Blood pressure prediction method, device and system

Abstract

The invention relates to a blood pressure prediction method, device and system, and the method comprises the steps: obtaining a user face picture and blood pressure related parameters of a user, and the blood pressure related parameters of the user are determined based on parameters collected by a PPG sensor; according to the user face picture, physiological feature information of the user is determined, and the physiological feature information of the user is at least one of age, gender, body weight index and skin color information; and determining a blood pressure predicted value of the user according to the physiological feature information of the user and the blood pressure related parameters of the user.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and more specifically, to a blood pressure prediction method, device and system. Background Art

[0002] Traditional blood pressure monitoring methods include arterial catheterization, auscultation, and oscillometric methods. Arterial catheterization can obtain continuous and accurate blood pressure values, but it is more harmful to patients and is only suitable for critically ill patients. Auscultation and oscillometric methods are two commonly used blood pressure monitoring methods. Both are intermittent monitoring methods and require an inflatable cuff. The inflation and deflation process of the cuff will cause discomfort to the user. Summary of the invention

[0003] One object of the present disclosure is to provide a new technical solution for blood pressure prediction method.

[0004] According to a first aspect of the present disclosure, a blood pressure prediction method is provided, comprising:

[0005] Acquire a user face picture and blood pressure related parameters of the user, wherein the blood pressure related parameters of the user are determined based on parameters collected by a PPG sensor;

[0006] Determine the user's physiological characteristic information according to the user's face image, wherein the user's physiological characteristic information is at least one of age, gender, body mass index and skin color information;

[0007] Determine a predicted blood pressure value of the user based on the physiological characteristic information of the user and the blood pressure related parameters of the user.

[0008] Optionally, determining the physiological characteristic information of the user according to the user face picture includes:

[0009] The user's face image is input into a set user physiological feature recognition model to obtain the user's physiological feature information.

[0010] Optionally, the set user physiological feature recognition model is determined based on training with a first training sample set and verification with a first test sample set, wherein each sample in the first training sample set and the first test sample set includes a face image and physiological feature information of the corresponding user.

[0011] Optionally, determining the predicted blood pressure value of the user according to the physiological characteristic information of the user and the blood pressure-related parameters of the user includes:

[0012] The user's physiological characteristic information and the user's blood pressure related parameters are input into a set blood pressure prediction model to obtain the user's blood pressure prediction value.

[0013] Optionally, the set blood pressure prediction model is determined based on training with a second training sample set and testing with a second test sample set, wherein each sample in the second training sample set and the second test sample set includes the user's physiological characteristic information, the user's blood pressure-related parameters and the corresponding blood pressure value.

[0014] Optionally, the method further includes:

[0015] Obtaining the user's blood pressure measurement value, a weight coefficient corresponding to the blood pressure measurement value, and a weight coefficient corresponding to the blood pressure prediction value;

[0016] The corrected blood pressure value of the user is determined according to the predicted blood pressure value of the user, the measured blood pressure value of the user, the weight coefficient corresponding to the measured blood pressure value and the weight coefficient corresponding to the predicted blood pressure value.

[0017] Optionally, obtaining the user's blood pressure measurement value includes:

[0018] Obtaining a blood pressure measurement result picture, wherein the blood pressure measurement result picture displays the blood pressure measurement value;

[0019] The blood pressure measurement value of the user is extracted from the blood pressure measurement result image.

[0020] Optionally, the user's blood pressure related parameters are at least one of the duration of cardiac contraction, the duration of cardiac diastole, pulse interval, time required for cardiac contraction to reach peak, time required for cardiac diastole to reach peak, time interval between cardiac contraction peak and cardiac diastole peak, time interval between two adjacent cardiac contraction peaks, cardiac contraction width, and cardiac diastole width.

[0021] According to a second aspect of the present disclosure, there is provided a blood pressure prediction device, comprising:

[0022] An acquisition module, used to acquire a user face picture and blood pressure related parameters of the user, wherein the blood pressure related parameters of the user are determined based on parameters collected by a PPG sensor;

[0023] A physiological characteristic information determination module, used to determine the physiological characteristic information of the user according to the user's face picture, wherein the physiological characteristic information of the user is at least one of age, gender, body mass index and skin color information;

[0024] The blood pressure prediction module is used to determine the user's blood pressure prediction value based on the user's physiological characteristic information and the user's blood pressure related parameters.

