Blood pressure detection device

Abstract

A blood pressure detection device comprises a camera used for collecting a body surface image of the body surface in a first area on the body of a user to be detected; the body surface vibration sensor is used for collecting vibration waves of the body surface in a second area on the body of the user to be detected; the processor is used for calculating the blood pressure value of the to-be-measured user based on the body surface image collected by the camera within the first time and the vibration waves collected by the body surface vibration sensor within the first time, and outputting the blood pressure value. In this way, the double-point information is collected through the camera and the body surface vibration sensor, the blood pressure value can be calculated, blood pressure detection can be conveniently carried out, and the accuracy is high.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence (AI) technology, and in particular to a blood pressure detection device. Background Art

[0002] In daily life, people pay more and more attention to their own health. Among them, blood pressure, as an important physiological indicator, has gradually attracted people's attention. In order to obtain the current blood pressure value, it is often necessary to perform corresponding blood pressure tests on the human body. Therefore, providing a convenient and highly accurate blood pressure detection device is a technical problem that needs to be solved urgently. Summary of the invention

[0003] The present application provides a blood pressure detection device that can conveniently perform blood pressure detection with high accuracy.

[0004] The present application provides a blood pressure detection device, comprising: a camera, used to collect a body surface image of a body surface in a first area on the body of a user to be tested; a body surface vibration sensor, used to collect vibration waves of the body surface in a second area on the body of the user to be tested; a processor, used to calculate the blood pressure value of the user to be tested based on the body surface image collected by the camera in a first time and the vibration waves collected by the body surface vibration sensor in the first time, and output the blood pressure value, wherein.

[0005] In this way, by collecting dual-point information through the camera and the body surface vibration sensor, the time difference related to the blood flow rate can be obtained, and the blood pressure value can be calculated through the time difference, thereby realizing convenient blood pressure detection with high accuracy.

[0006] In a possible implementation, the first area is the face and / or neck of the user to be tested; and the second area is the wrist of the user to be tested.

[0007] In a possible implementation, the camera, the body surface vibration sensor, and the processor are all configured in the wearable device. In this way, blood pressure detection can be performed using the wearable device, which improves the flexibility of blood pressure detection.

[0008] In a possible implementation, a camera is configured in a terminal device, a body surface vibration sensor is configured in a wearable device, and a processor is configured in the terminal device or the wearable device, wherein the terminal device and the wearable device establish a communication connection through a network. In this way, blood pressure detection can be performed using the terminal device and the wearable device, which improves the flexibility of blood pressure detection.

[0009] In a possible implementation, the vibration wave includes a tidal wave.

[0010] In a possible implementation, when the processor calculates the blood pressure value of the user to be measured based on the body surface image collected by the camera in the first time and the vibration wave collected by the body surface vibration sensor in the first time, it is specifically used to: based on the pixel value of each pixel in the R channel of the body surface image collected by the camera in the first stage in the first time, filter out at least one first pixel from the R channel, wherein the pixel value of the first pixel changes periodically in the first stage; based on the pixel value of at least one first pixel on the body surface image collected by the camera in the second stage in the first time and the vibration wave collected by the body surface vibration sensor in the second stage, calculate the blood pressure value of the user to be measured, wherein the first stage is earlier than the second stage. Exemplarily, taking the first area as the face of the user to be measured as an example, since blood will flow to the face when the heart contracts, the pixel value of a certain pixel in the facial image reaches a peak value at this time, and blood will flow to the heart when the heart relaxes, and the pixel value of the same pixel in the facial image will reach a valley value at this time. When a certain pixel changes periodically over a period of time, it indicates that the change of the pixel value of the pixel is closely related to the beating of the heart, so the pixel can be selected for subsequent calculations. In addition, since blood pressure is red, the pixels in the R channel of the image can be selected for calculation. Further, after the pixels in the R channel are screened out, the blood pressure of the user to be measured can be calculated by the fluctuation of the screened pixels in a certain stage and the fluctuation of the vibration wave in the same stage.

