技术领域Technical Field
本发明涉及健康监测和人工智能领域，具体涉及到一种用于皮肤移植的生命体征监测方法和装置。The present invention relates to the fields of health monitoring and artificial intelligence, and in particular to a vital sign monitoring method and device for skin transplantation.
背景技术Background Art
生命体征监测装置能够测量患者的多种生理参数。这些生理参数可以包括心率、心电图(ECG)信号、光电容积描记(PPG)信号和其他类似的信号和信息。生命体征监测装置有多种形式，包括智能手表、可穿戴装置等。随着用户变得更加注重健康，此类装置的使用变得普及。Vital sign monitoring devices are capable of measuring various physiological parameters of a patient. These physiological parameters may include heart rate, electrocardiogram (ECG) signals, photoplethysmography (PPG) signals, and other similar signals and information. Vital sign monitoring devices come in many forms, including smart watches, wearable devices, etc. As users become more health-conscious, the use of such devices has become popular.
在皮肤移植领域，需要对皮肤移植后，对用户的多种生理参数进行快速有效监测，且现有的生命体征监测设备都很昂贵，难以满足生命体征检测的时效性和准确性的要求。In the field of skin transplantation, it is necessary to quickly and effectively monitor the user's various physiological parameters after skin transplantation, and the existing vital signs monitoring equipment is very expensive and can hardly meet the requirements of timeliness and accuracy of vital signs detection.
发明内容Summary of the invention
本发明主要解决现有生命体征监测装置难以在皮肤移植后对用户的多种生理参数进行快速有效监测的问题，本发明公开了一种用于皮肤移植的生命体征监测方法和装置。The present invention mainly solves the problem that the existing vital signs monitoring device is difficult to quickly and effectively monitor multiple physiological parameters of a user after skin transplantation. The present invention discloses a vital signs monitoring method and device for skin transplantation.
本申请实施例第一方面，公开了一种用于皮肤移植的生命体征监测方法，包括：In a first aspect of the embodiments of the present application, a method for monitoring vital signs for skin transplantation is disclosed, comprising:
S1，获取生命体征监测信号集合；所述生命体征监测信号集合，包括心率信号序列、血氧饱和度信号序列、呼吸信号序列和脑电信号序列等；S1, obtaining a set of vital sign monitoring signals; the set of vital sign monitoring signals includes a heart rate signal sequence, a blood oxygen saturation signal sequence, a breathing signal sequence, and an electroencephalogram signal sequence, etc.;
S2，对所述生命体征监测信号集合进行预处理，得到预处理生命体征监测信号集合；S2, preprocessing the vital sign monitoring signal set to obtain a preprocessed vital sign monitoring signal set;
S3，利用预训练的生命体征监测模型，对所述预处理生命体征监测信号集合进行处理，得到生命体征监测结果值。S3, using a pre-trained vital sign monitoring model, processing the pre-processed vital sign monitoring signal set to obtain a vital sign monitoring result value.
所述生命体征监测模型，包括：第一特征提取网络、第二特征提取网络和体征识别网络；The vital signs monitoring model comprises: a first feature extraction network, a second feature extraction network and a vital signs recognition network;
所述第一特征提取网络，包括第一输入模块、第一卷积模块、深度可分离卷积模块、第一升维卷积模块、第二升维卷积模块、第三升维卷积模块、第四升维卷积模块、第二卷积模块、第一池化模块、第三卷积模块和第一全连接模块；The first feature extraction network includes a first input module, a first convolution module, a depth-separable convolution module, a first dimension-raising convolution module, a second dimension-raising convolution module, a third dimension-raising convolution module, a fourth dimension-raising convolution module, a second convolution module, a first pooling module, a third convolution module and a first fully connected module;
所述第二特征提取网络，包括第二输入模块、第四卷积模块、第五卷积模块、第六卷积模块、第二池化模块、第七卷积模块、第二全连接模块和第三全连接模块；The second feature extraction network includes a second input module, a fourth convolution module, a fifth convolution module, a sixth convolution module, a second pooling module, a seventh convolution module, a second fully connected module and a third fully connected module;
所述体征识别网络包括第八卷积模块、第九卷积模块、第十卷积模块、第十一卷积模块、第一融合模块、第二融合模块、第三融合模块、第一归一化模块、第二归一化模块、第一激活模块。The vital sign recognition network includes an eighth convolution module, a ninth convolution module, a tenth convolution module, an eleventh convolution module, a first fusion module, a second fusion module, a third fusion module, a first normalization module, a second normalization module, and a first activation module.
所述对所述生命体征监测信号集合进行预处理，得到预处理生命体征监测信号集合，包括：The preprocessing of the vital sign monitoring signal set to obtain a preprocessed vital sign monitoring signal set includes:
S21，对所述生命体征监测信号集合进行野值剔除处理，得到第一数据集合；S21, performing outlier elimination processing on the vital sign monitoring signal set to obtain a first data set;
S22，对所述第一数据集合进行边界检查处理，得到预处理生命体征监测信号集合。S22, performing boundary check processing on the first data set to obtain a pre-processed vital sign monitoring signal set.
所述对所述第一数据集合进行边界检查处理，得到预处理生命体征监测信号集合，包括：The performing boundary check processing on the first data set to obtain a pre-processed vital sign monitoring signal set includes:
S221，对第一数据集合的每一个数据属性，预设对应的取值范围；所述取值范围，包括取值范围上界值和取值范围下界值；S221, for each data attribute of the first data set, preset a corresponding value range; the value range includes an upper limit value of the value range and a lower limit value of the value range;
S222，对所述第一数据集合的每个数据属性的每个数据，根据该数据属性的取值范围，判别所述数据的取值是否在所述取值范围内；当在所述取值范围内时，不对所述数据进行处理；当不在所述取值范围内时，设定所述数据的取值为与其最接近的所述取值范围的取值范围上界值或取值范围下界值；S222, for each data of each data attribute of the first data set, judging whether the value of the data is within the value range according to the value range of the data attribute; if the data is within the value range, not processing the data; if the data is not within the value range, setting the value of the data to the upper limit value or the lower limit value of the value range that is closest to the data;
S223，对所有数据属性的数据完成S222后，得到检查完毕的数据；利用所有检查完毕的数据，构建得到预处理生命体征监测信号集合。S223, after completing S222 for all data attributes, the checked data are obtained; using all the checked data, a pre-processed vital sign monitoring signal set is constructed.
