CN116246793A - User health portrait generation method and device based on wearable equipment - Google Patents
User health portrait generation method and device based on wearable equipmentDownload PDFInfo
- Publication number
- CN116246793A CN116246793ACN202211710641.7ACN202211710641ACN116246793ACN 116246793 ACN116246793 ACN 116246793ACN 202211710641 ACN202211710641 ACN 202211710641ACN 116246793 ACN116246793 ACN 116246793A
- Authority
- CN
- China
- Prior art keywords
- data
- source
- portrait
- user
- sign
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本申请涉及计算机技术领域，尤其涉及一种基于可穿戴设备的用户健康画像生成方法及装置。The present application relates to the field of computer technology, and in particular to a wearable device-based user health profile generation method and device.
背景技术Background technique
相关技术中，用户画像方法多依赖于用户主动使用相关设备、app采集埋点数据构建行为习惯画像，少有能够与可穿戴设备结合的方法，缺乏数据更新的实时性；另一方面，用户画像方法大多使用单批次数据独立地构建用户画像，无法利用到长期数据及实时数据，画像扩展性低；最后，用户画像方法单一地对用户当前体征特征、行为特征等进行特征抽取及画像构建，无法应对用户罹患疾病、行为习惯改变等情况造成的用户特征短期内快速偏离，从而使得画像整体有偏。In related technologies, the user portrait method mostly relies on the user to actively use related equipment and app to collect buried point data to construct a behavior habit portrait, and there are few methods that can be combined with wearable devices, lacking real-time data update; on the other hand, user portrait Most of the methods use a single batch of data to independently construct user portraits, which cannot use long-term data and real-time data, and the portrait scalability is low; finally, the user portrait method only performs feature extraction and portrait construction on the user's current physical signs and behavior characteristics. Unable to cope with the rapid deviation of user characteristics in a short period of time caused by users suffering from diseases, changes in behavior habits, etc., which makes the overall portrait biased.
发明内容Contents of the invention
为此，本申请提供一种基于可穿戴设备的用户健康画像生成方法及装置。本申请的技术方案如下：To this end, the present application provides a wearable device-based user health profile generation method and device. The technical scheme of the application is as follows:
根据本申请实施例的第一方面，提供一种基于可穿戴设备的用户健康画像生成方法，所述方法包括：According to the first aspect of the embodiments of the present application, a wearable device-based user health profile generation method is provided, the method comprising:
获取对象的多源体征数据；Obtain the multi-source sign data of the subject;
对所述多源体征数据进行融合处理，以得到融合数据；performing fusion processing on the multi-source sign data to obtain fusion data;
确定所述多源体征数据的数据类型；所述数据类型包括正常数据和异常数据；Determine the data type of the multi-source sign data; the data type includes normal data and abnormal data;
响应于所述多源体征数据的数据类型为正常数据，基于所述融合数据，对所述对象的预先构建的用户常规画像进行更新处理；In response to the fact that the data type of the multi-source vital sign data is normal data, based on the fusion data, update the pre-built user routine portrait of the object;
响应于所述多源体征数据的数据类型为异常数据，基于所述融合数据生成用户偏置画像。In response to the fact that the data type of the multi-source vital sign data is abnormal data, a user bias portrait is generated based on the fusion data.
根据本申请的一个实施例，所述对象的多源体征数据包括所述对象的体征状态；所述确定所述多源体征数据的数据类型，包括：According to an embodiment of the present application, the multi-source vital sign data of the subject includes the subject's sign status; the determining the data type of the multi-source sign data includes:
基于所述对象的多源体征数据，获取所述对象的体征状态；Obtaining the sign status of the subject based on the multi-source sign data of the subject;
响应于所述体征状态为异常状态，确定所述多源体征数据的类型为异常数据；In response to the sign state being an abnormal state, determining that the type of the multi-source sign data is abnormal data;
响应于所述体征状态为正常状态，确定所述多源体征数据的类型为正常数据。In response to the sign state being a normal state, it is determined that the type of the multi-source sign data is normal data.
根据本申请的一个实施例，所述响应于所述多源体征数据的数据类型为异常数据，基于所述融合数据生成用户偏置画像，还包括：According to an embodiment of the present application, in response to the fact that the data type of the multi-source vital sign data is abnormal data, generating a user bias portrait based on the fusion data further includes:
响应于所述多源体征数据的数据类型为异常数据，将所述体征状态确定为所述多源体征数据对应的第一标签；In response to the data type of the multi-source sign data being abnormal data, determining the sign state as the first label corresponding to the multi-source sign data;
查找与所述第一标签对应的用户偏置画像；Find a user bias portrait corresponding to the first label;
响应于查找到与所述第一标签对应的用户偏置画像，基于所述融合数据，对与所述第一标签对应的用户偏置画像进行更新处理；In response to finding the user bias portrait corresponding to the first tag, based on the fusion data, update the user bias portrait corresponding to the first tag;
响应于未查找到与所述标签对应的用户偏置画像，基于所述融合数据，生成与所述第一标签对应的用户偏置画像。In response to finding no user bias portrait corresponding to the tag, based on the fusion data, generate a user bias portrait corresponding to the first tag.
根据本申请的一个实施例，所述确定所述多源体征数据的数据类型，还包括：According to an embodiment of the present application, the determining the data type of the multi-source vital sign data further includes:
响应于接收到客户端发送的异常数据时间段和所述异常数据时间段对应的第二标签，确定所述异常数据时间段对应的多源体征数据的数据类型为异常数据。In response to receiving the abnormal data time period sent by the client and the second tag corresponding to the abnormal data time period, it is determined that the data type of the multi-source vital sign data corresponding to the abnormal data time period is abnormal data.