[0011] In a possible implementation, there is a time difference between the peak on the first waveform and the peak on the second waveform, and the time difference is used to reflect the blood flow rate in the body of the user to be tested. The first waveform is obtained based on the pixel value of at least one first pixel point on the body surface image collected by the camera in the second stage; the second waveform is obtained based on the vibration wave collected by the body surface vibration sensor in the second stage. In this way, the blood pressure value can be calculated by the time difference between the peaks on the two waveforms.

[0012] In a possible implementation, when the processor calculates the blood pressure value of the user to be measured based on the pixel value of at least one first pixel point on the body surface image collected by the camera in the second stage and the vibration wave collected by the body surface vibration sensor in the second stage, it is specifically used to: perform first-order derivative calculation and second-order derivative calculation on the pixel value of at least one first pixel point in the second stage, and merge the calculation result with the pixel value of at least one first pixel point in the second stage to obtain a pixel value set; perform first-order derivative calculation and second-order derivative calculation on the vibration wave collected by the body surface vibration sensor in the second stage, and merge the calculation result with the vibration wave collected by the body surface vibration sensor in the second stage to obtain a vibration wave set; process the pixel value set and the vibration wave set through a neural network model to obtain a blood pressure value. In this way, the blood pressure value can be calculated through the neural network model. In addition, by performing first-order derivative calculation on the waveform, the change in the slope or speed of the waveform can be detected, and by performing second-order derivative calculation on the waveform, the change in the convexity or acceleration of the waveform can be detected, and the use of this information can better improve the accuracy of blood pressure calculation.

[0013] In a possible implementation, the blood pressure detection device further includes: a display screen for displaying blood pressure values. In this way, the user can intuitively obtain blood pressure information through the display screen.

[0014] In a possible implementation, the blood pressure detection device further includes: a reminder for reminding the user to complete the blood pressure detection, so that the user can quickly know whether the blood pressure detection is completed through the reminder. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a structural schematic diagram of a blood pressure detection device provided in an embodiment of the present application;

[0016] Figure 2 It is a schematic diagram comparing a waveform diagram of a pixel value and a waveform diagram of a vibration wave provided in an embodiment of the present application;

[0017] Figure 3 This is a schematic diagram of a process for calculating blood pressure values ​​provided in an embodiment of the present application;

[0018] Figure 4 is another schematic diagram of a process for calculating blood pressure values ​​provided in an embodiment of the present application;

[0019] Figure 5 It is a flow chart of a blood pressure detection method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0021] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of the objects. For example, a first response message and a second response message are used to distinguish different response messages rather than to describe a specific order of the response messages.

[0022] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0023] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple processing units refer to two or more processing units, etc.; multiple elements refer to two or more elements, etc.

[0024] For example, Figure 1 FIG. 1 is a schematic diagram showing the structure of a blood pressure detection device provided in an embodiment of the present application. Figure 1 As shown, the blood pressure detection device 100 may include: a camera 110 , a body surface vibration sensor 120 and a processor 130 .

[0025] The camera 110 is mainly used to collect a body surface image of a body surface in a first area on the body of the user to be tested. Exemplarily, the first area may be the face and / or neck of the user to be tested. Of course, the first area may also be other areas on the body of the user to be tested. In addition, the first area is not covered by objects such as clothes.

