至用户手机。又或者，同一个用户可能使用多个不同的穿戴式设备监测自身的人体生理参数。这些情况下，均需要识别生理数据是否来源于同一个个体，对多源数据进行数据对齐、数据融合等操作。In the field of mobile health, health monitoring devices are becoming more and more intelligent, and smart wearable devices are becoming more and more popular. Users can use wearable devices and home health monitoring devices to collect human physiological parameters. At this time, the user may need to check the physiological parameters of multiple individuals. For example, a user needs to pay attention to the physical health of multiple family members. In this case, the physiological data of each family member may need to be transmitted to the user's mobile phone. Or it is transmitted to the cloud server, and the cloud server processes the physiological data of multiple family members and then pushes it to the user's mobile phone. Alternatively, the same user may use multiple different wearable devices to monitor his own human physiological parameters. In these cases, it is necessary to identify whether the physiological data comes from the same individual, and perform operations such as data alignment and data fusion on the multi-source data.

需要说明的是，上述图1和图2仅仅是一些可能涉及的系统架构和可能涉及的场景，具体应用中，本申请实施例的多源数据处理方案还可以应用于其它系统架构和场景。It should be noted that the above-mentioned FIG. 1 and FIG. 2 are only some possible involved system architectures and possible involved scenarios. In specific applications, the multi-source data processing solutions in the embodiments of the present application may also be applied to other system architectures and scenarios.

在介绍完本申请实施例可能涉及的系统架构和可能涉及的场景之后，下面将对本申请实施例提供的方案进行详细阐述。After introducing the possible system architecture and possible scenarios involved in the embodiments of the present application, the solutions provided by the embodiments of the present application will be described in detail below.

参见图3示出的一种多源数据处理方法的一种流程示意框图，该方法可以包括以下步骤：Referring to a schematic flow diagram of a multi-source data processing method shown in FIG. 3, the method may include the following steps:

步骤S301、获取第一电子设备采集的第一生理数据和第二电子设备采集的第二生理数据，其中，上述第一生理数据和第二生理数据均包括用于表征数据产生时间的时间戳信息，而第一生理数据和第二生理数据是同一个生理参数在预设时间段内的数据。Step S301: Obtain first physiological data collected by the first electronic device and second physiological data collected by the second electronic device, wherein the first physiological data and the second physiological data both include timestamp information used to characterize the time when the data was generated , and the first physiological data and the second physiological data are data of the same physiological parameter within a preset time period.

具体地，第三电子设备获取第一电子设备采集的第一生理数据和第二电子设备采集的第二生理数据。该第三电子设备可以是用户终端，例如，该第三电子设备为手机，第一电子设备为智能手环，第二电子设备为PSG设备；也可以是云端服务器，或者是其他终端设备。Specifically, the third electronic device acquires the first physiological data collected by the first electronic device and the second physiological data collected by the second electronic device. The third electronic device may be a user terminal, for example, the third electronic device is a mobile phone, the first electronic device is a smart bracelet, and the second electronic device is a PSG device; it may also be a cloud server, or other terminal devices.

第一生理数据和第二生理数据均携带有时间戳信息，该时间戳信息可以表征生理数据的产生时间，一般情况下，每一个数据均对应一个时间戳信息。该时间戳信息与原始设备的时间保持一致，即第一生理数据中的每个数据的时间戳信息与第一电子设备的设备时间保持一致，第二生理数据中的每个数据的时间戳信息与第二电子设备的设备时间保持一致。Both the first physiological data and the second physiological data carry timestamp information, and the timestamp information can represent the generation time of the physiological data. Generally, each data corresponds to a timestamp information. The time stamp information is consistent with the time of the original device, that is, the time stamp information of each data in the first physiological data is consistent with the device time of the first electronic device, and the time stamp information of each data in the second physiological data is consistent with the device time of the first electronic device. Consistent with the device time of the second electronic device.

本申请实施例中，该时间戳信息可以具体表现为时间戳，即每个数据均携带有时间戳；也可以具体表现为可以表征时间戳的信息，即每个数据所携带不是时间戳，而是可以用于推测出数据产生时间的信息，即可以用于推测出时间戳的信息。在此不对时间戳信息的具体表现形式进行限定。In this embodiment of the present application, the time stamp information may be embodied as a time stamp, that is, each data carries a time stamp; it may also be embodied as information that can represent a time stamp, that is, the time stamp carried by each data is not a time stamp, but It is information that can be used to infer the time of data generation, that is, information that can be used to infer the timestamp. The specific representation form of the timestamp information is not limited here.

第一生理数据和第二生理数据是同一个生理参数在一定时间段内的数据，该生理参数可以是心率、血氧、体温或者呼吸率等。例如，第一生理数据和第二生理数据均为心率数据，且第一生理数据和第二生理数据是9时30分～10时00分这个时间段内的心率数据。The first physiological data and the second physiological data are data of the same physiological parameter within a certain period of time, and the physiological parameter may be heart rate, blood oxygen, body temperature, or respiration rate. For example, both the first physiological data and the second physiological data are heart rate data, and the first physiological data and the second physiological data are heart rate data in the time period from 9:30 to 10:00.

另外，生理数据的采集方法可以是任意的，具体来说，电子设备采集生理数据的方法包括但不限于光学、电学、磁场和成像等。In addition, the acquisition method of the physiological data may be arbitrary, and specifically, the methods of acquisition of the physiological data by the electronic device include, but are not limited to, optics, electricity, magnetic fields, and imaging.

步骤S302、确定相似度满足预设条件的第一目标数据片段和第二目标数据片段，该第一目标数据片段是从第一生理数据中截取的预设时间长度的信号片段，该第二目标数据片段是从第二生理数据中截取的预设时间长度的信号片段。Step S302: Determine a first target data segment and a second target data segment whose similarity satisfies a preset condition, where the first target data segment is a signal segment of a preset time length intercepted from the first physiological data, and the second target data segment is The data segment is a signal segment of a preset time length intercepted from the second physiological data.

需要说明的是，第一目标数据片段和第二目标数据片段均是预设时间长度的数据片段，该预设时间长度可以根据实际需要进行设定。一般情况下，该预设时间长度的数值决定了用于进行相似度匹配的数据片段的长度，为了使得用于进行匹配度评估的指标有一定的区分度，用于相似度匹配的数据片段的长度需要适中，故预设时间长度的数值需要适中。也就是说，所截取或选取的数据片段不宜过长，也不宜过短。例如，当第一生理数据和第二生理数据均为心率数据，正常人的心率一般在60～120Hz。若以瞬时心率(beat-to-beat的心率)的生理数据进行相似度匹配，此时，预设时间长度以120～200s为佳，具体长度还可以结合心率预测准确度和心率变化程度来确定。It should be noted that both the first target data segment and the second target data segment are data segments with a preset time length, and the preset time length can be set according to actual needs. In general, the value of the preset time length determines the length of the data segment used for similarity matching. The length needs to be moderate, so the value of the preset time length needs to be moderate. That is to say, the intercepted or selected data segment should not be too long or too short. For example, when the first physiological data and the second physiological data are both heart rate data, the heart rate of a normal person is generally 60-120 Hz. If the similarity matching is performed based on the physiological data of the instantaneous heart rate (beat-to-beat heart rate), at this time, the preset time length is preferably 120-200s, and the specific length can also be determined by combining the accuracy of heart rate prediction and the degree of heart rate variation. .

根据生理数据的相似度，从第一生理数据中找出第一目标数据片段，从第二生理数据中找出第二目标数据片段。第一目标数据片段和第二目标数据片段的相似度满足预设条件，该预设条件根据用于相似度评估指标的不同，也可能会有相应地不同。作为示例而非限定，若相似度评估指标包括相关系数和欧氏距离，此时，该预设条件为相关系数大于阈值且欧氏距离小于阈值。According to the similarity of the physiological data, the first target data segment is found from the first physiological data, and the second target data segment is found from the second physiological data. The similarity between the first target data segment and the second target data segment satisfies a preset condition, and the preset condition may also be correspondingly different according to different indicators used for similarity evaluation. As an example and not a limitation, if the similarity evaluation index includes the correlation coefficient and the Euclidean distance, in this case, the preset condition is that the correlation coefficient is greater than the threshold and the Euclidean distance is less than the threshold.

具体应用中，相似度匹配的过程可以具备表现为多种形式，即确定相似度满足预设条件的第一目标数据片段和第二目标数据片段的过程可以表现为多种形式。下面将示例性地介绍两种方式。In a specific application, the process of similarity matching may have various forms, that is, the process of determining the first target data segment and the second target data segment whose similarity satisfies a preset condition may be represented in various forms. Two ways will be exemplarily introduced below.

第一种方式：The first way:

参见图4示出的相似度匹配过程的流程示意框图，该相似度匹配的过程可以包括以下步骤：Referring to the schematic flowchart of the similarity matching process shown in FIG. 4 , the similarity matching process may include the following steps:

步骤S401、分别在第一生理数据中设置预设时间长度的第一时间滑动窗口和在第二生理数据中设置预设时间长度的第二时间滑动窗口。Step S401 , respectively setting a first time sliding window with a preset time length in the first physiological data and a second time sliding window with a preset time length in the second physiological data.

步骤S402、计算第一时间滑动窗口对应的第一数据片段和第二时间滑动窗口对应的第二数据片段之间的相似度评估指标。Step S402: Calculate the similarity evaluation index between the first data segment corresponding to the first time sliding window and the second data segment corresponding to the second time sliding window.

需要说明的是，该相似度评估指标可以包括但不限于相关系数、欧氏距离、曼哈顿聚类和切比雪夫距离中的一种或多种，即可以通过一种或多种相似度评估指标来进行相似度匹配，来评估两个数据片段的匹配度。例如，相似度评估指标包括相关系数和欧氏距离时，计算两个滑动窗口内的数据片段之间的相关系数和欧氏距离。相关系数和欧氏距离的计算过程在此不再赘述。It should be noted that the similarity evaluation index may include, but is not limited to, one or more of correlation coefficient, Euclidean distance, Manhattan clustering, and Chebyshev distance, that is, one or more similarity evaluation indicators may be used. to perform similarity matching to evaluate the matching degree of two data segments. For example, when the similarity evaluation index includes the correlation coefficient and the Euclidean distance, the correlation coefficient and the Euclidean distance between the data segments within the two sliding windows are calculated. The calculation process of the correlation coefficient and the Euclidean distance will not be repeated here.

在计算数据片段的相似度评估指标时，可以直接基于数据来计算；也可以先将数据转换成曲线后，再计算曲线之间的相似度评估指标。具体地，可以先对第一数据片段和第二数据片段进行滤波和傅里叶变换，得到第一数据片段对应的第一曲线和第二数据片段对应的第二曲线，第一曲线和第二曲线均是生理参数随着原始设备时间变换的曲线。最后，计算第一曲线和第二曲线的相似度评估指标，以得到第一数据片段和第二数据片段的相似度评估指标。When calculating the similarity evaluation index of the data segments, the calculation can be directly based on the data; it is also possible to first convert the data into a curve, and then calculate the similarity evaluation index between the curves. Specifically, filtering and Fourier transform may be performed on the first data segment and the second data segment to obtain a first curve corresponding to the first data segment and a second curve corresponding to the second data segment, the first curve and the second The curves are all the curves of the physiological parameters changing with the time of the original equipment. Finally, the similarity evaluation index of the first curve and the second curve is calculated to obtain the similarity evaluation index of the first data segment and the second data segment.

步骤S403、根据相似度评估指标，确定第一数据片段和第二数据片段之间的相似度是否满足预设条件。若相似度满足预设条件，进入步骤S404；反之，若相似度不满足预设条件，则进入步骤S405。Step S403 , according to the similarity evaluation index, determine whether the similarity between the first data segment and the second data segment satisfies a preset condition. If the similarity satisfies the preset condition, go to step S404; otherwise, if the similarity does not meet the preset condition, go to step S405.

作为示例而非限定，若相似度评估指标包括相关系数和距离度量指标，距离度量指标用于表征样本间距离，例如，欧氏距离和曼哈顿距离等；As an example and not a limitation, if the similarity evaluation index includes a correlation coefficient and a distance metric index, the distance metric index is used to represent the distance between samples, such as Euclidean distance and Manhattan distance, etc.;

此时，根据相似性评估指标，确定第一数据片段和第二数据片段之间的相似度是否满足预设条件的过程可以包括：若第一数据片段和第二数据片段之间的相关系数大于第一预设阈值，且距离度量指标小于第二预设阈值，可以确定第一数据片段和第二数据片段之间的相似度满足预设条件；若第一数据片段和第二数据片段之间的相关系数小于或等于第一预设阈值，或距离度量指标大于或等于第二预设阈值，亦或者，相关系数小于或等于第一预设阈值且距离度量指标大于或等于第二预设阈值，可以确定第一数据片段和第二数据片段之间的相似度不满足预设条件。At this time, according to the similarity evaluation index, the process of determining whether the similarity between the first data segment and the second data segment satisfies the preset condition may include: if the correlation coefficient between the first data segment and the second data segment is greater than The first preset threshold value, and the distance metric index is less than the second preset threshold value, it can be determined that the similarity between the first data segment and the second data segment satisfies the preset condition; if there is a difference between the first data segment and the second data segment The correlation coefficient is less than or equal to the first preset threshold, or the distance metric is greater than or equal to the second preset threshold, or, the correlation coefficient is less than or equal to the first preset threshold and the distance metric is greater than or equal to the second preset threshold , it can be determined that the similarity between the first data segment and the second data segment does not meet the preset condition.

当然，在其它一些实施例中，除了可以根据距离度量指标来评估数据片段之间的相似度之外，还可以通过幅值的大小来评估。此时，若两个数据片段的相关系数大于一定阈值，且两个数据片段之间的幅值差小于一定阈值时，也可以认为两个数据片段的相似度满足预设条件。Of course, in some other embodiments, in addition to evaluating the similarity between the data segments according to the distance metric, it can also evaluate the magnitude of the magnitude. At this time, if the correlation coefficient of the two data segments is greater than a certain threshold, and the amplitude difference between the two data segments is smaller than a certain threshold, it may also be considered that the similarity of the two data segments satisfies the preset condition.

步骤S404、将第一数据片段作为第一目标数据片段，第二数据片段作为第二目标数据片段。Step S404, taking the first data segment as the first target data segment and the second data segment as the second target data segment.

步骤S405、若没有遍历完第一生理数据和第二生理数据，滑动其中一个时间滑动窗口后，返回上述步骤S402和S403，直到遍历完第一生理数据和第二生理数据或者找到相似度满足预设条件的数据片段为止。Step S405, if the first physiological data and the second physiological data have not been traversed, after sliding one of the time sliding windows, return to the above-mentioned steps S402 and S403, until the first physiological data and the second physiological data are traversed or the similarity is found. until the data segment for which the condition is set.