所述第一特征提取网络的第一输入模块的输入端，用于接收输入数据；所述第一特征提取网络的第一输入模块的输出端，与所述第一特征提取网络的第一卷积模块的输入端相连接；所述第一特征提取网络的第一卷积模块的输出端，与所述第一特征提取网络的深度可分离卷积模块的输入端相连接；所述第一特征提取网络的深度可分离卷积模块的输出端，与所述第一特征提取网络的第一升维卷积模块的输入端相连接；所述第一特征提取网络的第一升维卷积模块的输出端，与所述第一特征提取网络的第二升维卷积模块的输入端相连接；所述第一特征提取网络的第二升维卷积模块的输出端，与所述第一特征提取网络的第三升维卷积模块的输入端相连接；所述第一特征提取网络的第三升维卷积模块的输出端，与所述第一特征提取网络的第四升维卷积模块的输入端相连接；所述第一特征提取网络的第四升维卷积模块的输出端，与所述第一特征提取网络的第二卷积模块的输入端相连接；所述第一特征提取网络的第二卷积模块的输出端，与所述第一特征提取网络的第一池化模块的输入端相连接；所述第一特征提取网络的第一池化模块的输出端，与所述第一特征提取网络的第三卷积模块的输入端相连接；所述第一特征提取网络的第三卷积模块的输出端，与所述第一特征提取网络的第一全连接模块的输入端相连接；所述第一特征提取网络的第一全连接模块的输出端，用于输出第一特征信息。The input end of the first input module of the first feature extraction network is used to receive input data; the output end of the first input module of the first feature extraction network is connected to the input end of the first convolution module of the first feature extraction network; the output end of the first convolution module of the first feature extraction network is connected to the input end of the depthwise separable convolution module of the first feature extraction network; the output end of the depthwise separable convolution module of the first feature extraction network is connected to the input end of the first dimensionality-raising convolution module of the first feature extraction network; the output end of the first dimensionality-raising convolution module of the first feature extraction network is connected to the input end of the second dimensionality-raising convolution module of the first feature extraction network; the output end of the second dimensionality-raising convolution module of the first feature extraction network is connected to the input end of the third dimensionality-raising convolution module of the first feature extraction network. Connection; the output end of the third dimensionality-raising convolution module of the first feature extraction network is connected to the input end of the fourth dimensionality-raising convolution module of the first feature extraction network; the output end of the fourth dimensionality-raising convolution module of the first feature extraction network is connected to the input end of the second convolution module of the first feature extraction network; the output end of the second convolution module of the first feature extraction network is connected to the input end of the first pooling module of the first feature extraction network; the output end of the first pooling module of the first feature extraction network is connected to the input end of the third convolution module of the first feature extraction network; the output end of the third convolution module of the first feature extraction network is connected to the input end of the first fully connected module of the first feature extraction network; the output end of the first fully connected module of the first feature extraction network is used to output the first feature information.
所述第二特征提取网络的第二输入模块的输入端，用于接收输入数据；所述第二特征提取网络的第二输入模块的输出端，与所述第二特征提取网络的第四卷积模块的输入端相连接；所述第二特征提取网络的第四卷积模块的输出端，与所述第二特征提取网络的第五卷积模块的输入端相连接；所述第二特征提取网络的第五卷积模块的输出端，与所述第二特征提取网络的第六卷积模块的输入端相连接；所述第二特征提取网络的第六卷积模块的输出端，与所述第二特征提取网络的第二池化模块的输入端相连接；所述第二特征提取网络的第二池化模块的输出端，与所述第二特征提取网络的第七卷积模块的输入端相连接；所述第二特征提取网络的第七卷积模块的输出端，与所述第二特征提取网络的第二全连接模块的输入端相连接；所述第二特征提取网络的第二全连接模块的输出端，与所述第二特征提取网络的第三全连接模块的输入端相连接；所述第二特征提取网络的第三全连接模块的输出端，用于输出第二特征信息；The input end of the second input module of the second feature extraction network is used to receive input data; the output end of the second input module of the second feature extraction network is connected to the input end of the fourth convolution module of the second feature extraction network; the output end of the fourth convolution module of the second feature extraction network is connected to the input end of the fifth convolution module of the second feature extraction network; the output end of the fifth convolution module of the second feature extraction network is connected to the input end of the sixth convolution module of the second feature extraction network; the output end of the sixth convolution module of the second feature extraction network is connected to the input end of the second pooling module of the second feature extraction network; the output end of the second pooling module of the second feature extraction network is connected to the input end of the seventh convolution module of the second feature extraction network; the output end of the seventh convolution module of the second feature extraction network is connected to the input end of the second fully connected module of the second feature extraction network; the output end of the second fully connected module of the second feature extraction network is connected to the input end of the third fully connected module of the second feature extraction network; the output end of the third fully connected module of the second feature extraction network is used to output second feature information;
所述第八卷积模块的输入端，与所述第一特征提取网络的第一全连接模块的输出端连接，用于接收所述第一特征信息，所述第八卷积模块的输出端分别连接所述第一融合模块的输入端和所述第二融合模块的输入端；所述第一融合模块的输出端连接所述第十卷积模块的输入端；所述第十卷积模块的输出端连接所述第一归一化模块的输入端；所述第一归一化模块的输出端连接所述第三融合模块的输入端；所述第九卷积模块的输入端，与所述第二特征提取网络的第三全连接模块的输出端连接，用于接收所述第二特征信息，所述第九卷积模块的输出端分别连接所述第一融合模块的输入端和所述第三融合模块的输入端；所述第二融合模块的输出端连接所述第十一卷积模块的输入端；所述第十一卷积模块的输出端连接所述第二归一化模块的输入端；所述第二归一化模块的输出端连接所述第三融合模块的输入端；所述第三融合模块的输出端连接所述第一激活模块的输入端；所述第一激活模块的输出端，用于输出所述预测的生命体征监测结果值。The input end of the eighth convolution module is connected to the output end of the first fully connected module of the first feature extraction network, and is used to receive the first feature information. The output end of the eighth convolution module is respectively connected to the input end of the first fusion module and the input end of the second fusion module; the output end of the first fusion module is connected to the input end of the tenth convolution module; the output end of the tenth convolution module is connected to the input end of the first normalization module; the output end of the first normalization module is connected to the input end of the third fusion module; the input end of the ninth convolution module is connected to the output end of the third fully connected module of the second feature extraction network, and is used to receive the second feature information. The output end of the ninth convolution module is respectively connected to the input end of the first fusion module and the input end of the third fusion module; the output end of the second fusion module is connected to the input end of the eleventh convolution module; the output end of the eleventh convolution module is connected to the input end of the second normalization module; the output end of the second normalization module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the input end of the first activation module; the output end of the first activation module is used to output the predicted vital sign monitoring result value.
所述生命体征监测模型的训练过程，包括：The training process of the vital signs monitoring model includes:
获取训练信息集合；所述训练信息集合，包括心率信号序列、血氧饱和度信号序列、呼吸信号序列、脑电信号序列和对应的标签值；Acquire a training information set; the training information set includes a heart rate signal sequence, a blood oxygen saturation signal sequence, a breathing signal sequence, an electroencephalogram signal sequence and corresponding label values;
将所述训练信息集合划分为第一训练子集合和第二训练子集合；所述第一训练子集合，包括第一训练信息；所述第一训练信息，包括心率信号序列、血氧饱和度信号序列、脑电信号序列、呼吸信号序列和对应的标签值；所述第二训练子集合，包括第二训练信息；所述第二训练信息，包括心率信号序列、血氧饱和度信号序列、脑电信号序列、呼吸信号序列和对应的标签值；Dividing the training information set into a first training subset and a second training subset; the first training subset includes first training information; the first training information includes a heart rate signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence, a respiratory signal sequence and corresponding label values; the second training subset includes second training information; the second training information includes a heart rate signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence, a respiratory signal sequence and corresponding label values;
利用所述训练信息集合，对生命体征监测模型进行训练处理，得到训练完毕的生命体征监测模型。The training information set is used to train the vital signs monitoring model to obtain a trained vital signs monitoring model.