[0026] The body surface vibration sensor 120 is mainly used to collect vibration waves on the body surface in the second area on the body of the user to be tested. Exemplarily, the second area can be the wrist of the user to be tested. Of course, the second area can also be other areas on the body of the user to be tested. In addition, the second area may be covered by objects such as clothes, or may not be covered by objects such as clothes, depending on the actual situation. Exemplarily, the body surface vibration sensor 120 can be a radar sensor, an ultrasonic sensor, or a mechanical sensor. In some embodiments, the body surface vibration sensor 120 can be a low-frequency resonant radar, which can be a micro-vibration sensor on the human body surface in a low-frequency band (for example: 2.4 GHz to 2.49 GHz). Since the low-frequency resonant radar can detect physical vibrations, it is less affected by noise, so it can capture more detailed information related to blood pressure, which enables it to detect the micro-vibrations on the skin surface caused by blood flowing through blood vessels, and then detect tidal waves, such as detecting the return wave after the blood reaches the end of the finger, such as Figure 2 As shown in the areas 23 and 24 in FIG. Of course, the body surface vibration sensor 120 may also be a radar such as photoplethysmo graphy (PPG).

[0027] The processor 130 is mainly used to calculate the blood pressure value of the user to be measured based on the body surface image collected by the camera 110 in the first time and the vibration wave collected by the body surface vibration sensor 120 in the first time, and output the blood pressure value. Exemplarily, the body surface image collected by the camera 110 in the first time can form a video, and each frame of the video can be a body surface image. In this embodiment, the processor 130 can input the acquired body surface image and vibration wave into a pre-trained neural network model, so that the blood pressure value of the user to be measured is output by the neural network model. Exemplarily, the processor 130 can be a general-purpose processor or a dedicated processor. For example, the processor 130 can include a central processing unit (CPU) and / or a neural network processor (NPU). In some embodiments, the processor 130 can be an NPU, wherein the NPU can quickly process the input information by drawing on the biological neural network structure, such as drawing on the transmission mode between neurons in the human brain, and can also continuously self-learn.

[0028] In some embodiments, before calculating the blood pressure value, the processor 130 may first filter out at least one first pixel from the R channel based on the pixel values ​​of each pixel in the red (red, R) channel in the body surface image collected by the camera in the second time. The pixel value of the first pixel changes periodically in the second time. Since the color of blood pressure is red, the first pixel selected in the embodiment of the present application is a pixel on the R channel. Of course, the processor 130 may also filter out the at least one first pixel through the body surface image collected by the camera 110 in the first stage within the first time; then, the body surface image collected by the camera 110 in the second stage within the first time and the vibration wave collected by the body surface vibration sensor 120 in the second stage are used to calculate the blood pressure value of the user to be measured. The end point of the first stage is the same as the starting point of the second stage, or the end point of the first stage is earlier than the starting point of the second stage, that is, the first stage is earlier than the second stage. For example, when the first time is 9:15am-9:18am, the first stage may be 9:15am-9:16am, the second stage may be 9:16am-9:18am, or the second stage may be 9:17am-9:18am.

[0029] The following describes the principles of selecting the first pixel point and calculating the blood pressure value by the processor 130.

[0030] In the embodiment of the present application, when the blood pressure detection device 100 is used to perform blood pressure detection, the camera 110 may first continuously collect multiple body surface images (also referred to as body surface images) in the first area of ​​the body of the user to be detected within a period of time, and input the collected multiple images into the processor 130. Then, the processor 130 may perform statistical analysis on the pixel values ​​of each pixel point in the R channel of these images to filter out the pixel points whose pixel values ​​change periodically during the time when the camera 110 collects the multiple images.

[0031] After screening out the first pixel point, the camera 110 can continue to collect multiple body surface images in the first area of ​​the body of the user to be tested within a period of time (of course, the camera 110 can continue to collect images during the screening of the first pixel point, which is not limited here), and the collected images are input into the processor 130. At the same time, the body surface vibration sensor 120 is used to collect the vibration waves of the body surface in the second area of ​​the body of the user to be tested during this period of time, and the collected vibration waves are input into the processor 130. After acquiring the images captured by the camera 110, the processor 130 can extract the pixel value of the first pixel point in each image. Through the extracted pixel value of the first pixel point, the processor 130 can obtain a waveform diagram obtained by the pixel value of the first pixel point, such as Figure 2By obtaining the vibration wave, the processor 130 can obtain the waveform of the vibration wave, such as Figure 2 The waveform diagram of the vibration wave shown in . As the heart contracts each time, blood will flow from the heart to the various tissue ends of the body (such as fingers), and due to the different distances from the heart, the time it takes for blood to reach the ends of each tissue will also be different, so there is a time difference between the time it arrives at different ends. Furthermore, since the time difference is caused by the different distances of blood transmission, the time difference side contains important information such as blood flow rate. Continue reading Figure 2 ,exist Figure 2 In the waveform diagram of the pixel value, the time difference between the peak 21 and the peak 22 in the waveform diagram of the vibration wave can be considered as the time difference between the time when the blood reaches different ends of the body of the user to be tested.