根据本申请的一个实施例，所述响应于所述多源体征数据为异常数据，基于所述融合数据生成用户偏置画像，还包括：According to an embodiment of the present application, generating a biased portrait of a user based on the fused data in response to the multi-source vital sign data being abnormal data further includes:
响应于所述多源体征数据为异常数据，查找与所述第二标签对应的用户偏置画像；In response to the fact that the multi-source vital sign data is abnormal data, search for a user bias portrait corresponding to the second tag;
响应于查找到与所述第二标签对应的用户偏置画像，基于所述融合数据，对与所述第二标签对应的用户偏置画像进行更新处理；In response to finding the user bias portrait corresponding to the second tag, based on the fusion data, update the user bias portrait corresponding to the second tag;
响应于未查找到与所述第二标签对应的用户偏置画像，基于所述融合数据，生成与所述第二标签对应的用户偏置画像。In response to finding no user bias portrait corresponding to the second tag, generating a user bias portrait corresponding to the second tag based on the fusion data.
根据本申请的一个实施例，在所述响应于接收到客户端发送的异常数据时间段和所述异常数据时间段对应的第二标签，确定所述异常数据时间段对应的多源体征数据的数据类型为异常数据之后，还包括：According to an embodiment of the present application, in response to receiving the abnormal data time period sent by the client and the second tag corresponding to the abnormal data time period, determine the multi-source sign data corresponding to the abnormal data time period After the data type is abnormal data, it also includes:
响应于已经基于所述异常数据时间段对应的多源体征数据对所述用户常规画像进行更新处理，将更新处理后的所述用户常规画像调整为更新处理前的用户常规画像。In response to updating the user's regular portrait based on the multi-source sign data corresponding to the abnormal data time period, the updated user's regular portrait is adjusted to the user's regular portrait before the update process.
根据本申请实施例的第二方面，提供一种基于可穿戴设备的用户健康画像生成装置装置，所述装置包括：According to the second aspect of the embodiment of the present application, there is provided a wearable device-based user health portrait generating device, the device comprising:
获取模块，用于获取对象的多源体征数据；An acquisition module, configured to acquire multi-source sign data of an object;
融合模块，用于对所述多源体征数据进行融合处理，以得到融合数据；a fusion module, configured to perform fusion processing on the multi-source sign data to obtain fusion data;
确定模块，用于确定所述多源体征数据的数据类型；所述数据类型包括正常数据和异常数据；A determining module, configured to determine the data type of the multi-source sign data; the data type includes normal data and abnormal data;
更新模块，用于响应于所述多源体征数据的数据类型为正常数据，基于所述融合数据，对所述对象的预先构建的用户常规画像进行更新处理；An update module, configured to update the pre-built user routine portrait of the object based on the fusion data in response to the fact that the data type of the multi-source vital sign data is normal data;
生成模块，用于响应于所述多源体征数据的数据类型为异常数据，基于所述融合数据生成用户偏置画像。A generation module, configured to generate a user bias portrait based on the fusion data in response to the data type of the multi-source vital sign data being abnormal data.
根据本申请实施例的第三方面，提供一种电子设备，包括：处理器，以及与所述处理器通信连接的存储器；According to a third aspect of the embodiments of the present application, there is provided an electronic device, including: a processor, and a memory communicatively connected to the processor;
所述存储器存储计算机执行指令；the memory stores computer-executable instructions;
所述处理器执行所述存储器存储的计算机执行指令，以实现如第一方面中任一项所述的方法。The processor executes the computer-implemented instructions stored in the memory to implement the method according to any one of the first aspects.
根据本申请实施例的第四方面，提供一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机执、行指令，所述计算机执行指令被处理器执行时用于实现如第一方面中任一项所述的方法。According to the fourth aspect of the embodiments of the present application, there is provided a computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the above-mentioned method when executed by a processor. The method of any one of the aspects.
根据本申请实施例的第五方面，提供一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现第一方面中任一项所述的方法According to a fifth aspect of the embodiments of the present application, there is provided a computer program product, including a computer program, which implements the method described in any one of the first aspects when the computer program is executed by a processor
本申请的实施例提供的技术方案至少带来以下有益效果：The technical solutions provided by the embodiments of the present application bring at least the following beneficial effects:
通过通过获取对象的多源体征数据；对多源体征数据进行融合处理，以得到融合数据；确定多源体征数据的数据类型；响应于多源体征数据的数据类型为正常数据，基于融合数据，对对象的预先构建的用户常规画像进行更新处理；响应于多源体征数据的数据类型为异常数据，基于融合数据生成用户偏置画像，从而保证对用户画像及时更新的同时提高了用户画像的准确性；另外，通过为同一对象分别构建用户常规画像和用户偏置画像，能够更加准确的掌握对象在健康状态下和患病状态下的身体情况，同时提升画像下游预警功能效果。By acquiring the multi-source sign data of the object; performing fusion processing on the multi-source sign data to obtain fusion data; determining the data type of the multi-source sign data; responding to the fact that the data type of the multi-source sign data is normal data, based on the fusion data, Update the pre-built user portrait of the object; in response to the data type of the multi-source sign data being abnormal data, generate a user bias portrait based on the fusion data, thereby ensuring timely update of the user portrait and improving the accuracy of the user portrait In addition, by constructing user regular portraits and user offset portraits for the same object, it is possible to more accurately grasp the physical condition of the object in a healthy state and in a diseased state, and at the same time improve the downstream early warning function of the portrait.
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本申请。It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
附图说明Description of drawings
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本申请的实施例，并与说明书一起用于解释本申请的原理，并不构成对本申请的不当限定。The accompanying drawings here are incorporated into the specification and constitute a part of the specification, show the embodiment consistent with the application, and are used together with the specification to explain the principle of the application, and do not constitute an improper limitation of the application.
图1为本申请实施例中的一种基于可穿戴设备的用户健康画像生成方法的流程图；FIG. 1 is a flow chart of a wearable device-based user health profile generation method in an embodiment of the present application;
图2为本申请实施例中的另一种基于可穿戴设备的用户健康画像生成方法的流程图；FIG. 2 is a flow chart of another wearable device-based user health profile generation method in the embodiment of the present application;
图3为本申请实施例中的一种基于可穿戴设备的用户健康画像生成装置的结构框图；FIG. 3 is a structural block diagram of a wearable device-based user health portrait generation device in an embodiment of the present application;
图4为本申请实施例中的一种电子设备的框图。Fig. 4 is a block diagram of an electronic device in an embodiment of the present application.