所述利用所述训练信息集合，对生命体征监测模型进行训练处理，得到训练完毕的生命体征监测模型，包括：The training information set is used to train the vital sign monitoring model to obtain a trained vital sign monitoring model, including:
S301，对第一训练次数值进行初始化；S301, initializing a first training number value;
S302，从所述训练信息集合中获取第一训练信息，将所获取的第一训练信息输入生命体征监测模型的第二特征提取网络；所述获取的第一训练信息，在S301至S307中保持不变；S302, obtaining first training information from the training information set, and inputting the obtained first training information into a second feature extraction network of a vital sign monitoring model; the obtained first training information remains unchanged in S301 to S307;
S303，将所述训练信息集合中的第二训练信息输入生命体征监测模型中的第一特征提取网络；确定输入所述生命体征监测模型的第二训练信息对应的标签值，为标签信息；在每次执行S303中，输入生命体征监测模型中的第一特征提取网络的第二训练信息是不同的；S303, inputting the second training information in the training information set into the first feature extraction network in the vital sign monitoring model; determining the label value corresponding to the second training information input into the vital sign monitoring model as label information; in each execution of S303, the second training information input into the first feature extraction network in the vital sign monitoring model is different;
S304，利用生命体征监测模型对输入信息进行处理，得到预测的生命体征监测结果值；S304, using the vital sign monitoring model to process the input information to obtain a predicted vital sign monitoring result value;
S305，利用损失函数对所述预测的生命体征监测结果值和标签信息进行计算，得到差异值；S305, using a loss function to calculate the predicted vital sign monitoring result value and the label information to obtain a difference value;
S306，对所述第一训练次数值进行累加操作；S306, performing an accumulation operation on the first training times;
S307，判断所述第一训练次数值是否超过预设的第一训练次数阈值，得到第一判断结果；当所述第一判断结果为是时，执行S308；S307, determining whether the first training times value exceeds a preset first training times threshold, and obtaining a first determination result; when the first determination result is yes, executing S308;
当所述第一判断结果为否时，判断所述差异值是否小于设定的收敛阈值，得到第二判断结果；When the first judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a second judgment result;
当所述第二判断结果为是时，执行S308；当所述第二判断结果为否时，利用更新模型对所述第一特征提取网络进行参数更新，执行S303；When the second judgment result is yes, execute S308; when the second judgment result is no, update the parameters of the first feature extraction network using the update model, and execute S303;
S308，对第二训练次数值进行初始化；S308, initializing the second training times value;
S309，从所述训练信息集合中获取第二训练信息，将所获取的第二训练信息输入生命体征监测模型的第一特征提取网络；所述获取的第二训练信息，在S310至S314中保持不变；S309, obtaining second training information from the training information set, and inputting the obtained second training information into the first feature extraction network of the vital sign monitoring model; the obtained second training information remains unchanged in S310 to S314;
S310，将所述训练信息集合中的第一训练信息输入生命体征监测模型中的第二特征提取网络；确定输入所述生命体征监测模型的第一训练信息对应的标签值，为标签信息；在每次执行S310中，输入生命体征监测模型中的第二特征提取网络的第一训练信息是不同的；S310, inputting the first training information in the training information set into the second feature extraction network in the vital sign monitoring model; determining the label value corresponding to the first training information input into the vital sign monitoring model as label information; in each execution of S310, the first training information input into the second feature extraction network in the vital sign monitoring model is different;
S311，利用生命体征监测模型对输入信息进行处理，得到预测的生命体征监测结果值；S311, using the vital sign monitoring model to process the input information to obtain a predicted vital sign monitoring result value;
S312，利用损失函数对所述预测的生命体征监测结果值和标签信息进行计算，得到差异值；S312, using a loss function to calculate the predicted vital sign monitoring result value and label information to obtain a difference value;
S313，对所述第二训练次数值进行累加操作；S313, performing an accumulation operation on the second training times value;
S314，判断所述第二训练次数值是否超过预设的第二训练次数阈值，得到第三判断结果；当所述第三判断结果为是时，完成训练过程，得到训练完毕的生命体征监测模型；S314, determining whether the second training times value exceeds a preset second training times threshold value, and obtaining a third determination result; when the third determination result is yes, completing the training process, and obtaining a trained vital sign monitoring model;
当所述第三判断结果为否时，判断所述差异值是否小于设定的收敛阈值，得到第四判断结果；When the third judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a fourth judgment result;
当所述第四判断结果为是时，完成训练过程，得到训练完毕的生命体征监测模型；当所述第四判断结果为否时，利用更新模型对所述第二特征提取网络和体征识别网络进行参数更新，执行S310。When the fourth judgment result is yes, the training process is completed to obtain a trained vital sign monitoring model; when the fourth judgment result is no, the updated model is used to update the parameters of the second feature extraction network and the vital sign recognition network, and S310 is executed.
所述更新模型为：The update model is:
， ,
， ,
式中，为所述训练信息集合中的第i个输入信息输入生命体征监测模型后的差异值的计算函数，为参数更新值，为需要进行参数更新的网络的参数，为预设的初始参数学习率，为预设的动量角度参数，，表示针对变量求偏导数；所述第i个输入信息，包括第一训练信息和第二训练信息。In the formula, A calculation function for the difference value after the i-th input information in the training information set is input into the vital sign monitoring model, Update the value for the parameter, are the parameters of the network that need to be updated. is the preset initial parameter learning rate, is the preset momentum angle parameter, , Indicates that for variables Finding partial derivatives; the i-th input information includes first training information and second training information.
本发明实施例第二方面，公开了一种用于皮肤移植的生命体征监测装置，所述装置包括：In a second aspect of an embodiment of the present invention, a vital sign monitoring device for skin transplantation is disclosed, the device comprising:
存储有可执行程序代码的存储器；A memory storing executable program code;
与所述存储器耦合的处理器；a processor coupled to the memory;
所述处理器调用所述存储器中存储的所述可执行程序代码，执行所述的用于皮肤移植的生命体征监测方法。The processor calls the executable program code stored in the memory to execute the vital signs monitoring method for skin transplantation.
本发明实施例第三方面，公开了一种计算机可存储介质，所述计算机可存储介质存储有计算机指令，所述计算机指令被计算机调用时，用于执行所述的用于皮肤移植的生命体征监测方法。According to a third aspect of an embodiment of the present invention, a computer storable medium is disclosed, wherein the computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the vital signs monitoring method for skin transplantation.
本发明实施例第四方面，公开了一种信息数据处理终端，所述信息数据处理终端用于实现所述的用于皮肤移植的生命体征监测方法。According to a fourth aspect of the embodiments of the present invention, an information data processing terminal is disclosed. The information data processing terminal is used to implement the vital signs monitoring method for skin transplantation.
本发明的有益效果为：The beneficial effects of the present invention are:
本发明能够实现在皮肤移植后，对用户的多种生理参数进行快速有效监测，具有实施成本低且维护简单的优点，满足了生命体征监测的时效性和准确性的要求。The present invention can realize rapid and effective monitoring of multiple physiological parameters of a user after skin transplantation, has the advantages of low implementation cost and simple maintenance, and meets the requirements of timeliness and accuracy of vital sign monitoring.