[0032] Since the time difference between the peak in the waveform obtained by the pixel value of the first pixel point and the peak in the waveform of the vibration wave can reflect the blood flow rate in the body of the user to be tested, and the blood flow rate is strongly correlated with the blood pressure. Therefore, the blood pressure value of the user to be tested can be calculated by obtaining the time difference between the peak in the waveform obtained by the pixel value of the first pixel point and the peak in the waveform of the vibration wave. Therefore, the processor 130 can calculate the blood pressure value of the user to be tested based on the pixel value of the first pixel point on the body surface image collected by the camera 110 within the first time and the vibration wave collected by the body surface vibration sensor 120 within the first time.

[0033] In some embodiments, when there are multiple first pixel points selected, the average value or variance of the pixel values ​​of the multiple first pixel points at a certain moment can be calculated first, and then the blood pressure is calculated by the vibration wave and the pixel values ​​obtained at each moment. For the calculation process, see the process of calculation using one first pixel point, which will not be repeated here.

[0034] Next, the process of calculating the blood pressure value by the processor 130 is introduced.

[0035] For example, Figure 3 FIG. 2 is a schematic diagram showing a process of calculating a blood pressure value by a processor provided in an embodiment of the present application. Figure 3As shown, after the processor 130 obtains the pixel value of the first pixel point on the body surface image collected by the camera 110 within the first time, the first-order derivative and the second-order derivative can be respectively performed on the waveform composed of the pixel value of the first pixel point within the first time, and the processed result can be merged with the waveform composed of the pixel value of the first pixel point within the first time to obtain a waveform set (also referred to as a pixel value set). Among them, by calculating the first-order derivative of the waveform, the change of the slope or speed of the waveform can be detected, and by calculating the second-order derivative of the waveform, the change of the concavity or acceleration of the waveform can be detected. Using this information can better improve the accuracy of blood pressure calculation. Then, the processor 130 can filter the waveform obtained after merging through a filter, and perform regularization processing on the filtered data, and input the processed waveform data into the neural network model. In some embodiments, the processor 130 can also directly input the pixel value of the first pixel point within the first time into the neural network model, or only perform filtering processing and then input it into the neural network model, or perform both filtering processing and regularization processing and then input it into the neural network model. The specific can be determined according to the actual situation and is not limited here.

[0036] After the processor 130 obtains the vibration wave collected by the body surface vibration sensor 120 in the first time, it can also perform the first-order derivative and the second-order derivative of the waveform of the vibration wave respectively, and merge the processed results with the vibration wave to obtain a waveform set (also referred to as a vibration wave set). Then, the processor 130 can filter the waveform obtained after merging through a filter, remove the baseline drift in the waveform, and perform regularization processing on the data after removing the baseline drift, and input the processed waveform data into the neural network model. In some embodiments, the processor 130 can also directly input the vibration wave into the neural network model, or only perform filtering processing and then input it into the neural network model, or perform both filtering processing and regularization processing and then input it into the neural network model. The specific details can be determined according to the actual situation and are not limited here.

[0037] After acquiring data related to the body surface image, the neural network model can extract features from these data through the convolution layer therein. In addition, after acquiring data related to the vibration wave, the neural network model can also extract features from these data through the convolution layer therein. Finally, the neural network module can process the extracted features through the fully connected layer therein to obtain the blood pressure value of the user to be measured. In some embodiments, after acquiring data related to the body surface image and data related to the vibration wave, the neural network model can also directly process these data through the fully connected layer therein to obtain the blood pressure value of the user to be measured. The specific details can be determined according to the actual situation and are not limited here.

[0038] In addition, when the vibration wave collected by the body surface vibration sensor 120 includes a tidal wave, the neural network model can also capture the relationship between the peak of the tidal wave and the peak of the vibration wave in the vibration wave, and consider the influence of this relationship when calculating the blood pressure value later. The blood pressure calculation process at this time can be as follows: Figure 4 shown. Figure 4 and Figure 3 The main difference is that: Figure 4 In the neural network model, the self-attention layer can use the relationship between the peak of the tidal wave in the vibration wave and the peak of the vibration wave, and transmit the captured information to the fully connected layer. Finally, the fully connected layer can comprehensively process the features extracted by the convolution layer and the features extracted by the self-attention layer to obtain the blood pressure value of the user to be measured.

[0039] In the embodiment of the present application, the camera 110, the body surface vibration sensor 120 and the processor 130 can all be configured in a wearable device, such as a smart watch or a smart bracelet. In this way, blood pressure measurement can be achieved through the wearable device.

[0040] In addition, the camera 110 can also be configured in a terminal device, such as a mobile phone or a tablet computer, the body surface vibration sensor 120 can be configured in a wearable device, and the processor 130 can be configured in both the terminal device and the wearable device. At this time, a communication connection can be established between the terminal device and the wearable device through a network such as Bluetooth to exchange data. In this way, blood pressure measurement can be achieved by combining the terminal device and the wearable device. Of course, the camera 110, the body surface vibration sensor 120 and the processor 130 can also be configured in other devices, depending on the actual situation.

[0041] In addition, the blood pressure detection device 100 may also include a display screen and / or a reminder. The display screen may be used to display the blood pressure value calculated by the processor 130, so that the user can intuitively obtain the blood pressure information. The reminder may remind the user to complete the blood pressure detection after the processor 130 completes the blood pressure measurement. Exemplarily, the reminder may be a vibration motor, a buzzer, and the like.

[0042] The above is an introduction to the blood pressure detection device provided in the embodiment of the present application. The following is an introduction to the effect of using the blood pressure detection device to perform blood pressure detection.

[0043] Exemplarily, in this embodiment, the detection effect of using pulse wave (also called vibration wave) alone and facial image alone is compared with the detection effect of the blood pressure detection device provided in the embodiment of the present application. In the detection process, all are based on 124 sets of self-collected data, among which the diastolic blood pressure (DBP) ranges from 56 to 78 mmHg and the systolic blood pressure (SBP) ranges from 92 to 118 mmHg. The performance of the deep learning model is shown in Table 1, where the performance of the test is statistically calculated in the form of mean absolute error ± standard deviation, that is, the smaller the value, the higher the measurement accuracy.

[0044]

[0045] Table 1

[0046] In Table 1, it can be seen that if only the pulse wave is used to measure blood pressure, the average absolute error of SBP is 5.5, and if only the facial image is used, the average absolute error of SBP is 6.1. However, when both the pulse wave and the facial image are used, the average absolute error of SBP decreases by 4.9, and the measurement accuracy of blood pressure is improved by at least 10.9%, which is in line with the expectations of the measurement principle. It can be seen that the blood pressure detection device 100 provided in the embodiment of the present application can achieve high-accuracy blood pressure detection.

[0047] Next, based on the blood pressure detection device described in the above embodiment, a blood pressure detection method provided in an embodiment of the present application is introduced.

[0048] For example, Figure 5 FIG. 1 is a flow chart of a blood pressure detection method provided in an embodiment of the present application. Figure 5 As shown, the blood pressure detection method may include the following steps:

[0049] S501: Use a camera to collect a body surface image of a first area on the body of a user to be tested.