[0025] According to a third aspect of the present disclosure, a blood pressure prediction system is provided, comprising an electronic device and a wearable device for executing the method provided in the first aspect, wherein the wearable device establishes a communication connection with the electronic device, and the wearable device is provided with a PPG sensor.

[0026] The blood pressure prediction method provided by the embodiment of the present disclosure obtains the user's blood pressure prediction value based on the user's physiological characteristic information and the user's blood pressure related parameters, thereby realizing cuffless blood pressure measurement of the user. In addition, the user's blood pressure prediction value obtained based on the user's physiological characteristic information and the user's blood pressure related parameters takes individual differences into consideration, thereby ensuring the accuracy of the user's blood pressure prediction.

[0027] Features and advantages of the embodiments of the present specification will become apparent from the following detailed description of exemplary embodiments of the present specification with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the specification and, together with the description, serve to explain the principles of the embodiments of the specification.

[0029] Figure 1 It is a processing flow chart of a blood pressure prediction method according to an embodiment of the present disclosure.

[0030] Figure 2 It is a schematic diagram of a curve determined based on parameters collected by a PPG sensor according to an embodiment of the present disclosure.

[0031] Figure 3 The present invention is a flowchart of determining the physiological characteristic information of a user based on a set user physiological characteristic recognition model according to an embodiment of the present invention.

[0032] Figure 4 It is a schematic diagram of the fusion of the physiological characteristic information of a user and the blood pressure related parameters of the user according to an embodiment of the present disclosure.

[0033] Figure 5 It is a principle block diagram of a blood pressure prediction device according to an embodiment of the present disclosure.

[0034] Figure 6 is a hardware structure block diagram of an electronic device according to an embodiment of the present disclosure.

[0035] Figure 7 It is a block diagram of the equipment composition of a blood pressure prediction system according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] Various exemplary embodiments of the present specification will now be described in detail with reference to the accompanying drawings.

[0037] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the embodiments of the present specification and its application or uses.

[0038] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0039] Figure 1 The flowchart of the blood pressure prediction method according to one embodiment of the present disclosure is shown. The method can be applied to an APP (application). The APP can be a client APP or a web APP. Figure 1 As shown, the method includes steps S110 to S130.

[0040] Step S110, obtaining a user face picture and the user's blood pressure related parameters, wherein the user's blood pressure related parameters are determined based on parameters collected by the PPG sensor.

[0041] In some embodiments, in response to the user triggering the start of the APP, the APP interface displays an upload interactive control for the user's face picture. When the user triggers the upload interactive control, the user's face picture window is displayed. The user can upload the user's face picture based on the user's face picture. The user's face picture can be selected and uploaded by the user from pictures stored locally on the terminal device on which the APP is installed, and can also be taken and uploaded using a camera module of the terminal device on which the APP is installed.

[0042] The PPG (Photoplethysmogram) sensor is a biosensor that uses optical principles to monitor changes in blood vessel volume.

[0043] The terminal device installed with the above APP is provided with a PPG sensor. Alternatively, the PPG sensor is provided on other terminal devices, which may be wearable devices, such as smart watches and smart bracelets.

[0044] In the case where the PPG sensor is set on other terminal devices, the terminal device equipped with the PPG sensor establishes a communication connection with the terminal device installed with the above-mentioned APP, and the communication connection can be any of WIFI connection, Bluetooth connection, and NFC connection. The terminal device equipped with the PPG sensor sends the parameters collected by the PPG sensor to the terminal device installed with the above-mentioned APP through the communication connection. The terminal device installed with the above-mentioned APP determines the user's blood pressure related parameters based on the received parameters collected by the PPG sensor. The terminal device equipped with the PPG sensor determines the user's blood pressure related parameters based on the parameters collected by the PPG sensor, and sends the user's blood pressure related parameters to the terminal device installed with the above-mentioned APP.

[0045] The user's blood pressure related parameters are at least one of the duration of cardiac contraction, the duration of cardiac diastole, pulse interval, time required for cardiac contraction to reach peak, time required for cardiac diastole to reach peak, time interval between cardiac contraction peak and cardiac diastole peak, time interval between two adjacent cardiac contraction peaks, cardiac contraction width, and cardiac diastole width.

[0046] The duration of cardiac systole (T sys ) is the time that the heart muscle contracts and pumps blood to blood vessels throughout the body.

[0047] The duration of cardiac diastole (T dia ) is the time the heart relaxes and allows blood to flow from the atria into the ventricles in preparation for the next contraction.

[0048] Pulse interval (T pi ) is the time interval between two pulse beats.

[0049] The time required for the heart to reach its peak contraction (T sp ) is the time required for the heart to reach its peak contraction in one cardiac cycle.

[0050] The time required for the heart to reach the peak of diastole (T dp ) is the time required for the heart to reach its peak relaxation in one cardiac cycle.

[0051] The time interval (ΔT) between the peak of the cardiac systolic period and the peak of the cardiac diastolic period is the time interval between the time corresponding to the time when the cardiac systolic peak value is reached and the time when the cardiac diastolic peak value is reached in one cardiac cycle.

[0052] The time interval between two adjacent cardiac contraction peaks (T pp ) is the time interval between the moments when the heart contractions reach their peak in two consecutive cardiac cycles.

[0053] The cardiac cycle is the duration of each contraction and relaxation of the heart.

[0054] The systolic width (T sw50 ) is the time required for the amplitude of the heart contraction period to increase from 50% of the amplitude corresponding to the peak value to the amplitude corresponding to the peak value.

[0055] Diastolic width (T dw50 ) is the time required for the amplitude of the heart contraction period to drop from the amplitude corresponding to the peak value to 50% of the amplitude corresponding to the peak value.

[0056] Figure 2 The curve shown is a curve determined based on the parameters collected by the PPG sensor. By combining this curve, the meaning represented by the blood pressure related parameters of each user mentioned above can be understood.

[0057] Step S120, determining the user's physiological characteristic information based on the user's face image, wherein the user's physiological characteristic information is at least one of age, gender, body mass index and skin color information.

[0058] This can save users from the need to manually input physiological characteristic information, avoid errors introduced by manual input of physiological characteristic information, improve interaction efficiency, and optimize user experience.

[0059] The skin color information is one of six types of skin color classified according to the internationally accepted Fitzpatrick Scale (Fitzpatrick skin typing) standard.

[0060] In some embodiments, step S120 specifically includes: inputting the user's face image into a set user physiological feature recognition model to obtain the user's physiological feature information.

[0061] The set user physiological feature recognition model is determined based on the first training sample set training and the first test sample set. Each sample in the first training sample set and the first test sample set includes a face image and the corresponding user's physiological feature information. The user's physiological feature information in each sample is artificially annotated information.

[0062] The user physiological feature recognition model to be trained is a deep convolutional neural network. The deep neural network includes an input layer, a convolutional layer, a fully connected layer, and an output layer. First, the user physiological feature recognition model to be trained is trained using the first training sample set, so that the user physiological feature recognition model to be trained learns the correlation between the face image in each training sample and the corresponding user's physiological feature information. Then, the trained user physiological feature recognition model is verified using the first test sample set. When the output result of the user physiological feature recognition model meets the preset requirements, the training of the user physiological feature recognition model is stopped, and the trained user physiological feature recognition model is used as the set user physiological feature recognition model.

[0063] Figure 3 The schematic diagram shows how to obtain the user's physiological characteristics information based on a face picture by using a set user physiological characteristics recognition model. Figure 3 The input layer is used to determine a multidimensional array based on the input face image. The multidimensional array retains the key semantic information after being processed by multiple convolutional layers, and then outputs the corresponding user physiological feature information through the fully connected layer.

[0064] In some embodiments, before inputting the user face picture into the set user physiological feature recognition model, the user face picture is preprocessed to obtain a preprocessed user face picture, and the preprocessed user face picture is input into the set user physiological feature recognition model. Preprocessing includes image size adjustment, filtering and noise reduction, normalization processing, and cropping of facial image parts from the user face picture.

[0065] Step S130, determining the user's blood pressure prediction value based on the user's physiological characteristic information and the user's blood pressure related parameters.

[0066] The predicted blood pressure value includes the predicted systolic blood pressure value and the predicted diastolic blood pressure value.

[0067] In some embodiments, step S130 specifically includes: inputting the user's physiological characteristic information and the user's blood pressure related parameters into a set blood pressure prediction model to obtain the user's blood pressure prediction value.

[0068] according to Figure 4 As shown, the user's physiological characteristic information is an array, and the user's blood pressure related parameters are an array. Before the user's physiological characteristic information and the user's blood pressure related parameters are input into the set blood pressure prediction model, the two arrays are fused to obtain a fused array, and the fused array is used as a vector and input into the set blood pressure prediction model.

[0069] The set user blood pressure prediction model is based on the second training sample set training and the second test sample set. Each sample in the second training sample set and the second test sample set includes the user's physiological characteristic information, the user's blood pressure related parameters and the corresponding blood pressure value. The blood pressure value in each sample is the actual measured value of the user's blood pressure.

[0070] The user blood pressure prediction model to be trained is a machine learning model (such as logistic regression, support vector machine) or a deep learning model (such as convolutional neural network, recurrent neural network). First, the user blood pressure prediction model to be trained is trained using the second training sample set, so that the user blood pressure prediction model to be trained learns the correlation between the user's physiological characteristic information, the user's blood pressure related parameters and the corresponding blood pressure values ​​in each training sample. Then, the trained user blood pressure prediction model is verified using the second test sample set. When the output result of the user blood pressure prediction model meets the preset requirements, the training of the user blood pressure prediction model is stopped, and the trained user blood pressure prediction model is used as the set user blood pressure prediction model.

[0071] The blood pressure prediction method provided by the embodiment of the present disclosure obtains the user's blood pressure prediction value based on the user's physiological characteristic information and the user's blood pressure related parameters, thereby realizing cuffless blood pressure measurement of the user. In addition, the user's blood pressure prediction value obtained based on the user's physiological characteristic information and the user's blood pressure related parameters takes individual differences into consideration, thereby ensuring the accuracy of the user's blood pressure prediction.

[0072] In some embodiments, the method further includes: obtaining the user's blood pressure measurement value, the weight coefficient corresponding to the blood pressure measurement value, and the weight coefficient corresponding to the blood pressure prediction value; determining the user's corrected blood pressure value according to the user's blood pressure prediction value, the user's blood pressure measurement value, the weight coefficient corresponding to the blood pressure measurement value, and the weight coefficient corresponding to the blood pressure prediction value. The user's blood pressure prediction value can be corrected by the user's blood pressure measurement value, thereby ensuring the accuracy of the user's blood pressure value result.

[0073] Blood pressure measurements include systolic and diastolic blood pressure measurements.

[0074] The user's corrected blood pressure value BP is determined based on the following calculation formula:

[0075] BP=BP1×α+BP2×β

[0076] Where BP1 is the predicted blood pressure value, α is the weight coefficient corresponding to the predicted blood pressure value, BP2 is the measured blood pressure value, and β is the weight coefficient corresponding to the measured blood pressure value. When the predicted blood pressure value of BP1 is the predicted value of systolic pressure, BP2 is the measured value of systolic pressure. When the predicted blood pressure value of BP1 is the predicted value of diastolic pressure, BP2 is the measured value of diastolic pressure.

[0077] The user's blood pressure measurement value is a historical blood pressure measurement value, not the user's current blood pressure measurement value.

[0078] The user's blood pressure measurement value is the blood pressure measurement value triggered and uploaded by the user on the APP interface. Alternatively, the user's blood pressure measurement value is determined based on a blood pressure measurement result image triggered and uploaded by the user on the APP interface.

[0079] Determining the user's blood pressure measurement value based on the blood pressure measurement result picture specifically includes: obtaining the blood pressure measurement result picture, wherein the blood pressure measurement value is displayed on the blood pressure measurement result picture; extracting the user's blood pressure measurement value from the blood pressure measurement result picture. First, using OCR (Optical Character Recognition), each character is identified from the blood pressure measurement result picture, and each character includes Chinese characters, English and numbers. Then, using NER (Named Entity Recognition), the blood pressure measurement value is determined from each identified character. In this way, the user's blood pressure measurement value can be automatically identified, eliminating the user's operation of manually entering the blood pressure measurement value, improving the interaction efficiency, and optimizing the user experience.

[0080] This embodiment provides a blood pressure prediction device for implementing any of the above method embodiments. Figure 5 FIG. 4 shows a structural block diagram of a blood pressure prediction device according to an embodiment of the present disclosure. Figure 5 As shown, the blood pressure prediction device 500 includes an acquisition module 510 , a physiological characteristic information determination module 520 , and a blood pressure prediction module 530 .

[0081] The acquisition module 510 is used to acquire a user face picture and the user's blood pressure related parameters, wherein the user's blood pressure related parameters are determined based on the parameters collected by the PPG sensor;

[0082] The physiological characteristic information determination module 520 is used to determine the user's physiological characteristic information based on the user's face picture, wherein the user's physiological characteristic information is at least one of age, gender, body mass index and skin color information.

[0083] The blood pressure prediction module 530 is used to determine the user's blood pressure prediction value based on the user's physiological characteristic information and the user's blood pressure related parameters.

[0084] In some embodiments, the set user physiological feature recognition model is determined based on training with a first training sample set and verification with a first test sample set, wherein each sample in the first training sample set and the first test sample set includes a face image and physiological feature information of the corresponding user.

[0085] In some embodiments, the blood pressure prediction module 530 is further used to input the user's physiological characteristic information and the user's blood pressure related parameters into a set blood pressure prediction model to obtain the user's blood pressure prediction value.

[0086] In some embodiments, the set blood pressure prediction model is determined based on training with a second training sample set and testing with a second test sample set, wherein each sample in the second training sample set and the second test sample set includes the user's physiological characteristic information, the user's blood pressure-related parameters and the corresponding blood pressure value.

[0087] In some embodiments, the device further includes a correction module. The correction module is used to obtain the user's blood pressure measurement value, the weight coefficient corresponding to the blood pressure measurement value, and the weight coefficient corresponding to the blood pressure prediction value; and determine the user's corrected blood pressure value according to the user's blood pressure prediction value, the user's blood pressure measurement value, the weight coefficient corresponding to the blood pressure measurement value, and the weight coefficient corresponding to the blood pressure prediction value.

[0088] In some embodiments, the correction module is used to obtain a blood pressure measurement result picture, wherein the blood pressure measurement result picture displays the blood pressure measurement value; and extract the user's blood pressure measurement value from the blood pressure measurement result picture.

[0089] The present disclosure also provides an electronic device for implementing any of the above method embodiments. Figure 6 FIG. 6 shows a hardware structure block diagram of an electronic device 600 according to an embodiment of the present disclosure. Figure 6 As shown, the electronic device 600 includes a processor 610 and a memory 620 for storing instructions executable by the processor 610. The processor 610 is configured to implement the method according to any embodiment of the present disclosure when executing the instructions stored in the memory 620.

[0090] The processor 610 is used to execute computer instructions, which can be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 620 includes, for example, ROM (read-only memory), RAM (random access memory), a non-volatile memory such as a hard disk, etc., which are not limited here.

[0091] The present disclosure also provides a non-volatile computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method provided in any one of the above embodiments is implemented.

[0092] The present disclosure also provides a blood pressure prediction system for implementing any of the above method embodiments. Figure 7 A schematic diagram of the equipment composition of a blood pressure prediction system according to an embodiment of the present disclosure is shown.

[0093] according to Figure 7 As shown, the system includes an electronic device and a wearable device. The wearable device establishes a communication connection with the electronic device, and the wearable device is provided with a PPG sensor.

[0094] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. For the device embodiment, its related parts can be referred to the partial description of the method embodiment.

[0095] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The embodiments of the present specification may be systems, methods and / or computer program products. The computer program product may include a computer-readable storage medium carrying computer instructions for causing a processor to implement various aspects of the embodiments of the present specification.

[0097] A computer-readable storage medium may be a tangible device that can hold and store computer instructions used by a computer instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which computer instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0098] The computer instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device through a network layer, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network layer may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network layer adapter card or network layer interface in each computing / processing device receives the computer instructions from the network layer and forwards the computer instructions for storage in a computer-readable storage medium in each computing / processing device.

[0099] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the multiple embodiments of this specification. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a computer instruction, and a part of a module, a program segment or a computer instruction contains one or more executable computer instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0100] The embodiments of the present specification have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art without departing from the scope of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A blood pressure prediction method, characterized in that: include: Acquire a user face picture and blood pressure related parameters of the user, wherein the blood pressure related parameters of the user are determined based on parameters collected by a PPG sensor; Determine the user's physiological characteristic information according to the user's face image, wherein the user's physiological characteristic information is at least one of age, gender, body mass index and skin color information; Determine a predicted blood pressure value of the user based on the physiological characteristic information of the user and the blood pressure related parameters of the user.

2. The method according to claim 1, characterized in that Determining the physiological characteristic information of the user according to the user face picture includes: The user's face image is input into a set user physiological feature recognition model to obtain the user's physiological feature information.

3. The method according to claim 2, characterized in that The set user physiological feature recognition model is determined based on training with a first training sample set and verification with a first test sample set, wherein each sample in the first training sample set and the first test sample set includes a face image and corresponding physiological feature information of the user.

4. The method according to claim 1, characterized in that: The step of determining the predicted blood pressure value of the user according to the physiological characteristic information of the user and the blood pressure related parameters of the user includes: The user's physiological characteristic information and the user's blood pressure related parameters are input into a set blood pressure prediction model to obtain the user's blood pressure prediction value.

5. The method according to claim 4, characterized in that The set blood pressure prediction model is determined based on training with a second training sample set and testing with a second test sample set, wherein each sample in the second training sample set and the second test sample set includes the user's physiological characteristic information, the user's blood pressure-related parameters and the corresponding blood pressure value.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining the user's blood pressure measurement value, a weight coefficient corresponding to the blood pressure measurement value, and a weight coefficient corresponding to the blood pressure prediction value; The corrected blood pressure value of the user is determined according to the predicted blood pressure value of the user, the measured blood pressure value of the user, the weight coefficient corresponding to the measured blood pressure value and the weight coefficient corresponding to the predicted blood pressure value.

7. The method according to claim 6, characterized in that The obtaining of the user's blood pressure measurement value comprises: Obtaining a blood pressure measurement result picture, wherein the blood pressure measurement result picture displays the blood pressure measurement value; The blood pressure measurement value of the user is extracted from the blood pressure measurement result image.

8. The method according to claim 1, characterized in that The user's blood pressure related parameters are at least one of the duration of cardiac contraction, the duration of cardiac diastole, pulse interval, time required for cardiac contraction to reach peak value, time required for cardiac diastole to reach peak value, time interval between cardiac contraction peak and cardiac diastole peak, time interval between two adjacent cardiac contraction peaks, cardiac contraction width, and cardiac diastole width.

9. A blood pressure prediction device, characterized in that: include: An acquisition module, used to acquire a user face picture and blood pressure related parameters of the user, wherein the blood pressure related parameters of the user are determined based on parameters collected by a PPG sensor; A physiological characteristic information determination module, used to determine the physiological characteristic information of the user according to the user's face picture, wherein the physiological characteristic information of the user is at least one of age, gender, body mass index and skin color information; The blood pressure prediction module is used to determine the user's blood pressure prediction value based on the user's physiological characteristic information and the user's blood pressure related parameters.

10. A blood pressure prediction system, characterized in that: Comprising an electronic device and a wearable device for executing the method described in any one of claims 1 to 8, wherein the wearable device establishes a communication connection with the electronic device, and the wearable device is provided with a PPG sensor.

Images