一般情况下，第一时间滑动窗口和第二时间滑动窗口一开始是同一时间段的窗口，即先判断同一时间段的两个数据片段的相似度是否满足预设条件。如果不满足，则先固定一个滑动窗口不变，以一定的滑动步长来滑动另一个滑动窗口，并在滑动的过程中计算两个滑动窗口对应的两个数据片段的相似度，根据该相似度来寻找第一目标数据片段和第二目标数据片段。通过固定一个滑动窗口不变，滑动另一个滑动窗口，以遍历其中一个生理数据。如果遍历完其中一个生理数据仍然没有找相似度满足预设条件的第一目标数据片段和第二目标数据片段，则改变之前固定的滑动窗口，具体可以以一定滑动步长来滑动之前固定的滑动窗口，滑动一次之后，再不断滑动另一个滑动窗口，依此不断重复，直到两个生理数据均遍历完成或者找到相似度满足预设条件的第一目标数据片段和第二目标数据片段。In general, the first time sliding window and the second time sliding window are windows of the same time period at the beginning, that is, it is first judged whether the similarity of the two data segments in the same time period meets a preset condition. If it is not satisfied, first fix one sliding window unchanged, slide another sliding window with a certain sliding step, and calculate the similarity of the two data fragments corresponding to the two sliding windows during the sliding process. According to the similarity degree to find the first target data segment and the second target data segment. By fixing one sliding window unchanged, another sliding window is slid to traverse one of the physiological data. If the first target data segment and the second target data segment whose similarity satisfies the preset condition is still not found after traversing one of the physiological data, the previously fixed sliding window can be changed. Specifically, the previously fixed sliding window can be slid with a certain sliding step. Window, after sliding once, and then sliding another sliding window continuously, and so on, until the traversal of the two physiological data is completed or the first target data segment and the second target data segment whose similarity satisfies the preset condition are found.

如果遍历完两个生理数据之后，仍然没有找到满足预设条件的第一目标数据片段和第二目标数据片段，则认为两个生理数据中不存在第一目标数据片段和第二目标数据片段，此时，可以判定这两个生理数据不是同属于一个个体。If the first target data segment and the second target data segment that satisfy the preset conditions are still not found after traversing the two physiological data, it is considered that the first target data segment and the second target data segment do not exist in the two physiological data, and At this time, it can be determined that the two physiological data do not belong to the same individual.

特殊情况下，第一时间滑动窗口和第二时间滑动窗口一开始也可以不是同一个时间段的窗口。In a special case, the first time sliding window and the second time sliding window may not be windows of the same time period at the beginning.

例如，预设时间长度为5s，即第一时间滑动窗口和第二时间滑动窗口对应的数据片段的时间长度为5s。获取到第一生理数据和第二生理数据是0～100s的数据。第一时间滑动窗口对应的数据片段为第一生理数据中10s～15s的数据，第二时间滑动窗口对应的数据片段为第二生理数据中10s～15s的数据，即一开始两个时间滑动窗口对应同一个时间段的数据片段。先计算10s～15s两个时间滑动窗口对应的数据片段的相似度评估指标，判断着两个数据片段的相似度是否满足预设条件。如果不满足，则需要固定其中一个滑动窗口，滑动另一个滑动窗口，此时，可以固定第一生理数据对应的滑动窗口，滑动第二生理数据的滑动窗口。也就是说，第一生理数据中用于进行相似度匹配的数据片段仍然是10s～15s对应的数据片段，而第二时间滑动窗口对应的数据片段会不断地改变。For example, the preset time length is 5s, that is, the time length of the data segments corresponding to the first time sliding window and the second time sliding window is 5s. The acquired first physiological data and the second physiological data are data of 0 to 100 s. The data segment corresponding to the first time sliding window is the data of 10s to 15s in the first physiological data, and the data segment corresponding to the second time sliding window is the data of 10s to 15s of the second physiological data, that is, two time sliding windows at the beginning Data fragments corresponding to the same time period. First, the similarity evaluation index of the data segments corresponding to the two time sliding windows of 10s to 15s is calculated, and it is judged whether the similarity of the two data segments meets the preset condition. If not, one of the sliding windows needs to be fixed and the other sliding window needs to be slid. At this time, the sliding window corresponding to the first physiological data can be fixed, and the sliding window of the second physiological data can be slid. That is to say, the data segments used for similarity matching in the first physiological data are still the data segments corresponding to 10s to 15s, while the data segments corresponding to the second time sliding window are constantly changing.

以滑动步长为2s为例，固定第一时间滑动窗口，将第二时间滑动窗口往前滑动一步，滑动之后的第二时间滑动窗口对应的数据片段为12s～17s的数据。然后，确定第一生理数据中10s～15s的数据和第二生理数据中12s～17s的数据的相似度是否满足预设条件。如果不满足，则继续滑动第二时间滑动窗口。再将第二时间滑动窗口往前滑动一步，滑动之后的第二时间滑动窗口对应的数据为14s～19s的数据。接着，确定第一生理数据中10s～15s的数据和第二生理数据中14s～19s的数据的相似度是否满足预设条件。如果还不满足，继续滑动第二时间滑动窗口，重复上述过程。Taking the sliding step size of 2s as an example, the first time sliding window is fixed, and the second time sliding window is slid one step forward, and the data segment corresponding to the second time sliding window after sliding is the data of 12s to 17s. Then, it is determined whether the similarity between the data of 10s to 15s in the first physiological data and the data of 12s to 17s of the second physiological data satisfy a preset condition. If not satisfied, continue to slide the second time sliding window. Then slide the second time sliding window one step forward, and the data corresponding to the second time sliding window after sliding is the data of 14s-19s. Next, it is determined whether the similarity between the data of 10s to 15s in the first physiological data and the data of 14s to 19s of the second physiological data meets a preset condition. If it is still not satisfied, continue to slide the second time sliding window, and repeat the above process.

如果遍历完第二生理数据之后，仍然没有找到相似度满足预设条件的第一目标数据片段和第二目标数据片段。此时，可以改变第一时间滑动窗口后，再依次滑动第二时间滑动窗口。以第一时间滑动窗口的滑动步长为1s为例，将第一时间滑动窗口滑动一步后，第一时间滑动窗口对应的数据片段为第一生理数据中11s～16s的数据。然后，确定滑动之后的第一时间滑动窗口对应的数据片段和第二时间滑动窗口对应的数据片段的相似度度是否满足预设条件。如果不满足，则固定第一时间滑动窗口不变，不断地滑动第二时间滑动窗口，重复上述过程。If after traversing the second physiological data, the first target data segment and the second target data segment whose similarity satisfies the preset condition are still not found. In this case, after changing the first time sliding window, the second time sliding window can be sequentially moved. Taking the sliding step size of the first time sliding window as 1s as an example, after sliding the first time sliding window by one step, the data segment corresponding to the first time sliding window is the data of 11s˜16s in the first physiological data. Then, it is determined whether the similarity between the data segment corresponding to the first time sliding window and the data segment corresponding to the second time sliding window after sliding satisfies a preset condition. If it is not satisfied, fix the first time sliding window unchanged, continuously slide the second time sliding window, and repeat the above process.

依此类推，不断地改变第一时间滑动窗口，直到遍历完第一生理数据。第一生理数据和第二生理数据均遍历完成后，如果还找不到相似度满足预设条件的两个数据片段，则可以认为这两个生理数据不属于同一个个体。在此过程中，如果能找到相似度满足预设条件的两个数据片段，则将这两个数据作为第一目标数据片段和第二目标数据片段。By analogy, the first time sliding window is continuously changed until the first physiological data is traversed. After the traversal of the first physiological data and the second physiological data is completed, if two pieces of data whose similarity satisfies the preset condition cannot be found, it may be considered that the two physiological data do not belong to the same individual. In this process, if two data segments whose similarity satisfies the preset condition can be found, the two data segments are used as the first target data segment and the second target data segment.

需要说明的是，上文提及的预设时间长度、滑动步长和生理数据的时间长度等均是为了举例方便。实际应用中，这些数值并不受上文提及的数值影响。It should be noted that the preset time length, the sliding step length and the time length of the physiological data mentioned above are all for the convenience of examples. In practice, these values are not affected by the values mentioned above.

此外，上文提及的相似度匹配过程中，除了可以基于生理数据来进行匹配，也可以基于生理数据对应的曲线来进行匹配，即先将生理数据转换成对应的曲线，再基于曲线进行相似度匹配，找到相似度满足预设条件的第一目标数据片段和第二目标数据片段。In addition, in the similarity matching process mentioned above, in addition to matching based on physiological data, matching can also be performed based on the curve corresponding to the physiological data, that is, the physiological data is first converted into a corresponding curve, and then similarity based on the curve is performed. degree matching, and find the first target data segment and the second target data segment whose similarity satisfies a preset condition.

还需要指出的是，时间滑动窗口的滑动步长可以是固定的，也可以是不固定的。当每个时间滑动窗口对应的滑动步长固定，如果基于当前滑动步长没有找到满足相似度满足预设条件的两个数据片段，可以改变当前滑动步长，再进行一次相似度匹配过程。例如，当前滑动步长为2s，改变后的滑动步长为1s。滑动步长的具体数值可以根据实际应用需要进行设定。It should also be pointed out that the sliding step size of the time sliding window may be fixed or not. When the sliding step size corresponding to each time sliding window is fixed, if two data segments that satisfy the similarity and the preset condition are not found based on the current sliding step size, the current sliding step size can be changed, and the similarity matching process can be performed again. For example, the current sliding step is 2s, and the changed sliding step is 1s. The specific value of the sliding step size can be set according to actual application needs.

在上述第一种方式中，基于两个预设时间长度的时间滑动窗口来进行相似度匹配，在其它实现方式中，也可以不用基于时间滑动窗口来寻找相似度满足预设条件的两个数据片段。下面将对第二种方式进行介绍。In the above-mentioned first manner, similarity matching is performed based on time sliding windows of two preset time lengths. In other implementation manners, it is not necessary to search for two data whose similarity satisfies preset conditions based on time sliding windows. Fragment. The second method will be introduced below.

第二种方式：The second way:

在实现方式中，确定相似度满足预设条件的第一目标数据片段和第二目标数据片段的过程可以包括以下步骤：In an implementation manner, the process of determining the first target data segment and the second target data segment whose similarity satisfies a preset condition may include the following steps:

第一步、从第一生理数据中截取预设时间长度的至少一个第一数据片段，从第二生理数据中截取预设时间长度的至少一个第二数据片段。In the first step, at least one first data segment of a preset time length is intercepted from the first physiological data, and at least one second data segment of a preset time length is intercepted from the second physiological data.

第二步、分别计算每个第一数据片段和每个第二数据片段之间的相似性评估指标。In the second step, the similarity evaluation index between each first data segment and each second data segment is calculated respectively.

第三步、根据相似性评估指标，确定第一数据片段和第二数据片段之间的相似度是否满足预设条件。The third step is to determine whether the similarity between the first data segment and the second data segment satisfies a preset condition according to the similarity evaluation index.

第四步、将相似度满足预设条件对应的第一数据片段作为第一目标数据片段，对应的第二数据片段作为第二目标数据片段。In the fourth step, the first data segment corresponding to which the similarity satisfies the preset condition is used as the first target data segment, and the corresponding second data segment is used as the second target data segment.

具体地，分别从第一生理数据中截取预设时间长度的多个第一数据片段，从第二生理数据中截取预设时间长度的多个第一数据片段。然后再计算第一数据片段和第二数据片段之间的相似度评估指标，根据相似度评估指标找到相似度满足预设条件的两个数据片段。Specifically, a plurality of first data segments of a preset time length are intercepted from the first physiological data, and a plurality of first data segments of a preset time length are intercepted from the second physiological data. Then, the similarity evaluation index between the first data segment and the second data segment is calculated, and two data segments whose similarity satisfies a preset condition are found according to the similarity evaluation index.

例如，预设时间长度为10s，第一生理数据和第二生理数据是0s～100s的数据。从第一生理数据中截取多个第一数据片段，该第一数据片段示例性包括：1s～11s的数据片段、2s～12s的数据片段、3s～13s的数据片段、5s～15s的数据片段、20s～30s的数据片段、85s～95s的数据片段等。从第二生理数据中截取多个第二数据片段，该第二数据片段示例性包括：1s～11s的数据片段、2s～12s的数据片段、3s～13s的数据片段、4s～14s的数据片段、20s～30s的数据片段、80s～90s的数据片段等。然后，分别计算每一个第一数据片段和每一个第二数据片段的相似度评估指标。再根据相似度评估指标找出第一目标数据片段和第二目标数据片段。For example, the preset time length is 10s, and the first physiological data and the second physiological data are data of 0s˜100s. A plurality of first data segments are intercepted from the first physiological data, and the first data segments exemplarily include: data segments of 1s to 11s, data segments of 2s to 12s, data segments of 3s to 13s, and data segments of 5s to 15s , 20s ~ 30s data fragment, 85s ~ 95s data fragment, etc. A plurality of second data segments are intercepted from the second physiological data, and the second data segments exemplarily include: data segments of 1s to 11s, data segments of 2s to 12s, data segments of 3s to 13s, and data segments of 4s to 14s , 20s ~ 30s data fragment, 80s ~ 90s data fragment, etc. Then, the similarity evaluation index of each first data segment and each second data segment is calculated respectively. Then, the first target data segment and the second target data segment are found according to the similarity evaluation index.

需要指出的是，在计算第一数据片段和第二数据片段之间的相似度评估指标时，可以先对第一数据片段和第二数据片段先进行数据预处理，例如，滤波和傅里叶变换等，再根据预处理之后的数据片段计算相似度评估指标；也可以先对第一数据片段和第二数据片段进行数据预处理，生成第一数据片段对应的第一曲线和第二数据片段对应的第二曲线，再计算第一曲线和第二曲线之间的相似度评估指标。第一曲线和第二曲线均是生理参数随着原设备的时间变化的曲线，例如，第一曲线是心率随着第一电子设备的时间变化的曲线。It should be pointed out that when calculating the similarity evaluation index between the first data segment and the second data segment, data preprocessing can be performed on the first data segment and the second data segment, for example, filtering and Fourier transform. transformation, etc., and then calculate the similarity evaluation index according to the preprocessed data segment; it is also possible to perform data preprocessing on the first data segment and the second data segment to generate the first curve and the second data segment corresponding to the first data segment. For the corresponding second curve, the similarity evaluation index between the first curve and the second curve is calculated. Both the first curve and the second curve are curves of physiological parameters changing with time of the original device, for example, the first curve is a curve of heart rate changing with time of the first electronic device.

在其他一些实施例中，确定相似度满足预设条件的第一目标数据片段和第二目标数据片段的过程还可以具体表现为其它形式，在此不作限定。In some other embodiments, the process of determining the first target data segment and the second target data segment whose similarity satisfies a preset condition may also be embodied in other forms, which are not limited herein.

在确定出相似度满足预设条件的第一目标数据片段和第二目标数据片段之后，可以根据这两个数据片段的时间戳信息来得到两个设备之间的时间偏差。After determining the first target data segment and the second target data segment whose similarity satisfies the preset condition, the time offset between the two devices can be obtained according to the timestamp information of the two data segments.

步骤S303、根据第一目标数据片段对应的时间戳信息和第二目标数据片段对应的时间戳信息，确定第一电子设备和第二电子设备之间的时间偏差。Step S303: Determine the time offset between the first electronic device and the second electronic device according to the time stamp information corresponding to the first target data segment and the time stamp information corresponding to the second target data segment.

可以理解的是，每个数据均存在对应的时间戳信息，第一目标数据片段和第二目标数据片段内均包括多个数据。基于此，可以将第一目标数据片段和第二目标数据片段对齐之后，再根据某一个时间点的数据来计算两个设备的时间片段。It can be understood that each piece of data has corresponding timestamp information, and both the first target data segment and the second target data segment include multiple pieces of data. Based on this, after aligning the first target data segment and the second target data segment, the time segments of the two devices can be calculated according to the data at a certain time point.