[0050] S502: Collect vibration waves on the surface of the user in a second area using a body surface vibration sensor.

[0051] S503: Calculate the blood pressure value of the user to be measured based on the body surface image collected by the camera within the first time and the vibration wave collected by the body surface vibration sensor within the first time.

[0052] S504: Output the blood pressure value of the user to be measured.

[0053] For the detailed process from S501 to S504, please refer to the above-mentioned description of the blood pressure detection device 100, which will not be described in detail here.

[0054] It is understandable that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0055] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0056] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0057] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0058] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A blood pressure detection device, characterized in that: include: A camera, used to collect a body surface image of a first area on the body of the user to be tested; A body surface vibration sensor, used for collecting vibration waves on the body surface of the second area of ​​the body of the user to be tested; The processor is used to calculate the blood pressure value of the user to be measured based on the body surface image collected by the camera within the first time and the vibration wave collected by the body surface vibration sensor within the first time, and output the blood pressure value.

2. The blood pressure detection device according to claim 1, characterized in that: The first area is the face and / or neck of the user to be tested; The second area is the wrist of the user to be tested.

3. The blood pressure detection device according to claim 1 or 2, characterized in that: The camera, the body surface vibration sensor and the processor are all configured in a wearable device.

4. The blood pressure detection device according to claim 1 or 2, characterized in that: The camera is configured in a terminal device, the body surface vibration sensor is configured in a wearable device, and the processor is configured in the terminal device or the wearable device, wherein the terminal device and the wearable device establish a communication connection through a network.

5. The blood pressure detection device according to any one of claims 1 to 4, characterized in that: The vibration waves include tidal waves.

6. The blood pressure detection device according to any one of claims 1 to 5, characterized in that: When the processor calculates the blood pressure value of the user to be measured based on the body surface image collected by the camera within the first time and the vibration wave collected by the body surface vibration sensor within the first time, it is specifically used to: Based on the pixel values ​​of each pixel point in the R channel of the body surface image acquired by the camera in the first stage within the first time, at least one first pixel point is screened out from the R channel, wherein the pixel value of the first pixel point changes periodically within the first stage; The blood pressure value of the user to be measured is calculated based on the pixel value of at least one first pixel point on the body surface image collected by the camera in the second stage within the first time and the vibration wave collected by the body surface vibration sensor in the second stage, wherein the first stage is earlier than the second stage.

7. The blood pressure detection device according to claim 6, characterized in that: There is a time difference between the peak on the first waveform and the peak on the second waveform, and the time difference is used to reflect the blood flow rate in the body of the user to be tested; Wherein, the first waveform is obtained based on the pixel value of the at least one first pixel point on the body surface image acquired by the camera in the second stage; The second waveform diagram is obtained based on the vibration waves collected by the body surface vibration sensor in the second stage.

8. The blood pressure detection device according to claim 6 or 7, characterized in that: When the processor calculates the blood pressure value of the user to be measured based on the pixel value of the at least one first pixel point on the body surface image collected by the camera in the second stage within the first time and the vibration wave collected by the body surface vibration sensor in the second stage, it is specifically used to: Performing first-order derivative calculation and second-order derivative calculation on the pixel value of the at least one first pixel point in the second stage respectively, and combining the calculation result with the pixel value of the at least one first pixel point in the second stage to obtain a pixel value set; Performing first-order derivative calculation and second-order derivative calculation on the vibration waves collected by the body surface vibration sensor in the second stage respectively, and combining the calculation results with the vibration waves collected by the body surface vibration sensor in the second stage to obtain a vibration wave set; The pixel value set and the vibration wave set are processed by a neural network model to obtain the blood pressure value.

9. The blood pressure detection device according to any one of claims 1 to 8, characterized in that: Also includes: A display screen is used to display the blood pressure value.

10. The blood pressure detection device according to any one of claims 1 to 9, characterized in that: Also includes: Reminder to complete blood pressure test.

Images