本发明提出了针对专门皮肤移植后的生命体征监测的生命体征监测模型，该模型通过采用两级特征提取网络，提取得到不同类型的生命体征，建立体征识别网络，实现了对细微生命体征的异常识别，提高了生命体征监的准确性。The present invention proposes a vital sign monitoring model for monitoring vital signs after special skin transplantation. The model extracts different types of vital signs by adopting a two-level feature extraction network, establishes a vital sign recognition network, realizes abnormal recognition of subtle vital signs, and improves the accuracy of vital sign monitoring.
本发明在对生命体征监测模型进行训练过程中，为了提高训练准确性，提出了专门针对两级特征提取网络的两级训练方法，该方法确保了两类不同的特征提取的准确性。In the process of training the vital sign monitoring model, the present invention proposes a two-stage training method specifically for the two-stage feature extraction network in order to improve the training accuracy. The method ensures the accuracy of extracting two different types of features.
本发明方法针对生命体征监测模型，专门提出了对应的更新模型：，，该模型确保了训练过程的实时性和收敛性，提升了模型的实用性。The method of the present invention specifically proposes a corresponding update model for the vital signs monitoring model: , ,This model ensures the real-time and convergence of the training process and improves the practicability of the model.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1为本发明方法的实施流程图。FIG1 is a flow chart of the implementation of the method of the present invention.
具体实施方式DETAILED DESCRIPTION
为了更好的了解本发明内容，这里给出一个实施例。In order to better understand the content of the present invention, an embodiment is given here.
图1为本发明方法的实施流程图。FIG1 is a flow chart of the implementation of the method of the present invention.
针对现有生命体征监测装置难以在皮肤移植后对用户的多种生理参数进行快速有效监测的问题，本发明公开了一种用于皮肤移植的生命体征监测方法和装置。Aiming at the problem that existing vital signs monitoring devices are difficult to quickly and effectively monitor multiple physiological parameters of a user after skin transplantation, the present invention discloses a vital signs monitoring method and device for skin transplantation.
本申请实施例第一方面，公开了一种用于皮肤移植的生命体征监测方法，包括：In a first aspect of the embodiments of the present application, a method for monitoring vital signs for skin transplantation is disclosed, comprising:
S1，获取生命体征监测信号集合；所述生命体征监测信号集合，包括心率信号序列、血氧饱和度信号序列、呼吸信号序列和脑电信号序列等；S1, obtaining a set of vital sign monitoring signals; the set of vital sign monitoring signals includes a heart rate signal sequence, a blood oxygen saturation signal sequence, a breathing signal sequence, and an electroencephalogram signal sequence, etc.;
S2，对所述生命体征监测信号集合进行预处理，得到预处理生命体征监测信号集合；S2, preprocessing the vital sign monitoring signal set to obtain a preprocessed vital sign monitoring signal set;
S3，利用预训练的生命体征监测模型，对所述预处理生命体征监测信号集合进行处理，得到生命体征监测结果值。S3, using a pre-trained vital sign monitoring model, processing the pre-processed vital sign monitoring signal set to obtain a vital sign monitoring result value.
所述对所述生命体征监测信号集合进行预处理，得到预处理生命体征监测信号集合，包括：The preprocessing of the vital sign monitoring signal set to obtain a preprocessed vital sign monitoring signal set includes:
S221，对所述生命体征监测信号集合进行野值剔除处理，得到第一数据集合；S221, performing outlier elimination processing on the vital sign monitoring signal set to obtain a first data set;
S222，对所述第一数据集合进行边界检查处理，得到预处理生命体征监测信号集合。S222: Perform boundary check processing on the first data set to obtain a pre-processed vital sign monitoring signal set.
所述对所述第一数据集合进行边界检查处理，得到预处理生命体征监测信号集合，包括：The performing boundary check processing on the first data set to obtain a pre-processed vital sign monitoring signal set includes:
S2221，对第一数据集合的每一个数据属性，预设对应的取值范围；所述取值范围，包括取值范围上界值和取值范围下界值；S2221, for each data attribute of the first data set, preset a corresponding value range; the value range includes an upper limit value of the value range and a lower limit value of the value range;
S2222，对所述第一数据集合的每个数据属性的每个数据，根据该数据属性的取值范围，判别所述数据的取值是否在所述取值范围内；当在所述取值范围内时，不对所述数据进行处理；当不在所述取值范围内时，设定所述数据的取值为与其最接近的所述取值范围的取值范围上界值或取值范围下界值；S2222, for each data of each data attribute of the first data set, judging whether the value of the data is within the value range according to the value range of the data attribute; if the data is within the value range, not processing the data; if the data is not within the value range, setting the value of the data to the upper limit value or the lower limit value of the value range that is closest to the data;
S2223，对所有数据属性的数据完成S2222后，得到检查完毕的数据；利用所有检查完毕的数据，构建得到预处理生命体征监测信号集合。S2223, after completing S2222 for all data attributes, the checked data are obtained; using all the checked data, a pre-processed vital sign monitoring signal set is constructed.