例如，第一目标数据片段是第一生理数据中10s～20s的时间段对应的数据，第二目标数据片段是第二生理数据中14s～24s的时间段对应的数据。以第一目标数据片段中10s对应的数据和第二生理数据中14s对应的数据为例，此时认为这两个数据是同一个时刻的生理数据，而一个的时间是10s，另一个的时间是14s，是因为两个设备的时间存在偏差，且偏差为4s。这样，可以得到第一电子设备和第二电子设备的时间偏差为4s。For example, the first target data segment is data corresponding to a time period of 10s to 20s in the first physiological data, and the second target data segment is data corresponding to a time period of 14s to 24s in the second physiological data. Take the data corresponding to 10s in the first target data segment and the data corresponding to 14s in the second physiological data as an example. At this time, the two data are considered to be the physiological data at the same time, and the time of one is 10s, and the time of the other is It is 14s, because the time of the two devices has a deviation, and the deviation is 4s. In this way, it can be obtained that the time offset between the first electronic device and the second electronic device is 4s.

步骤S304、根据时间偏差，对第一生理数据和第二生理数据进行数据对齐操作。Step S304 , perform a data alignment operation on the first physiological data and the second physiological data according to the time deviation.

具体地，在确定出第一电子设备和第二电子设备之间的时间偏差之后，可以基于该时间偏差，将两个设备的生理数据的时间戳调整至同步，以使两个生理数据对齐。Specifically, after the time offset between the first electronic device and the second electronic device is determined, the time stamps of the physiological data of the two devices may be adjusted to be synchronized based on the time offset, so as to align the two physiological data.

由上可见，基于每个个体的生理学参数随时间变化的唯一性，通过从第一生理数据和第二生理数据中确定出相似度满足预设条件的第一目标数据片段和第二目标数据片段，根据这两个目标数据片段的时间戳信息得到两个电子设备之间的时间偏差，再根据时间偏差进行数据对齐，不用预先记录两个电子设备之间的时间偏差，也能将多源数据进行对齐，保证了对于时间依赖性很强且没有预先记录设备时间偏差的数据也能正常使用，从而提高了数据的利用率，降低了数据采集成本和时间，减少了产品开发的周期和成本。As can be seen from the above, based on the uniqueness of the physiological parameters of each individual changing over time, the first target data segment and the second target data segment whose similarity satisfies the preset condition is determined from the first physiological data and the second physiological data. , obtain the time offset between the two electronic devices according to the timestamp information of the two target data segments, and then align the data according to the time offset, without pre-recording the time offset between the two electronic devices, multi-source data Alignment ensures that data with strong time dependence and no pre-recorded device time deviation can be used normally, thereby improving the utilization of data, reducing the cost and time of data collection, and reducing the cycle and cost of product development.

比如，在现有技术中，如果没有预先记录设备时间偏差，电子设备采集的多源数据无法进行数据对齐，进而使得这些数据变成不可用的数据。而通过本申请实施例的方案，即使没有预先记录设备时间偏差，也可以根据数据的相似度高低来确定时间偏差，从而进行数据对齐，进而使得这些数据仍然是可用的数据。这样，提高了数据利用率，降低了数据采集成本和时间。For example, in the prior art, if the device time offset is not pre-recorded, data alignment cannot be performed on the multi-source data collected by the electronic device, thus making the data unusable. With the solution of the embodiment of the present application, even if the device time offset is not pre-recorded, the time offset can be determined according to the similarity of the data, so as to align the data, so that the data is still available data. In this way, the utilization rate of data is improved, and the cost and time of data collection are reduced.

需要指出的是，如果需要进行多个设备的数据对齐操作，可以依次进行上文提及的两个设备之间的多源数据处理过程，以实现多个设备的数据对齐。It should be pointed out that, if the data alignment operation of multiple devices needs to be performed, the multi-source data processing process between the two devices mentioned above can be performed in sequence, so as to realize the data alignment of the multiple devices.

另外，还需要指出的是，不同设备采集的生理数据可以是同源的，例如，都是心电图(ECG)；也可以不是同源的，例如，一个设备是光电容积图(PPG)，另一个设备是心电图(ECG)。且采集的可以是同一部位，也可以是不同部位。In addition, it should also be pointed out that the physiological data collected by different devices may be homologous, for example, both are electrocardiograms (ECGs); or they may not be homologous, for example, one device is a photoplethysmography (PPG), and the other is a photoplethysmogram (PPG). The device is an electrocardiogram (ECG). And the collection can be from the same part or from different parts.

在上述根据相似度寻找满足预设条件的第一目标数据片段和第二目标数据片段的过程中，如果能找到相似度满足预设条件的第一目标数据片段和第二目标数据片段，除了可以根据第一目标数据片段和第二目标数据片段确定两个设备的时间偏差之外，还可以判定这两个生理数据是来源于同一个个体。而如果遍历完两个生理数据仍然找不到相似度满足预设条件的第一目标数据片段和第二目标数据片段，则可以判定这两个生理数据不是来源于同一个个体。In the above process of searching for the first target data segment and the second target data segment that meet the preset condition according to the similarity, if the first target data segment and the second target data segment whose similarity meets the preset condition can be found, except that the In addition to determining the time offset of the two devices according to the first target data segment and the second target data segment, it can also be determined that the two physiological data originate from the same individual. However, if the first target data segment and the second target data segment whose similarity satisfies the preset condition cannot be found after traversing the two physiological data, it can be determined that the two physiological data do not originate from the same individual.

也就是说，在一些实施例中，上述方法还可以包括：若存在相似度满足预设条件的第一目标数据片段和第二目标数据片段，确定第一生理数据和第二生理数据属于同一个个体；若不存在相似度满足预设条件的第一目标数据片段和第二目标数据片段，确定第一生理数据和第二生理数据不属于同一个个体。That is to say, in some embodiments, the above method may further include: if there are a first target data segment and a second target data segment whose similarity satisfies a preset condition, determining that the first physiological data and the second physiological data belong to the same individual; if there is no first target data segment and second target data segment whose similarity satisfies the preset condition, it is determined that the first physiological data and the second physiological data do not belong to the same individual.

除了可以根据上文提及的方式来确定两个生理数据是否是来源于同一个个体之外，还可以通过其它方式来确定两个生理数据是否来源于同一个个体。In addition to determining whether the two physiological data originate from the same individual according to the above-mentioned manner, there may also be other ways to determine whether the two physiological data originate from the same individual.

在另一些实施例中，也可以先确定出两个生理数据是否来源于同一个个体，若两个生理数据来源于同一个个体，再计算两个设备之间的时间偏差。也就是说，在确定相似度满足预设条件的第一目标数据片段和第二目标数据片段之前，上述方法可以还包括以下步骤：In other embodiments, it may also be determined first whether the two physiological data originate from the same individual, and if the two physiological data originate from the same individual, the time offset between the two devices is then calculated. That is to say, before determining the first target data segment and the second target data segment whose similarity satisfies the preset condition, the above method may further include the following steps:

第一步、计算第一生理数据和第二生理数据中重叠时间段对应的数据的相似度度量特征。该相似度度量特征可以包括但不限于欧氏距离和曼哈顿距离。The first step is to calculate the similarity measurement feature of the data corresponding to the overlapping time periods in the first physiological data and the second physiological data. The similarity measure feature may include, but is not limited to, Euclidean distance and Manhattan distance.

第二步、提取第一生理数据和第二生理数据的线性特征、非线性特征和离散型特征。该现象特征包括VLI和VAI等。离散型特征包括方差和均值等。In the second step, linear features, nonlinear features and discrete features of the first physiological data and the second physiological data are extracted. Features of this phenomenon include VLI and VAI, among others. Discrete features include variance and mean.

第三步、根据相似度度量特征、线性特征、非线性特征和离散型特征进行线性回归分析，得到第一生理数据和第二生理数据的差异性评估结果。In the third step, a linear regression analysis is performed according to the similarity measure feature, the linear feature, the nonlinear feature and the discrete feature to obtain a difference evaluation result between the first physiological data and the second physiological data.

具体应用中，可以使用线性回归模型来对两个数据的差异性大小进行评估。In specific applications, a linear regression model can be used to evaluate the magnitude of the difference between two data.

第四步、若差异性评估结果小于第三预设阈值，确定第一生理数据和第二生理数据属于同一个个体；Step 4: If the difference evaluation result is less than the third preset threshold, determine that the first physiological data and the second physiological data belong to the same individual;

第五步、若差异性评估结果大于第三预设阈值，确定第一生理数据和第二生理数据不属于同一个个体。Step 5: If the difference evaluation result is greater than the third preset threshold, it is determined that the first physiological data and the second physiological data do not belong to the same individual.

需要说明的是，上述第三预设阈值可以根据实际需要进行设定，在此不作限定。It should be noted that the above-mentioned third preset threshold can be set according to actual needs, which is not limited here.

具体来说，不仅计算两个生理数据之间的相似度度量特征，还引入了数据的线性、非线性和离散型特征等。然后，再通过对这些特征进行线性回归分析，得到用于评估两个生理数据的差异性大小的评估结果，若差异性较大，则认为两个数据不属于同一个个体，反之，差异性较小，则认为两个数据属于同一个个体。Specifically, not only the similarity measure feature between two physiological data is calculated, but also the linear, nonlinear and discrete features of the data are introduced. Then, by performing linear regression analysis on these features, the evaluation results for evaluating the difference between the two physiological data are obtained. If the difference is large, it is considered that the two data do not belong to the same individual. is small, the two data are considered to belong to the same individual.

需要指出的是，上文示例性地提供了两种确定生理数据是否来源于同一个个体的方式，第一种依托于根据相似度寻找满足预设条件的第一目标数据片段和第二目标数据片段的过程，基于能否找到两个目标数据片段来确定数据是否来源于同一个个体。第二种是基于数据的各种特征来评估两个数据之间的差异性，根据差异性大小来确定数据是否来源于同一个个体。第一种方式是在进行相似度匹配过程之前，先假设这两个生理数据是同一个体，该方式先进行相似度匹配，然后再确定两个生理数据是否来源于同一个个体。而第二种方式是在相似度匹配之前，先确定两个生理数据是否来源于同一个个体，在确定两个生理数据来源于同一个个体之后，再进行相似度匹配。It should be pointed out that the above exemplarily provides two ways to determine whether the physiological data originates from the same individual. The first method relies on finding the first target data segment and the second target data that meet the preset conditions according to the similarity. The fragmentation process determines whether the data originates from the same individual based on whether two target data fragments can be found. The second is to evaluate the difference between two data based on various characteristics of the data, and to determine whether the data comes from the same individual according to the size of the difference. The first method is to assume that the two physiological data are the same individual before performing the similarity matching process. This method first performs similarity matching, and then determines whether the two physiological data originate from the same individual. The second method is to determine whether the two physiological data originate from the same individual before similarity matching, and then perform similarity matching after determining that the two physiological data originate from the same individual.

值得指出的是，上文提及的用于确定出两个或者多个生理数据是否来源于同一个个体的方式还可以应用于智慧全场景中的身份识别。具体来说，在全场景中，每个人都可能有多个不同终端设备，且不同的终端设备可能并不是只有一个用户使用，故需要确定终端设备所传输的数据是哪个用户的数据。基于此，可以通过上文提及的方式，确定终端设备所传输或者所采集的数据是哪个用户的数据，从而实现全场景的身份识别。It is worth pointing out that the above-mentioned method for determining whether two or more physiological data originate from the same individual can also be applied to the identification in the whole scene of intelligence. Specifically, in the whole scenario, everyone may have multiple different terminal devices, and different terminal devices may not be used by only one user, so it is necessary to determine which user the data transmitted by the terminal device belongs to. Based on this, it is possible to determine which user's data the data transmitted or collected by the terminal device belongs to in the manner mentioned above, so as to realize the full-scene identity recognition.

在确定出多个生理数据是来源于同一个个体，且对多个生理数据进行数据对齐之后，可以对多个生理数据进行数据融合，得到融合的生理数据。进一步地，在得到融合的生理数据后，还可以根据融合的生理数据生成对应的数据分析报告。下面将对此过程进行介绍。After it is determined that the plurality of physiological data originate from the same individual, and after data alignment is performed on the plurality of physiological data, data fusion can be performed on the plurality of physiological data to obtain the fused physiological data. Further, after obtaining the fused physiological data, a corresponding data analysis report can also be generated according to the fused physiological data. This process is described below.

在一些实施例中，在根据时间偏差，对第一生理数据和第二生理数据进行数据对齐操作之后，还可以对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据。In some embodiments, after performing a data alignment operation on the first physiological data and the second physiological data according to the time offset, data fusion may also be performed on the first physiological data and the second physiological data to obtain fused physiological data.

需要指出的是，若需要对多个生理数据进行数据对齐和数据融合操作，可以根据上述数据对齐方案，先进行两两数据对齐。然后，将所有生理数据进行数据对齐之后，再将多个生理数据进行数据融合，得到融合后的生理数据。It should be pointed out that, if data alignment and data fusion operations need to be performed on multiple physiological data, pairwise data alignment may be performed first according to the above data alignment scheme. Then, after aligning all the physiological data, data fusion of multiple physiological data is performed to obtain the fused physiological data.

数据融合的过程可以包括：数据质量比对过程和缺失数据补偿过程。通过质量比对保留数据质量较高的数据片段。而对于一些缺少的数据段，可以使用其它生理数据的相应时间段的数据段进行多源补偿。The process of data fusion can include: data quality comparison process and missing data compensation process. Data fragments with higher data quality are retained by quality alignment. For some missing data segments, multi-source compensation can be performed using data segments of other physiological data in corresponding time segments.

具体地，先通过数据质量评价指标对第一生理数据和第二生理数据进行质量对比，获得相同时间段内质量较高的第三数据段。即选取两个生理数据中质量较高的数据段。Specifically, the quality of the first physiological data and the second physiological data is first compared through the data quality evaluation index, and a third data segment with higher quality within the same time period is obtained. That is, the data segment with higher quality among the two physiological data is selected.

该数据质量评价指标可以包括但不限于数据的完整性、一致性、准确性和冗余性等。另外，也可以通过数据可用性和数据量等来评价数据质量。比如，对于某一个时间段，第一生理数据存在数据段A，第二生理数据存在数据段B。通过数据质量评价指标，评价数据段A和数据段B的质量高低，如果数据段A的质量高于数据段B，则保留数据段A，即将数据段A作为该融合的生理数据中某一个时间段的数据。反之，如果数据段A的质量低于数据段B，则保留数据段B。依此过程，得到第一生理数据和第二生理数据中数据质量较高的数据片段。The data quality evaluation indicators may include, but are not limited to, data integrity, consistency, accuracy, and redundancy. In addition, data quality can also be evaluated by data availability and data volume. For example, for a certain time period, the first physiological data exists in data segment A, and the second physiological data exists in data segment B. Through the data quality evaluation index, the quality of data segment A and data segment B is evaluated. If the quality of data segment A is higher than that of data segment B, data segment A is retained, that is, data segment A is used as a certain time in the fused physiological data. segment data. Conversely, if the quality of data segment A is lower than that of data segment B, then data segment B is retained. According to this process, data segments with higher data quality among the first physiological data and the second physiological data are obtained.

然后，如果第一生理数据和第二生理数据中的其中一个生理数据存在缺失的数据段，则可以获得另外一个生理数据中相应时间段对应的第四数据段。例如，在某一个时间段，第一生理数据中存在该时间段对应的数据段C，但是第二生理数据中不存在该时间段对应的数据段，即第二生理数据中该时间段的数据是缺少的。此时，可以使用第一生理数据中该时间段对应的数据段C作为融合的生理数据中该时间段的数据。Then, if there is a missing data segment in one of the first physiological data and the second physiological data, a fourth data segment corresponding to a corresponding time period in the other physiological data can be obtained. For example, in a certain time period, the first physiological data contains the data segment C corresponding to the time period, but the second physiological data does not have the data segment corresponding to the time period, that is, the data of the time period in the second physiological data is missing. At this time, the data segment C corresponding to the time period in the first physiological data can be used as the data of the time period in the fused physiological data.

最后，按照时间顺序将第三数据段和第四数据段进行合并，得到融合后的生理数据。Finally, the third data segment and the fourth data segment are merged in time sequence to obtain the fused physiological data.

可以理解的是，当生理数据是三个或者更多时，其融合过程与两个生理数据的融合过程类似，在此不再赘述。It can be understood that when there are three or more physiological data, the fusion process is similar to the fusion process of two physiological data, and details are not repeated here.

在将多个生理数据进行数据融合，得到融合的生理数据之后，还可以根据融合后的生理数据，生成对应的生理数据分析报告。After data fusion of a plurality of physiological data is performed to obtain the fused physiological data, a corresponding physiological data analysis report can also be generated according to the fused physiological data.

举例来说，第一生理数据是智能手环采集的心率数据，第二生理数据是PSG设备采集的心率数据，智能手环和PSG设备采集的心率数据均传输到用户手机。用户手机可以将智能手环和PSG设备采集的心率数据进行数据对齐，再进行数据融合，然后根据数据融合后的心率数据生成心率数据分析报告，并将该报告显示给用户。For example, the first physiological data is the heart rate data collected by the smart bracelet, the second physiological data is the heart rate data collected by the PSG device, and the heart rate data collected by the smart bracelet and the PSG device are both transmitted to the user's mobile phone. The user's mobile phone can align the heart rate data collected by the smart bracelet and the PSG device, and then perform data fusion, and then generate a heart rate data analysis report based on the heart rate data after data fusion, and display the report to the user.

在一些实施例中，在进行数据对齐之后，数据融合之前，还可以根据数据对齐之后的生理数据进行二次相似度匹配，再根据相似度匹配结果来选择生成一份生理数据分析报告，还是多份生理数据分析报告。In some embodiments, after data alignment and before data fusion, secondary similarity matching may be performed according to the physiological data after data alignment, and then a physiological data analysis report may be generated according to the similarity matching result, or more Physiological data analysis report.

具体地，在对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据之前，对数据对齐后的第一生理数据和第二生理数据进行相似度计算，得到目标相似度。该目标相似度可以是通过欧氏距离来评估。Specifically, before data fusion is performed on the first physiological data and the second physiological data to obtain the fused physiological data, the similarity calculation is performed on the aligned first physiological data and the second physiological data to obtain the target similarity. The target similarity may be evaluated by Euclidean distance.

具体应用中，基于数据对齐之后的两个生理数据的重叠时间段内的数据，计算得到欧氏距离。In a specific application, the Euclidean distance is calculated based on the data in the overlapping time period of the two physiological data after data alignment.

然后，判断目标相似度是否大于第四预设阈值，若目标相似度大于第四预设阈值，进入对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据的步骤，即将多个生理数据进行数据融合，然后，再根据融合的生理数据生成生理数据分析报告。反之，如果目标相似度小于第四预设阈值，则分别生成第一生理数据的生理数据分析报告和第二生理数据的生理分析报告。也就是说，如果目标相似度小于第四预设阈值，则认为第一生理数据和第二生理数据不是同一个个体的数据，或者第一生理数据和第二生理数据的数据质量较差，此时，不进行数据融合过程，分别生成第一生理数据和第二生理数据的生理数据分析报告。Then, determine whether the target similarity is greater than the fourth preset threshold, and if the target similarity is greater than the fourth preset threshold, enter the step of data fusion of the first physiological data and the second physiological data to obtain the fused physiological data, that is A plurality of physiological data are data fused, and then a physiological data analysis report is generated according to the fused physiological data. Conversely, if the target similarity is less than the fourth preset threshold, a physiological data analysis report of the first physiological data and a physiological analysis report of the second physiological data are generated respectively. That is to say, if the target similarity is less than the fourth preset threshold, it is considered that the first physiological data and the second physiological data are not the data of the same individual, or the data quality of the first physiological data and the second physiological data is poor. When the data fusion process is not performed, the physiological data analysis reports of the first physiological data and the second physiological data are respectively generated.

需要指出的是，对数据对齐之后的生理数据进行二次相似度匹配，可以进一步提高数据融合和所生成的数据分析报告的准确性。It should be pointed out that performing secondary similarity matching on the physiological data after data alignment can further improve the accuracy of data fusion and the generated data analysis report.

在上文提及的技术方案中，可以根据相似度匹配结果来确定多个生理数据是否来源于同一个个体，也可以在相似度匹配之前确定多个生理数据是否来源于同一个个体。具体应用中，这两种方案的整体数据处理过程可能会稍有不同。下面将分别对这两种情况进行介绍。In the above-mentioned technical solution, it can be determined whether multiple physiological data originate from the same individual according to the similarity matching result, or whether multiple physiological data originate from the same individual can be determined before similarity matching. In specific applications, the overall data processing procedures of the two schemes may be slightly different. These two cases will be introduced separately below.

第一种情况first case

以两个设备采集的生理数据为例，先假设两个设备采集的生理数据是来源于同一个个体，然后进行相似度匹配，如果能找到相似度满足预设条件的第一目标数据片段和第二目标数据片段，则判定两个生理数据是来源于同一个个体，反之，则不是来源于同一个个体。Taking the physiological data collected by two devices as an example, first assume that the physiological data collected by the two devices are from the same individual, and then perform similarity matching. For two target data segments, it is determined that the two physiological data are from the same individual, otherwise, they are not from the same individual.

具体地，参见图5示出的多源数据处理方法的又一种流程示意框图，该过程可以包括以下步骤：Specifically, referring to another schematic flow diagram of the multi-source data processing method shown in FIG. 5 , the process may include the following steps:

步骤S501、分别接收两个电子设备所采集的生理信号，分别记为S₁(t)和S₂(t)。In step S501, the physiological signals collected by the two electronic devices are respectively received, which are respectively denoted as S₁ (t) and S₂ (t).

例如，一个电子设备是智能手环，另一个电子设备是PSG设备，智能手环和PSG设备将采集的心率信号发送至手机。For example, one electronic device is a smart bracelet, the other electronic device is a PSG device, and the smart bracelet and the PSG device transmit the collected heart rate signals to the mobile phone.

作为示例，参见图6示出的S₁(t)和S₂(t)的示意图，其中，图6(a)为S₁(t)的示意图，横轴是时间，竖轴是心率，图6(b)为S₂(t)的示意图，横轴是时间，竖轴是心率。图6(a)是ECG心电信号，图6(b)是PPG心电信号。As an example, see the schematic diagrams of S₁ (t) and S₂ (t) shown in FIG. 6 , wherein FIG. 6( a ) is a schematic diagram of S₁ (t), the horizontal axis is time, the vertical axis is heart rate, and the 6(b) is a schematic diagram of S₂ (t), the horizontal axis is time, and the vertical axis is heart rate. Fig. 6(a) is the ECG signal, and Fig. 6(b) is the PPG signal.

可以理解的是，S₁(t)和S₂(t)均是时间序列数据，即各个设备采集的生理信号随着时间变化而变化。且各个生理信号的时间戳和原始设备的时间保持一致。且所采集的是同一个生理参数的信号。It can be understood that both S₁ (t) and S₂ (t) are time-series data, that is, the physiological signals collected by each device change with time. And the time stamp of each physiological signal is consistent with the time of the original device. And what is collected is the signal of the same physiological parameter.

步骤S502、分别从S₁(t)和S₂(t)中截取一小段信号，记为D₁(t)和D₂(t)。Step S502: Cut out a small segment of the signal from S₁ (t) and S₂ (t), respectively, denoted as D₁ (t) and D₂ (t).

需要说明的是，D₁(t)和D₂(t)的长度是相同的，具体可以通过设置预设时间长度来确定所截取的信号片段的长短。一般情况下，所截取的信号长度需要适中，不能过长也不能过短。It should be noted that the lengths of D₁ (t) and D₂ (t) are the same, and specifically, the length of the intercepted signal segment may be determined by setting a preset time length. In general, the length of the intercepted signal needs to be moderate, neither too long nor too short.

作为示例，参见图6，图6(a)中的D1和图6(b)中的D2对应的数据即为所截取的信号片段。As an example, referring to FIG. 6 , the data corresponding to D1 in FIG. 6( a ) and D2 in FIG. 6( b ) are the intercepted signal segments.

步骤S503、对D₁(t)和D₂(t)进行滤波和傅里叶变换等预处理操作，得到两个信号片段对应的曲线。Step S503 , performing preprocessing operations such as filtering and Fourier transform on D₁ (t) and D₂ (t) to obtain curves corresponding to the two signal segments.

可以理解的是，该曲线是某一个共同生理参数(例如心率)的生理信号在截取时间内随时间变化的曲线。It can be understood that the curve is a curve of the physiological signal of a certain common physiological parameter (for example, heart rate) changing with time during the interception time.

步骤S504、计算D₁(t)和D₂(t)对应的曲线的匹配度。Step S504: Calculate the matching degree of the curves corresponding to D₁ (t) and D₂ (t).

步骤S505、根据匹配度判断截取时间内的信号是否能对齐。Step S505, according to the matching degree, determine whether the signals within the interception time can be aligned.

具体地，上述曲线匹配度的评估指标是相似度评估指标，即使用曲线的相似度评估指标来评估曲线的匹配度。例如，可以使用相关系数、欧氏距离和曼哈顿距离的一种或多种来评估曲线的匹配度。Specifically, the above-mentioned evaluation index of the matching degree of the curve is the similarity evaluation index, that is, the matching degree of the curve is evaluated by using the similarity evaluation index of the curve. For example, one or more of correlation coefficient, Euclidean distance, and Manhattan distance can be used to assess the fit of the curves.

以欧氏距离和相关系数来评估曲线匹配度为例，如果欧氏距离小于设定的阈值，且相关系数大于设定的阈值，则认为两个信号对齐，即能找到满足预设条件的第一目标数据片段和第二目标数据片段。反之，如果欧氏距离大于设定的阈值，或者相关系数小于设定的阈值，亦或者，欧氏距离大于设定的阈值且相关系数小于设定阈值，认为两个信号对齐，即找不到满足预设条件的第一目标数据片段和第二目标数据片段。Taking the Euclidean distance and the correlation coefficient to evaluate the curve matching degree as an example, if the Euclidean distance is less than the set threshold and the correlation coefficient is greater than the set threshold, the two signals are considered to be aligned, that is, the first signal that satisfies the preset conditions can be found. A target data segment and a second target data segment. Conversely, if the Euclidean distance is greater than the set threshold, or the correlation coefficient is less than the set threshold, or, the Euclidean distance is greater than the set threshold and the correlation coefficient is less than the set threshold, the two signals are considered to be aligned, that is, they cannot be found. The first target data segment and the second target data segment that satisfy the preset conditions.

将两个信号对齐时的两个信号片段作为上文提及的第一目标数据片段和第二目标数据片段。The two signal segments when the two signals are aligned are taken as the first target data segment and the second target data segment mentioned above.

此时，需要根据曲线匹配度来找出信号对齐时的两个信号片段。该过程与上文提及的相似度匹配过程类似，即与上文确定相似度满足预设条件的第一目标数据片段和第二目标数据片段的过程类似。At this time, it is necessary to find out the two signal segments when the signals are aligned according to the curve matching degree. This process is similar to the above-mentioned similarity matching process, that is, it is similar to the above process of determining the first target data segment and the second target data segment whose similarity meets the preset condition.

具体地，若D₁(t)和D₂(t)对应的两个信号没有对齐，即这两个信号片段不满足预设条件，则固定一个片段，滑动另一个信号片段的时间戳，重复步骤S502～S505，直到找到信号对齐时的两个信号片段。如果已经遍历完另一个信号片段对应的生理信号，仍然没有找到信号对齐的两个信号片段，则改变之前固定的信号片段，滑动另一个信号片段的时间戳，重复步骤S502～S505，直到找到信号对齐的信号片段。Specifically, if the two signals corresponding to D₁ (t) and D₂ (t) are not aligned, that is, the two signal segments do not meet the preset conditions, fix one segment, slide the timestamp of the other signal segment, and repeat Steps S502-S505, until two signal segments when the signals are aligned are found. If the physiological signal corresponding to another signal segment has been traversed, and the two signal segments that are aligned with the signals are still not found, change the previously fixed signal segment, slide the timestamp of the other signal segment, and repeat steps S502 to S505 until the signal is found. Aligned signal fragments.

如果遍历完两个生理信号，仍然没有找到信号对齐的信号片段，则认为两个生理信号不是同一个个体的生理数据，反之，如果可以找到，则认为两个生理信号时同一个个体的生理信号。If the two physiological signals are traversed, and the signal segment of the signal alignment is still not found, it is considered that the two physiological signals are not the physiological data of the same individual. On the contrary, if they can be found, it is considered that the two physiological signals are the physiological signals of the same individual. .

例如，参见图6，保持图6(a)中的D₁不变，改变图6(b)中的D₂，每滑动一次D₂，则计算一次D₁和D₂之间的相似度评估指标，确定D₁和D₂是否满足预设条件。如果不能满足，继续滑动D₂，直到遍历完S₂(t)。如果遍历完S₂(t)仍然没有找打满足预设条件的D₁和D₂，则滑动D₁，然后继续滑动D₂，重复上述过程，直到遍历完S₁(t)，或者，找到满足预设条件的两个信号片段。For example, referring to Fig. 6, keep D₁ in Fig. 6(a) unchanged, change D₂ in Fig. 6(b), and calculate the similarity evaluation between D₁ and D₂ every time D₂ is slid index to determine whether D₁ and D₂ meet the preset conditions. If not satisfied, continue to slide D₂ until S₂ (t) is traversed. If the D₁ and D₂ that meet the preset conditions are still not found after traversing S₂ (t), slide D₁ , then continue to slide D₂ , and repeat the above process until S₁ (t) is traversed, or, find Two signal segments that meet preset conditions.

步骤S506、若截取时间内的信号能对齐，确定S₁(t)和S₂(t)来源于同一个个体，并根据D₁(t)和D₂(t)的时间戳计算两个生理信号的时间戳偏差。Step S506, if the signals within the interception time can be aligned, determine that S₁ (t) and S₂ (t) originate from the same individual, and calculate the two physiological parameters according to the time stamps of D₁ (t) and D₂ (t). Timestamp skew of the signal.

步骤S507、若截取时间内的信号不能对齐，确定是否遍历完两个生理信号，如果没有遍历完，则返回步骤S502，继续寻找信号对齐时的两个信号片段。如果遍历完成，进入步骤S508。Step S507 , if the signals within the interception time cannot be aligned, determine whether the two physiological signals have been traversed, if not, return to step S502 to continue searching for the two signal segments when the signals are aligned. If the traversal is completed, go to step S508.

例如，参见图7示出的信号未对齐时的示意图。一条曲线是手环设备的PPG瞬时心率曲线，另一条曲线是PSG设备的ECG瞬时心率曲线。这两个信号片段的相关系数为0.79328，即corrcoef＝0.79328。预先设定的相关系数阈值为0.85，这两个信号片段的相关系数小于设定的相关系数阈值，则认为这两个信号片段截取时间内没有对齐，即这两个信号片段的相似度不满足预设条件。此时，这两个信号的时间戳偏差为661.2s，即timediff-t1-t2＝661.2s。For example, see the schematic diagram shown in FIG. 7 when the signals are not aligned. One curve is the PPG instantaneous heart rate curve of the bracelet device, and the other curve is the ECG instantaneous heart rate curve of the PSG device. The correlation coefficient of the two signal segments is 0.79328, ie corrcoef=0.79328. The preset correlation coefficient threshold is 0.85, and the correlation coefficient of the two signal fragments is less than the set correlation coefficient threshold, then it is considered that the two signal fragments are not aligned within the interception time, that is, the similarity of the two signal fragments is not satisfied. preset conditions. At this time, the time stamp deviation of the two signals is 661.2s, that is, timediff-t1-t2=661.2s.

参见图8示出的信号对齐时的示意图，如图8所示，其横轴为时间，竖轴为瞬时心率。一条曲线是手环设备的PPG瞬时心率曲线，另一条曲线是PSG设备的ECG瞬时心率曲线。这两个信号片段的相关系数为0.9964，即corrcoef＝0.9964。预先设定的相关系数阈值为0.85，这两个信号片段的相关系数大于设定的相关系数阈值，则认为这两个信号片段在截取时间内信号对齐，即这两个信号片段的相似度满足预设条件。此时，这两个信号的时间戳偏差为-9.8s，即timediff-t1-t2＝-9.8s。也就是说，手环设备和PSG设备之间的时间偏差为-9.8s。确定出手环设备和PGS设备之间的时间偏差之后，可以根据该时间偏差调整对应生理数据的时间戳，以将两个设备的生理数据进行数据对齐。Referring to the schematic diagram of signal alignment shown in FIG. 8 , as shown in FIG. 8 , the horizontal axis is time, and the vertical axis is instantaneous heart rate. One curve is the PPG instantaneous heart rate curve of the bracelet device, and the other curve is the ECG instantaneous heart rate curve of the PSG device. The correlation coefficient of the two signal segments is 0.9964, ie corrcoef=0.9964. The preset correlation coefficient threshold is 0.85, and the correlation coefficient of the two signal fragments is greater than the set correlation coefficient threshold, then the two signal fragments are considered to be aligned within the interception time, that is, the similarity of the two signal fragments satisfies preset conditions. At this time, the time stamp deviation of the two signals is -9.8s, that is, timediff-t1-t2=-9.8s. That is to say, the time deviation between the bracelet device and the PSG device is -9.8s. After the time deviation between the wristband device and the PGS device is determined, the time stamp of the corresponding physiological data can be adjusted according to the time deviation, so as to align the physiological data of the two devices.

步骤S508、确定S₁(t)和S₂(t)不是来源于同一个个体，无法计算两个生理信号的时间戳偏差。Step S508, it is determined that S₁ (t) and S₂ (t) are not from the same individual, and the time stamp deviation of the two physiological signals cannot be calculated.

在计算出两个电子设备的时间偏差之后，可以使用该时间偏差对两个生理信号进行数据对齐，将两个生理信号的时间多调整至同步。After the time offset of the two electronic devices is calculated, the time offset can be used to align the data of the two physiological signals, so as to adjust the time of the two physiological signals to be more synchronized.

在进行数据对齐操作之后，可以再进行数据融合，生成生理数据分析报告等操作。After the data alignment operation, data fusion can be performed to generate physiological data analysis reports and other operations.

第二种情况second case

在这种情况下，先确定多个生理数据是否来源于同一个个体，如果是同一个个体，则进行相似度匹配，得到两个设备的时间戳偏差，再根据时间戳偏差进行数据对齐，数据融合，生成数据分析报告等操作。In this case, first determine whether multiple physiological data originate from the same individual, and if it is the same individual, perform similarity matching to obtain the timestamp deviation of the two devices, and then align the data according to the timestamp deviation. Fusion, generating data analysis reports and other operations.

具体地，参见图9示出的多源数据处理方法的一种示意图，如图9所示，首先，提取多个生理数据的欧氏距离、VLI、VAI、均值和方差等特征。然后，根据这些特征进行线性回归分析，得到一个线性回归分析结果。该线性回归分析结果用于评估数据之间的差异化大小。如果差异化小于阈值A，则认为多个生理数据是同一个个体的数据，反之，如果差异化大于阈值A，则认为多个生理数据不是同一个个体的数据。Specifically, referring to a schematic diagram of a multi-source data processing method shown in FIG. 9 , as shown in FIG. 9 , first, features such as Euclidean distance, VLI, VAI, mean and variance of multiple physiological data are extracted. Then, perform linear regression analysis based on these features to obtain a linear regression analysis result. The results of this linear regression analysis were used to assess the magnitude of the differences between the data. If the difference is less than the threshold value A, it is considered that the multiple physiological data are the data of the same individual. On the contrary, if the difference is greater than the threshold value A, it is considered that the multiple physiological data are not the data of the same individual.

确定多个生理数据是同一个个体的数据之后，可以对通过相似度匹配，确定多个设备的时间戳偏差。确定设备间的是时间戳偏差的过程可以参见上文第一种情况的过程和上文确定满足预设条件的第一目标数据片段和第二目标数据片段对应的内容，在此不再赘述。After it is determined that the multiple physiological data are data of the same individual, the time stamp deviation of multiple devices can be determined through similarity matching. For the process of determining the time stamp deviation between devices, refer to the process of the first case above and the content corresponding to the determination of the first target data segment and the second target data segment that meet the preset conditions above, which will not be repeated here.

计算得到设备间的时间偏差之后，将多个生理数据进行数据对齐。然后再基于数据对齐后的生理数据，计算欧氏距离，根据欧氏距离进行二次相似度匹配。如果欧氏距离小于阈值B，则进行数据融合操作，再基于融合的生理数据生成融合报告。如果欧氏距离大于阈值B，则认为多个生理数据不是同一个个体数据或者多个生理数据的数据质量较差，不进行数据融合，生成多份数据分析报告，每一个生理数据对应一份报告。After calculating the time offset between devices, data alignment is performed on multiple physiological data. Then, based on the physiological data after data alignment, the Euclidean distance is calculated, and the second similarity matching is performed according to the Euclidean distance. If the Euclidean distance is smaller than the threshold B, perform data fusion operation, and then generate a fusion report based on the fused physiological data. If the Euclidean distance is greater than the threshold B, it is considered that the multiple physiological data are not the same individual data or the data quality of the multiple physiological data is poor, data fusion is not performed, and multiple data analysis reports are generated, one for each physiological data. .

需要指出的是，上述数据融合过程可以参见上文提及的数据融合过程，在此不再赘述。It should be pointed out that, for the above data fusion process, reference may be made to the data fusion process mentioned above, which will not be repeated here.

需要说明的是，上述第一种情况和第二种情况中一些细节和相关介绍可以参见上文相应内容，在此不再赘述。It should be noted that, for some details and related introductions in the first and second situations above, reference may be made to the corresponding content above, and details are not repeated here.

对应于上文实施例的多源数据处理方法，图10示出了本申请实施例提供的多源数据处理装置的结构框图，为了便于说明，仅示出了与本申请实施例相关的部分。Corresponding to the multi-source data processing method of the above embodiment, FIG. 10 shows a structural block diagram of the multi-source data processing apparatus provided by the embodiment of the present application. For convenience of description, only the part related to the embodiment of the present application is shown.

参照图10，该装置可以包括：10, the apparatus may include:

生理数据获取模块101，用于获取第一电子设备采集的第一生理数据和第二电子设备采集的第二生理数据，第一生理数据和第二生理数据均包括用于表征数据产生时间的时间戳信息，第一生理数据和第二生理数据是同一个生理参数在预设时间段内的数据；The physiologicaldata acquisition module 101 is used for acquiring the first physiological data collected by the first electronic device and the second physiological data collected by the second electronic device. Stamp information, the first physiological data and the second physiological data are data of the same physiological parameter within a preset time period;

目标数据片段确定模块102，用于确定相似度满足预设条件的第一目标数据片段和第二目标数据片段，第一目标数据片段是从第一生理数据中截取的预设时间长度的信号片段，第二目标数据片段是从第二生理数据中截取的预设时间长度的信号片段；A target datasegment determination module 102, configured to determine a first target data segment and a second target data segment whose similarity satisfies a preset condition, where the first target data segment is a signal segment of a preset time length intercepted from the first physiological data , the second target data segment is a signal segment of a preset time length intercepted from the second physiological data;

设备间时间偏差确定模块103，用于根据第一目标数据片段对应的时间戳信息和第二目标数据片段对应的时间戳信息，确定第一电子设备和第二电子设备之间的时间偏差；an inter-device time offsetdetermination module 103, configured to determine the time offset between the first electronic device and the second electronic device according to the timestamp information corresponding to the first target data segment and the timestamp information corresponding to the second target data segment;

数据对齐模块104，用于根据时间偏差，对第一生理数据和第二生理数据进行数据对齐操作。Thedata alignment module 104 is configured to perform a data alignment operation on the first physiological data and the second physiological data according to the time offset.

在一些实施例中，上述目标数据片段确定模块可以具体用于：分别在第一生理数据中设置预设时间长度的第一时间滑动窗口和在第二生理数据中设置预设时间长度的第二时间滑动窗口；计算第一时间滑动窗口对应的第一数据片段和第二时间滑动窗口对应的第二数据片段之间的相似度评估指标；根据相似度评估指标，确定第一数据片段和第二数据片段之间的相似度是否满足预设条件；若相似度满足预设条件，将第一数据片段作为第一目标数据片段，第二数据片段作为第二目标数据片段；若相似度不满足预设条件，滑动其中一个时间滑动窗口后，返回计算第一时间滑动窗口对应的第一数据片段和第二时间滑动窗口对应的第二数据片段之间的相似度评估指标，根据相似度评估指标确定第一数据片段和第二数据片段之间的相似度是否满足预设条件的步骤，直到遍历完第一生理数据和第二生理数据或者找到相似度满足预设条件的数据片段为止；In some embodiments, the above target data segment determination module may be specifically configured to: respectively set a first time sliding window with a preset time length in the first physiological data and a second time sliding window with a preset time length in the second physiological data, respectively. time sliding window; calculating the similarity evaluation index between the first data segment corresponding to the first time sliding window and the second data segment corresponding to the second time sliding window; determining the first data segment and the second data segment according to the similarity evaluation index Whether the similarity between the data segments satisfies the preset condition; if the similarity satisfies the preset condition, the first data segment is used as the first target data segment, and the second data segment is used as the second target data segment; Set the condition, after sliding one of the time sliding windows, return to calculate the similarity evaluation index between the first data segment corresponding to the first time sliding window and the second data segment corresponding to the second time sliding window, and determine according to the similarity evaluation index The step of whether the similarity between the first data segment and the second data segment satisfies a preset condition, until the first physiological data and the second physiological data are traversed or a data segment whose similarity meets the preset condition is found;

或者，从第一生理数据中截取预设时间长度的至少一个第一数据片段，从第二生理数据中截取预设时间长度的至少一个第二数据片段；分别计算每个第一数据片段和每个第二数据片段之间的相似性评估指标；根据相似性评估指标，确定第一数据片段和第二数据片段之间的相似度是否满足预设条件；将相似度满足预设条件对应的第一数据片段作为第一目标数据片段，对应的第二数据片段作为第二目标数据片段。Alternatively, intercept at least one first data segment of a preset time length from the first physiological data, and intercept at least one second data segment of a preset time length from the second physiological data; respectively calculate each first data segment and each The similarity evaluation index between the second data segments; according to the similarity evaluation index, determine whether the similarity between the first data segment and the second data segment meets the preset condition; A data segment is used as the first target data segment, and the corresponding second data segment is used as the second target data segment.

在一些实施例中，若相似度评估指标包括相关系数和距离度量指标，距离度量指标用于表征样本间距离。上述目标数据片段确定模块可以具体用于：若第一数据片段和第二数据片段之间的相关系数大于第一预设阈值，且距离度量指标小于第二预设阈值，确定第一数据片段和第二数据片段之间的相似度满足预设条件；若第一数据片段和第二数据片段之间的相关系数小于或等于第一预设阈值，和/或距离度量指标大于或等于第二预设阈值，确定第一数据片段和第二数据片段之间的相似度不满足预设条件。In some embodiments, if the similarity evaluation index includes a correlation coefficient and a distance metric index, the distance metric index is used to characterize the distance between samples. The above target data segment determination module may be specifically configured to: if the correlation coefficient between the first data segment and the second data segment is greater than the first preset threshold, and the distance metric index is less than the second preset threshold, determine the first data segment and the second data segment. The similarity between the second data segments satisfies the preset condition; if the correlation coefficient between the first data segment and the second data segment is less than or equal to the first preset threshold, and/or the distance metric is greater than or equal to the second preset threshold A threshold is set to determine that the similarity between the first data segment and the second data segment does not meet a preset condition.

在一些实施例中，该装置还可以包括：第一判断模块，用于若存在相似度满足预设条件的第一目标数据片段和第二目标数据片段，确定第一生理数据和第二生理数据属于同一个个体；若不存在相似度满足预设条件的第一目标数据片段和第二目标数据片段，确定第一生理数据和第二生理数据不属于同一个个体。In some embodiments, the apparatus may further include: a first judgment module, configured to determine the first physiological data and the second physiological data if there are a first target data segment and a second target data segment whose similarity satisfies a preset condition belong to the same individual; if there is no first target data segment and second target data segment whose similarity satisfies the preset condition, it is determined that the first physiological data and the second physiological data do not belong to the same individual.

在一些实施例中，该装置还可以包括：第二判断模块，用于计算第一生理数据和第二生理数据中重叠时间段对应的数据的相似度度量特征；提取第一生理数据和第二生理数据的线性特征、非线性特征和离散型特征；根据相似度度量特征、线性特征、非线性特征和离散型特征进行线性回归分析，得到第一生理数据和第二生理数据的差异性评估结果；若差异性评估结果小于第三预设阈值，确定第一生理数据和第二生理数据属于同一个个体；若差异性评估结果大于第三预设阈值，确定第一生理数据和第二生理数据不属于同一个个体。In some embodiments, the apparatus may further include: a second judgment module, configured to calculate similarity measurement features of data corresponding to overlapping time periods in the first physiological data and the second physiological data; extracting the first physiological data and the second physiological data Linear features, nonlinear features and discrete features of the physiological data; perform linear regression analysis according to the similarity measurement features, linear features, nonlinear features and discrete features to obtain the difference evaluation results of the first physiological data and the second physiological data ; if the difference evaluation result is less than the third preset threshold, determine that the first physiological data and the second physiological data belong to the same individual; if the difference evaluation result is greater than the third preset threshold, determine that the first physiological data and the second physiological data not belong to the same individual.

在一些实施例中，若确定出第一生理数据和第二生理数据属于同一个个体，该装置还可以包括：数据融合模块，用于对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据。In some embodiments, if it is determined that the first physiological data and the second physiological data belong to the same individual, the apparatus may further include: a data fusion module, configured to perform data fusion on the first physiological data and the second physiological data to obtain fused physiological data.

在一些实施例中，上述数据融合模块可以具体用于：通过数据质量评价指标对第一生理数据和第二生理数据进行质量对比，获得相同时间段内质量较高的第三数据段；若第一生理数据和第二生理数据中的其中一个生理数据存在缺失的数据段，获得另外一个生理数据中相应时间段对应的第四数据段，按照时间顺序将第三数据段和第四数据段进行合并，得到融合后的生理数据。In some embodiments, the above-mentioned data fusion module can be specifically used to: compare the quality of the first physiological data and the second physiological data through the data quality evaluation index, and obtain a third data segment with higher quality in the same time period; There is a missing data segment in one of the physiological data and the second physiological data, obtain a fourth data segment corresponding to the corresponding time segment in the other physiological data, and perform the third data segment and the fourth data segment according to the time sequence. Merge to obtain fused physiological data.