具体实施方式Detailed ways
为了使本领域普通人员更好地理解本申请的技术方案，下面将结合附图，对本申请实施例中的技术方案进行清楚、完整地描述。In order to enable ordinary persons in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。以下示例性实施例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。It should be noted that the terms "first" and "second" in the description and claims of the present application and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.
需要说明的是，基于可穿戴设备能够实时监测用户的心率、血氧、心率变异性、体温、活动情况等体征信息，用于用户对个人健康情况的实时监测。同时基于以上体征信息也能够构建用户的个人健康画像，从而应用于下游推荐、预警等场景中。一般来说，用户的个人健康画像与传统的健康画像不同，传统的用户画像着重于学习用户的行为习惯、个人特征等形成标签，并主要应用于商品服务推荐场景，而用户健康画像着重于利用用户个人短期或长期的健康信息，学习构建用户个人不同体征的常态稳态值，从而在下游疾病预警、辅助诊断等场景中提供重要的患者健康信息，提升后续应用效果。目前用户画像方法多依赖于用户主动使用相关设备、app采集埋点数据构建行为习惯画像，少有能够与可穿戴设备结合的方法，缺乏数据更新的实时性；另一方面，目前的用户画像方法大多使用单批次数据独立地构建用户画像，无法利用到长期数据及实时数据，画像扩展性低；最后，目前的用户画像方法单一地对用户当前体征特征、行为特征等进行特征抽取及画像构建，无法应对用户罹患疾病、行为习惯改变等情况造成的用户特征短期内快速偏离，从而使得画像整体有偏。It should be noted that based on the wearable device, it can monitor the user's heart rate, blood oxygen, heart rate variability, body temperature, activity status and other sign information in real time, which is used for real-time monitoring of the user's personal health. At the same time, a user's personal health portrait can also be constructed based on the above physical signs, which can be applied to downstream recommendation, early warning and other scenarios. Generally speaking, the user's personal health profile is different from the traditional health profile. The traditional user profile focuses on learning the user's behavior habits and personal characteristics to form tags, which are mainly used in commodity service recommendation scenarios, while the user health profile focuses on using The user's personal short-term or long-term health information, learn to build the normal steady-state value of different personal signs of the user, so as to provide important patient health information in downstream disease early warning, auxiliary diagnosis and other scenarios, and improve the follow-up application effect. At present, user portrait methods mostly rely on the user's active use of related equipment and app to collect embedded data to construct behavior habit portraits. There are few methods that can be combined with wearable devices, and lack real-time data update; on the other hand, the current user portrait methods Most of them use a single batch of data to independently construct user portraits, which cannot use long-term data and real-time data, and the portrait scalability is low; finally, the current user portrait methods only perform feature extraction and portrait construction on the user's current physical signs and behavior characteristics. , unable to cope with the rapid deviation of user characteristics in a short period of time caused by users suffering from diseases, changes in behavior habits, etc., which makes the overall portrait biased.
基于上述问题，本申请提出了一种基于可穿戴设备的用户健康画像生成方法及装置，可以实现通过获取对象的多源体征数据；对多源体征数据进行融合处理，以得到融合数据；确定多源体征数据的数据类型；响应于多源体征数据的数据类型为正常数据，基于融合数据，对对象的预先构建的用户常规画像进行更新处理；响应于多源体征数据的数据类型为异常数据，基于融合数据生成用户偏置画像。从而保证对用户画像及时更新的同时提高了用户画像的准确性；另外，通过为同一对象分别构建用户常规画像和用户偏置画像，能够更加准确的掌握对象在健康状态下和患病状态下的身体情况，同时提升画像下游预警功能效果。Based on the above problems, this application proposes a method and device for generating user health portraits based on wearable devices, which can obtain multi-source physical sign data of objects; perform fusion processing on multi-source physical sign data to obtain fusion data; determine multiple The data type of the source sign data; in response to the fact that the data type of the multi-source sign data is normal data, based on the fusion data, the pre-built user routine portrait of the object is updated; in response to the data type of the multi-source sign data being abnormal data, Generate user bias portraits based on fused data. In this way, the accuracy of user portraits is improved while ensuring timely update of user portraits; in addition, by constructing user regular portraits and user bias portraits for the same object, it is possible to more accurately grasp the status of the object in a healthy state and in a diseased state. Physical condition, and at the same time improve the effect of the downstream warning function of the portrait.
图1为本申请实施例中的一种基于可穿戴设备的用户健康画像生成方法的流程图。FIG. 1 is a flow chart of a wearable device-based user health profile generation method in an embodiment of the present application.
如图1所示，该基于可穿戴设备的用户健康画像生成方法包括：As shown in Figure 1, the wearable device-based user health profile generation method includes:
步骤101，获取对象的多源体征数据。
作为一种可能实施的示例，多源体征数据可以由可穿戴设备采集得到，上述可穿戴设备可以是手环、手表、皮肤贴片、眼镜中的任意一种或多种。上述多源体征数据可以包括但不限于体温、心率、心率变异性、呼吸率、血氧、活动状况、睡眠状况等信息。As an example of a possible implementation, the multi-source vital sign data may be collected by a wearable device, and the wearable device may be any one or more of a bracelet, a watch, a skin patch, and glasses. The above multi-source sign data may include but not limited to body temperature, heart rate, heart rate variability, respiration rate, blood oxygen, activity status, sleep status and other information.
步骤102，对多源体征数据进行融合处理，以得到融合数据。
作为一种可能实施的示例，步骤102包括以下步骤：As an example of a possible implementation,
步骤A1，获取对象在第一时间段的各数据源的体征数据。Step A1, acquiring the vital sign data of each data source of the subject in the first time period.
其中，在本申请实施例中，每个数据源的体征数据均包括多个体征值和多个体征值各自的采集时间。Wherein, in the embodiment of the present application, the sign data of each data source includes a plurality of sign values and respective collection times of the plurality of sign values.
