Blood pressure measuring method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of blood pressure measurement, and discloses a blood pressure measurement method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring blood pressure measurement information to form audio data; preprocessing the audio data to obtain a preprocessing result; inputting the preprocessing result into an automatic blood pressure generation model to generate blood pressure so as to obtain a generation result; outputting a generation result; wherein the blood pressure automatic generation model is obtained by collecting blood pressure measurement information of multiple persons as a sample set to train the deep learning model. By means of the method, high-precision, intelligent and automatic measurement of the blood pressure value is achieved, and the method has the remarkable technical effect and practical application value.

Description

Technical Field

[0001] The present invention relates to blood pressure measurement technology, and more specifically to a blood pressure measurement method, device, computer equipment and storage medium. Background Art

[0002] With the rapid development of medical technology, electronic blood pressure monitors have been widely recognized and applied in the market due to their convenience and intelligent features. Especially in the fields of family health management and daily monitoring of medical institutions, the demand for electronic blood pressure monitors continues to grow. Among them, electronic blood pressure monitors based on auscultation (Korotkoff sound method) determine blood pressure values ​​by detecting the sound of arterial blood flow (Korotkoff sound), becoming one of the mainstream technologies.

[0003] The working principle of the existing Korotkoff sound electronic blood pressure monitor is as follows: the cuff is wrapped around the patient's arm and pressurized by an air pump until the cuff pressure exceeds the maximum pressure of the artery (systolic pressure). At this time, the artery is completely closed, blood cannot circulate, and no sound can be heard. Then, the pressure in the cuff is slowly released, the artery begins to partially open, and blood turbulence produces Korotkoff sounds. When the Korotkoff sound first appears, the corresponding cuff pressure is the systolic pressure; and when the Korotkoff sound completely disappears, the corresponding cuff pressure is the diastolic pressure.

[0004] However, although Korotkoff sound electronic sphygmomanometers occupy an important position in the field of blood pressure measurement, they still have many challenges and limitations:

[0005] Algorithms and signal processing: Currently, most Korotkoff sound electronic blood pressure monitors rely on processors to perform digital signal processing technology to analyze audio data. However, the choice of algorithm, the accuracy of feature extraction, and real-time processing capabilities directly affect the accuracy of blood pressure measurement. Imperfections in the algorithm or errors in signal processing may cause the measurement results to deviate from the actual value.

[0006] Piezoelectric signal capture: Some blood pressure monitors try to use piezoelectric sensors to capture the mechanical vibration of the brachial artery pulsation to measure blood pressure. However, this method is easily disturbed by external vibrations, and the vibration signal itself is relatively weak, which increases the uncertainty and error of the measurement.

[0007] Application of electret microphone: In order to improve the measurement accuracy, some blood pressure monitors use electret microphones to pick up Korotkoff sound signals. However, the introduction of electret microphones increases the complexity of circuit design and requires additional amplifiers and filters for signal processing. If the circuit design is improper, it is easy to introduce additional noise and distortion, affecting the accuracy of the measurement results. In addition, the parameters of electret microphones (such as sensitivity and frequency response) are less consistent in mass production, further increasing the measurement error.

[0008] Environmental factors and individual differences: Blood pressure measurement is also affected by environmental noise and individual differences of patients (such as age, gender, body shape, degree of arteriosclerosis, etc.). These factors may cause changes in the intensity, frequency and duration of Korotkoff sound signals, thus affecting the accuracy and reliability of the measurement.

[0009] Given the above limitations, the industry urgently needs to develop new, efficient and accurate blood pressure measurement technologies to improve the accuracy of blood pressure measurement and user experience. Summary of the invention

[0010] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a blood pressure measurement method, device, equipment and medium.

[0011] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0012] In a first aspect, a blood pressure measurement method is provided, comprising:

[0013] Obtaining blood pressure measurement information to generate audio data;

[0014] Preprocessing the audio data to obtain a preprocessing result;

[0015] Inputting the preprocessing result into the blood pressure automatic generation model to generate the blood pressure, so as to obtain the generation result;

[0016] Output generation results;

[0017] Among them, the automatic blood pressure generation model is obtained by collecting blood pressure measurement information of multiple people as a sample set to train the deep learning model.

[0018] In a second aspect, a blood pressure measuring device is provided, comprising:

[0019] An acquisition forming unit, used for acquiring blood pressure measurement information to form audio data;

[0020] A preprocessing unit, used for preprocessing the audio data to obtain a preprocessing result;

[0021] An automatic generation unit, used for inputting the preprocessing result into the blood pressure automatic generation model to generate the blood pressure, so as to obtain a generation result;

[0022] An output unit, used for outputting the generated results;

[0023] Among them, the automatic blood pressure generation model is obtained by collecting blood pressure measurement information of multiple people as a sample set to train the deep learning model.

[0024] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned blood pressure measurement method when executing the computer program.

[0025] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned blood pressure measurement method are implemented.

[0026] The above-mentioned blood pressure measurement method obtains blood pressure measurement information and forms audio data. This step ensures the integrity and authenticity of the original data. Then, by preprocessing the audio data, noise and interference are effectively removed, and the purity and availability of the data are improved. A deep learning model is then introduced as a blood pressure automatic generation model. The model collects blood pressure measurement information of multiple people as a sample set for training, and can learn rich blood pressure features, thereby achieving high-precision prediction and generation of blood pressure values. The preprocessed data is directly input into the blood pressure automatic generation model to generate blood pressure values ​​without human intervention, thereby realizing the intelligence and automation of blood pressure measurement, which not only improves the measurement efficiency, but also reduces the errors caused by human operation, making blood pressure measurement more convenient and accurate.

[0027] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0029] Figure 1 A schematic diagram of a flow chart of a blood pressure measurement method provided by an embodiment of the present invention;

[0030] Figure 2 A schematic block diagram of a blood pressure measurement structure provided by an embodiment of the present invention;

[0031] Figure 3 A schematic block diagram of a blood pressure automatic generation model provided by an embodiment of the present invention;

[0032] Figure 4 A schematic block diagram of a blood pressure measurement device provided in an embodiment of the present invention;

[0033] Figure 5 It is a schematic diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0035] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0036] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0037] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0038] See also Figures 1 to 3 In the specific embodiment shown, the present invention discloses a blood pressure measurement method, comprising the following steps:

[0039] S110, obtaining blood pressure measurement information to generate audio data;

[0040] Specifically, see Figure 2 The blood pressure measurement structure shown in the figure includes an air pump, an air valve, a cuff, a sound sensor, a display screen, a key input, an ADC, a pressure sensor, and a microcontroller. The cuff includes an inflatable air bag and a stethoscope attached to the inner surface of the cuff. The inflatable air bag is connected to the multi-way valve, the air pump, the air valve, and the pressure sensor through a catheter, and the stethoscope is connected to the sound sensor through another catheter. The microcontroller is used to control the entire blood pressure measurement process and external input and output signals, including air pump inflation, air valve deflation, control of the display screen to output display content, detection of key operations, receiving signals from the sound sensor, and reading signals from the pressure sensor.

[0041] More specifically, the sound sensor uses a MEMS sound sensor module, which integrates a MEMS microphone to capture sound signals (sound waves) in the surrounding environment. The sound is picked up by the microphone in the form of sound pressure signals. The captured analog sound pressure signal is converted into a digital signal through an ADC (analog-to-digital converter), and the converted digital audio signal is transmitted through an I 2 S interface for further processing by a microcontroller or other device.

[0042] In one embodiment, the blood pressure measurement information is obtained to form audio data, including: using a microcontroller to read the pressure data of the voltage signal of the pressure sensor converted by ADC to control inflation and deflation, when deflation begins, a sound sensor connected to the stethoscope starts recording sound, and ends recording when deflation ends to obtain the blood pressure measurement information, which is then stored in the microcontroller to form audio data.

[0043] Specifically, after starting the system, the microcontroller first performs initialization, including ADC calibration, sensor self-test, etc., to ensure measurement accuracy. The microcontroller controls the airbag to inflate quickly to a preset pressure level, while continuously reading the data of the pressure sensor through the ADC to monitor pressure changes. Once the maximum inflation pressure is reached, the microcontroller controls the airbag to start slowly deflation. At this time, the sound sensor starts synchronously and starts recording the sound of arterial pulsation. During the deflation process, the microcontroller continuously monitors the pressure data and determines the systolic and diastolic pressures according to a preset algorithm (such as identifying the first Korotkoff sound and the final disappearing sound). When the last Korotkoff sound is identified, the microcontroller instructs the sound sensor to stop recording. After the recording is completed, the microcontroller stores the recorded audio data (which may be compressed to reduce storage space) in an internal or external storage unit.

[0044] More specifically, by combining the data from the pressure sensor and the sound sensor, systolic and diastolic blood pressure can be determined more accurately, reducing human error. The entire measurement process is controlled by a microcontroller, without the need to manually operate the stethoscope or record data, which improves the level of automation and user convenience of the measurement. The storage of audio data makes subsequent data analysis possible, such as further optimizing the measurement results through software algorithms, or for remote medical consultation and diagnosis. It is not only suitable for traditional sphygmomanometers, but can also be integrated into smart wearable devices to meet blood pressure monitoring needs in different scenarios.

[0045] S120, preprocessing the audio data to obtain a preprocessing result;

[0046] In one embodiment, the preprocessing of the audio data to obtain a preprocessing result includes: decoding the audio data to obtain time-related data, performing Fourier transform on each frame of the data to obtain a frequency distribution, and finally combining the frequency distribution according to time to obtain a spectrum diagram, i.e., the preprocessing result.

[0047] Specifically, first, the audio data to be processed is obtained from the microcontroller. If the audio data is in a compressed format (such as MP3, WAV, FLAC, etc.), it is necessary to first decompress or decode it and convert it into an uncompressed PCM (pulse code modulation) format or similar raw audio data. The purpose of this step is to obtain audio signal data directly related to time, that is, audio waveform data. Then the decoded audio data is divided into multiple short time periods in time order, and each time period is called a frame. The purpose of framing is to decompose long-time audio signals into short-time signals that are easier to process. On the basis of framing, a window function (such as Hanning window, Hamming window, etc.) is applied to each frame of audio data to reduce the spectrum leakage at the edge of the frame. Fast Fourier transform is performed on each frame of windowed audio data to convert the time domain signal into a frequency domain signal to obtain the frequency distribution (i.e., spectrum) of the frame. The spectrum of each frame is arranged in time order to form a two-dimensional matrix, in which the horizontal axis represents time, the vertical axis represents frequency, and the value in the matrix represents the signal strength (i.e., spectrum energy) at the corresponding time and frequency. Use a graphical tool or algorithm to convert the above two-dimensional matrix into a visual spectrum diagram. The spectrogram can intuitively display the frequency characteristics of audio signals changing over time.

[0048] More specifically, through Fourier transform, the audio signal can be converted from the time domain to the frequency domain, so as to effectively extract the frequency features in the audio, which is crucial for subsequent signal analysis, feature recognition and other steps. In addition, the selection of frame processing and windowing function can balance the time resolution and frequency resolution, so that the spectrogram can capture the rapid changes of the audio signal and accurately reflect its frequency components. In addition, the generation of the spectrogram makes the feature analysis of the audio signal more intuitive and convenient, which helps to discover hidden information, abnormal signals or specific patterns in the audio. This technology is not only suitable for audio data preprocessing in blood pressure measurement, but also can be widely used in speech recognition, music analysis, noise monitoring, fault diagnosis and other fields, and has a wide range of practical value.

[0049] S130, inputting the preprocessing result into the blood pressure automatic generation model to generate blood pressure, so as to obtain a generation result;

[0050] Specifically, see Figure 3The blood pressure automatic generation model shown in the figure collects a large number of sample sets containing blood pressure measurements and corresponding audio data during the research and development phase. Using these sample sets, a blood pressure prediction model is trained through machine learning or deep learning algorithms (such as convolutional neural networks (CNNs)). During the training process, the model learns the complex relationship between audio signals and blood pressure values. The trained model is installed on the target device, such as a smart bracelet, a health monitor, a blood pressure measurement structure, etc. When the device receives the user's audio data, it is input into the deployed model. The convolution layer in the model extracts features from the input audio data, and extracts key features in the audio signal, such as frequency and amplitude, through sliding and convolution operations of multiple convolution kernels. The parameters in the model (such as weights and biases) have been optimized during the training process, and can accurately map the extracted features to blood pressure values. Through a series of nonlinear transformations and linear combinations, accurate blood pressure prediction results are finally obtained. The model outputs the values ​​of systolic and diastolic pressures, and then displays the calculated blood pressure values ​​to the user in real time through the device's display.

[0051] More specifically, models trained by machine learning or deep learning algorithms can accurately capture the complex relationship between audio signals and blood pressure values, and achieve high-precision blood pressure prediction. The entire analysis process is fast and efficient, and can provide blood pressure prediction results within a short time after the user records the audio, improving the user experience. Using audio data for blood pressure prediction avoids the invasiveness and discomfort of traditional blood pressure measurement methods, and improves the convenience and comfort of measurement. This technology is not only suitable for home health monitoring, but can also be applied to medical institutions, sports and fitness and other fields, with broad market prospects and practical value.

[0052] S140, outputting the generated result;

[0053] In one embodiment, outputting the generation result includes: displaying the generation result in a visual manner.

[0054] Specifically, the corresponding blood pressure report is generated according to the trained model, and a visual display is provided so that users can easily view and compare. The generation of blood pressure reports will use custom templates, and the display format can include multiple visual expressions such as tables and charts.

[0055] Among them, the automatic blood pressure generation model is obtained by collecting blood pressure measurement information of multiple people as a sample set to train the deep learning model.

[0056] In one embodiment, the blood pressure automatic generation model is obtained by collecting blood pressure measurement information of multiple people as a sample set to train a deep learning model, including:

[0057] Collecting blood pressure measurement information of multiple people and marking the blood pressure measurement information to obtain a sample set;

[0058] First, blood pressure measurement information is collected from different numbers of volunteers, including but not limited to systolic blood pressure, diastolic blood pressure and the corresponding measurement time. Ensure that the samples are diverse and cover individuals of different ages, genders, and health conditions to improve the generalization ability of the model. Then, the collected blood pressure measurement information is annotated, marking the specific values ​​of systolic and diastolic blood pressure, as well as their corresponding time points. These annotated data will constitute the sample set required for training the deep learning model.

[0059] Build deep learning models;

[0060] Among them, choose a deep learning framework suitable for processing time series data, such as TensorFlow or PyTorch. Build a deep learning model. The initial model structure can be a multi-layer perceptron (MLP) or convolutional neural network (CNN) as the basis for preliminary feature extraction.

[0061] Adjust parameters of deep learning models;

[0062] Among them, the hyperparameters of the deep learning model (such as learning rate, batch size, number of network layers, etc.) are adjusted to optimize the model performance.

[0063] Use the sample set to train the deep learning model after parameter adjustment to obtain a preliminary trained model;

[0064] Among them, the adjusted model is trained using a labeled sample set, and the model weights are updated through the back propagation algorithm until the performance of the model on the validation set is no longer significantly improved, thus obtaining a preliminary trained model.

[0065] The performance of the preliminary training model was evaluated and optimized to obtain an automatic blood pressure generation model.

[0066] Among them, the performance of the preliminary training model is evaluated by cross-validation, accuracy, recall, F1 score and other indicators. According to the evaluation results, the model structure or training strategy is optimized, such as adding regularization terms, adjusting the number of network layers or activation functions, until the model performance reaches a satisfactory level, forming the final blood pressure automatic generation model. The blood pressure measurement data is converted into a spectrogram, and time features are added to the spectrogram to retain the time series information. The spectrogram with time features is input into the neural network for encoding to extract deep information (micro information), especially the features in the time series. A two-layer bidirectional long short-term memory network (Bi-LSTM) is constructed, which can gradually process the features of each time point in the time dimension and capture the long-term dependencies in the time series. A decoder module is designed to decode the output of the two-layer bidirectional LSTM network into target values, that is, the predicted values ​​of systolic and diastolic blood pressure. By setting the target values ​​(standard values), the model can be trained according to these standards, and the model parameters are continuously adjusted to improve the prediction accuracy. The output of the two-layer bidirectional LSTM network is mapped to the target prediction space, which contains the predicted start and end time of systolic and diastolic blood pressure. According to the predicted start and end time, the specific values ​​of systolic and diastolic blood pressure are determined to realize the automatic generation and prediction of blood pressure.

[0067] More specifically, through the training and optimization of the deep learning model, the individual's systolic and diastolic blood pressure can be predicted more accurately, improving the accuracy of blood pressure measurement. The model can automatically process the input blood pressure measurement data and complete the prediction and generation of blood pressure without human intervention, which improves work efficiency. The model is trained by collecting blood pressure measurement information from multiple people, has strong generalization ability, and can be applied to blood pressure prediction for different populations. In addition, by adding time features and using a two-layer bidirectional LSTM network for processing, the model can better capture the long-term dependencies in the time series and improve the stability of the prediction.

[0068] The above-mentioned blood pressure measurement method obtains blood pressure measurement information and forms audio data. This step ensures the integrity and authenticity of the original data. Then, by preprocessing the audio data, noise and interference are effectively removed, the purity and availability of the data are improved, and a deep learning model is introduced as a blood pressure automatic generation model. The model collects blood pressure measurement information of multiple people as a sample set for training, and can learn rich blood pressure features, thereby realizing high-precision prediction and generation of blood pressure values. The preprocessed data is directly input into the blood pressure automatic generation model to generate blood pressure values ​​without manual intervention, realizing the intelligence and automation of blood pressure measurement, not only improving the measurement efficiency, but also reducing the errors caused by manual operation, making blood pressure measurement more convenient and accurate. In addition, because the deep learning model has strong learning ability and generalization ability, it can adapt to the blood pressure characteristics of different populations, including individual differences such as different ages, genders, and body shapes, and has wider applicability and higher accuracy in practical applications. In addition, the method of the present invention is based on existing electronic sphygmomanometer technology and deep learning technology, without the need for additional hardware equipment investment, and can be realized by simply upgrading or developing the software, which reduces costs and makes the method easier to promote and apply in the fields of medical institutions and family health monitoring.

[0069] Figure 4 is a schematic block diagram of a blood pressure measurement device 300 provided in an embodiment of the present invention. Figure 4 As shown, corresponding to the above blood pressure measurement method, the present invention also provides a blood pressure measurement device 300. The blood pressure measurement device 300 includes a unit for executing the above blood pressure measurement method, and the device can be configured in a server. Figure 4 , the blood pressure measurement device 300 includes an acquisition forming unit 301, a pre-processing unit 302, an automatic generation unit 303 and an output unit 304;

[0070] An acquisition forming unit 301 is used to acquire blood pressure measurement information to form audio data;

[0071] The preprocessing unit 302 is used to preprocess the audio data to obtain a preprocessing result;

[0072] The automatic generation unit 303 is used to input the preprocessing result into the blood pressure automatic generation model to generate the blood pressure to obtain the generation result;

[0073] The output unit 304 is used to output the generated result.

[0074] In one embodiment, in the acquisition forming unit 301, inflation and deflation are controlled by using a microcontroller to read the pressure data of the voltage signal of the pressure sensor converted through ADC. When deflation starts, the sound sensor connected to the stethoscope starts recording the sound, and the recording ends when deflation ends to obtain blood pressure measurement information, which is then stored in the microcontroller to form audio data.

[0075] In one embodiment, the preprocessing unit 302 decodes the audio data to obtain time-related data, then performs Fourier transform on each frame of the data to obtain a frequency distribution, and finally combines the frequency distribution according to time to obtain a spectrum diagram, i.e., the preprocessing result.

[0076] In one embodiment, the blood pressure measurement device 300 further includes a model generation unit, which is used to train a deep learning model by collecting blood pressure measurement information of multiple people as a sample set.

[0077] In one embodiment, the above-mentioned model generation unit includes:

[0078] A sample set generation subunit, used to collect blood pressure measurement information of multiple persons and mark the blood pressure measurement information to obtain a sample set;

[0079] A model building subunit, used to build a deep learning model;

[0080] The parameter adjustment subunit is used to adjust the parameters of the deep learning model;

[0081] The training subunit is used to train the deep learning model after parameter adjustment using the sample set to obtain a preliminarily trained model;

[0082] The optimization subunit is used to evaluate and optimize the performance of the preliminary training model to obtain an automatic blood pressure generation model.

[0083] In one embodiment, the output unit 304 is used to display the generated results in a visual manner.

[0084] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned blood pressure measurement device 300 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and brevity of description, it will not be repeated here.

[0085] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it implements the functions or steps on the server side of a blood pressure measurement method.

[0086] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0087] Acquire blood pressure measurement information to generate audio data; preprocess the audio data to obtain a preprocessing result; input the preprocessing result into a blood pressure automatic generation model to generate blood pressure to obtain a generation result; output the generation result; wherein the blood pressure automatic generation model is obtained by collecting blood pressure measurement information of multiple people as a sample set to train a deep learning model.

[0088] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0089] Acquire blood pressure measurement information to generate audio data; preprocess the audio data to obtain a preprocessing result; input the preprocessing result into a blood pressure automatic generation model to generate blood pressure to obtain a generation result; output the generation result; wherein the blood pressure automatic generation model is obtained by collecting blood pressure measurement information of multiple people as a sample set to train a deep learning model.

[0090] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0091] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0092] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0093] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A blood pressure measurement method, characterized in that: include: Obtaining blood pressure measurement information to generate audio data; Preprocessing the audio data to obtain a preprocessing result; Inputting the preprocessing result into the blood pressure automatic generation model to generate the blood pressure, so as to obtain the generation result; Output generation results; Among them, the automatic blood pressure generation model is obtained by collecting blood pressure measurement information of multiple people as a sample set to train the deep learning model.

2. The blood pressure measurement method according to claim 1, characterized in that: The obtaining of blood pressure measurement information to generate audio data includes: A microcontroller is used to read the pressure data of the voltage signal of the pressure sensor converted by ADC to control inflation and deflation. When deflation starts, the sound sensor connected to the stethoscope starts recording sound and stops recording when deflation ends to obtain blood pressure measurement information, which is then stored in the microcontroller as audio data.

3. The blood pressure measurement method according to claim 1, characterized in that: The preprocessing of the audio data to obtain a preprocessing result includes: The audio data is decoded to obtain time-related data, and each frame of the data is Fourier transformed to obtain a frequency distribution. Finally, the frequency distribution is combined according to time to obtain a spectrum diagram, which is the preprocessing result.

4. The blood pressure measurement method according to claim 1, characterized in that: The blood pressure automatic generation model is obtained by collecting blood pressure measurement information of multiple people as a sample set to train a deep learning model, including: Collecting blood pressure measurement information of multiple people and marking the blood pressure measurement information to obtain a sample set; Build deep learning models; Adjust parameters of deep learning models; Use the sample set to train the deep learning model after parameter adjustment to obtain a preliminary trained model; The performance of the preliminary training model was evaluated and optimized to obtain an automatic blood pressure generation model.

5. The blood pressure measurement method according to claim 1, characterized in that: The output generation result includes: Visualize the generated results.

6. A blood pressure measuring device, characterized in that: include: An acquisition forming unit, used for acquiring blood pressure measurement information to form audio data; A preprocessing unit, used for preprocessing the audio data to obtain a preprocessing result; An automatic generation unit, used for inputting the preprocessing result into the blood pressure automatic generation model to generate the blood pressure, so as to obtain a generation result; An output unit, used for outputting the generated results; Among them, the automatic blood pressure generation model is obtained by collecting blood pressure measurement information of multiple people as a sample set to train the deep learning model.

7. The blood pressure measuring device according to claim 6, characterized in that: In the acquisition unit, a microcontroller is used to read the pressure data of the voltage signal of the pressure sensor converted by ADC to control inflation and deflation. When deflation starts, the sound sensor connected to the stethoscope starts recording sound, and stops recording when deflation ends to obtain blood pressure measurement information, which is then stored in the microcontroller to form audio data.

8. The blood pressure measuring device according to claim 6, characterized in that: In the preprocessing unit, the audio data is decoded to obtain time-related data, and each frame of the data is Fourier transformed to obtain a frequency distribution. Finally, the frequency distribution is combined according to time to obtain a spectrum diagram, that is, the preprocessing result.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the blood pressure measurement method according to any one of claims 1 to 5 are implemented.

10. A storage medium, wherein the computer-readable storage medium stores a computer program, characterized in that: When the computer program is executed by a processor, the steps of the blood pressure measurement method according to any one of claims 1 to 5 are implemented.

Images