所述生命体征监测模型，包括：第一特征提取网络、第二特征提取网络和体征识别网络；The vital signs monitoring model comprises: a first feature extraction network, a second feature extraction network and a vital signs recognition network;
所述第一特征提取网络，包括第一输入模块、第一卷积模块、深度可分离卷积模块、第一升维卷积模块、第二升维卷积模块、第三升维卷积模块、第四升维卷积模块、第二卷积模块、第一池化模块、第三卷积模块和第一全连接模块；The first feature extraction network includes a first input module, a first convolution module, a depth-separable convolution module, a first dimension-raising convolution module, a second dimension-raising convolution module, a third dimension-raising convolution module, a fourth dimension-raising convolution module, a second convolution module, a first pooling module, a third convolution module and a first fully connected module;
所述第一特征提取网络的第一输入模块的输入端，用于接收所述第二训练信息；所述第一特征提取网络的第一输入模块的输出端，与所述第一特征提取网络的第一卷积模块的输入端相连接；所述第一特征提取网络的第一卷积模块的输出端，与所述第一特征提取网络的深度可分离卷积模块的输入端相连接；所述第一特征提取网络的深度可分离卷积模块的输出端，与所述第一特征提取网络的第一升维卷积模块的输入端相连接；所述第一特征提取网络的第一升维卷积模块的输出端，与所述第一特征提取网络的第二升维卷积模块的输入端相连接；所述第一特征提取网络的第二升维卷积模块的输出端，与所述第一特征提取网络的第三升维卷积模块的输入端相连接；所述第一特征提取网络的第三升维卷积模块的输出端，与所述第一特征提取网络的第四升维卷积模块的输入端相连接；所述第一特征提取网络的第四升维卷积模块的输出端，与所述第一特征提取网络的第二卷积模块的输入端相连接；所述第一特征提取网络的第二卷积模块的输出端，与所述第一特征提取网络的第一池化模块的输入端相连接；所述第一特征提取网络的第一池化模块的输出端，与所述第一特征提取网络的第三卷积模块的输入端相连接；所述第一特征提取网络的第三卷积模块的输出端，与所述第一特征提取网络的第一全连接模块的输入端相连接；所述第一特征提取网络的第一全连接模块的输出端，用于输出所述第一特征信息；The input end of the first input module of the first feature extraction network is used to receive the second training information; the output end of the first input module of the first feature extraction network is connected to the input end of the first convolution module of the first feature extraction network; the output end of the first convolution module of the first feature extraction network is connected to the input end of the depthwise separable convolution module of the first feature extraction network; the output end of the depthwise separable convolution module of the first feature extraction network is connected to the input end of the first dimensionality-increasing convolution module of the first feature extraction network; the output end of the first dimensionality-increasing convolution module of the first feature extraction network is connected to the input end of the second dimensionality-increasing convolution module of the first feature extraction network; the output end of the second dimensionality-increasing convolution module of the first feature extraction network is connected to the input end of the third dimensionality-increasing convolution module of the first feature extraction network connected; the output end of the third dimensionality-raising convolution module of the first feature extraction network is connected to the input end of the fourth dimensionality-raising convolution module of the first feature extraction network; the output end of the fourth dimensionality-raising convolution module of the first feature extraction network is connected to the input end of the second convolution module of the first feature extraction network; the output end of the second convolution module of the first feature extraction network is connected to the input end of the first pooling module of the first feature extraction network; the output end of the first pooling module of the first feature extraction network is connected to the input end of the third convolution module of the first feature extraction network; the output end of the third convolution module of the first feature extraction network is connected to the input end of the first fully connected module of the first feature extraction network; the output end of the first fully connected module of the first feature extraction network is used to output the first feature information;
所述第二特征提取网络，包括第二输入模块、第四卷积模块、第五卷积模块、第六卷积模块、第二池化模块、第七卷积模块、第二全连接模块和第三全连接模块；The second feature extraction network includes a second input module, a fourth convolution module, a fifth convolution module, a sixth convolution module, a second pooling module, a seventh convolution module, a second fully connected module and a third fully connected module;
所述第二特征提取网络的第二输入模块的输入端，用于接收所述第一训练信息；所述第二特征提取网络的第二输入模块的输出端，与所述第二特征提取网络的第四卷积模块的输入端相连接；所述第二特征提取网络的第四卷积模块的输出端，与所述第二特征提取网络的第五卷积模块的输入端相连接；所述第二特征提取网络的第五卷积模块的输出端，与所述第二特征提取网络的第六卷积模块的输入端相连接；所述第二特征提取网络的第六卷积模块的输出端，与所述第二特征提取网络的第二池化模块的输入端相连接；所述第二特征提取网络的第二池化模块的输出端，与所述第二特征提取网络的第七卷积模块的输入端相连接；所述第二特征提取网络的第七卷积模块的输出端，与所述第二特征提取网络的第二全连接模块的输入端相连接；所述第二特征提取网络的第二全连接模块的输出端，与所述第二特征提取网络的第三全连接模块的输入端相连接；所述第二特征提取网络的第三全连接模块的输出端，用于输出所述第二特征信息；The input end of the second input module of the second feature extraction network is used to receive the first training information; the output end of the second input module of the second feature extraction network is connected to the input end of the fourth convolution module of the second feature extraction network; the output end of the fourth convolution module of the second feature extraction network is connected to the input end of the fifth convolution module of the second feature extraction network; the output end of the fifth convolution module of the second feature extraction network is connected to the input end of the sixth convolution module of the second feature extraction network; the output end of the sixth convolution module of the second feature extraction network is connected to the input end of the second pooling module of the second feature extraction network; the output end of the second pooling module of the second feature extraction network is connected to the input end of the seventh convolution module of the second feature extraction network; the output end of the seventh convolution module of the second feature extraction network is connected to the input end of the second fully connected module of the second feature extraction network; the output end of the second fully connected module of the second feature extraction network is connected to the input end of the third fully connected module of the second feature extraction network; the output end of the third fully connected module of the second feature extraction network is used to output the second feature information;
所述体征识别网络包括第八卷积模块、第九卷积模块、第十卷积模块、第十一卷积模块、第一融合模块、第二融合模块、第三融合模块、第一归一化模块、第二归一化模块、第一激活模块；The vital sign recognition network includes an eighth convolution module, a ninth convolution module, a tenth convolution module, an eleventh convolution module, a first fusion module, a second fusion module, a third fusion module, a first normalization module, a second normalization module, and a first activation module;
所述第八卷积模块的输入端，与所述第一特征提取网络的第一全连接模块的输出端连接，用于接收所述第一特征信息，所述第八卷积模块的输出端分别连接所述第一融合模块的输入端和所述第二融合模块的输入端；所述第一融合模块的输出端连接所述第十卷积模块的输入端；所述第十卷积模块的输出端连接所述第一归一化模块的输入端；所述第一归一化模块的输出端连接所述第三融合模块的输入端；所述第九卷积模块的输入端，与所述第二特征提取网络的第三全连接模块的输出端连接，用于接收所述第二特征信息，所述第九卷积模块的输出端分别连接所述第一融合模块的输入端和所述第三融合模块的输入端；所述第二融合模块的输出端连接所述第十一卷积模块的输入端；所述第十一卷积模块的输出端连接所述第二归一化模块的输入端；所述第二归一化模块的输出端连接所述第三融合模块的输入端；所述第三融合模块的输出端连接所述第一激活模块的输入端；所述第一激活模块的输出端，用于输出所述预测的生命体征监测结果值。The input end of the eighth convolution module is connected to the output end of the first fully connected module of the first feature extraction network, and is used to receive the first feature information. The output end of the eighth convolution module is respectively connected to the input end of the first fusion module and the input end of the second fusion module; the output end of the first fusion module is connected to the input end of the tenth convolution module; the output end of the tenth convolution module is connected to the input end of the first normalization module; the output end of the first normalization module is connected to the input end of the third fusion module; the input end of the ninth convolution module is connected to the output end of the third fully connected module of the second feature extraction network, and is used to receive the second feature information. The output end of the ninth convolution module is respectively connected to the input end of the first fusion module and the input end of the third fusion module; the output end of the second fusion module is connected to the input end of the eleventh convolution module; the output end of the eleventh convolution module is connected to the input end of the second normalization module; the output end of the second normalization module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the input end of the first activation module; the output end of the first activation module is used to output the predicted vital sign monitoring result value.
所述卷积模块，可采用3维多通道卷积来实现；The convolution module can be implemented by using 3D multi-channel convolution;
所述深度可分离卷积模块，可采用通道拆分子模块和单通道卷积子模块相连接来实现，具体的，可采用MobileNet网络中的深度可分离卷积模块来实现。The depthwise separable convolution module can be implemented by connecting a channel splitting submodule and a single-channel convolution submodule. Specifically, it can be implemented by using the depthwise separable convolution module in the MobileNet network.
所述升维卷积模块，可采用ResNet网络中的升维卷积模块来实现；The dimension-raising convolution module can be implemented by using the dimension-raising convolution module in the ResNet network;
所述池化模块，可采用最大化池化操作来实现。The pooling module can be implemented by using a maximum pooling operation.
所述融合模块，包括N个多头注意力子模块；N与其输入通道的数目相同。The fusion module includes N multi-head attention sub-modules; N is the same as the number of its input channels.
所述生命体征监测模型的训练过程，包括：The training process of the vital signs monitoring model includes:
获取训练信息集合；所述训练信息集合，包括心率信号序列、血氧饱和度信号序列、呼吸信号序列、脑电信号序列和对应的标签值；所述标签值，是各类信号序列对应的生命体征监测结果值；Acquire a training information set; the training information set includes a heart rate signal sequence, a blood oxygen saturation signal sequence, a respiratory signal sequence, an electroencephalogram signal sequence and corresponding label values; the label value is a vital sign monitoring result value corresponding to each signal sequence;
将所述训练信息集合划分为第一训练子集合和第二训练子集合；所述第一训练子集合，包括第一训练信息；所述第一训练信息，包括心率信号序列、血氧饱和度信号序列、脑电信号序列、呼吸信号序列和对应的标签值；所述第二训练子集合，包括第二训练信息；所述第二训练信息，包括心率信号序列、血氧饱和度信号序列、脑电信号序列、呼吸信号序列和对应的标签值；Dividing the training information set into a first training subset and a second training subset; the first training subset includes first training information; the first training information includes a heart rate signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence, a respiratory signal sequence and corresponding label values; the second training subset includes second training information; the second training information includes a heart rate signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence, a respiratory signal sequence and corresponding label values;
利用所述训练信息集合，对生命体征监测模型进行训练处理，得到训练完毕的生命体征监测模型；Using the training information set, training the vital signs monitoring model to obtain a trained vital signs monitoring model;
所述利用所述训练信息集合，对生命体征监测模型进行训练处理，得到训练完毕的生命体征监测模型，包括：The training information set is used to train the vital sign monitoring model to obtain a trained vital sign monitoring model, including:
S301，对第一训练次数值进行初始化；S301, initializing a first training number value;
S302，从所述训练信息集合中获取第一训练信息，将所获取的第一训练信息输入生命体征监测模型的第二特征提取网络；所述获取的第一训练信息，在S301至S307中保持不变；S302, obtaining first training information from the training information set, and inputting the obtained first training information into a second feature extraction network of a vital sign monitoring model; the obtained first training information remains unchanged in S301 to S307;
S303，将所述训练信息集合中的第二训练信息输入生命体征监测模型中的第一特征提取网络；确定输入所述生命体征监测模型的第二训练信息对应的标签值，为标签信息；在每次执行S303中，输入生命体征监测模型中的第一特征提取网络的第二训练信息是不同的；S303, inputting the second training information in the training information set into the first feature extraction network in the vital sign monitoring model; determining the label value corresponding to the second training information input into the vital sign monitoring model as label information; in each execution of S303, the second training information input into the first feature extraction network in the vital sign monitoring model is different;
S304，利用生命体征监测模型对输入信息进行处理，得到预测的生命体征监测结果值；S304, using the vital sign monitoring model to process the input information to obtain a predicted vital sign monitoring result value;
S305，利用损失函数对所述预测的生命体征监测结果值和标签信息进行计算，得到差异值；S305, using a loss function to calculate the predicted vital sign monitoring result value and the label information to obtain a difference value;
S306，对所述第一训练次数值进行累加操作；S306, performing an accumulation operation on the first training times;
S307，判断所述第一训练次数值是否超过预设的第一训练次数阈值，得到第一判断结果；当所述第一判断结果为是时，执行S308；S307, determining whether the first training times value exceeds a preset first training times threshold, and obtaining a first determination result; when the first determination result is yes, executing S308;
当所述第一判断结果为否时，判断所述差异值是否小于设定的收敛阈值，得到第二判断结果；When the first judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a second judgment result;
当所述第二判断结果为是时，执行S308；当所述第二判断结果为否时，利用更新模型对所述第一特征提取网络进行参数更新，执行S303；When the second judgment result is yes, execute S308; when the second judgment result is no, update the parameters of the first feature extraction network using the update model, and execute S303;
S308，对第二训练次数值进行初始化；S308, initializing the second training times value;
S309，从所述训练信息集合中获取第二训练信息，将所获取的第二训练信息输入生命体征监测模型的第一特征提取网络；所述获取的第二训练信息，在S310至S314中保持不变；S309, obtaining second training information from the training information set, and inputting the obtained second training information into the first feature extraction network of the vital sign monitoring model; the obtained second training information remains unchanged in S310 to S314;
S310，将所述训练信息集合中的第一训练信息输入生命体征监测模型中的第二特征提取网络；确定输入所述生命体征监测模型的第一训练信息对应的标签值，为标签信息；在每次执行S310中，输入生命体征监测模型中的第二特征提取网络的第一训练信息是不同的；S310, inputting the first training information in the training information set into the second feature extraction network in the vital sign monitoring model; determining the label value corresponding to the first training information input into the vital sign monitoring model as label information; in each execution of S310, the first training information input into the second feature extraction network in the vital sign monitoring model is different;
S311，利用生命体征监测模型对输入信息进行处理，得到预测的生命体征监测结果值；S311, using the vital sign monitoring model to process the input information to obtain a predicted vital sign monitoring result value;
S312，利用损失函数对所述预测的生命体征监测结果值和标签信息进行计算，得到差异值；S312, using a loss function to calculate the predicted vital sign monitoring result value and label information to obtain a difference value;
S313，对所述第二训练次数值进行累加操作；S313, performing an accumulation operation on the second training times value;
S314，判断所述第二训练次数值是否超过预设的第二训练次数阈值，得到第三判断结果；当所述第三判断结果为是时，完成训练过程，得到训练完毕的生命体征监测模型；S314, determining whether the second training times value exceeds a preset second training times threshold value, and obtaining a third determination result; when the third determination result is yes, completing the training process, and obtaining a trained vital sign monitoring model;
当所述第三判断结果为否时，判断所述差异值是否小于设定的收敛阈值，得到第四判断结果；When the third judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a fourth judgment result;
当所述第四判断结果为是时，完成训练过程，得到训练完毕的生命体征监测模型；当所述第四判断结果为否时，利用更新模型对所述第二特征提取网络和体征识别网络进行参数更新，执行S310。When the fourth judgment result is yes, the training process is completed to obtain a trained vital sign monitoring model; when the fourth judgment result is no, the updated model is used to update the parameters of the second feature extraction network and the vital sign recognition network, and S310 is executed.
所述更新模型为：The update model is:
， ,
， ,
式中，为所述训练信息集合中的第i个输入信息输入生命体征监测模型后的差异值的计算函数，为参数更新值，为需要进行参数更新的网络的参数，为预设的初始参数学习率，为预设的动量角度参数，，表示针对变量求偏导数。所述第i个输入信息，包括第一训练信息和第二训练信息。In the formula, A calculation function for the difference value after the i-th input information in the training information set is input into the vital sign monitoring model, Update the value for the parameter, are the parameters of the network that need to be updated. is the preset initial parameter learning rate, is the preset momentum angle parameter, , Indicates that for variables The partial derivative is calculated. The i-th input information includes first training information and second training information.