作为一种可能实施的示例，抽取对象佩戴可穿戴设备测得的第一时间段不同源的体征数据，传感器采集类数据可以包括温度传感器计算的温度、加速度传感器计算的活动频次、呼吸传感器计算的呼吸率、光学心率传感器计算的心率值、光学血氧传感器计算的血氧饱和度；电信号类数据可以包括PPG皮肤电信号、ECG心电信号、EEG脑电信号、EMG肌电信号等原始电信号波形数据；用户信息包括用户的基本信息、对应App埋点信息、用户健康画像等；公开数据集类包括美国的MIT-BIH ECG心电数据集、美国AHA心率失常的ECG心电数据集等各种电信号数据集。As an example of a possible implementation, the physical sign data from different sources in the first time period measured by the subject wearing a wearable device is extracted. The sensor collection data may include the temperature calculated by the temperature sensor, the activity frequency calculated by the acceleration sensor, and the frequency calculated by the respiration sensor. Respiration rate, heart rate value calculated by optical heart rate sensor, blood oxygen saturation calculated by optical blood oxygen sensor; electrical signal data can include PPG skin electrical signal, ECG electrocardiographic signal, EEG brain electrical signal, EMG electromyographic signal and other raw electrical signals Signal waveform data; user information includes basic information of the user, corresponding App buried point information, user health portrait, etc.; public data sets include the MIT-BIH ECG data set in the United States, the ECG data set of AHA arrhythmia in the United States, etc. Various electrical signal datasets.
步骤A2，根据多个体征值各自采集时间，按照第一预设时长将每个数据源的体征数据分别划分为多组子数据。Step A2, divide the vital sign data of each data source into multiple groups of sub-data according to the first preset duration according to the respective collection times of the multiple vital sign values.
在本申请一些实施例中，第一预设时长有多个，步骤A2具体包括：针对每个第一预设时长，根据多个体征值各自的采集时间，按照第一预设时长将每个数据源的体征数据分别划分为多组子数据。In some embodiments of the present application, there are multiple first preset durations, and step A2 specifically includes: for each first preset duration, according to the respective acquisition times of multiple sign values, each The sign data of the data source are divided into multiple groups of sub-data respectively.
可选的，第一预设时长可以是根据实际需求预先设定的时长。Optionally, the first preset duration may be a preset duration according to actual needs.
作为一种可能实施的示例，为了增加整合后数据的适用性，可以将各数据源的体征数据按照不同的预设时长划分为不长度的子数据。举例来说，第一预设时长可以是5分钟、10分钟、20分钟，第一时间段为2小时。则根据多个体征值各自的采集时间，将每个数据源的体征数据将每5分钟采集到的体征数据划分为1组子数据，从而使每个数据源的体征数据均得到36组子数据；将每个数据源的体征数据将每10分钟采集到的体征数据划分为1组子数据，从而使每个数据源的体征数据均得到18组子数据；将每个数据源的体征数据将每20分钟采集到的体征数据划分为1组子数据，从而使每个数据源的体征数据均得到9组子数据。As an example of a possible implementation, in order to increase the applicability of the integrated data, the sign data of each data source may be divided into sub-data of different lengths according to different preset time lengths. For example, the first preset duration can be 5 minutes, 10 minutes, 20 minutes, and the first time period is 2 hours. According to the collection time of multiple sign values, the sign data of each data source is divided into 1 group of sub-data collected every 5 minutes, so that the sign data of each data source can get 36 groups of sub-data ; The sign data of each data source is divided into 1 group of sub-data by the sign data collected every 10 minutes, so that the sign data of each data source is obtained 18 groups of sub-data; The sign data of each data source is divided into The sign data collected every 20 minutes is divided into 1 group of sub-data, so that the sign data of each data source can get 9 groups of sub-data.
步骤A3，基于多组子数据的体征值，分别确定每组子数据各自的目标指标值。Step A3, based on the sign values of multiple sets of sub-data, respectively determine the respective target index value of each set of sub-data.
在本申请一些实施例中，步骤A3包括：In some embodiments of the present application, step A3 includes:
步骤A31，分别确定每组子数据各自的所属类型。Step A31, respectively determine the type to which each group of sub-data belongs.
步骤A32，根据每组子数据各自的所属类型，分别确定每组子数据各自的至少一种目标指标值的类型。Step A32, according to the respective types of each group of sub-data, respectively determine the type of at least one target index value for each group of sub-data.
可以理解的是，不同数据源的体征数据所属类型不同，因此根据每组子数据各自的所属类型，分别确定每组子数据各自的至少一种目标指标值的类型。举例来说，对于全部类型的体征数据，均需要计算以下类型的目标指标值：均值、中位数、标准差、分位距(IQR)、峰度、偏度、测量点个数、分箱占比情况。若体征数据类型为心率数据，目标指标值的类型还包括心率变异性指标。It can be understood that different data sources have different types of vital sign data, so according to the respective types of each group of sub-data, the type of at least one target index value for each group of sub-data is respectively determined. For example, for all types of sign data, the following types of target index values need to be calculated: mean, median, standard deviation, quantile range (IQR), kurtosis, skewness, number of measurement points, binning proportion. If the sign data type is heart rate data, the type of the target index value also includes a heart rate variability index.
步骤A33，基于子数据的体征值，分别计算至少一种目标指标值的类型各自对应的目标指标值。Step A33, based on the sign values of the sub-data, respectively calculate target index values corresponding to at least one type of target index value.
步骤A4，将所属同一采集时间的子数据以及所属同一采集时间的子数据各自对应的目标指标值确定为一组融合子数据。In step A4, the sub-data belonging to the same collection time and the corresponding target index values of the sub-data belonging to the same collection time are determined as a set of fused sub-data.
步骤A5，将多组融合子数据确定为多源数据的融合数据。In step A5, multiple sets of fused sub-data are determined as fused data of multi-source data.
作为一种可能实施的示例，服务器将所属同一采集时间的子数据以及所属同一采集时间的子数据各自对应的目标指标值确定为一组融合子数据，将多组融合子数据确定为多源数据的融合数据。As an example of a possible implementation, the server determines the sub-data belonging to the same collection time and the target index values corresponding to the sub-data belonging to the same collection time as a set of fused sub-data, and determines multiple sets of fused sub-data as multi-source data fusion data.
步骤103，确定多源体征数据的数据类型。
其中，在本申请实施例中，数据类型包括正常数据和异常数据。Wherein, in the embodiment of the present application, the data type includes normal data and abnormal data.
其中，在本申请一些实施例中，对象的多源体征数据包括对象的体征状态，步骤103包括：Wherein, in some embodiments of the present application, the multi-source sign data of the subject includes the sign status of the subject, and step 103 includes:
步骤a1，基于对象的多源体征数据，获取对象的体征状态。Step a1, based on the multi-source sign data of the subject, the sign status of the subject is acquired.
作为一种可能实施方式的示例，多源体征数据包括对象的体征状态，可以从对象的多源体征数据中获取对象的体征状态。例如，若多源体征数据中包括对象的病例信息，则可以在病例信息中获取到对象的体征状态，如发烧、高血压等。As an example of a possible implementation manner, the multi-source sign data includes the subject's sign state, and the subject's sign state may be acquired from the subject's multi-source sign data. For example, if the multi-source sign data includes the subject's case information, the subject's sign status, such as fever and high blood pressure, can be obtained from the case information.
步骤a2，响应于体征状态为异常状态，确定多源体征数据的类型为异常数据。In step a2, in response to the fact that the sign state is an abnormal state, it is determined that the type of the multi-source sign data is abnormal data.
作为一种可能实施方式的示例，响应于体征状态非健康状态，则确定该体征状态为异常状态，进而确定多源体征数据的类型为异常数据。As an example of a possible implementation manner, in response to the sign state being unhealthy, it is determined that the sign state is an abnormal state, and then the type of the multi-source sign data is determined to be abnormal data.
步骤a3，响应于体征状态为正常状态，确定多源体征数据的类型为正常数据。In step a3, in response to the fact that the sign status is normal, it is determined that the type of the multi-source sign data is normal data.
作为一种可能实施方式的示例，响应于体征状态健康状态，确定体征状态为正常状态，进而确定多源体征数据的类型为正常数据。As an example of a possible implementation manner, in response to the health status of the physical signs, it is determined that the physical signs are in a normal state, and then the type of the multi-source physical sign data is determined to be normal data.
步骤104，响应于多源体征数据的数据类型为正常数据，基于融合数据，对对象的预先构建的用户常规画像进行更新处理。
作为一种可能实施方式的示例，画像更新是在用户已建立的常规画像的基础上，使用新采集的正常数据更新画像的过程。根据画像所使用的统计指标的不同，计算方式不同，常见的均值与标准差更新的方法如下：As an example of a possible implementation, the portrait update is a process of updating the portrait with newly collected normal data on the basis of the regular portrait established by the user. Depending on the statistical indicators used in the portrait, the calculation methods are different. The common methods for updating the mean and standard deviation are as follows:
其中，m0为画像更新前体征均值，v0为画像更新前体征标准差，n0为画像更新前体征数据条数，以上三个数据均从已建立的画像中获取；Dn为新体征数据队列，n1为该队列体征数据条数，以上两个数据从新采集数据中获取；m1为画像更新后体征均值，v1为画像更新后体征标准差。同时需要将画像体征数据条数予以更新。Among them, m0 is the mean value of the physical signs before the portrait update, v0 is the standard deviation of the physical signs before the portrait update, n0 is the number of physical sign data before the portrait update, and the above three data are obtained from the established portraits; Dn is the new physical signs Data queue, n1 is the number of physical signs data in this queue, and the above two data are obtained from newly collected data; m1 is the mean value of physical signs after the portrait is updated, and v1 is the standard deviation of physical signs after the portrait is updated. At the same time, the number of portrait sign data items needs to be updated.
步骤105，响应于多源体征数据的数据类型为异常数据，基于融合数据生成用户偏置画像。
其中，在本申请一些实施例中，步骤105包括：Wherein, in some embodiments of the present application,
步骤b1，响应于多源体征数据的数据类型为异常数据，将体征状态确定为多源体征数据对应的第一标签。Step b1, in response to the fact that the data type of the multi-source sign data is abnormal data, determine the sign state as the first label corresponding to the multi-source sign data.
举例来说，对象的体征状态为发烧，则确定对象的多源体征数据的数据类型为异常数据，将发烧确定为多源体征数据对应的第一标签。For example, if the sign status of the subject is fever, the data type of the multi-source sign data of the subject is determined to be abnormal data, and fever is determined as the first label corresponding to the multi-source sign data.
步骤b2，查找与第一标签对应的用户偏置画像。Step b2, searching for the user bias portrait corresponding to the first tag.
步骤b3，响应于查找到与第一标签对应的用户偏置画像，基于融合数据，对与第一标签对应的用户偏置画像进行更新处理。Step b3, in response to finding the user bias portrait corresponding to the first tag, based on the fusion data, update the user bias portrait corresponding to the first tag.
作为一种可能实施方式的示例，响应于查找到与第一标签对应的用户偏置画像，说明已经建立了与第一标签对应的用户偏置画像，基于融合数据对与第一标签对应的用户偏置画像进行更新处理。As an example of a possible implementation, in response to finding the user bias portrait corresponding to the first label, it means that the user bias portrait corresponding to the first label has been established, and based on the fusion data, the user corresponding to the first label The offset image is updated.
步骤b4，响应于未查找到与标签对应的用户偏置画像，基于融合数据，生成与第一标签对应的用户偏置画像。Step b4, in response to finding no user bias portrait corresponding to the label, based on the fused data, generate a user bias portrait corresponding to the first label.
作为一种可能实施方式的示例，响应于未查找到与标签对应的用户偏置画像，说明还未经建立了与第一标签对应的用户偏置画像，因此，基于融合数据生成与第一标签对应的用户偏置画像。As an example of a possible implementation, in response to not finding the user bias portrait corresponding to the label, it means that the user bias portrait corresponding to the first label has not yet been established, therefore, based on the fused data, a user bias portrait corresponding to the first label is generated Corresponding user bias profile.
根据本申请实施例的基于可穿戴设备的用户健康画像生成方法，通过获取对象的多源体征数据；对多源体征数据进行融合处理，以得到融合数据；确定多源体征数据的数据类型；响应于多源体征数据的数据类型为正常数据，基于融合数据，对对象的预先构建的用户常规画像进行更新处理；响应于多源体征数据的数据类型为异常数据，基于融合数据生成用户偏置画像。从而保证对用户画像及时更新的同时提高了用户画像的准确性；另外，通过为同一对象分别构建用户常规画像和用户偏置画像，能够更加准确的掌握对象在健康状态下和患病状态下的身体情况，同时提升画像下游预警功能效果。According to the method for generating a health portrait of a user based on a wearable device according to an embodiment of the present application, by acquiring the multi-source sign data of the object; performing fusion processing on the multi-source sign data to obtain the fused data; determining the data type of the multi-source sign data; responding Since the data type of the multi-source sign data is normal data, based on the fusion data, the pre-built user routine portrait of the object is updated; in response to the data type of the multi-source sign data being abnormal data, the user bias portrait is generated based on the fusion data . In this way, the accuracy of user portraits is improved while ensuring timely update of user portraits; in addition, by constructing user regular portraits and user bias portraits for the same object, it is possible to more accurately grasp the status of the object in a healthy state and in a diseased state. Physical condition, and at the same time improve the effect of the downstream warning function of the portrait.
图2为本申请实施例中的另一种基于可穿戴设备的用户健康画像生成方法的流程图。FIG. 2 is a flow chart of another wearable device-based user health profile generation method in the embodiment of the present application.
如图2所示，该基于可穿戴设备的用户健康画像生成方法包括：As shown in Figure 2, the wearable device-based user health profile generation method includes:
步骤201，获取对象的多源体征数据。
在本申请的实施例中，步骤201可以分别采用本申请的各实施例中的任一种方式实现，本申请实施例并不对此作出限定，也不再赘述。In the embodiment of the present application,
步骤202，对多源体征数据进行融合处理，以得到融合数据。
在本申请的实施例中，步骤202可以分别采用本申请的各实施例中的任一种方式实现，本申请实施例并不对此作出限定，也不再赘述。In the embodiment of the present application,
步骤203，确定多源体征数据的数据类型。
其中，在本申请实施例中，数据类型包括正常数据和异常数据。Wherein, in the embodiment of the present application, the data type includes normal data and abnormal data.
其中，在本申请一些实施例中，步骤203包括：响应于接收到客户端发送的异常数据时间段和异常数据时间段对应的第二标签，确定异常数据时间段对应的多源体征数据的数据类型为异常数据。Wherein, in some embodiments of the present application,
可选的，可以通过客户端对患病等异常事件的起止时间及事件类型进行标记，以便于后需统计计算何时、因何事的偏置画像。标记来源可以包括但不限于用户自主选定、通过医院病历自动解析、通过体征监测自动分类等。Optionally, the client can mark the start and end times and event types of abnormal events such as illnesses, so as to facilitate statistical calculation of when and why biased portraits. Marking sources may include, but are not limited to, self-selection by users, automatic analysis through hospital medical records, automatic classification through physical sign monitoring, etc.
步骤204，响应于已经基于异常数据时间段对应的多源体征数据对用户常规画像进行更新处理，将更新处理后的用户常规画像调整为更新处理前的用户常规画像。
可选的，可以在事件开始发生后先选定开始时间、时间结束后选定结束时间，也可以在事件结束后一次性选定起止时间。Optionally, the start time can be selected first after the event starts to occur, and the end time can be selected after the time ends, or the start and end time can be selected all at once after the event ends.
作为一种可能实施的示例，响应于已经基于异常数据时间段对应的多源体征数据对用户常规画像进行更新处理，此时的用户常规画像已经出现了偏差，因此将更新处理后的用户常规画像回溯为上述更新处理前的用户常规画像，从而将异常数据从用户常规画像中去除，以保证用户常规画像的准确性。As an example of a possible implementation, in response to the fact that the user's regular portrait has been updated based on the multi-source sign data corresponding to the abnormal data time period, the user's regular portrait at this time has already deviated, so the processed user's regular portrait will be updated Backtrack to the user's regular portrait before the above update process, so as to remove abnormal data from the user's regular portrait to ensure the accuracy of the user's regular portrait.
步骤205，响应于多源体征数据的数据类型为正常数据，基于融合数据，对对象的预先构建的用户常规画像进行更新处理。
在本申请的实施例中，步骤205可以分别采用本申请的各实施例中的任一种方式实现，本申请实施例并不对此作出限定，也不再赘述。In the embodiment of the present application,
步骤206，响应于多源体征数据的数据类型为异常数据，基于融合数据生成用户偏置画像。
其中，在本申请一些实施例中，步骤206包括：Wherein, in some embodiments of the present application,
步骤b1，响应于多源体征数据为异常数据，查找与第二标签对应的用户偏置画像。Step b1, in response to the fact that the multi-source vital sign data is abnormal data, search for a biased portrait of the user corresponding to the second label.
步骤b2，响应于查找到与第二标签对应的用户偏置画像，基于融合数据，对与第二标签对应的用户偏置画像进行更新处理。Step b2, in response to finding the user bias portrait corresponding to the second tag, based on the fused data, update the user bias portrait corresponding to the second tag.
作为一种可能实施方式的示例，响应于查找到与第二标签对应的用户偏置画像，说明已经建立了与第二标签对应的用户偏置画像，基于融合数据对与第二标签对应的用户偏置画像进行更新处理。As an example of a possible implementation, in response to finding the user bias portrait corresponding to the second label, it means that the user bias portrait corresponding to the second label has been established, and based on the fusion data, the user corresponding to the second label The offset image is updated.
步骤b3，响应于未查找到与第二标签对应的用户偏置画像，基于融合数据，生成与第二标签对应的用户偏置画像。Step b3, in response to finding no user bias portrait corresponding to the second tag, based on the fused data, generate a user bias portrait corresponding to the second tag.
作为一种可能实施方式的示例，响应于未查找到与标签对应的用户偏置画像，说明还未经建立了与第二标签对应的用户偏置画像，因此，基于融合数据生成与第二标签对应的用户偏置画像。As an example of a possible implementation, in response to not finding the user bias portrait corresponding to the label, it means that the user bias portrait corresponding to the second label has not yet been established, therefore, based on the fusion data, a Corresponding user bias profile.
根据本申请实施例的基于可穿戴设备的用户健康画像生成方法，通过响应于接收到客户端发送的异常数据时间段和异常数据时间段对应的第二标签，确定异常数据时间段对应的多源体征数据的数据类型为异常数据。从而提高了用户偏置画像构建和更新的灵活性，能够根据实际需求生成用户偏置画像。According to the wearable device-based user health portrait generation method according to the embodiment of the present application, by responding to receiving the abnormal data time period sent by the client and the second label corresponding to the abnormal data time period, the multi-source corresponding to the abnormal data time period is determined The data type of the sign data is abnormal data. Therefore, the flexibility of constructing and updating user bias portraits is improved, and user bias portraits can be generated according to actual needs.
图3为本申请实施例中的一种基于可穿戴设备的用户健康画像生成装置的结构框图。Fig. 3 is a structural block diagram of an apparatus for generating a user's health profile based on a wearable device in an embodiment of the present application.
如图3所示，该基于可穿戴设备的用户健康画像生成装置包括：As shown in Figure 3, the device for generating user health portraits based on wearable devices includes:
获取模块301，用于获取对象的多源体征数据；An
融合模块302，用于对多源体征数据进行融合处理，以得到融合数据；A
确定模块303，用于确定多源体征数据的数据类型；数据类型包括正常数据和异常数据；A determining
更新模块304，用于响应于多源体征数据的数据类型为正常数据，基于融合数据，对对象的预先构建的用户常规画像进行更新处理；An
生成模块305，用于响应于多源体征数据的数据类型为异常数据，基于融合数据生成用户偏置画像。The
根据本申请实施例的基于可穿戴设备的用户健康画像生成装置，通过获取对象的多源体征数据；对多源体征数据进行融合处理，以得到融合数据；确定多源体征数据的数据类型；响应于多源体征数据的数据类型为正常数据，基于融合数据，对对象的预先构建的用户常规画像进行更新处理；响应于多源体征数据的数据类型为异常数据，基于融合数据生成用户偏置画像。从而保证对用户画像及时更新的同时提高了用户画像的准确性；另外，通过为同一对象分别构建用户常规画像和用户偏置画像，能够更加准确的掌握对象在健康状态下和患病状态下的身体情况，同时提升画像下游预警功能效果。According to the wearable device-based user health portrait generation device according to the embodiment of the present application, by acquiring the multi-source sign data of the object; performing fusion processing on the multi-source sign data to obtain the fused data; determining the data type of the multi-source sign data; responding Since the data type of the multi-source sign data is normal data, based on the fusion data, the pre-built user routine portrait of the object is updated; in response to the data type of the multi-source sign data being abnormal data, a user bias portrait is generated based on the fusion data . In this way, the accuracy of user portraits is improved while ensuring timely update of user portraits; in addition, by constructing user regular portraits and user bias portraits for the same object, it is possible to more accurately grasp the status of the object in a healthy state and in a diseased state. Physical condition, and at the same time improve the effect of the downstream warning function of the portrait.
图4为本申请实施例中的一种电子设备的框图。如图4所示，该电子设备可以包括：收发器41、处理器42、存储器43。Fig. 4 is a block diagram of an electronic device in an embodiment of the present application. As shown in FIG. 4 , the electronic device may include: a transceiver 41 , a processor 42 , and a
处理器42执行存储器存储的计算机执行指令，使得处理器42执行上述实施例中的方案。处理器42可以是通用处理器，包括中央处理器CPU、网络处理器(network processor，NP)等；还可以是数字信号处理器DSP、专用集成电路ASIC、现场可编程门阵列FPGA或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。The processor 42 executes the computer-executable instructions stored in the memory, so that the processor 42 executes the solutions in the above-mentioned embodiments. Processor 42 can be a general processor, including a central processing unit CPU, a network processor (network processor, NP) etc.; it can also be a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable Logic devices, discrete gate or transistor logic devices, discrete hardware components.
存储器43通过系统总线与处理器42连接并完成相互间的通信，存储器43用于存储计算机程序指令。The
收发器41可以用于获取待运行任务和待运行任务的配置信息。The transceiver 41 may be used to acquire tasks to be executed and configuration information of the tasks to be executed.
系统总线可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。系统总线可以分为地址总线、数据总线、控制总线等。为便于表示，图中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。收发器用于实现数据库访问装置与其他计算机(例如客户端、读写库和只读库)之间的通信。存储器可能包含随机存取存储器(randomaccess memory，RAM)，也可能还包括非易失性存储器(non-volatile memory)。The system bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus or the like. The system bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. Transceivers are used to enable communication between database access devices and other computers such as clients, read-write libraries, and read-only libraries. The memory may include random access memory (random access memory, RAM), and may also include non-volatile memory (non-volatile memory).
本申请实施例提供的电子设备，可以是上述实施例的终端设备。The electronic device provided in the embodiment of the present application may be the terminal device in the foregoing embodiment.
本申请实施例还提供一种运行指令的芯片，该芯片用于执行上述实施例中消息处理方法的技术方案。The embodiment of the present application also provides a chip for running instructions, and the chip is used to implement the technical solution of the message processing method in the above embodiment.
本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质中存储有计算机指令，当该计算机指令在计算机上运行时，使得计算机执行上述实施例消息处理方法的技术方案。The embodiment of the present application also provides a computer-readable storage medium, where computer instructions are stored in the computer-readable storage medium, and when the computer instructions are run on the computer, the computer is made to execute the technical solution of the message processing method of the above-mentioned embodiment.
本申请实施例还提供一种计算机程序产品，该计算机程序产品包括计算机程序，其存储在计算机可读存储介质中，至少一个处理器可以从计算机可读存储介质读取计算机程序，至少一个处理器执行计算机程序时可实现上述实施例中消息处理方法的技术方案。The embodiment of the present application also provides a computer program product, the computer program product includes a computer program, which is stored in a computer-readable storage medium, at least one processor can read the computer program from the computer-readable storage medium, at least one processor The technical solutions of the message processing method in the foregoing embodiments can be realized when the computer program is executed.
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本申请的其它实施方案。本申请旨在涵盖本申请的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本申请的一般性原理并包括本申请未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本申请的真正范围和精神由下面的权利要求书指出。Other embodiments of the present application will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the application, these modifications, uses or adaptations follow the general principles of the application and include common knowledge or conventional technical means in the technical field not disclosed in the application . The specification and examples are to be considered exemplary only, with a true scope and spirit of the application indicated by the following claims.
应当理解的是，本申请并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本申请的范围仅由所附的权利要求书来限制。It should be understood that the present application is not limited to the precise constructions which have been described above and shown in the accompanying drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211710641.7ACN116246793A (en) | 2022-12-29 | 2022-12-29 | User health portrait generation method and device based on wearable equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211710641.7ACN116246793A (en) | 2022-12-29 | 2022-12-29 | User health portrait generation method and device based on wearable equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116246793Atrue CN116246793A (en) | 2023-06-09 |
Family
ID=86625200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211710641.7APendingCN116246793A (en) | 2022-12-29 | 2022-12-29 | User health portrait generation method and device based on wearable equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116246793A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118942604A (en)* | 2024-06-27 | 2024-11-12 | 讯飞医疗科技股份有限公司 | User portrait construction method, system and related device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108847288A (en)* | 2018-07-13 | 2018-11-20 | 武汉久乐科技有限公司 | A kind of healthy early warning method and apparatus |
| CN110765170A (en)* | 2019-09-26 | 2020-02-07 | 维沃移动通信有限公司 | A method for generating user portrait and wearable device |
| US20210082551A1 (en)* | 2019-09-13 | 2021-03-18 | Honeywell International Inc. | Method and apparatus for providing real-time periodic health updates |
| CN113140323A (en)* | 2020-12-31 | 2021-07-20 | 上海明品医学数据科技有限公司 | Health portrait generation method, system, medium and server |
| CN113643814A (en)* | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Health management scheme recommendation method, device, equipment and storage medium |
| CN113901084A (en)* | 2021-09-17 | 2022-01-07 | 作业帮教育科技（北京）有限公司 | User portrait real-time generation device and method and electronic equipment |
| CN114758781A (en)* | 2022-06-15 | 2022-07-15 | 武汉博科国泰信息技术有限公司 | A method and system, device and storage medium for generating a user's health portrait |
| CN115512798A (en)* | 2022-09-24 | 2022-12-23 | 深圳启脉科技有限公司 | A data acquisition method and cloud computing system for health portraits |
- 2022
- 2022-12-29CNCN202211710641.7Apatent/CN116246793A/enactivePending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108847288A (en)* | 2018-07-13 | 2018-11-20 | 武汉久乐科技有限公司 | A kind of healthy early warning method and apparatus |
| US20210082551A1 (en)* | 2019-09-13 | 2021-03-18 | Honeywell International Inc. | Method and apparatus for providing real-time periodic health updates |
| CN110765170A (en)* | 2019-09-26 | 2020-02-07 | 维沃移动通信有限公司 | A method for generating user portrait and wearable device |
| CN113140323A (en)* | 2020-12-31 | 2021-07-20 | 上海明品医学数据科技有限公司 | Health portrait generation method, system, medium and server |
| CN113643814A (en)* | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Health management scheme recommendation method, device, equipment and storage medium |
| CN113901084A (en)* | 2021-09-17 | 2022-01-07 | 作业帮教育科技（北京）有限公司 | User portrait real-time generation device and method and electronic equipment |
| CN114758781A (en)* | 2022-06-15 | 2022-07-15 | 武汉博科国泰信息技术有限公司 | A method and system, device and storage medium for generating a user's health portrait |
| CN115512798A (en)* | 2022-09-24 | 2022-12-23 | 深圳启脉科技有限公司 | A data acquisition method and cloud computing system for health portraits |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118942604A (en)* | 2024-06-27 | 2024-11-12 | 讯飞医疗科技股份有限公司 | User portrait construction method, system and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12036030B2 (en) | Methods for modeling neurological development and diagnosing a neurological impairment of a patient | |
| Haque et al. | State-of-the-art of stress prediction from heart rate variability using artificial intelligence | |
| Yang et al. | Lifelogging data validation model for internet of things enabled personalized healthcare | |
| CN108877890A (en) | Amount of exercise monitoring method, equipment and computer readable storage medium | |
| US20160242664A1 (en) | An apparatus and method for evaluating multichannel ecg signals | |
| JP2022037153A (en) | ECG analyzer, ECG analysis method and program | |
| JP2019025311A (en) | Data generation apparatus, biological data measurement system, discriminator generation apparatus, data generation method, discriminator generation method, and program | |
| Luo et al. | Exploring adaptive graph topologies and temporal graph networks for EEG-based depression detection | |
| CN105593860B (en) | For determining the device and patient health condition determiner of composite score distribution | |
| Poon et al. | Special issue on health informatics and personalized medicine | |
| WO2025073180A1 (en) | Method and device for identifying rapid eye movement in sleep period, and storage medium | |
| CN116246793A (en) | User health portrait generation method and device based on wearable equipment | |
| CN116244660A (en) | Multi-source data fusion method and device of wearable device and electronic device | |
| Meena et al. | IoT and BSN Applications for Real Time Monitoring and Disease Prediction | |
| CN109528218A (en) | A kind of psychological pressure detection method based on heart rate Yu social media microblogging | |
| CN110415778B (en) | A method and system for personal health data management based on cloud data | |
| CN118841169A (en) | Health analysis method and system based on artificial intelligence | |
| Quadir et al. | IoT-Based Mental Health Monitoring System Using Machine Learning Stress Prediction Algorithm in Real-Time Application | |
| CN114947773B (en) | Body temperature monitoring method, device, terminal equipment and storage medium | |
| Ishtiaque et al. | IoT-based low-cost remote patient monitoring and management system with deep learning-based arrhythmia and pneumonia detection | |
| DE112018005890T5 (en) | INFORMATION PROCESSING DEVICE, PROCEDURE AND PROGRAM | |
| Pinge et al. | mTanaaw: A System for Assessment and Analysis of Mental Health with Wearables | |
| James et al. | An IoT-Based Health Monitoring System for Stress Detection in Human Beings | |
| Rani et al. | Mobile health application for early disease outbreak-period detection | |
| JP7426015B1 (en) | Healthcare data analysis system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |