Method, device and electronic device for constructing blood pressure calculation model based on AI

By building an AI blood pressure calculation model on a cloud server, using data such as ECG signals, pulse wave signals, etc. for intelligent analysis and deep learning, the problem of low measurement accuracy of electronic blood pressure meter is solved, and a higher accuracy blood pressure measurement is achieved.

CN117390513BInactive Publication Date: 2024-11-19ZHONGKE YUANYI INTELLIGENT (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311407301.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-10-26
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing electronic blood pressure meter has low blood pressure measurement accuracy due to the high cost of the blood pressure chip and limited computing power.

Method used

The target parameter set is extracted through the cloud server and a blood pressure calculation model is constructed using AI, including intelligent analysis and deep learning processing of electrocardiogram signals, pulse wave signals, air pressure signals and attitude perception signals to improve the accuracy of blood pressure measurement.

Benefits of technology

It significantly improves the measurement accuracy of the blood pressure calculation model, reduces costs, and solves the problem of limited computing power of the blood pressure meter chip.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117390513B_ABST
    Figure CN117390513B_ABST
Patent Text Reader

Abstract

The present invention provides a method, device and electronic device for constructing a blood pressure calculation model based on AI, which relates to the technical field of medical algorithms, including: receiving blood pressure sample data sent by a sphygmomanometer, wherein the blood pressure sample data includes: the electrocardiogram signal and pulse wave signal of the sample user during the blood pressure measurement process; performing intelligent data analysis and processing on the electrocardiogram signal and the pulse wave signal to determine a target parameter set; performing deep learning processing on the target parameter set by presetting an oscillometric blood pressure calculation model to determine a target blood pressure calculation model. The present invention extracts the target parameter set through a cloud server, and uses the target parameter set to construct a blood pressure calculation model, which can significantly improve the measurement accuracy of the blood pressure calculation model.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of medical algorithms, and in particular to a method, device and electronic equipment for constructing a blood pressure calculation model based on AI. Background Art

[0002] Sphygmomanometers usually include electronic sphygmomanometers using the oscillometric method and mercury sphygmomanometers using the auscultatory method. Since mercury sphygmomanometers are difficult to use, electronic sphygmomanometers using the oscillometric method are widely used in households. At present, relevant technologies have proposed that the blood pressure of the user to be measured can be estimated by using a sphygmomanometer chip based on the envelope amplitude coefficient method. However, due to the high cost of the sphygmomanometer chip and the limited computing power of the chip, the measurement accuracy of the sphygmomanometer in this solution is low. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a method, device and electronic device for constructing an AI-based blood pressure calculation model. By extracting a target parameter set through a cloud server and using the target parameter set to construct a blood pressure calculation model, the measurement accuracy of the blood pressure calculation model can be significantly improved.

[0004] In the first aspect, an embodiment of the present invention provides a method for constructing an AI-based blood pressure calculation model, which is applied to a cloud server, and includes: receiving blood pressure sample data sent by a sphygmomanometer, wherein the blood pressure sample data includes: the electrocardiogram signal and pulse wave signal of the sample user during the blood pressure measurement process; performing intelligent data analysis and processing on the electrocardiogram signal and the pulse wave signal to determine a target parameter set; and performing deep learning processing on the target parameter set through a preset oscillometric blood pressure calculation model to determine a target blood pressure calculation model.

[0005] In one embodiment, the target parameter set includes: pulse wave propagation velocity, respiratory signal, pulse wave envelope diagram and pulse wave filtering, and the steps of performing intelligent data analysis and processing on the ECG signal and the pulse wave signal to determine the target parameter set include: determining the respiratory signal, the pulse wave envelope diagram and the pulse wave filtering according to the signal characteristics of the ECG signal and the pulse wave signal; and comparing the ECG signal and the pulse wave signal to determine the time difference between the peaks of the ECG signal and the pulse wave signal; and determining the pulse wave propagation velocity based on the time difference by using a preset blood flow velocity calculation model.

[0006] In one embodiment, the steps of determining a respiratory signal, a pulse wave envelope diagram and a pulse wave filter based on signal characteristics of an electrocardiogram signal and a pulse wave signal include: determining a respiratory signal based on a periodic variation pattern of the waveform of the electrocardiogram signal; performing curve feature analysis processing on the pulse wave signal by a preset adaptive spectral line enhancer to determine a pulse wave filter and a pulse wave envelope diagram corresponding to the pulse wave signal.

[0007] In one embodiment, the blood pressure sample data also includes: the air pressure signal of the sphygmomanometer air bag, and the target parameter set also includes: blocking time point information, performing intelligent data analysis and processing on the electrocardiogram signal and the pulse wave signal, and determining the step of the target parameter set, also includes: comparing the air pressure signal with the pulse wave signal; when the air pressure signal is in the rising stage and the pulse wave signal drops to a preset signal threshold, it is determined that the pulse wave disappears, and the blocking time point information of the pulse wave disappearance is recorded.

[0008] In one embodiment, the blood pressure sample data also includes: the accelerometer signal and the gyroscope signal of the blood pressure monitor posture sensing module, the step of performing intelligent data analysis and processing on the electrocardiogram signal and the pulse wave signal, and determining the target parameter set, and also includes: determining the posture information of the blood pressure monitor based on the accelerometer signal and the gyroscope signal through a preset posture analysis model, wherein the posture information includes: jitter range and tilt angle; if the jitter range of the blood pressure monitor is greater than the preset range threshold and, or the tilt angle is greater than the preset angle threshold, the blood pressure sample data of the sample user is marked as invalid data, and the invalid data is deleted.

[0009] In a second aspect, an embodiment of the present invention provides an AI-based blood pressure calculation method, which is applied to a sphygmomanometer, and the method includes: obtaining blood pressure measurement data of a user to be measured; preprocessing the blood pressure measurement data and sending it to a cloud server, so that a target blood pressure calculation model pre-constructed in the cloud server performs data analysis and processing on the blood pressure measurement data after data preprocessing to determine the blood pressure measurement result; wherein the target blood pressure calculation model is constructed based on the AI-based blood pressure calculation model construction method of any one of the items provided in the first aspect.

[0010] In the third aspect, an embodiment of the present invention also provides a device for constructing an AI-based blood pressure calculation model, which is applied to a cloud server and includes: a sample data acquisition module, which receives blood pressure sample data sent by a sphygmomanometer, wherein the blood pressure sample data includes: the electrocardiogram (ECG) signal and the pulse wave signal of the sample user during the blood pressure measurement process; a data processing module, which performs intelligent data analysis and processing on the ECG signal and the pulse wave signal to determine a target parameter set; and a model training module, which performs deep learning processing on the target parameter set through a preset oscillometric blood pressure calculation model to determine a target blood pressure calculation model.

[0011] In a fourth aspect, an embodiment of the present invention further provides an AI-based blood pressure calculation device, which is applied to a sphygmomanometer, and the device includes: a user data acquisition module, which obtains blood pressure measurement data of a user to be measured; a blood pressure calculation module, which pre-processes the blood pressure measurement data and sends it to a cloud server, so that a target blood pressure calculation model pre-constructed in the cloud server performs data analysis and processing on the blood pressure measurement data after data pre-processing to determine the blood pressure measurement result; wherein the target blood pressure calculation model is constructed based on the AI-based blood pressure calculation model construction method of any one of the items provided in the first aspect.

[0012] In a fifth aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement any one of the methods provided in the first aspect.

[0013] In a sixth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0014] The embodiments of the present invention bring the following beneficial effects:

[0015] An embodiment of the present invention provides a method, device and electronic device for constructing an AI-based blood pressure calculation model. When constructing a blood pressure calculation model, the method first receives blood pressure sample data sent by a sphygmomanometer, then performs intelligent data analysis and processing on the blood pressure sample data to determine a target parameter set, and performs deep learning processing on the target parameter set through a preset oscillometric blood pressure calculation model to determine the target blood pressure calculation model. The embodiment of the present invention extracts the target parameter set through a cloud server and constructs a blood pressure calculation model using the target parameter set, which can significantly improve the measurement accuracy of the blood pressure calculation model.

[0016] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flowchart of a method for constructing an AI-based blood pressure calculation model provided in an embodiment of the present invention;

[0020] Figure 2 A flow chart of a blood pressure calculation method based on AI provided in an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of the structure of a device for constructing an AI-based blood pressure calculation model provided in an embodiment of the present invention;

[0022] Figure 4 A schematic diagram of the structure of a blood pressure calculation device based on AI provided in an embodiment of the present invention;

[0023] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described in combination with the embodiments below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] At present, sphygmomanometers generally include electronic sphygmomanometers using the oscillometric method and mercury sphygmomanometers using the auscultatory method. Since the mercury sphygmomanometer is difficult to use, the electronic sphygmomanometer using the oscillometric method is widely used in households. The electronic sphygmomanometer mainly estimates the blood pressure of the user to be measured through the sphygmomanometer chip based on the envelope amplitude coefficient method. However, due to the high cost of the sphygmomanometer chip and the limited computing power of the chip, the measurement accuracy of the sphygmomanometer in this solution is low. Based on this, the present invention implements the method for constructing an AI-based blood pressure calculation model, which extracts a target parameter set through a cloud server and constructs a blood pressure calculation model using the target parameter set, thereby significantly improving the measurement accuracy of the blood pressure calculation model.

[0026] See also Figure 1The flowchart of a method for constructing a blood pressure calculation model based on AI is shown, and the method mainly includes the following steps S102 to S106:

[0027] Step S102, receiving blood pressure sample data sent by the sphygmomanometer, wherein the blood pressure sample data includes: the electrocardiogram signal, pulse wave signal, air pressure signal of the sphygmomanometer airbag of the sample user during the blood pressure measurement process, and the accelerometer signal and gyroscope signal of the sphygmomanometer posture sensing module during the blood pressure measurement process of the sample user. In one embodiment, the electrocardiogram signal and pulse wave signal of the sample user's wrist can be collected by the photoelectric sensor in the sphygmomanometer.

[0028] Step S104, perform intelligent data analysis and processing on the ECG signal and the pulse wave signal to determine a target parameter set, wherein the target parameter set includes: pulse wave propagation velocity, respiratory signal, pulse wave envelope diagram and blocking time point information. In one embodiment, the blood pressure sample data sent by the sphygmomanometer is compressed data, and the data needs to be decompressed and filtered, and then the filtered data is intelligently analyzed and processed to determine the target parameter set, wherein the target parameter set is the blood pressure measurement parameters corresponding to a sample user during the blood pressure measurement process.

[0029] Step S106, through the preset oscillometric blood pressure calculation model, deep learning processing is performed on the target parameter set to determine the target blood pressure calculation model. In one embodiment, more than 1000 groups of sample users corresponding to the target parameter set and the calibration data set are required to perform deep learning processing to determine the target blood pressure calculation model, wherein the calibration data set is the mercury blood pressure count value measured by two people.

[0030] The above-mentioned AI-based blood pressure calculation model construction method provided in an embodiment of the present invention extracts a target parameter set through a cloud server, and constructs a blood pressure calculation model using the target parameter set, which can significantly improve the measurement accuracy of the blood pressure calculation model.

[0031] The embodiment of the present invention also provides an implementation method for a cloud server to perform intelligent data analysis and processing on blood pressure sample data to construct a blood pressure calculation model. For details, see (1) to (3) below:

[0032] (1) The ECG signal and the pulse wave signal are compared to determine the time difference between the peaks of the ECG signal and the pulse wave signal, and the pulse wave propagation velocity is determined based on the time difference by using a preset blood flow velocity calculation model, wherein the time difference PTT between the peaks of the ECG signal and the pulse wave signal represents the time difference from the start of the heart beat to the blood flow to the test site (such as the wrist). In one embodiment, since the ECG signal propagation and collection principle is the speed of light, the propagation time can be ignored as 0, but it takes a certain amount of time for the blood to flow to the wrist. Therefore, PTT is mainly affected by the blood flow velocity. Since the blood flow velocity is mainly affected by the blood pressure, the distance from the heart to the wrist is divided by the time to determine the pulse wave propagation velocity PWV.

[0033] (2) Determine the respiratory signal and the pulse wave envelope diagram according to the signal characteristics of the ECG signal and the pulse wave signal: Determine the respiratory signal according to the periodic variation law of the ECG signal waveform, and perform curve feature analysis and processing on the pulse wave signal through a preset adaptive spectral line enhancer to determine the pulse wave envelope diagram and pulse wave filter corresponding to the pulse wave signal, wherein when the pulse wave filter moves according to a certain motion law, the image of all its instantaneous positions is retained, and there will be a curve that can be tangent to all positions of the motion curve, and this curve is determined as the envelope of the motion curve of the pulse wave filter, that is, the pulse wave envelope diagram. In one embodiment, the characteristic points of the ECG signal can be identified by the r-wave amplitude method, and the trend change of the respiratory signal can be judged by using the periodic variation of the r-wave amplitude. In another embodiment, the pulse wave envelope diagram corresponding to the pulse wave signal can be determined by a preset adaptive spectral line enhancer based on a polynomial smoothing method. The present invention does not limit the above-mentioned r-wave amplitude method, the preset adaptive spectral line enhancer and the polynomial smoothing method. At the same time, those skilled in the art should be aware that the above-mentioned r-wave amplitude method, preset adaptive spectral line enhancer and polynomial smoothing method are not used to limit the present invention, and other algorithms for determining respiratory signals and pulse wave envelope diagrams are also within the scope of protection of the present invention.

[0034] (3) Compare the air pressure signal with the pulse wave signal: When the air pressure signal is in the rising stage and the pulse wave signal drops to the preset signal threshold, it is determined that the pulse wave disappears, and the blocking time point information of the pulse wave disappearance is recorded. In one embodiment, since the user's arteriolar blood vessels are compressed by the airbag during the inflation of the airbag, the pulse wave signal will be blocked. Therefore, when the pulse wave signal is observed to decrease sharply, the time point can also be determined as the blocking time point information of the pulse wave signal. In practical applications, since the posture and stability when measuring blood pressure are very important and can directly affect the measurement results, the posture information of the blood pressure meter can be determined by the preset posture analysis model based on the accelerometer signal of the accelerometer and the gyroscope signal of the gyroscope in the blood pressure meter posture perception module. If the jitter range of the blood pressure meter is greater than the preset range threshold and, or the tilt angle is greater than the preset angle threshold, the blood pressure sample data of the sample user is marked as invalid data and the invalid data is deleted, wherein the posture information includes: jitter range and tilt angle.

[0035] See also Figure 2 The flowchart of a blood pressure calculation method based on AI is shown, and the method mainly includes the following steps S202 to S204:

[0036] Step S202, obtaining blood pressure measurement data of the user to be measured, wherein the blood pressure measurement data includes: the electrocardiogram signal, pulse wave signal, air pressure signal of the sphygmomanometer airbag of the user to be measured during the blood pressure measurement process, and the accelerometer signal and gyroscope signal of the sphygmomanometer during the blood pressure measurement process of the user to be measured.

[0037] Step S204, the blood pressure measurement data is pre-processed and then sent to the cloud server, so that the target blood pressure calculation model pre-constructed in the cloud server performs data analysis and processing on the blood pressure measurement data after data pre-processing to determine the blood pressure measurement result, wherein the target blood pressure calculation model is constructed based on any of the above-mentioned AI-based blood pressure calculation model construction methods. In one embodiment, the sphygmomanometer and the cloud server exchange information through the network. The sphygmomanometer needs to losslessly compress the blood pressure measurement data and send the compressed data to the cloud server, so that the cloud server decompresses and filters the compressed data, and then performs data analysis to determine the blood pressure measurement result.

[0038] The AI-based blood pressure calculation method provided in the embodiment of the present invention can solve the technical problem of limited computing power of blood pressure meter chips in the prior art by uploading the blood pressure measurement data of the user to be measured to the cloud server to obtain the blood pressure measurement results, thereby significantly improving the blood pressure measurement accuracy while reducing costs.

[0039] For the method for constructing a blood pressure calculation model based on AI provided in the above-mentioned embodiment, an embodiment of the present invention provides a device for constructing a blood pressure calculation model based on AI, which is applied to a cloud server, see Figure 3 The structure diagram of a device for constructing a blood pressure calculation model based on AI is shown, and the device includes the following parts:

[0040] The sample data acquisition module 302 receives the blood pressure sample data sent by the sphygmomanometer, wherein the blood pressure sample data includes: the electrocardiogram signal and the pulse wave signal of the sample user during the blood pressure measurement process;

[0041] The data processing module 304 performs intelligent data analysis and processing on the ECG signal and the pulse wave signal to determine the target parameter set;

[0042] The model training module 306 performs deep learning processing on the target parameter set by presetting the oscillometric blood pressure calculation model to determine the target blood pressure calculation model.

[0043] The above-mentioned AI-based blood pressure calculation model construction device provided in the embodiment of the present application extracts the target parameter set through the cloud server, and uses the target parameter set to construct the blood pressure calculation model, which can significantly improve the measurement accuracy of the blood pressure calculation model.

[0044] In one embodiment, the target parameter set includes: pulse wave propagation velocity, respiratory signal, pulse wave envelope diagram and pulse wave filtering. When performing intelligent data analysis and processing on the ECG signal and the pulse wave signal to determine the target parameter set, the above-mentioned data processing module 304 is also used to: determine the respiratory signal, pulse wave envelope diagram and pulse wave filtering according to the signal characteristics of the ECG signal and the pulse wave signal; and compare the ECG signal and the pulse wave signal to determine the time difference between the peaks of the ECG signal and the pulse wave signal; and determine the pulse wave propagation velocity based on the time difference by using a preset blood flow velocity calculation model.

[0045] In one embodiment, when performing the step of determining the respiratory signal, pulse wave envelope diagram and pulse wave filtering according to the signal characteristics of the electrocardiogram signal and the pulse wave signal, the above-mentioned data processing module 304 is also used to: determine the respiratory signal according to the periodic change law of the waveform of the electrocardiogram signal; perform curve feature analysis and processing on the pulse wave signal through a preset adaptive spectral line enhancer to determine the pulse wave filter and pulse wave envelope diagram corresponding to the pulse wave signal.

[0046] In one embodiment, the blood pressure sample data also includes: the air pressure signal of the sphygmomanometer air bag, and the target parameter set also includes: blocking time point information. When performing intelligent data analysis and processing on the electrocardiogram signal and the pulse wave signal to determine the target parameter set, the above-mentioned data processing module 304 is also used to: compare the air pressure signal with the pulse wave signal; when the air pressure signal is in the rising stage and the pulse wave signal drops to the preset signal threshold, it is determined that the pulse wave disappears, and the blocking time point information of the pulse wave disappearance is recorded.

[0047] In one embodiment, the blood pressure sample data also includes: the accelerometer signal and the gyroscope signal of the blood pressure monitor posture sensing module. When performing data intelligent analysis and processing on the electrocardiogram signal and the pulse wave signal to determine the target parameter set, the above-mentioned data processing module 304 is also used to: determine the posture information of the blood pressure monitor based on the accelerometer signal and the gyroscope signal through a preset posture analysis model, wherein the posture information includes: jitter range and tilt angle; if the jitter range of the blood pressure monitor is greater than the preset range threshold and, or the tilt angle is greater than the preset angle threshold, the blood pressure sample data of the sample user is marked as invalid data, and the invalid data is deleted.

[0048] For the AI-based blood pressure calculation method provided in the above-mentioned embodiment, an embodiment of the present invention provides an AI-based blood pressure calculation device, which is applied to a sphygmomanometer, see Figure 4 The structure diagram of a blood pressure calculation device based on AI is shown, and the device includes the following parts:

[0049] The user data collection module 402 obtains the blood pressure measurement data of the user to be measured;

[0050] The blood pressure calculation module 404 performs data preprocessing on the blood pressure measurement data and sends it to the cloud server, so that the target blood pressure calculation model pre-constructed in the cloud server performs data analysis and processing on the blood pressure measurement data after data preprocessing to determine the blood pressure measurement result; wherein, the target blood pressure calculation model is constructed based on any of the above-mentioned AI-based blood pressure calculation model construction methods.

[0051] The above-mentioned AI-based blood pressure calculation device provided in the embodiment of the present application obtains the blood pressure measurement results by uploading the blood pressure measurement data of the user to be measured to the cloud server, which can solve the technical problem of limited computing power of the blood pressure meter chip in the prior art, and significantly improve the blood pressure measurement accuracy while reducing costs.

[0052] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0053] An embodiment of the present invention provides an electronic device. Specifically, the electronic device includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned implementation methods.

[0054] Figure 5 A structural diagram of an electronic device provided in an embodiment of the present invention, the electronic device 100 includes: a processor 50, a memory 51, a bus 52 and a communication interface 53, wherein the processor 50, the communication interface 53 and the memory 51 are connected via the bus 52; the processor 50 is used to execute an executable module stored in the memory 51, such as a computer program.

[0055] The memory 51 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 53 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0056] The bus 52 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0057] Among them, the memory 51 is used to store programs, and the processor 50 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 50 or implemented by the processor 50.

[0058] The processor 50 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 50. The above processor 50 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor to be executed, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 51, and the processor 50 reads the information in the memory 51 and completes the steps of the above method in combination with its hardware.

[0059] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be referred to the previous method embodiments, which will not be repeated here.

[0060] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0061] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for constructing a blood pressure calculation model based on AI, characterized in that: The method is applied to a cloud server, and the method comprises: Receiving blood pressure sample data sent by a sphygmomanometer, wherein the blood pressure sample data includes: an electrocardiogram signal and a pulse wave signal of a sample user during blood pressure measurement; Performing intelligent data analysis and processing on the electrocardiogram signal and the pulse wave signal to determine a target parameter set, wherein the target parameter set includes: pulse wave propagation velocity, respiratory signal and pulse wave envelope diagram; By presetting the oscillometric blood pressure calculation model, deep learning processing is performed on the target parameter set to determine the target blood pressure calculation model; The step of performing intelligent data analysis and processing on the ECG signal and the pulse wave signal to determine the target parameter set includes: determining the respiratory signal, the pulse wave envelope diagram and the pulse wave filtering according to the signal characteristics of the ECG signal and the pulse wave signal; and comparing the ECG signal and the pulse wave signal to determine the time difference between the peaks of the ECG signal and the pulse wave signal; and determining the pulse wave propagation speed based on the time difference by using a preset blood flow velocity calculation model; Wherein, the step of determining the respiratory signal, the pulse wave envelope diagram and the pulse wave filter according to the signal characteristics of the electrocardiogram signal and the pulse wave signal comprises: determining the respiratory signal according to the periodic variation law of the waveform of the electrocardiogram signal; performing curve characteristic analysis processing on the pulse wave signal by a preset adaptive spectral line enhancer to determine the pulse wave filter and the pulse wave envelope diagram corresponding to the pulse wave signal; Wherein, the blood pressure sample data also includes: the air pressure signal of the sphygmomanometer airbag, the target parameter set also includes: blocking time point information, the step of performing intelligent data analysis and processing on the electrocardiogram signal and the pulse wave signal to determine the target parameter set also includes: comparing the air pressure signal with the pulse wave signal; when the air pressure signal is in the rising stage and the pulse wave signal drops to a preset signal threshold, determining that the pulse wave disappears, and recording the blocking time point information when the pulse wave disappears; Among them, the blood pressure sample data also includes: the accelerometer signal and the gyroscope signal of the blood pressure monitor posture sensing module, and the step of performing data intelligent analysis and processing on the electrocardiogram signal and the pulse wave signal to determine the target parameter set also includes: determining the posture information of the blood pressure monitor based on the accelerometer signal and the gyroscope signal through a preset posture analysis model, wherein the posture information includes: jitter range and tilt angle; if the jitter range of the blood pressure monitor is greater than the preset range threshold and / or the tilt angle is greater than the preset angle threshold, the blood pressure sample data of the sample user is marked as invalid data, and the invalid data is deleted.

2. A blood pressure calculation method based on AI, characterized in that: The method is applied to a sphygmomanometer, and the method comprises: Obtain blood pressure measurement data of the user to be tested; The blood pressure measurement data is pre-processed and then sent to the cloud server, so that the target blood pressure calculation model pre-constructed in the cloud server performs data analysis and processing on the pre-processed blood pressure measurement data to determine the blood pressure measurement result; Wherein, the target blood pressure calculation model is constructed based on the method for constructing the AI-based blood pressure calculation model described in claim 1.

3. A device for constructing a blood pressure calculation model based on AI, characterized in that: The device is applied to a cloud server, and the device includes: A sample data acquisition module receives blood pressure sample data sent by a sphygmomanometer, wherein the blood pressure sample data includes: an electrocardiogram signal and a pulse wave signal of a sample user during blood pressure measurement; A data processing module performs intelligent data analysis and processing on the electrocardiogram signal and the pulse wave signal to determine a target parameter set, wherein the target parameter set includes: pulse wave propagation velocity, respiratory signal and pulse wave envelope diagram; A model training module, which performs deep learning processing on the target parameter set by presetting an oscillometric blood pressure calculation model to determine a target blood pressure calculation model; The step of performing intelligent data analysis and processing on the ECG signal and the pulse wave signal to determine the target parameter set includes: determining the respiratory signal, the pulse wave envelope diagram and the pulse wave filtering according to the signal characteristics of the ECG signal and the pulse wave signal; and comparing the ECG signal and the pulse wave signal to determine the time difference between the peaks of the ECG signal and the pulse wave signal; and determining the pulse wave propagation speed based on the time difference by using a preset blood flow velocity calculation model; Wherein, the step of determining the respiratory signal, the pulse wave envelope diagram and the pulse wave filter according to the signal characteristics of the electrocardiogram signal and the pulse wave signal comprises: determining the respiratory signal according to the periodic variation law of the waveform of the electrocardiogram signal; performing curve characteristic analysis processing on the pulse wave signal by a preset adaptive spectral line enhancer to determine the pulse wave filter and the pulse wave envelope diagram corresponding to the pulse wave signal; Wherein, the blood pressure sample data also includes: the air pressure signal of the sphygmomanometer airbag, the target parameter set also includes: blocking time point information, the step of performing intelligent data analysis and processing on the electrocardiogram signal and the pulse wave signal to determine the target parameter set also includes: comparing the air pressure signal with the pulse wave signal; when the air pressure signal is in the rising stage and the pulse wave signal drops to a preset signal threshold, determining that the pulse wave disappears, and recording the blocking time point information when the pulse wave disappears; Among them, the blood pressure sample data also includes: the accelerometer signal and the gyroscope signal of the blood pressure monitor posture sensing module, and the step of performing data intelligent analysis and processing on the electrocardiogram signal and the pulse wave signal to determine the target parameter set also includes: determining the posture information of the blood pressure monitor based on the accelerometer signal and the gyroscope signal through a preset posture analysis model, wherein the posture information includes: jitter range and tilt angle; if the jitter range of the blood pressure monitor is greater than the preset range threshold and / or the tilt angle is greater than the preset angle threshold, the blood pressure sample data of the sample user is marked as invalid data, and the invalid data is deleted.

4. A blood pressure calculation device based on AI, characterized in that: The device is applied to a sphygmomanometer, and comprises: User data collection module, to obtain the blood pressure measurement data of the user to be tested; A blood pressure calculation module, which performs data preprocessing on the blood pressure measurement data and sends it to the cloud server, so that the target blood pressure calculation model pre-constructed in the cloud server performs data analysis and processing on the blood pressure measurement data after data preprocessing to determine the blood pressure measurement result; Wherein, the target blood pressure calculation model is constructed based on the method for constructing the AI-based blood pressure calculation model described in claim 1.

5. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 2.