所述损失函数，可采用交叉熵损失函数。The loss function may adopt a cross entropy loss function.
所述差异值是否满足收敛条件，是指差异值是否小于预设的误差门限值；当差异值小于预设的误差门限值时，判断所述差异值满足收敛条件，当差异值大于预设的误差门限值时，判断所述差异值不满足收敛条件。Whether the difference value satisfies the convergence condition refers to whether the difference value is less than a preset error threshold value; when the difference value is less than the preset error threshold value, it is judged that the difference value satisfies the convergence condition; when the difference value is greater than the preset error threshold value, it is judged that the difference value does not satisfy the convergence condition.
所述野值剔除处理，包括数据清理处理；The outlier elimination process includes data cleaning process;
所述数据清理处理，包括填补缺失值、光滑噪声数据、平滑或删除野值点；所述光滑噪声数据，是首先判别得到噪声数据，再根据噪声数据的前后数据，对噪声数据进行平滑处理；所述噪声数据，是其取值小于观测数据的传感器的探测灵敏度，或大于观测数据的传感器的测量上限的值。所述野值点的判别，可以采用卡尔曼滤波方法。对于缺失值的填补值的确定，可对缺失值的前后一定采样区间内的测量值取平均得到。The data cleaning process includes filling missing values, smoothing noise data, and smoothing or deleting outliers; the smoothed noise data is obtained by first determining the noise data, and then smoothing the noise data according to the data before and after the noise data; the noise data is a value whose value is less than the detection sensitivity of the sensor of the observed data, or greater than the measurement upper limit of the sensor of the observed data. The outlier point can be determined by the Kalman filter method. The filling value of the missing value can be determined by averaging the measured values within a certain sampling interval before and after the missing value.
所述自回归-滑动平均建模，可采用ARMA方法来实现；The autoregressive-moving average modeling can be implemented using the ARMA method;
所述对所述第一数据集合进行边界检查处理，得到训练信息集合，包括：The performing boundary checking on the first data set to obtain a training information set includes:
S22201，对所述第一数据集合的每一类数据属性的数据，以所述数据的数据采集信息为自变量，以所述数据的数据取值为因变量，进行自回归-滑动平均建模，分别得到所述类数据属性的回归模型；利用所述回归模型，对所述自变量进行计算处理，得到回归数据取值；判别所述回归数据取值与对应的因变量值之差的绝对值，是否大于设定的第一回归判别阈值；若大于所述第一回归判别阈值，将所述数据从所述第一数据集合中删除，若小于所述第一回归判别阈值，不对所述数据进行处理；S22201, for each type of data attribute of the first data set, using the data collection information of the data as an independent variable and the data value of the data as a dependent variable, perform autoregression-sliding average modeling to obtain regression models of the data attributes; using the regression model, perform calculation processing on the independent variable to obtain regression data values; determine whether the absolute value of the difference between the regression data value and the corresponding dependent variable value is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the first data set; if it is less than the first regression discrimination threshold, do not process the data;
S22202，对所有数据属性的数据完成S22201后，得到训练信息集合。S22202, after completing S22201 for all data attributes, a training information set is obtained.
所述数据采集信息，包括采集时间信息、采集空间信息等。The data collection information includes collection time information, collection space information, etc.
所述利用预训练的生命体征监测模型，对所述预处理生命体征监测信号集合进行处理，得到生命体征监测结果值，包括：The pre-trained vital sign monitoring model is used to process the pre-processed vital sign monitoring signal set to obtain a vital sign monitoring result value, including:
对每个时刻得到的所述预处理生命体征监测信号集合，分别输入预训练的生命体征监测模型，得到该时刻的生命体征监测结果值；The pre-processed vital sign monitoring signal set obtained at each moment is respectively input into the pre-trained vital sign monitoring model to obtain the vital sign monitoring result value at that moment;
对每个时刻的预处理生命体征监测信号集合进行权重计算处理，得到该时刻的权重；Perform weight calculation on the pre-processed vital sign monitoring signal set at each moment to obtain the weight at that moment;
利用每个时刻的权重，对对应时刻的生命体征监测结果值进行加权处理，得到最终的生命体征监测结果值；Using the weight of each moment, weighted processing is performed on the vital sign monitoring result value at the corresponding moment to obtain the final vital sign monitoring result value;
所述权重计算，包括：The weight calculation includes:
将所述预处理生命体征监测信号集合，表示为信号矩阵；所述信号矩阵的行向量，是一种生命体征的监测信号序列；The pre-processed vital sign monitoring signal set is represented as a signal matrix; the row vector of the signal matrix is a vital sign monitoring signal sequence;
对所述信号矩阵，进行第一标准计算处理，得到第一标准矩阵；Performing a first standard calculation process on the signal matrix to obtain a first standard matrix;
所述第一标准计算处理的表达式为：The expression of the first standard calculation process is:
， ,
其中，m表示信号矩阵的行数目，表示所述信号矩阵的第i行、第j列的元素，表示第一标准矩阵的第i行、第j列的元素；Wherem represents the number of rows in the signal matrix, represents the element of the i-th row and j-th column of the signal matrix, represents the element of the i-th row and j-th column of the first standard matrix;
对所述第一标准矩阵进行列最优处理，得到最优解向量；Performing column optimization processing on the first standard matrix to obtain an optimal solution vector;
所述列最优处理，是取出每一列中最大的数，构成最优解向量；所述最优解向量的表达式为：The column optimal processing is to take out the largest number in each column to form the optimal solution vector ; The expression of the optimal solution vector is:
， ,
其中，n为场景想定信息数目；Where n is the number of scenario information;
对所述第一标准矩阵进行列最劣处理，得到最劣解向量；Performing column worst processing on the first standard matrix to obtain a worst solution vector;
所述列最劣处理，是取出每一列中最小的数，构成最劣解向量；所述最劣解向量的表达式为：The worst column processing is to take out the smallest number in each column to form the worst solution vector ; The expression of the worst solution vector is:
， ,
对所述最劣解向量和最优解向量进行第一计算处理，得到权重值s；所述第一计算处理处理的表达式为：The worst solution vector and the best solution vector are subjected to a first calculation process to obtain a weight value s; the expression of the first calculation process is:
， ,
式中，为预设的第j个重要性权重；，通过预先设置得到，或通过计算第一标准矩阵的每一列的方差值得到。In the formula, is the presetj -th importance weight; , obtained by presetting, or by calculating the variance value of each column of the first standard matrix.
本发明实施例第二方面，公开了一种用于皮肤移植的生命体征监测装置，所述装置包括：In a second aspect of an embodiment of the present invention, a vital sign monitoring device for skin transplantation is disclosed, the device comprising:
存储有可执行程序代码的存储器；A memory storing executable program code;
与所述存储器耦合的处理器；a processor coupled to the memory;
所述处理器调用所述存储器中存储的所述可执行程序代码，执行所述的用于皮肤移植的生命体征监测方法。The processor calls the executable program code stored in the memory to execute the vital signs monitoring method for skin transplantation.