在一些实施例中，该装置还可以包括：报告生成模块，用于根据融合后的生理数据，生成对应的生理数据分析报告。In some embodiments, the apparatus may further include: a report generation module, configured to generate a corresponding physiological data analysis report according to the fused physiological data.

在一些实施例中，该装置还可以包括：二次相似度匹配模块，用于对数据对齐后的第一生理数据和第二生理数据进行相似度计算，得到目标相似度；若目标相似度大于第四预设阈值，进入对第一生理数据和第二生理数据进行数据融合，得到融合后的生理数据的步骤；若目标相似度小于第四预设阈值，分别生成第一生理数据的生理数据分析报告和第二生理数据的生理分析报告。In some embodiments, the apparatus may further include: a secondary similarity matching module, configured to perform similarity calculation on the first physiological data and the second physiological data after data alignment to obtain the target similarity; if the target similarity is greater than The fourth preset threshold value is entered into the step of data fusion of the first physiological data and the second physiological data to obtain the fused physiological data; if the target similarity is less than the fourth preset threshold value, the physiological data of the first physiological data are respectively generated The analysis report and the physiological analysis report of the second physiological data.

在一些实施例中，生理参数可以为但不限于心率、呼吸率、体温或血氧等。In some embodiments, the physiological parameter may be, but is not limited to, heart rate, respiration rate, body temperature, or blood oxygen, among others.

上述多源数据处理装置具有实现上述多源数据处理方法的功能，该功能可以通过硬件实现，也可以通过硬件执行相应的软件实现，硬件或软件包括一个或多个与上述功能相对应的模块，模块可以是软件和/或硬件。The above-mentioned multi-source data processing device has the function of realizing the above-mentioned multi-source data processing method, and this function can be realized by hardware, and can also be realized by executing corresponding software through hardware, and the hardware or software includes one or more modules corresponding to the above-mentioned functions, Modules can be software and/or hardware.

需要说明的是，上述装置/模块之间的信息交互、执行过程等内容，由于与本申请方法实施例基于同一构思，其具体功能及带来的技术效果，具体可参见方法实施例部分，此处不再赘述。It should be noted that the information exchange, execution process and other contents between the above-mentioned devices/modules are based on the same concept as the method embodiments of the present application. For specific functions and technical effects, please refer to the method embodiments section. It is not repeated here.

本申请实施例中，用于采集用户生理数据的电子设备的类型可以是任意的，其可以是可穿戴式设备，也可以是家用健康监测设备等。作为示例而非限定，当为可穿戴设备时，该可穿戴设备还可以是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称，如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上，或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备，更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能，如智能手表或智能眼镜等，以及只专注于某一类应用功能，需要和其它设备如智能手机配合使用，如各类进行体征监测的智能手环、智能首饰等。当然，该可穿戴设备具备生理数据采集功能。In the embodiment of the present application, the type of the electronic device used to collect the physiological data of the user may be any type, and it may be a wearable device, a home health monitoring device, or the like. As an example and not a limitation, when it is a wearable device, the wearable device can also be a general term for the intelligent design of daily wear and the development of wearable devices using wearable technology, such as glasses, gloves, watches, clothing and shoes, etc. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. In a broad sense, wearable smart devices include full-featured, large-scale, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, and only focus on a certain type of application function, which needs to be used in conjunction with other devices such as smart phones. , such as various types of smart bracelets and smart jewelry that monitor physical signs. Of course, the wearable device has the function of collecting physiological data.

而用于获取各个设备采集的生理数据，并对这些数据进行多源数据处理操作，诸如确定设备间时间偏差、数据对齐、数据融合和生成数据报告等的电子设备可以是指具有数据处理功能的任意类型的设备。例如，其可以是手机、电脑、平板和云端服务器。The electronic devices used to obtain physiological data collected by various devices and perform multi-source data processing operations on these data, such as determining the time deviation between devices, data alignment, data fusion and generating data reports, may refer to electronic devices with data processing functions. Any type of device. For example, it can be mobile phone, computer, tablet and cloud server.

作为示例而非限定，如图11所示，电子设备100可以包括处理器110，外部存储器接口120，内部存储器121，通用串行总线(universal serial bus，USB)接口130，充电管理模块140，电源管理模块141，电池142，天线1，天线2，移动通信模块150，无线通信模块160，音频模块170，扬声器170A，受话器170B，麦克风170C，耳机接口170D，传感器模块180，按键190，马达191，指示器192，摄像头193，显示屏194，以及用户标识模块(subscriberidentification module，SIM)卡接口195等。其中传感器模块180可以包括压力传感器180A，陀螺仪传感器180B，气压传感器180C，磁传感器180D，加速度传感器180E，距离传感器180F，接近光传感器180G，指纹传感器180H，温度传感器180J，触摸传感器180K，环境光传感器180L，骨传导传感器180M等。As an example and not limitation, as shown in FIG. 11 , theelectronic device 100 may include aprocessor 110, anexternal memory interface 120, an internal memory 121, a universal serial bus (USB)interface 130, acharging management module 140, a power supply Management module 141, battery 142, antenna 1, antenna 2,mobile communication module 150, wireless communication module 160,audio module 170,speaker 170A, receiver 170B,microphone 170C, headphone jack 170D, sensor module 180, button 190, motor 191, An indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM)card interface 195 and the like. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, and ambient light. Sensor 180L, bone conduction sensor 180M, etc.

可以理解的是，本申请实施例示意的结构并不构成对电子设备100的具体限定。在本申请另一些实施例中，电子设备100可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。It can be understood that the structures illustrated in the embodiments of the present application do not constitute a specific limitation on theelectronic device 100 . In other embodiments of the present application, theelectronic device 100 may include more or less components than shown, or combine some components, or separate some components, or arrange different components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

处理器110可以包括一个或多个处理单元，例如：处理器110可以包括应用处理器(application processor，AP)，调制解调处理器，图形处理器(graphics processingunit，GPU)，图像信号处理器(image signal processor，ISP)，控制器，存储器，视频编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器，和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。Theprocessor 110 may include one or more processing units, for example, theprocessor 110 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor ( image signal processor, ISP), controller, memory, video codec, digital signal processor (DSP), baseband processor, and/or neural-network processing unit (NPU), etc. . Wherein, different processing units may be independent devices, or may be integrated in one or more processors.

其中，控制器可以是电子设备100的神经中枢和指挥中心。控制器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。The controller may be the nerve center and command center of theelectronic device 100 . The controller can generate an operation control signal according to the instruction operation code and timing signal, and complete the control of fetching and executing instructions.

处理器110中还可以设置存储器，用于存储指令和数据。在一些实施例中，处理器110中的存储器为高速缓冲存储器。该存储器可以保存处理器110刚用过或循环使用的指令或数据。如果处理器110需要再次使用该指令或数据，可从所述存储器中直接调用。避免了重复存取，减少了处理器110的等待时间，因而提高了系统的效率。A memory may also be provided in theprocessor 110 for storing instructions and data. In some embodiments, the memory inprocessor 110 is cache memory. This memory may hold instructions or data that have just been used or recycled by theprocessor 110 . If theprocessor 110 needs to use the instruction or data again, it can be called directly from the memory. Repeated accesses are avoided and the latency of theprocessor 110 is reduced, thereby increasing the efficiency of the system.

在一些实施例中，处理器110可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口，集成电路内置音频(inter-integrated circuitsound，I2S)接口，脉冲编码调制(pulse code modulation，PCM)接口，通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口，移动产业处理器接口(mobile industry processor interface，MIPI)，通用输入输出(general-purposeinput/output，GPIO)接口，用户标识模块(subscriber identity module，SIM)接口，和/或通用串行总线(universal serial bus，USB)接口等。In some embodiments, theprocessor 110 may include one or more interfaces. The interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuitsound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver (universal asynchronous receiver) interface /transmitter, UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (SIM) interface, and/or Universal serial bus (universal serial bus, USB) interface, etc.

I2C接口是一种双向同步串行总线，包括一根串行数据线(serial data line，SDA)和一根串行时钟线(derail clock line，SCL)。在一些实施例中，处理器110可以包含多组I2C总线。处理器110可以通过不同的I2C总线接口分别耦合触摸传感器180K，充电器，闪光灯，摄像头193等。例如：处理器110可以通过I2C接口耦合触摸传感器180K，使处理器110与触摸传感器180K通过I2C总线接口通信，实现电子设备100的触摸功能。The I2C interface is a bidirectional synchronous serial bus that includes a serial data line (SDA) and a serial clock line (SCL). In some embodiments, theprocessor 110 may contain multiple sets of I2C buses. Theprocessor 110 can be respectively coupled to the touch sensor 180K, the charger, the flash, the camera 193 and the like through different I2C bus interfaces. For example, theprocessor 110 may couple the touch sensor 180K through the I2C interface, so that theprocessor 110 and the touch sensor 180K communicate with each other through the I2C bus interface, so as to realize the touch function of theelectronic device 100 .

I2S接口可以用于音频通信。在一些实施例中，处理器110可以包含多组I2S总线。处理器110可以通过I2S总线与音频模块170耦合，实现处理器110与音频模块170之间的通信。The I2S interface can be used for audio communication. In some embodiments, theprocessor 110 may contain multiple sets of I2S buses. Theprocessor 110 may be coupled with theaudio module 170 through an I2S bus to implement communication between theprocessor 110 and theaudio module 170 .

PCM接口也可以用于音频通信，将模拟信号抽样，量化和编码。在一些实施例中，音频模块170与无线通信模块160可以通过PCM总线接口耦合。所述I2S接口和所述PCM接口都可以用于音频通信。The PCM interface can also be used for audio communications, sampling, quantizing and encoding analog signals. In some embodiments, theaudio module 170 and the wireless communication module 160 may be coupled through a PCM bus interface. Both the I2S interface and the PCM interface can be used for audio communication.

UART接口是一种通用串行数据总线，用于异步通信。该总线可以为双向通信总线。它将要传输的数据在串行通信与并行通信之间转换。在一些实施例中，UART接口通常被用于连接处理器110与无线通信模块160。例如：处理器110通过UART接口与无线通信模块160中的蓝牙模块通信，实现蓝牙功能。The UART interface is a universal serial data bus used for asynchronous communication. The bus may be a bidirectional communication bus. It converts the data to be transmitted between serial communication and parallel communication. In some embodiments, a UART interface is typically used to connect theprocessor 110 with the wireless communication module 160 . For example, theprocessor 110 communicates with the Bluetooth module in the wireless communication module 160 through the UART interface to implement the Bluetooth function.

MIPI接口可以被用于连接处理器110与显示屏194，摄像头193等外围器件。MIPI接口包括摄像头串行接口(camera serial interface，CSI)，显示屏串行接口(displayserial interface，DSI)等。在一些实施例中，处理器110和摄像头193通过CSI接口通信，实现电子设备100的拍摄功能。处理器110和显示屏194通过DSI接口通信，实现电子设备100的显示功能。The MIPI interface can be used to connect theprocessor 110 with peripheral devices such as the display screen 194 and the camera 193 . The MIPI interface includes a camera serial interface (camera serial interface, CSI), a display serial interface (displayserial interface, DSI), and the like. In some embodiments, theprocessor 110 communicates with the camera 193 through a CSI interface, so as to realize the photographing function of theelectronic device 100 . Theprocessor 110 communicates with the display screen 194 through the DSI interface to implement the display function of theelectronic device 100 .

GPIO接口可以通过软件配置。GPIO接口可以被配置为控制信号，也可被配置为数据信号。在一些实施例中，GPIO接口可以用于连接处理器110与摄像头193，显示屏194，无线通信模块160，音频模块170，传感器模块180等。GPIO接口还可以被配置为I2C接口，I2S接口，UART接口，MIPI接口等。The GPIO interface can be configured by software. The GPIO interface can be configured as a control signal or as a data signal. In some embodiments, the GPIO interface may be used to connect theprocessor 110 with the camera 193, the display screen 194, the wireless communication module 160, theaudio module 170, the sensor module 180, and the like. The GPIO interface can also be configured as I2C interface, I2S interface, UART interface, MIPI interface, etc.

USB接口130是符合USB标准规范的接口，具体可以是Mini USB接口，Micro USB接口，USB Type C接口等。USB接口130可以用于连接充电器为电子设备100充电，也可以用于电子设备100与外围设备之间传输数据。也可以用于连接耳机，通过耳机播放音频。该接口还可以用于连接其他电子设备，例如AR设备等。TheUSB interface 130 is an interface that conforms to the USB standard specification, and may specifically be a Mini USB interface, a Micro USB interface, a USB Type C interface, and the like. TheUSB interface 130 can be used to connect a charger to charge theelectronic device 100, and can also be used to transmit data between theelectronic device 100 and peripheral devices. It can also be used to connect headphones to play audio through the headphones. The interface can also be used to connect other electronic devices, such as AR devices.

可以理解的是，本申请实施例示意的各模块间的接口连接关系，只是示意性说明，并不构成对电子设备100的结构限定。在本申请另一些实施例中，电子设备100也可以采用上述实施例中不同的接口连接方式，或多种接口连接方式的组合。It can be understood that the interface connection relationship between the modules illustrated in the embodiments of the present application is only a schematic illustration, and does not constitute a structural limitation of theelectronic device 100 . In other embodiments of the present application, theelectronic device 100 may also adopt different interface connection manners in the foregoing embodiments, or a combination of multiple interface connection manners.

充电管理模块140用于从充电器接收充电输入。其中，充电器可以是无线充电器，也可以是有线充电器。在一些有线充电的实施例中，充电管理模块140可以通过USB接口130接收有线充电器的充电输入。在一些无线充电的实施例中，充电管理模块140可以通过电子设备100的无线充电线圈接收无线充电输入。充电管理模块140为电池142充电的同时，还可以通过电源管理模块141为电子设备供电。Thecharging management module 140 is used to receive charging input from the charger. The charger may be a wireless charger or a wired charger. In some wired charging embodiments, thecharging management module 140 may receive charging input from the wired charger through theUSB interface 130 . In some wireless charging embodiments, thecharging management module 140 may receive wireless charging input through a wireless charging coil of theelectronic device 100 . While thecharging management module 140 charges the battery 142 , it can also supply power to the electronic device through the power management module 141 .

电源管理模块141用于连接电池142，充电管理模块140与处理器110。电源管理模块141接收电池142和/或充电管理模块140的输入，为处理器110，内部存储器121，外部存储器，显示屏194，摄像头193，和无线通信模块160等供电。电源管理模块141还可以用于监测电池容量，电池循环次数，电池健康状态(漏电，阻抗)等参数。在其他一些实施例中，电源管理模块141也可以设置于处理器110中。在另一些实施例中，电源管理模块141和充电管理模块140也可以设置于同一个器件中。The power management module 141 is used for connecting the battery 142 , thecharging management module 140 and theprocessor 110 . The power management module 141 receives input from the battery 142 and/or thecharging management module 140 and supplies power to theprocessor 110 , the internal memory 121 , the external memory, the display screen 194 , the camera 193 , and the wireless communication module 160 . The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle times, battery health status (leakage, impedance). In some other embodiments, the power management module 141 may also be provided in theprocessor 110 . In other embodiments, the power management module 141 and thecharging management module 140 may also be provided in the same device.

电子设备100的无线通信功能可以通过天线1，天线2，移动通信模块150，无线通信模块160，调制解调处理器以及基带处理器等实现。The wireless communication function of theelectronic device 100 may be implemented by the antenna 1, the antenna 2, themobile communication module 150, the wireless communication module 160, the modulation and demodulation processor, the baseband processor, and the like.

天线1和天线2用于发射和接收电磁波信号。电子设备100中的每个天线可用于覆盖单个或多个通信频带。不同的天线还可以复用，以提高天线的利用率。例如：可以将天线1复用为无线局域网的分集天线。在另外一些实施例中，天线可以和调谐开关结合使用。Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna inelectronic device 100 may be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, the antenna 1 can be multiplexed as a diversity antenna of the wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

移动通信模块150可以提供应用在电子设备100上的包括2G/3G/4G/5G等无线通信的解决方案。移动通信模块150可以包括至少一个滤波器，开关，功率放大器，低噪声放大器(low noise amplifier，LNA)等。移动通信模块150可以由天线1接收电磁波，并对接收的电磁波进行滤波，放大等处理，传送至调制解调处理器进行解调。移动通信模块150还可以对经调制解调处理器调制后的信号放大，经天线1转为电磁波辐射出去。在一些实施例中，移动通信模块150的至少部分功能模块可以被设置于处理器110中。在一些实施例中，移动通信模块150的至少部分功能模块可以与处理器110的至少部分模块被设置在同一个器件中。Themobile communication module 150 may provide wireless communication solutions including 2G/3G/4G/5G etc. applied on theelectronic device 100 . Themobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA) and the like. Themobile communication module 150 can receive electromagnetic waves from the antenna 1, filter and amplify the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. Themobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and then turn it into an electromagnetic wave for radiation through the antenna 1 . In some embodiments, at least part of the functional modules of themobile communication module 150 may be provided in theprocessor 110 . In some embodiments, at least part of the functional modules of themobile communication module 150 may be provided in the same device as at least part of the modules of theprocessor 110 .

调制解调处理器可以包括调制器和解调器。其中，调制器用于将待发送的低频基带信号调制成中高频信号。解调器用于将接收的电磁波信号解调为低频基带信号。随后解调器将解调得到的低频基带信号传送至基带处理器处理。低频基带信号经基带处理器处理后，被传递给应用处理器。应用处理器通过音频设备(不限于扬声器170A，受话器170B等)输出声音信号，或通过显示屏194显示图像或视频。在一些实施例中，调制解调处理器可以是独立的器件。在另一些实施例中，调制解调处理器可以独立于处理器110，与移动通信模块150或其他功能模块设置在同一个器件中。The modem processor may include a modulator and a demodulator. Wherein, the modulator is used to modulate the low frequency baseband signal to be sent into a medium and high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low frequency baseband signal. Then the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing. The low frequency baseband signal is processed by the baseband processor and passed to the application processor. The application processor outputs sound signals through audio devices (not limited to thespeaker 170A, the receiver 170B, etc.), or displays images or videos through the display screen 194 . In some embodiments, the modem processor may be a stand-alone device. In other embodiments, the modem processor may be independent of theprocessor 110, and may be provided in the same device as themobile communication module 150 or other functional modules.

无线通信模块160可以提供应用在电子设备100上的包括无线局域网(wirelesslocal area networks，WLAN)(如无线保真(wireless fidelity，Wi-Fi)网络)，蓝牙(bluetooth，BT)，全球导航卫星系统(global navigation satellite system，GNSS)，调频(frequency modulation，FM)，近距离无线通信技术(near field communication，NFC)，红外技术(infrared，IR)等无线通信的解决方案。无线通信模块160可以是集成至少一个通信处理模块的一个或多个器件。无线通信模块160经由天线2接收电磁波，将电磁波信号调频以及滤波处理，将处理后的信号发送到处理器110。无线通信模块160还可以从处理器110接收待发送的信号，对其进行调频，放大，经天线2转为电磁波辐射出去。The wireless communication module 160 can provide wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), and global navigation satellite systems applied on theelectronic device 100 . (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2 , frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to theprocessor 110 . The wireless communication module 160 can also receive the signal to be sent from theprocessor 110 , perform frequency modulation on it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2 .

在一些实施例中，电子设备100的天线1和移动通信模块150耦合，天线2和无线通信模块160耦合，使得电子设备100可以通过无线通信技术与网络以及其他设备通信。所述无线通信技术可以包括全球移动通讯系统(global system for mobile communications，GSM)，通用分组无线服务(general packet radio service，GPRS)，码分多址接入(codedivision multiple access，CDMA)，宽带码分多址(wideband code division multipleaccess，WCDMA)，时分码分多址(time-division code division multiple access，TD-SCDMA)，长期演进(long term evolution，LTE)，BT，GNSS，WLAN，NFC，FM，和/或IR技术等。所述GNSS可以包括全球卫星定位系统(global positioning system，GPS)，全球导航卫星系统(global navigation satellite system，GLONASS)，北斗卫星导航系统(beidounavigation satellite system，BDS)，准天顶卫星系统(quasi-zenith satellitesystem，QZSS)和/或星基增强系统(satellite based augmentation systems，SBAS)。In some embodiments, the antenna 1 of theelectronic device 100 is coupled with themobile communication module 150, and the antenna 2 is coupled with the wireless communication module 160, so that theelectronic device 100 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code Wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM , and/or IR technology, etc. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou satellite navigation system (BDS), a quasi-zenith satellite system (quasi- zenith satellite system, QZSS) and/or satellite based augmentation systems (SBAS).

电子设备100通过GPU，显示屏194，以及应用处理器等实现显示功能。GPU为图像处理的微处理器，连接显示屏194和应用处理器。GPU用于执行数学和几何计算，用于图形渲染。处理器110可包括一个或多个GPU，其执行程序指令以生成或改变显示信息。Theelectronic device 100 implements a display function through a GPU, a display screen 194, an application processor, and the like. The GPU is a microprocessor for image processing, and is connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering.Processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.

显示屏194用于显示图像，视频等。显示屏194包括显示面板。显示面板可以采用液晶显示屏(liquid crystal display，LCD)，有机发光二极管(organic light-emittingdiode，OLED)，有源矩阵有机发光二极体或主动矩阵有机发光二极体(active-matrixorganic light emitting diode的，AMOLED)，柔性发光二极管(flex light-emittingdiode，FLED)，Miniled，MicroLed，Micro-oLed，量子点发光二极管(quantum dot lightemitting diodes，QLED)等。在一些实施例中，电子设备100可以包括1个或N个显示屏194，N为大于1的正整数。Display screen 194 is used to display images, videos, and the like. Display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (active-matrix organic light-emitting diode). , AMOLED), flexible light-emitting diode (flex light-emitting diode, FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diodes (quantum dot light emitting diodes, QLED) and so on. In some embodiments, theelectronic device 100 may include one or N display screens 194 , where N is a positive integer greater than one.

电子设备100可以通过ISP，摄像头193，视频编解码器，GPU，显示屏194以及应用处理器等实现拍摄功能。Theelectronic device 100 may implement a shooting function through an ISP, a camera 193, a video codec, a GPU, a display screen 194, an application processor, and the like.

ISP用于处理摄像头193反馈的数据。例如，拍照时，打开快门，光线通过镜头被传递到摄像头感光元件上，光信号转换为电信号，摄像头感光元件将所述电信号传递给ISP处理，转化为肉眼可见的图像。ISP还可以对图像的噪点，亮度，肤色进行算法优化。ISP还可以对拍摄场景的曝光，色温等参数优化。在一些实施例中，ISP可以设置在摄像头193中。The ISP is used to process the data fed back by the camera 193 . For example, when taking a photo, the shutter is opened, the light is transmitted to the camera photosensitive element through the lens, the light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing, and converts it into an image visible to the naked eye. ISP can also perform algorithm optimization on image noise, brightness, and skin tone. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some embodiments, the ISP may be provided in the camera 193 .

摄像头193用于捕获静态图像或视频。物体通过镜头生成光学图像投射到感光元件。感光元件可以是电荷耦合器件(charge coupled device，CCD)或互补金属氧化物半导体(complementary metal-oxide-semiconductor，CMOS)光电晶体管。感光元件把光信号转换成电信号，之后将电信号传递给ISP转换成数字图像信号。ISP将数字图像信号输出到DSP加工处理。DSP将数字图像信号转换成标准的RGB，YUV等格式的图像信号。在一些实施例中，电子设备100可以包括1个或N个摄像头193，N为大于1的正整数。Camera 193 is used to capture still images or video. The object is projected through the lens to generate an optical image onto the photosensitive element. The photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. DSP converts digital image signals into standard RGB, YUV and other formats of image signals. In some embodiments, theelectronic device 100 may include 1 or N cameras 193 , where N is a positive integer greater than 1.

数字信号处理器用于处理数字信号，除了可以处理数字图像信号，还可以处理其他数字信号。例如，当电子设备100在频点选择时，数字信号处理器用于对频点能量进行傅里叶变换等。A digital signal processor is used to process digital signals, in addition to processing digital image signals, it can also process other digital signals. For example, when theelectronic device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy and so on.

视频编解码器用于对数字视频压缩或解压缩。电子设备100可以支持一种或多种视频编解码器。这样，电子设备100可以播放或录制多种编码格式的视频，例如：动态图像专家组(moving picture experts group，MPEG)1，MPEG2，MPEG3，MPEG4等。Video codecs are used to compress or decompress digital video. Theelectronic device 100 may support one or more video codecs. In this way, theelectronic device 100 can play or record videos in various encoding formats, for example, moving picture experts group (MPEG) 1, MPEG2, MPEG3, MPEG4, and so on.

NPU为神经网络(neural-network，NN)计算处理器，通过借鉴生物神经网络结构，例如借鉴人脑神经元之间传递模式，对输入信息快速处理，还可以不断的自学习。通过NPU可以实现电子设备100的智能认知等应用，例如：图像识别，人脸识别，语音识别，文本理解等。The NPU is a neural-network (NN) computing processor. By drawing on the structure of biological neural networks, such as the transfer mode between neurons in the human brain, it can quickly process the input information, and can continuously learn by itself. Applications such as intelligent cognition of theelectronic device 100 can be implemented through the NPU, such as image recognition, face recognition, speech recognition, text understanding, and the like.

外部存储器接口120可以用于连接外部存储卡，例如Micro SD卡，实现扩展电子设备100的存储能力。外部存储卡通过外部存储器接口120与处理器110通信，实现数据存储功能。例如将音乐，视频等文件保存在外部存储卡中。Theexternal memory interface 120 may be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of theelectronic device 100 . The external memory card communicates with theprocessor 110 through theexternal memory interface 120 to realize the data storage function. For example to save files like music, video etc in external memory card.

内部存储器121可以用于存储计算机可执行程序代码，所述可执行程序代码包括指令。处理器110通过运行存储在内部存储器121的指令，从而执行电子设备100的各种功能应用以及数据处理。内部存储器121可以包括存储程序区和存储数据区。其中，存储程序区可存储操作系统，至少一个功能所需的应用程序(比如声音播放功能，图像播放功能等)等。存储数据区可存储电子设备100使用过程中所创建的数据(比如音频数据，电话本等)等。此外，内部存储器121可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件，闪存器件，通用闪存存储器(universal flash storage，UFS)等。Internal memory 121 may be used to store computer executable program code, which includes instructions. Theprocessor 110 executes various functional applications and data processing of theelectronic device 100 by executing the instructions stored in the internal memory 121 . The internal memory 121 may include a storage program area and a storage data area. The storage program area can store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), and the like. The storage data area may store data (such as audio data, phone book, etc.) created during the use of theelectronic device 100 and the like. In addition, the internal memory 121 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, universal flash storage (UFS), and the like.

电子设备100可以通过音频模块170，扬声器170A，受话器170B，麦克风170C，耳机接口170D，以及应用处理器等实现音频功能。例如音乐播放，录音等。Theelectronic device 100 may implement audio functions through anaudio module 170, aspeaker 170A, a receiver 170B, amicrophone 170C, an earphone interface 170D, an application processor, and the like. Such as music playback, recording, etc.

音频模块170用于将数字音频信息转换成模拟音频信号输出，也用于将模拟音频输入转换为数字音频信号。音频模块170还可以用于对音频信号编码和解码。在一些实施例中，音频模块170可以设置于处理器110中，或将音频模块170的部分功能模块设置于处理器110中。Theaudio module 170 is used for converting digital audio information into analog audio signal output, and also for converting analog audio input into digital audio signal.Audio module 170 may also be used to encode and decode audio signals. In some embodiments, theaudio module 170 may be provided in theprocessor 110 , or some functional modules of theaudio module 170 may be provided in theprocessor 110 .

扬声器170A，也称“喇叭”，用于将音频电信号转换为声音信号。电子设备100可以通过扬声器170A收听音乐，或收听免提通话。Speaker 170A, also referred to as a "speaker", is used to convert audio electrical signals into sound signals. Theelectronic device 100 can listen to music through thespeaker 170A, or listen to a hands-free call.

受话器170B，也称“听筒”，用于将音频电信号转换成声音信号。当电子设备100接听电话或语音信息时，可以通过将受话器170B靠近人耳接听语音。The receiver 170B, also referred to as "earpiece", is used to convert audio electrical signals into sound signals. When theelectronic device 100 answers a call or a voice message, the voice can be answered by placing the receiver 170B close to the human ear.

麦克风170C，也称“话筒”，“传声器”，用于将声音信号转换为电信号。当拨打电话或发送语音信息时，用户可以通过人嘴靠近麦克风170C发声，将声音信号输入到麦克风170C。电子设备100可以设置至少一个麦克风170C。在另一些实施例中，电子设备100可以设置两个麦克风170C，除了采集声音信号，还可以实现降噪功能。在另一些实施例中，电子设备100还可以设置三个，四个或更多麦克风170C，实现采集声音信号，降噪，还可以识别声音来源，实现定向录音功能等。Themicrophone 170C, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can make a sound by approaching themicrophone 170C through a human mouth, and input the sound signal into themicrophone 170C. Theelectronic device 100 may be provided with at least onemicrophone 170C. In other embodiments, theelectronic device 100 may be provided with twomicrophones 170C, which can implement a noise reduction function in addition to collecting sound signals. In other embodiments, theelectronic device 100 may further be provided with three, four ormore microphones 170C to collect sound signals, reduce noise, identify sound sources, and implement directional recording functions.

耳机接口170D用于连接有线耳机。耳机接口170D可以是USB接口130，也可以是3.5mm的开放移动电子设备平台(open mobile terminal platform，OMTP)标准接口，美国蜂窝电信工业协会(cellular telecommunications industry association of the USA，CTIA)标准接口。The earphone jack 170D is used to connect wired earphones. The earphone port 170D may be theUSB port 130 or a 3.5mm open mobile terminal platform (OMTP) standard port, a cellular telecommunications industry association of the USA (CTIA) standard port.

压力传感器180A用于感受压力信号，可以将压力信号转换成电信号。在一些实施例中，压力传感器180A可以设置于显示屏194。压力传感器180A的种类很多，如电阻式压力传感器，电感式压力传感器，电容式压力传感器等。电容式压力传感器可以是包括至少两个具有导电材料的平行板。当有力作用于压力传感器180A，电极之间的电容改变。电子设备100根据电容的变化确定压力的强度。当有触摸操作作用于显示屏194，电子设备100根据压力传感器180A检测所述触摸操作强度。电子设备100也可以根据压力传感器180A的检测信号计算触摸的位置。在一些实施例中，作用于相同触摸位置，但不同触摸操作强度的触摸操作，可以对应不同的操作指令。例如：当有触摸操作强度小于第一压力阈值的触摸操作作用于短消息应用图标时，执行查看短消息的指令。当有触摸操作强度大于或等于第一压力阈值的触摸操作作用于短消息应用图标时，执行新建短消息的指令。The pressure sensor 180A is used to sense pressure signals, and can convert the pressure signals into electrical signals. In some embodiments, the pressure sensor 180A may be provided on the display screen 194 . There are many types of pressure sensors 180A, such as resistive pressure sensors, inductive pressure sensors, capacitive pressure sensors, and the like. The capacitive pressure sensor may be comprised of at least two parallel plates of conductive material. When a force is applied to the pressure sensor 180A, the capacitance between the electrodes changes. Theelectronic device 100 determines the intensity of the pressure according to the change in capacitance. When a touch operation acts on the display screen 194, theelectronic device 100 detects the intensity of the touch operation according to the pressure sensor 180A. Theelectronic device 100 may also calculate the touched position according to the detection signal of the pressure sensor 180A. In some embodiments, touch operations acting on the same touch position but with different touch operation intensities may correspond to different operation instructions. For example, when a touch operation whose intensity is less than the first pressure threshold acts on the short message application icon, the instruction for viewing the short message is executed. When a touch operation with a touch operation intensity greater than or equal to the first pressure threshold acts on the short message application icon, the instruction to create a new short message is executed.

陀螺仪传感器180B可以用于确定电子设备100的运动姿态。在一些实施例中，可以通过陀螺仪传感器180B确定电子设备100围绕三个轴(即，x，y和z轴)的角速度。陀螺仪传感器180B可以用于拍摄防抖。示例性的，当按下快门，陀螺仪传感器180B检测电子设备100抖动的角度，根据角度计算出镜头模组需要补偿的距离，让镜头通过反向运动抵消电子设备100的抖动，实现防抖。陀螺仪传感器180B还可以用于导航，体感游戏场景。The gyro sensor 180B may be used to determine the motion attitude of theelectronic device 100 . In some embodiments, the angular velocity ofelectronic device 100 about three axes (ie, x, y, and z axes) may be determined by gyro sensor 180B. The gyro sensor 180B can be used for image stabilization. Exemplarily, when the shutter is pressed, the gyro sensor 180B detects the shaking angle of theelectronic device 100, calculates the distance that the lens module needs to compensate according to the angle, and allows the lens to offset the shaking of theelectronic device 100 through reverse motion to achieve anti-shake. The gyro sensor 180B can also be used for navigation and somatosensory game scenarios.

气压传感器180C用于测量气压。在一些实施例中，电子设备100通过气压传感器180C测得的气压值计算海拔高度，辅助定位和导航。The air pressure sensor 180C is used to measure air pressure. In some embodiments, theelectronic device 100 calculates the altitude through the air pressure value measured by the air pressure sensor 180C to assist in positioning and navigation.

磁传感器180D包括霍尔传感器。电子设备100可以利用磁传感器180D检测翻盖皮套的开合。在一些实施例中，当电子设备100是翻盖机时，电子设备100可以根据磁传感器180D检测翻盖的开合。进而根据检测到的皮套的开合状态或翻盖的开合状态，设置翻盖自动解锁等特性。The magnetic sensor 180D includes a Hall sensor. Theelectronic device 100 can detect the opening and closing of the flip holster using the magnetic sensor 180D. In some embodiments, when theelectronic device 100 is a flip machine, theelectronic device 100 can detect the opening and closing of the flip according to the magnetic sensor 180D. Further, according to the detected opening and closing state of the leather case or the opening and closing state of the flip cover, characteristics such as automatic unlocking of the flip cover are set.

加速度传感器180E可检测电子设备100在各个方向上(一般为三轴)加速度的大小。当电子设备100静止时可检测出重力的大小及方向。还可以用于识别电子设备姿态，应用于横竖屏切换，计步器等应用。The acceleration sensor 180E can detect the magnitude of the acceleration of theelectronic device 100 in various directions (generally three axes). The magnitude and direction of gravity can be detected when theelectronic device 100 is stationary. It can also be used to identify the posture of electronic devices, and can be used in applications such as horizontal and vertical screen switching, pedometers, etc.

距离传感器180F，用于测量距离。电子设备100可以通过红外或激光测量距离。在一些实施例中，拍摄场景，电子设备100可以利用距离传感器180F测距以实现快速对焦。Distance sensor 180F for measuring distance. Theelectronic device 100 can measure the distance through infrared or laser. In some embodiments, when shooting a scene, theelectronic device 100 can use the distance sensor 180F to measure the distance to achieve fast focusing.

接近光传感器180G可以包括例如发光二极管(LED)和光检测器，例如光电二极管。发光二极管可以是红外发光二极管。电子设备100通过发光二极管向外发射红外光。电子设备100使用光电二极管检测来自附近物体的红外反射光。当检测到充分的反射光时，可以确定电子设备100附近有物体。当检测到不充分的反射光时，电子设备100可以确定电子设备100附近没有物体。电子设备100可以利用接近光传感器180G检测用户手持电子设备100贴近耳朵通话，以便自动熄灭屏幕达到省电的目的。接近光传感器180G也可用于皮套模式，口袋模式自动解锁与锁屏。Proximity light sensor 180G may include, for example, light emitting diodes (LEDs) and light detectors, such as photodiodes. The light emitting diodes may be infrared light emitting diodes. Theelectronic device 100 emits infrared light to the outside through the light emitting diode.Electronic device 100 uses photodiodes to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that there is an object near theelectronic device 100 . When insufficient reflected light is detected, theelectronic device 100 may determine that there is no object near theelectronic device 100 . Theelectronic device 100 can use the proximity light sensor 180G to detect that the user holds theelectronic device 100 close to the ear to talk, so as to automatically turn off the screen to save power. Proximity light sensor 180G can also be used in holster mode, pocket mode automatically unlocks and locks the screen.

环境光传感器180L用于感知环境光亮度。电子设备100可以根据感知的环境光亮度自适应调节显示屏194亮度。环境光传感器180L也可用于拍照时自动调节白平衡。环境光传感器180L还可以与接近光传感器180G配合，检测电子设备100是否在口袋里，以防误触。The ambient light sensor 180L is used to sense ambient light brightness. Theelectronic device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived ambient light brightness. The ambient light sensor 180L can also be used to automatically adjust the white balance when taking pictures. The ambient light sensor 180L can also cooperate with the proximity light sensor 180G to detect whether theelectronic device 100 is in a pocket, so as to prevent accidental touch.

指纹传感器180H用于采集指纹。电子设备100可以利用采集的指纹特性实现指纹解锁，访问应用锁，指纹拍照，指纹接听来电等。The fingerprint sensor 180H is used to collect fingerprints. Theelectronic device 100 can use the collected fingerprint characteristics to realize fingerprint unlocking, accessing application locks, taking pictures with fingerprints, answering incoming calls with fingerprints, and the like.

温度传感器180J用于检测温度。在一些实施例中，电子设备100利用温度传感器180J检测的温度，执行温度处理策略。例如，当温度传感器180J上报的温度超过阈值，电子设备100执行降低位于温度传感器180J附近的处理器的性能，以便降低功耗实施热保护。在另一些实施例中，当温度低于另一阈值时，电子设备100对电池142加热，以避免低温导致电子设备100异常关机。在其他一些实施例中，当温度低于又一阈值时，电子设备100对电池142的输出电压执行升压，以避免低温导致的异常关机。The temperature sensor 180J is used to detect the temperature. In some embodiments, theelectronic device 100 uses the temperature detected by the temperature sensor 180J to execute a temperature processing strategy. For example, when the temperature reported by the temperature sensor 180J exceeds a threshold value, theelectronic device 100 reduces the performance of the processor located near the temperature sensor 180J in order to reduce power consumption and implement thermal protection. In other embodiments, when the temperature is lower than another threshold, theelectronic device 100 heats the battery 142 to avoid abnormal shutdown of theelectronic device 100 caused by the low temperature. In some other embodiments, when the temperature is lower than another threshold, theelectronic device 100 boosts the output voltage of the battery 142 to avoid abnormal shutdown caused by low temperature.

触摸传感器180K，也称“触控面板”。触摸传感器180K可以设置于显示屏194，由触摸传感器180K与显示屏194组成触摸屏，也称“触控屏”。触摸传感器180K用于检测作用于其上或附近的触摸操作。触摸传感器可以将检测到的触摸操作传递给应用处理器，以确定触摸事件类型。可以通过显示屏194提供与触摸操作相关的视觉输出。在另一些实施例中，触摸传感器180K也可以设置于电子设备100的表面，与显示屏194所处的位置不同。Touch sensor 180K, also called "touch panel". The touch sensor 180K may be disposed on the display screen 194 , and the touch sensor 180K and the display screen 194 form a touch screen, also called a “touch screen”. The touch sensor 180K is used to detect a touch operation on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to touch operations may be provided through display screen 194 . In other embodiments, the touch sensor 180K may also be disposed on the surface of theelectronic device 100 , which is different from the location where the display screen 194 is located.

骨传导传感器180M可以获取振动信号。在一些实施例中，骨传导传感器180M可以获取人体声部振动骨块的振动信号。骨传导传感器180M也可以接触人体脉搏，接收血压跳动信号。在一些实施例中，骨传导传感器180M也可以设置于耳机中，结合成骨传导耳机。音频模块170可以基于所述骨传导传感器180M获取的声部振动骨块的振动信号，解析出语音信号，实现语音功能。应用处理器可以基于所述骨传导传感器180M获取的血压跳动信号解析心率信息，实现心率检测功能。The bone conduction sensor 180M can acquire vibration signals. In some embodiments, the bone conduction sensor 180M can acquire the vibration signal of the vibrating bone mass of the human voice. The bone conduction sensor 180M can also contact the pulse of the human body and receive the blood pressure beating signal. In some embodiments, the bone conduction sensor 180M can also be disposed in the earphone, combined with the bone conduction earphone. Theaudio module 170 can analyze the voice signal based on the vibration signal of the vocal vibration bone block obtained by the bone conduction sensor 180M, so as to realize the voice function. The application processor can analyze the heart rate information based on the blood pressure beat signal obtained by the bone conduction sensor 180M, and realize the function of heart rate detection.

按键190包括开机键，音量键等。按键190可以是机械按键。也可以是触摸式按键。电子设备100可以接收按键输入，产生与电子设备100的用户设置以及功能控制有关的键信号输入。The keys 190 include a power-on key, a volume key, and the like. Keys 190 may be mechanical keys. It can also be a touch key. Theelectronic device 100 may receive key inputs and generate key signal inputs related to user settings and function control of theelectronic device 100 .

马达191可以产生振动提示。马达191可以用于来电振动提示，也可以用于触摸振动反馈。例如，作用于不同应用(例如拍照，音频播放等)的触摸操作，可以对应不同的振动反馈效果。作用于显示屏194不同区域的触摸操作，马达191也可对应不同的振动反馈效果。不同的应用场景(例如：时间提醒，接收信息，闹钟，游戏等)也可以对应不同的振动反馈效果。触摸振动反馈效果还可以支持自定义。Motor 191 can generate vibrating cues. The motor 191 can be used for vibrating alerts for incoming calls, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, playing audio, etc.) can correspond to different vibration feedback effects. The motor 191 can also correspond to different vibration feedback effects for touch operations on different areas of the display screen 194 . Different application scenarios (for example: time reminder, receiving information, alarm clock, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

指示器192可以是指示灯，可以用于指示充电状态，电量变化，也可以用于指示消息，未接来电，通知等。The indicator 192 can be an indicator light, which can be used to indicate the charging state, the change of the power, and can also be used to indicate a message, a missed call, a notification, and the like.

SIM卡接口195用于连接SIM卡。SIM卡可以通过插入SIM卡接口195，或从SIM卡接口195拔出，实现和电子设备100的接触和分离。电子设备100可以支持1个或N个SIM卡接口，N为大于1的正整数。SIM卡接口195可以支持Nano SIM卡，Micro SIM卡，SIM卡等。同一个SIM卡接口195可以同时插入多张卡。所述多张卡的类型可以相同，也可以不同。SIM卡接口195也可以兼容不同类型的SIM卡。SIM卡接口195也可以兼容外部存储卡。电子设备100通过SIM卡和网络交互，实现通话以及数据通信等功能。在一些实施例中，电子设备100采用eSIM，即：嵌入式SIM卡。eSIM卡可以嵌在电子设备100中，不能和电子设备100分离。TheSIM card interface 195 is used to connect a SIM card. The SIM card can be contacted and separated from theelectronic device 100 by inserting into theSIM card interface 195 or pulling out from theSIM card interface 195 . Theelectronic device 100 may support 1 or N SIM card interfaces, where N is a positive integer greater than 1. TheSIM card interface 195 can support Nano SIM card, Micro SIM card, SIM card and so on. Multiple cards can be inserted into the sameSIM card interface 195 at the same time. The types of the plurality of cards may be the same or different. TheSIM card interface 195 can also be compatible with different types of SIM cards. TheSIM card interface 195 is also compatible with external memory cards. Theelectronic device 100 interacts with the network through the SIM card to implement functions such as call and data communication. In some embodiments, theelectronic device 100 employs an eSIM, ie: an embedded SIM card. The eSIM card can be embedded in theelectronic device 100 and cannot be separated from theelectronic device 100 .

电子设备100的软件系统可以采用分层架构，事件驱动架构，微核架构，微服务架构，或云架构。The software system of theelectronic device 100 may adopt a layered architecture, an event-driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture.

本申请实施例还提供了一种计算机可读存储介质，计算机可读存储介质存储有计算机程序，计算机程序被处理器执行时实现可实现上述各个方法实施例中的步骤。Embodiments of the present application further provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.

本申请实施例提供了一种计算机程序产品，当计算机程序产品在电子设备上运行时，使得电子设备执行时实现可实现上述各个方法实施例中的步骤。The embodiments of the present application provide a computer program product, when the computer program product runs on an electronic device, the steps in the foregoing method embodiments can be implemented when the electronic device executes.

本申请实施例还提供一种芯片系统，所述芯片系统包括处理器，所述处理器与存储器耦合，所述处理器执行存储器中存储的计算机程序，以实现如上述第一方面任一项所述的方法。所述芯片系统可以为单个芯片，或者多个芯片组成的芯片模组。An embodiment of the present application further provides a chip system, where the chip system includes a processor, the processor is coupled to a memory, and the processor executes a computer program stored in the memory, so as to implement any one of the above-mentioned first aspects. method described. The chip system may be a single chip, or a chip module composed of multiple chips.

在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。In the foregoing embodiments, the description of each embodiment has its own emphasis. For parts that are not described or described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。此外，在本申请说明书和所附权利要求书的描述中，术语“第一”、“第二”、“第三”等仅用于区分描述，而不能理解为指示或暗示相对重要性。在本申请说明书中描述的参考“一个实施例”或“一些实施例”等意味着在本申请的一个或多个实施例中包括结合该实施例描述的特定特征、结构或特点。由此，在本说明书中的不同之处出现的语句“在一个实施例中”、“在一些实施例中”、“在其他一些实施例中”、“在另外一些实施例中”等不是必然都参考相同的实施例，而是意味着“一个或多个但不是所有的实施例”，除非是以其他方式另外特别强调。It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. Furthermore, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be construed as indicating or implying relative importance. References in this specification to "one embodiment" or "some embodiments" and the like mean that a particular feature, structure or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in other embodiments," etc. in various places in this specification are not necessarily All refer to the same embodiment, but mean "one or more but not all embodiments" unless specifically emphasized otherwise.

最后应说明的是：以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何在本申请揭露的技术范围内的变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。Finally, it should be noted that: the above are only specific embodiments of the present application, but the protection scope of the present application is not limited to this, and any changes or replacements within the technical scope disclosed in the present application should be covered by the present application. within the scope of protection of the application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.