本发明实施例第三方面，公开了一种计算机可存储介质，所述计算机可存储介质存储有计算机指令，所述计算机指令被计算机调用时，用于执行所述的用于皮肤移植的生命体征监测方法。According to a third aspect of an embodiment of the present invention, a computer storable medium is disclosed, wherein the computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the vital signs monitoring method for skin transplantation.
本发明实施例第四方面，公开了一种信息数据处理终端，所述信息数据处理终端用于实现所述的用于皮肤移植的生命体征监测方法。According to a fourth aspect of the embodiments of the present invention, an information data processing terminal is disclosed. The information data processing terminal is used to implement the vital signs monitoring method for skin transplantation.
以上所述仅为本申请的实施例而已， 并不用于限制本申请。 对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。The above description is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411147034.3ACN118648878B (en) | 2024-08-21 | 2024-08-21 | Vital sign monitoring method and device for skin transplantation |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411147034.3ACN118648878B (en) | 2024-08-21 | 2024-08-21 | Vital sign monitoring method and device for skin transplantation |
| Publication Number | Publication Date |
|---|---|
| CN118648878Atrue CN118648878A (en) | 2024-09-17 |
| CN118648878B CN118648878B (en) | 2024-10-22 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411147034.3AActiveCN118648878B (en) | 2024-08-21 | 2024-08-21 | Vital sign monitoring method and device for skin transplantation |
| Country | Link |
|---|---|
| CN (1) | CN118648878B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119112141A (en)* | 2024-11-15 | 2024-12-13 | 中国人民解放军总医院 | A method and device for monitoring hemodynamics of experimental animals |
| CN119279536A (en)* | 2024-10-25 | 2025-01-10 | 中国人民解放军总医院第四医学中心 | A method and device for joint monitoring of multiple physiological parameters |
| CN119416048A (en)* | 2024-10-12 | 2025-02-11 | 中国人民解放军总医院第七医学中心 | A method and device for monitoring children's health based on smart bracelet |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230335271A1 (en)* | 2022-04-13 | 2023-10-19 | VitalTracer Ltd. | Monitoring Vital Signs via Machine Learning |
| CN117379015A (en)* | 2023-11-24 | 2024-01-12 | 军事科学院系统工程研究院卫勤保障技术研究所 | Multipurpose medical monitoring device and method |
| CN117898687A (en)* | 2024-01-12 | 2024-04-19 | 杭州光特医疗科技有限公司 | Multidimensional vital sign monitoring method, device and system and intelligent ring |
| CN117995403A (en)* | 2024-02-02 | 2024-05-07 | 中国人民解放军总医院第一医学中心 | Wearable vital sign monitoring system for field operations |
| WO2024130577A1 (en)* | 2022-12-21 | 2024-06-27 | 中国科学院深圳先进技术研究院 | Animal vital sign real-time monitoring system |
| CN118512161A (en)* | 2024-05-29 | 2024-08-20 | 深圳康恒医疗集团有限公司 | Real-time monitoring method and system for vital sign data based on deep learning |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230335271A1 (en)* | 2022-04-13 | 2023-10-19 | VitalTracer Ltd. | Monitoring Vital Signs via Machine Learning |
| WO2024130577A1 (en)* | 2022-12-21 | 2024-06-27 | 中国科学院深圳先进技术研究院 | Animal vital sign real-time monitoring system |
| CN117379015A (en)* | 2023-11-24 | 2024-01-12 | 军事科学院系统工程研究院卫勤保障技术研究所 | Multipurpose medical monitoring device and method |
| CN117898687A (en)* | 2024-01-12 | 2024-04-19 | 杭州光特医疗科技有限公司 | Multidimensional vital sign monitoring method, device and system and intelligent ring |
| CN117995403A (en)* | 2024-02-02 | 2024-05-07 | 中国人民解放军总医院第一医学中心 | Wearable vital sign monitoring system for field operations |
| CN118512161A (en)* | 2024-05-29 | 2024-08-20 | 深圳康恒医疗集团有限公司 | Real-time monitoring method and system for vital sign data based on deep learning |
| Title |
|---|
| 丁慧洁;: "基于物联网的危重病人体征监测报警方法研究", 计算机仿真, no. 12, 15 December 2015 (2015-12-15)* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119416048A (en)* | 2024-10-12 | 2025-02-11 | 中国人民解放军总医院第七医学中心 | A method and device for monitoring children's health based on smart bracelet |
| CN119279536A (en)* | 2024-10-25 | 2025-01-10 | 中国人民解放军总医院第四医学中心 | A method and device for joint monitoring of multiple physiological parameters |
| CN119112141A (en)* | 2024-11-15 | 2024-12-13 | 中国人民解放军总医院 | A method and device for monitoring hemodynamics of experimental animals |
| CN119112141B (en)* | 2024-11-15 | 2025-02-28 | 中国人民解放军总医院 | A method and device for monitoring hemodynamics of experimental animals |
| Publication number | Publication date |
|---|---|
| CN118648878B (en) | 2024-10-22 |
| Publication | Publication Date | Title |
|---|---|---|
| CN118648878B (en) | Vital sign monitoring method and device for skin transplantation | |
| CN111248879B (en) | Hypertension old people activity analysis method based on multi-mode attention fusion | |
| Chen et al. | Machine learning method for continuous noninvasive blood pressure detection based on random forest | |
| CN115624321B (en) | Desk-top health monitor | |
| CN112741593B (en) | Pain assessment method, system, device and storage medium | |
| CN110472481B (en) | Sleeping gesture detection method, device and equipment | |
| WO2018090304A1 (en) | Mental stress evaluation method and device | |
| CN108836269A (en) | It is a kind of to merge the dynamic sleep mode automatically of heart rate breathing body method by stages | |
| CN112597949B (en) | A video-based psychological stress measurement method and system | |
| CN114699040A (en) | Waking-up detection method, device, equipment and storage medium based on physiological signals | |
| CN107280660A (en) | A heart signal remote monitoring system and method | |
| CN113907727A (en) | Beat-to-beat blood pressure measuring system and method based on photoplethysmography | |
| CN117594227B (en) | Health state monitoring method, device, medium and equipment based on wearable equipment | |
| CN115120236A (en) | Emotion recognition method, device, wearable device and storage medium | |
| Zhang et al. | MSDN: A multistage deep network for heart-rate estimation from facial videos | |
| CN115458186A (en) | Respiratory disease risk early warning system and method based on long-time multi-sign signals | |
| CN110570949A (en) | Health monitoring method and equipment for old people in smart community and readable storage medium | |
| CN114795133A (en) | Sleep apnea detection method, device, equipment and storage medium | |
| CN112674759B (en) | A method and system for recognizing standing state of infants | |
| CN117064387A (en) | Autism spectrum disorder artificial intelligent auxiliary diagnosis system based on scene video | |
| CN111466877B (en) | LSTM network-based oxygen reduction state prediction method | |
| CN113892939A (en) | Method for monitoring respiratory frequency of human body in resting state based on multi-feature fusion | |
| CN117017233B (en) | Sleep apnea detection method, device, equipment and storage medium | |
| CN113197561B (en) | Low-rank regression-based robust noninvasive sleeveless blood pressure measurement method and system | |
| CN119112141B (en) | A method and device for monitoring hemodynamics of experimental animals |
| 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |