CN116369882A

CN116369882A - Blood pressure measurement method and device, blood pressure measurement equipment and electronic equipment

Info

Publication number: CN116369882A
Application number: CN202310074845.4A
Authority: CN
Inventors: 王付州; 江世盛
Original assignee: Hanwang Technology Co Ltd
Current assignee: Hanwang Technology Co Ltd
Priority date: 2023-01-13
Filing date: 2023-01-13
Publication date: 2023-07-04

Abstract

The application discloses a blood pressure measurement method, and belongs to the technical field of electronic equipment. The method comprises the following steps: acquiring a pressure signal and a piezoelectric signal, which are acquired by a cuff worn by an arm of a user and generated by brachial artery pulsation, wherein the pressure signal is a pressure signal in an air bag of the cuff, and the piezoelectric signal is acquired by a piezoelectric device arranged on one side of the cuff, which is attached to the arm of the user; performing signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal characteristics corresponding to each brachial artery pulsation; inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence; and obtaining a blood pressure measurement result of the user according to the blood pressure value category prediction result and the pressure signal. According to the method, the cuff structure is improved, and the auscultation link is improved to be based on the characteristics of the brachial artery pulse signals, so that the blood pressure value is predicted through the neural network, and the accuracy of a blood pressure measurement result is effectively improved.

Description

Blood pressure measurement method and device, blood pressure measurement equipment and electronic equipment

Technical Field

The present disclosure relates to the technical field of electronic devices, and in particular, to a blood pressure measurement method, a blood pressure measurement device, an electronic device, and a computer readable storage medium.

Background

Measurement of blood pressure is important for monitoring the health of the human body. In the prior art, a common noninvasive blood pressure measurement method comprises the following steps: korotkoff's sound method and electronic blood pressure meter. The oscillometric principle adopted by the electronic sphygmomanometer is that a blood pressure value is obtained according to the statistical relationship between the envelope curve of the shock wave and the diastolic and systolic pressures. The statistical relationship determines that the measurement method only has the accuracy of the blood pressure measurement of the theoretical group, and can not ensure the accuracy of the blood pressure measurement of a single tested person. The Korotkoff sound method has higher accuracy, but the method is easily influenced by surrounding environment sounds when the blood pressure measurement is actually carried out, so that the judgment error of a high-pressure value or a low-pressure value is caused.

It can be seen that there is a continuing need for improvements in the blood pressure measurement methods of the prior art.

Disclosure of Invention

The embodiment of the application provides a blood pressure measuring method and device, and blood pressure measuring equipment is beneficial to improving blood pressure measuring accuracy.

In a first aspect, an embodiment of the present application provides a blood pressure measurement method, including:

Acquiring a pressure signal and a piezoelectric signal, which are acquired by a cuff worn by an arm of a user and generated by brachial artery pulsation, wherein the pressure signal is a pressure signal in an air bag of the cuff, and the piezoelectric signal is acquired by a piezoelectric device arranged on one side of the cuff, which is attached to the arm of the user;

performing signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal characteristics corresponding to each brachial artery pulsation;

inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence;

and obtaining a blood pressure measurement result of the user according to the blood pressure value category prediction result and the pressure signal.

Optionally, the signal features include: the pressure wave difference, the first piezoelectric signal characteristic, the second piezoelectric signal characteristic and the acquisition time characteristic corresponding to the brachial artery pulsation, the signal processing is performed on the pressure signal and the piezoelectric signal, and a sequence of signal characteristics corresponding to each brachial artery pulsation is obtained, and the method comprises the following steps:

performing band-pass filtering on the pressure signal to obtain an oscillating wave signal in a preset frequency range;

determining the acquisition time of the pressure signal corresponding to each peak value of the shock wave signal;

Determining the acquisition time characteristics corresponding to the corresponding brachial artery pulse according to the acquisition time;

determining a pressure wave difference corresponding to the acquisition time according to the change amplitude of the pressure signal corresponding to the acquisition time in the oscillating wave signal;

determining a first piezoelectric signal characteristic corresponding to the corresponding acquisition time according to a first frequency band piezoelectric signal obtained after the piezoelectric signal is subjected to band-pass filtering;

determining a second piezoelectric signal characteristic corresponding to the corresponding acquisition time according to a second frequency band piezoelectric signal obtained after the piezoelectric signal is subjected to segmented bandpass filtering, wherein the frequency of the first frequency band piezoelectric signal is lower than that of the second frequency band piezoelectric signal;

and generating a sequence of the signal features according to the sequence of the acquisition time by using the acquisition time features, the pressure wave difference, the first piezoelectric signal features and the second piezoelectric signal features corresponding to the acquisition time.

Optionally, the blood pressure prediction model includes: the bidirectional long-short-time memory network and the full-connection layer, the sequence is input into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence, and the method comprises the following steps:

Inputting the sequence into the bidirectional long-short-time memory network, and carrying out feature coding on each signal feature in the sequence through the bidirectional long-short-time memory network to obtain an output vector corresponding to each signal feature;

respectively carrying out classification mapping on each output vector through the full connection layer to obtain a classification result of the blood pressure value in the change process from the high pressure value to the low pressure value corresponding to the signal characteristic;

and obtaining a blood pressure value category prediction result corresponding to the sequence according to the classification result corresponding to each signal characteristic.

Optionally, the obtaining the blood pressure measurement result of the user according to the blood pressure value category prediction result and the pressure signal includes:

according to the corresponding relation between the signal characteristics and the blood pressure value category prediction result in the sequence, determining the signal characteristics corresponding to a high pressure value as a first signal characteristic, and determining the signal characteristics corresponding to a low pressure value as a second signal characteristic;

obtaining a high-pressure measurement result of the user according to the pressure signal generated by the brachial artery pulsation corresponding to the first signal characteristic; and obtaining a low pressure measurement result of the user according to the pressure signal generated by the brachial artery pulsation corresponding to the second signal characteristic.

Optionally, the blood pressure prediction model is constructed based on a long-short-time memory network, and the blood pressure prediction model is trained by the following method:

obtaining a plurality of training samples, wherein sample data of each training sample is as follows: the signal characteristic sequence obtained after processing the pressure signal and the piezoelectric signal acquired based on single blood pressure measurement is as follows: marking a sequence of real values corresponding to the corresponding relation between the signal characteristics and a target blood pressure value, wherein the target blood pressure value is a blood pressure value corresponding to the change process from a high pressure value to a low pressure value;

for each training sample, sequentially inputting sample data of the training sample into the blood pressure prediction model to respectively obtain a sequence of predicted values of the corresponding relation between each signal characteristic in the sample data and the target blood pressure value;

calculating the loss of the blood pressure prediction model according to the sequence of the corresponding relation predicted values obtained for each training sample and the corresponding sample label;

and carrying out iterative training on the blood pressure prediction model by optimizing the loss.

Optionally, the piezoelectric device includes: and the piezoelectric sensing device is arranged integrally with the cuff and arranged on the inner side of the cuff, and is placed at a position close to the brachial artery of the tested user when the blood pressure of the user is measured.

Optionally, the piezoelectric device includes at least two piezoelectric sensing devices, and the piezoelectric signal is a superimposed piezoelectric signal of the at least two piezoelectric sensing devices.

In a second aspect, embodiments of the present application provide a blood pressure measurement device, including:

the device comprises a signal acquisition module, a control module and a control module, wherein the signal acquisition module is used for acquiring a pressure signal and a piezoelectric signal, wherein the pressure signal is acquired by a cuff worn by a user arm and generated by brachial artery pulsation, the pressure signal is a pressure signal in an air bag of the cuff, and the piezoelectric signal is acquired by a piezoelectric device arranged on one side of the cuff attached to the user arm;

the characteristic extraction module is used for carrying out signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal characteristics corresponding to each brachial artery pulsation;

the prediction module is used for inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence;

and the measurement result acquisition module is used for acquiring the blood pressure measurement result of the user according to the blood pressure value type prediction result and the pressure signal.

Optionally, the signal features include: the device comprises a pressure wave difference, a first piezoelectric signal characteristic, a second piezoelectric signal characteristic and an acquisition time characteristic corresponding to brachial artery pulsation, wherein the characteristic extraction module is further used for:

Optionally, the blood pressure prediction model includes: the prediction module is further used for:

Optionally, the measurement result obtaining module is further configured to:

In a third aspect, embodiments of the present application also disclose a blood pressure measurement device, including a cuff, the cuff including: an air bag, a pressure detection device, a piezoelectric device, and a signal output device, wherein,

the pressure detection device is configured to collect pressure signals within the balloon;

the piezoelectric device is arranged on one side, which is attached to the arm of the user, of the cuff and is configured to collect piezoelectric signals generated by brachial artery pulsation;

the signal output device is used for outputting the pressure signal and the piezoelectric signal.

In a fourth aspect, embodiments of the present application further disclose a blood pressure measurement device, including: a signal processing device, a cuff, and an air bag, a pressure detecting device and a piezoelectric device which are arranged on the cuff, wherein,

The signal processing device is used for acquiring a pressure signal and a piezoelectric signal, which are acquired by a cuff worn by an arm of a user and generated by brachial artery pulsation, wherein the pressure signal is a pressure signal in an air bag of the cuff, and the piezoelectric signal is a piezoelectric signal acquired by a piezoelectric device arranged on one side of the cuff attached to the arm of the user; performing signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal characteristics corresponding to each brachial artery pulsation; then, inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence; and obtaining a blood pressure measurement result of the user according to the blood pressure value category prediction result and the pressure signal.

In a fifth aspect, the embodiments of the present application further disclose an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the blood pressure measurement method described in the embodiments of the present application when executing the computer program.

In a sixth aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the blood pressure measurement method disclosed in embodiments of the present application.

According to the blood pressure measurement method disclosed by the embodiment of the application, the pressure signal and the piezoelectric signal which are acquired by the cuff worn by the arm of the user and generated by the brachial artery pulsation are acquired, wherein the pressure signal is the pressure signal in the air bag of the cuff, and the piezoelectric signal is acquired by the piezoelectric device arranged on one side of the cuff attached to the arm of the user; performing signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal characteristics corresponding to each brachial artery pulsation; inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence; and obtaining a blood pressure measurement result of the user according to the blood pressure value category prediction result and the pressure signal. According to the blood pressure measurement method disclosed by the embodiment of the application, the auscultation step during blood pressure measurement is improved to the blood pressure value prediction through the neural network based on the brachial artery pulse signal characteristics, so that the accuracy of a blood pressure measurement result is effectively improved.

The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.

Drawings

For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

FIG. 1 is a flow chart of a blood pressure measurement method of an embodiment of the present application;

FIG. 2 is a schematic view of a structure of the blood pressure measuring apparatus disclosed in the embodiment of the present application;

FIG. 3 is another schematic view of the blood pressure measuring device disclosed in the embodiments of the present application;

FIG. 4 is a schematic diagram of waveforms of pressure signals collected in an embodiment of the present application;

FIG. 5 is a schematic diagram of waveforms of piezoelectric signals collected in an embodiment of the present application;

FIG. 6 is a schematic diagram of the oscillating wave and bandpass pressure wave obtained after the filtering process in the embodiment of the present application;

FIG. 7 is a schematic diagram of the working principle of the blood pressure prediction model adopted in the embodiment of the present application;

FIG. 8 is a schematic view of a blood pressure measuring device according to an embodiment of the present application;

FIG. 9 schematically illustrates a block diagram of an electronic device for performing a method according to the present application; and

fig. 10 schematically shows a memory unit for holding or carrying program code implementing the method according to the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

The embodiment of the application discloses a blood pressure measurement method, as shown in fig. 1, which comprises the following steps: steps 110 to 140.

Step 110, acquiring a pressure signal and a piezoelectric signal, which are acquired by a cuff worn by an arm of a user and generated by brachial artery pulsation, wherein the pressure signal is a pressure signal in an air bag of the cuff, and the piezoelectric signal is acquired by a piezoelectric device arranged on one side of the arm of the user, which is attached to the cuff.

The blood pressure measurement method disclosed in the embodiments of the present application is applied to a blood pressure measurement apparatus including a cuff of an inflatable bladder, and a pressure detection device and a piezoelectric device need to be provided on the cuff. The following describes a specific embodiment for acquiring a pressure signal and a piezoelectric signal generated by a brachial artery pulsation acquired by a cuff worn by an arm of a user, with reference to schematic structural diagrams of the blood pressure measuring apparatus shown in fig. 2 and 3, respectively.

As shown in fig. 2, the blood pressure measuring apparatus includes: a cuff 200 and a signal output device 210, wherein the cuff 200 further comprises: an air bag 201, a pressure detection device 202, and a piezoelectric device 203. The pressure detecting means 202 and the piezoelectric means 203 are respectively communicatively connected to the signal output means 210.

Wherein the pressure detection device 202 is configured to collect pressure signals within the balloon. The pressure detection device 202 is provided in the airbag 201. In some embodiments of the present application, the pressure detection device 202 may be implemented based on a pressure sensing device. In the process of measuring blood pressure, first, the balloon 201 is inflated, the cuff 200 is pressurized, thereby blocking the blood flow of the upper arm artery vessel, and then the gas in the balloon 201 is slowly released at a speed of 2-4mmHg/s, and in the process of releasing the gas by the balloon 201, the pressure detection device 202 detects a corresponding pressure signal generated to the gas in the balloon due to the brachial artery pulsation.

The piezoelectric device 203 is disposed on a side of the cuff that is attached to the arm of the user, and is configured to collect piezoelectric signals generated by brachial artery pulsation. In some embodiments of the present application, the piezoelectric device 203 may be implemented based on a piezoelectric sensor device. As described above, in the process of measuring blood pressure, the balloon 201 is inflated first, the cuff 200 is pressurized, and thus the blood flow of the upper arm artery vessel is blocked, and then the gas in the balloon 201 is released slowly, and the piezoelectric device 203 detects the corresponding piezoelectric signal generated by the pressure of the upper arm to the cuff 200 generated by the brachial artery pulsation during the process of releasing the gas by the balloon 201.

The signal output device 210 is configured to output the pressure signal and the piezoelectric signal.

In some embodiments of the present application, the signal output device 210 may be implemented as a near field communication module such as a bluetooth module, so as to output the pressure signal detected by the pressure detecting device 202 and the piezoelectric signal detected by the piezoelectric device 203 to a matched signal processing device through a non-contact communication connection manner.

In other embodiments of the present application, the signal output device 210 may also be a signal output interface, so that the pressure signal detected by the pressure detecting device 202 and the piezoelectric signal detected by the piezoelectric device 203 are output to a signal processing device connected to the blood pressure measuring apparatus through a non-contact communication connection manner, so as to perform subsequent signal processing, and obtain a blood pressure value of the user. The signal processing device may be an intelligent terminal with signal processing capability.

In other embodiments of the present application, as shown in fig. 3, the blood pressure measuring apparatus includes: a cuff 300, a signal processing device 310, and a balloon 301, a pressure detecting device 302, and a piezoelectric device 303 provided in the cuff 300. The pressure detecting means 302 and the piezoelectric means 303 are respectively communicatively connected to the signal processing means 310.

Wherein the pressure detection device 302 is configured to collect pressure signals within the balloon 301;

the piezoelectric device 303 is disposed on the side of the cuff 300 that fits the arm of the user, and is configured to collect piezoelectric signals generated by brachial artery pulsation;

the signal processing device 310 is configured to obtain a pressure signal and a piezoelectric signal, which are acquired by a cuff 300 worn by an arm of a user and generated by a brachial artery pulsation, where the pressure signal is a pressure signal in an air bag of the cuff, and the piezoelectric signal is a piezoelectric signal acquired by a piezoelectric device disposed on one side of the cuff attached to the arm of the user; performing signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal characteristics corresponding to each brachial artery pulsation; then, inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence; and obtaining a blood pressure measurement result of the user according to the blood pressure value category prediction result and the pressure signal.

Inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence; and obtaining a specific embodiment of the blood pressure measurement result of the user according to the blood pressure value category prediction result and the pressure signal, which is described below and not repeated herein.

The structure and the working principle of the air bag 301 are the same as those of the air bag 201 in fig. 2, and will not be described here again.

The location, implementation, and principle of collecting the pressure signal of the pressure detecting device 302 are the same as those of the pressure detecting device 202, and will not be described herein.

The arrangement position, the specific implementation manner, and the principle of collecting the piezoelectric signal of the piezoelectric device 303 are the same as those of the piezoelectric device 203, and will not be described herein.

The blood pressure measuring device described in fig. 3 differs from the blood pressure measuring device shown in fig. 2 in that the blood pressure measuring device shown in fig. 3 is itself provided with signal processing means 310, which can perform signal processing on the pressure signal detected by the pressure detecting means 302 and the piezoelectric signal detected by the piezoelectric means 303 to obtain the blood pressure value of the user.

In the blood pressure measuring apparatus shown in fig. 2 and 3, the piezoelectric device 203 includes: and the piezoelectric sensing device is arranged integrally with the cuff and arranged on the inner side of the cuff, and is placed at a position close to the brachial artery of the upper arm of the tested user when the blood pressure of the user is measured. Wherein, the inner side of the cuff means the side close to the skin of the arm of the user when blood pressure is measured. The piezoelectric sensing device may be a piezoelectric patch. The piezoelectric sensor device can be fixed on the cuff in a pasting or sewing mode.

Wherein the piezoelectric device 203 includes at least two piezoelectric sensing devices, and the piezoelectric signal is a superimposed piezoelectric signal of the at least two piezoelectric sensing devices. For example, the piezoelectric signal may be the sum of the magnitudes of the piezoelectric signals acquired by the two piezoelectric sensing devices at the same time.

Adopt the structure of two piezoelectricity sensing device to with two piezoelectricity signal stack that piezoelectricity sensing device gathered, as the piezoelectricity signal that finally is used for discernment, not only can promote piezoelectricity signal's acquisition ability, simultaneously, through setting up two piezoelectricity sensing device in the position of being close to the user's arm brachial artery of being surveyed, make when measuring user's blood pressure, two piezoelectricity sensing device all can detect the signal of brachial artery, can promote the inclusion degree to the user wearing cuff position, make blood pressure measuring equipment more easy to use.

During the measurement of blood pressure, the brachial artery contracts when the heart returns, and contracts to the narrowest as the blood in the heart increases, and expands to the widest as the blood in the blood vessel increases when the heart pumps out the blood, and the widest and narrowest blood pressure values are the high and low pressure of the person. In the process of measuring the blood pressure of a user by adopting the blood pressure measuring equipment disclosed by the embodiment of the application, the cuff is bound on the outer side of the brachial artery, when the air bag is inflated, the pressure in the air bag is gradually increased, when the pressure is larger than a certain pressure value, the brachial artery is closed due to the pressure, then the air bag is deflated, the pressure in the air bag is gradually reduced, at the moment, the brachial artery is opened, blood flows through the brachial artery at the binding position of the cuff, and the pressure is generated on the air bag and the cuff. According to the blood pressure measuring device disclosed by the embodiment of the application, the pressure detection device arranged in the air bag of the cuff is used for detecting the change of the pressure in the air bag, so that a pressure signal is obtained, and the pressure of the brachial artery to the cuff and the air bag is detected through the piezoelectric device, so that a piezoelectric signal is obtained.

In the process of measuring blood pressure by adopting the blood pressure measuring device disclosed in the embodiment of the application, a pressure signal detected by the blood pressure measuring device through the pressure detecting device is shown in fig. 4. The pressure signal is an oscillating wave, and the curve in fig. 4 reflects the trend of the baseline of the oscillating wave, i.e. the trend of the pressure value.

In the process of measuring blood pressure by adopting the blood pressure measuring device disclosed in the embodiment of the application, a piezoelectric signal detected by the blood pressure measuring device through the piezoelectric device is shown in fig. 5. As can be seen from fig. 5, the piezoelectric signal is a pulse signal whose peak value changes, and the pulse generation period corresponds to the brachial artery pulsation and the peak value of the pulse changes with the measurement time.

In the embodiment of the application, the accurate blood pressure value is obtained by comprehensively analyzing the pressure signal and the piezoelectric signal.

And 120, performing signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal characteristics corresponding to each brachial artery pulse.

From the above analysis, it is known that the changes in the pressure signal and the piezoelectric signal are signals reflecting the frequency and amplitude of the brachial artery pulsation, and then the pressure signal and the piezoelectric signal are further subjected to signal processing to obtain a sequence of signal characteristics corresponding to each brachial artery pulsation.

In some embodiments of the present application, the signal features include: the pressure wave difference, the first piezoelectric signal characteristic, the second piezoelectric signal characteristic and the acquisition time characteristic corresponding to the brachial artery pulsation, the signal processing is performed on the pressure signal and the piezoelectric signal, and a sequence of signal characteristics corresponding to each brachial artery pulsation is obtained, and the method comprises the following steps: substep 1201 to substep 1207.

Step 1201, performing band-pass filtering on the pressure signal to obtain an oscillating wave signal in a preset frequency range.

The preset frequency range is determined according to the heartbeat range statistical data of the person. For example, the human heart beat range is 40-200 beats/min, the preset frequency range may be set to [0.67,3.3].

The band-pass filter filters out frequency signals other than the band-pass frequency in the original signal, thereby changing the original signal. In the embodiment of the present application, a band-pass filter with a frequency range of [0.67,3.3] may be used to band-pass filter the pressure signal detected by the pressure detection device, and filter out the interference signal outside the frequency range, where the obtained oscillating wave signal is shown in the waveform of the top line in fig. 6. Wherein, the band-pass filter can adopt a Butterworth band-pass filter.

The shock wave signal is a function of the acquisition time, the independent variable is the acquisition time, and the dependent variable is the pressure change value.

The specific implementation manner of performing band-pass filtering on the pressure signal to obtain the oscillating wave signal in the preset frequency range can refer to the prior art, and will not be described in detail in the embodiment of the present application.

Sub-step 1202, determining an acquisition time of the pressure signal corresponding to each peak of the shock wave signal.

Sub-step 1203, determining said acquisition time characteristics corresponding to the respective brachial artery beats from said acquisition times.

And then, acquiring the acquisition time of the pressure signal corresponding to each peak value of the shock wave signal. According to the detection principle of the pressure signal, each period of the oscillating wave signal corresponds to one brachial artery pulse, and the time difference between adjacent peaks of the oscillating wave signal is the period of the brachial artery pulse. Thus, the acquisition time of the pressure signal for each peak can be used as a feature to identify one brachial artery beat. In the embodiment of the present application, the collection time may be used as the collection time feature corresponding to the corresponding brachial artery pulse; the acquisition time sequence number corresponding to each brachial artery pulse can be determined according to the acquisition time, and the time sequence number is used as the acquisition time characteristic corresponding to the corresponding brachial artery pulse.

Next, other features corresponding to each brachial artery beat are separately determined.

Sub-step 1204, determining a pressure wave difference corresponding to the acquisition time according to a change amplitude of the pressure signal corresponding to the acquisition time in the shock wave signal.

In embodiments of the present application, the pressure signal extracted from each brachial artery beat corresponds to a pressure wave difference of the oscillatory wave signal. The pressure wave differential may reflect the magnitude of the pressure change produced by one brachial artery pulse.

Further, determining a pressure wave difference corresponding to the acquisition time according to a change amplitude of a pressure signal corresponding to the acquisition time in the oscillating wave signal includes: and determining a pressure wave difference corresponding to the acquisition time according to a signal maximum value and a signal minimum value corresponding to the acquisition time in the oscillating wave signal. For example, for each acquisition time determined in the foregoing step, according to the oscillation wave function, a signal maximum value and a signal minimum value corresponding to the oscillation wave signal in a brachial artery pulse period corresponding to each acquisition time, that is, a peak value and a trough value in the oscillation wave signal period corresponding to each acquisition time, may be determined, and then, a difference obtained by subtracting the signal minimum value from the signal maximum value is taken as a pressure wave difference corresponding to the acquisition time.

Sub-step 1205, determining a first piezoelectric signal characteristic corresponding to the corresponding acquisition time according to a first frequency band piezoelectric signal obtained by performing band-pass filtering processing on the piezoelectric signal.

Wherein the piezoelectric signal (e.g., a bimorph sensor signal) refers to a superimposed signal of the original piezoelectric signal acquired from the bimorph. The piezoelectric bandpass can better reflect the characteristics of high voltage values. Thus, in some embodiments of the present application, a first piezoelectric signal characteristic corresponding to a brachial artery beat is determined from a first frequency band piezoelectric signal obtained by bandpass filtering the piezoelectric signal.

In some embodiments of the present application, determining, according to a first frequency band piezoelectric signal obtained by performing band-pass filtering processing on the piezoelectric signal, a first piezoelectric signal feature corresponding to the corresponding acquisition time includes: and carrying out band-pass filtering on the piezoelectric signals based on a first preset frequency bandwidth to obtain first frequency band piezoelectric signals, and then determining first piezoelectric signal characteristics corresponding to the corresponding acquisition time according to the piezoelectric signal intensity of the first frequency band piezoelectric signals and the piezoelectric signal intensity corresponding to each acquisition time.

The first preset frequency bandwidth is selected according to the characteristics of the high-low voltage signals. The piezoelectric signal of frequency 20,40 has a stronger expressive power on the characteristics of the piezoelectric signal generated when the arterial vessel expands, and therefore, the bandwidth of the band-pass filter, i.e., the first preset frequency bandwidth, can be set to be 20, 40. Wherein, the band-pass filter can adopt a Butterworth band-pass filter.

After the piezoelectric signal is subjected to band-pass filtering through a band-pass filter, a first-frequency band piezoelectric signal shown in the waveform diagram of the lowest row in fig. 6 is obtained. As shown in fig. 6, the first-band piezoelectric signal has a piezoelectric signal intensity distribution corresponding to the brachial artery fluctuation period. Next, a first piezoelectric signal characteristic corresponding to each acquisition time may be determined according to the piezoelectric signal intensity of the first frequency band piezoelectric signal corresponding to each acquisition time determined in the previous step.

In some embodiments of the present application, determining, according to the piezoelectric signal intensities of the first frequency band piezoelectric signal and the respective acquisition times, a first piezoelectric signal characteristic corresponding to the respective acquisition times includes: for each acquisition time, taking the average value of the piezoelectric signal intensities acquired at a preset number of acquisition time points in a time period corresponding to the acquisition time of the first frequency band piezoelectric signal as a first piezoelectric signal characteristic corresponding to the acquisition time; or, for each acquisition time, taking the root mean square value of the intensity of the piezoelectric signal acquired at a preset number of acquisition time points in a time period corresponding to the acquisition time of the first frequency band piezoelectric signal as a first piezoelectric signal characteristic corresponding to the acquisition time.

The preset number of collection time points may be a plurality of time points, where the collection time corresponds to a preset time interval in a brachial artery pulse period.

Sub-step 1206, determining a second piezoelectric signal characteristic corresponding to the corresponding acquisition time according to a second frequency band piezoelectric signal obtained by performing segmented bandpass filtering processing on the piezoelectric signal, wherein the frequency of the first frequency band piezoelectric signal is lower than that of the second frequency band piezoelectric signal.

The piezoelectric segmented bandpass may better reflect the low-voltage value, so in some embodiments of the present application, the second piezoelectric signal characteristic corresponding to the brachial artery pulsation is determined according to the second frequency band piezoelectric signal obtained after the segmented bandpass filtering processing is performed on the piezoelectric signal.

In some embodiments of the present application, determining, according to a second frequency band piezoelectric signal obtained by performing a segmented bandpass filtering process on the piezoelectric signal, a second piezoelectric signal feature corresponding to the corresponding acquisition time includes: and carrying out segmented band-pass filtering on the piezoelectric signals based on a second preset frequency bandwidth to obtain second frequency band piezoelectric signals, and then determining second piezoelectric signal characteristics corresponding to the corresponding acquisition time according to the intensity of the piezoelectric signals corresponding to the acquisition time of the second frequency band piezoelectric signals.

The second preset frequency bandwidth may be, for example: the segmented bandpass bandwidths of [40,45], [55,95], [105,145], [155,195] to filter power frequency interference.

By observing the piezoelectric signals, the inventor finds that the piezoelectric signals with the frequencies [20,40] have stronger expressive power on the characteristics of the piezoelectric signals generated during arterial vasodilation, and the piezoelectric signals with the frequencies [40,200] have stronger expressive power on the characteristics of the piezoelectric signals generated during arterial vasoconstriction, so that the first-frequency-band piezoelectric signals and the second-frequency-band piezoelectric signals respectively obtained by carrying out the band-pass filtering processing and the sectional band-pass filtering processing on the piezoelectric signals can effectively filter interference, and the piezoelectric signals for expressing the pulse characteristics of the brachial artery can be reserved.

Sub-step 1207, generating a sequence of the signal features according to the sequence of the acquisition time, the acquisition time feature, the pressure wave difference, the first piezoelectric signal feature, and the second piezoelectric signal feature corresponding to each acquisition time.

After the acquisition time characteristics, the pressure wave difference, the first piezoelectric signal characteristics and the second piezoelectric signal characteristics corresponding to each acquisition time are acquired, the characteristics are arranged from front to back according to the sequence of the acquisition time, and then the sequence of the signal characteristics can be generated. For example, for a certain acquisition time, the acquisition time feature, the pressure wave difference, the first piezoelectric signal feature, and the second piezoelectric signal feature corresponding to the acquisition time may be used together as a four-dimensional signal feature corresponding to the acquisition time; and then, according to the sequence of the acquisition time, arranging one signal characteristic corresponding to the N acquisition time in sequence to obtain a sequence of signal characteristics with the length of N multiplied by 4, wherein N is an integer greater than 1.

And 130, inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence.

The sequence of the signal characteristics obtained in the previous step is a time sequence characteristic corresponding to the brachial artery pulse signal, and then the sequence is input into a blood pressure prediction model trained in advance based on the time sequence model so as to obtain a blood pressure value type prediction result corresponding to the sequence output by the blood pressure prediction model.

In some embodiments of the present application, the blood pressure prediction model comprises: the bidirectional long-short-time memory network and the full-connection layer, the sequence is input into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence, and the method comprises the following steps: inputting the sequence into the bidirectional long-short-time memory network, and carrying out feature coding on each signal feature in the sequence through the bidirectional long-short-time memory network to obtain an output vector corresponding to each signal feature; respectively carrying out classification mapping on each output vector through the full connection layer to obtain a classification result of the blood pressure value in the change process from the high pressure value to the low pressure value corresponding to the signal characteristic; and obtaining a blood pressure value category prediction result corresponding to the sequence according to the classification result corresponding to each signal characteristic.

As shown in FIG. 7, the sequence of signal features is X ₀ ，X ₁ ，X ₂ ,…,X _n-1 ,X _n Wherein X is _i The device consists of acquisition time characteristics, pressure wave differences, first piezoelectric signal characteristics and second piezoelectric signal four-dimensional data. Each signal characteristic in the sequence is sequentially input into a blood pressure prediction model and communicatedAnd performing feature coding on each Xi through a bi-directional long-short-time memory network to obtain an output vector corresponding to each signal feature, then sending each output vector into a full-connection layer of the blood pressure prediction model to classify, and outputting a prediction result of whether a brachial artery pulse signal corresponding to each signal feature is between high and low pressure values (comprising a high pressure value point and a low pressure value point). For example, in the classification result output by the fully-connected layer, 1 indicates that the blood pressure is between high and low pressure values, 0 indicates that the blood pressure is not between high and low pressure values, and correspondingly, taking n=10 in the foregoing sequence as an example, if the classification result output by the blood pressure prediction model is "0011111000", the method indicates that: the high-voltage value is the brachial artery pulse signal corresponding to the 3 rd sequence position, and the low-voltage value is the brachial artery pulse signal corresponding to the 7 th sequence position.

By adopting the bidirectional long-short-time memory network to construct the blood pressure prediction model, the extracted signal characteristics can be fused with the information of the pressure signal and the piezoelectric signal acquired at each time point in the blood pressure measurement process, so that the prediction accuracy of the blood pressure prediction model is further improved.

In some embodiments of the present application, the blood pressure prediction model may also be constructed based on neural network models of other structures, which are not exemplified herein.

And 140, obtaining a blood pressure measurement result of the user according to the blood pressure value type prediction result and the pressure signal.

Next, a blood pressure measurement result of the user may be obtained according to the blood pressure value category prediction result and the pressure signal obtained in the foregoing step 110.

In some embodiments of the present application, the obtaining the blood pressure measurement result of the user according to the blood pressure value class prediction result and the pressure signal includes: according to the corresponding relation between the signal characteristics and the blood pressure value category prediction result in the sequence, determining the signal characteristics corresponding to a high pressure value as a first signal characteristic, and determining the signal characteristics corresponding to a low pressure value as a second signal characteristic; obtaining a high-pressure measurement result of the user according to the pressure signal generated by the brachial artery pulsation corresponding to the first signal characteristic; and obtaining a low pressure measurement result of the user according to the pressure signal generated by the brachial artery pulsation corresponding to the second signal characteristic.

Sequence X still characterized by input sequence of blood pressure prediction model ₀ ，X ₁ ，X ₂ ,…,X _n-1 ,X _n For example, wherein X _i The blood pressure prediction model comprises acquisition time characteristics, pressure wave differences, first piezoelectric signal characteristics and second piezoelectric signal four-dimensional data, and a blood pressure value type prediction result output by the blood pressure prediction model is assumed to be expressed as an output sequence: y is Y ₀ ，Y ₁ ，Y ₂ ,…,Y _n-1 ,Y _n Wherein Y is _i Representing signal characteristics X in an input sequence _i And a corresponding blood pressure value category prediction result. Y is Y _i Is used to represent the signal characteristic X in the input sequence _i Whether the signal characteristics between the high and low voltage values match. For example, Y _i The value of 1 is between the high voltage value and the low voltage value, Y _i A value of 0 indicates that the voltage is not between the high and low voltage values. Further, from the time sequence of the occurrence of the high and low pressure values at the time of blood pressure measurement, Y, which is the first value of 1, is found in the output sequence representing the predicted result of the blood pressure value category _i The signal features corresponding to the values correspond to high voltage values, and the last Y takes on a value of 1 _i The signal characteristics corresponding to the values correspond to low voltage values. Based on this, Y, the first value of which is 1, can be determined _i A signal characteristic corresponding to the value is taken as a first signal characteristic, and the last Y with the value of 1 is determined _i And the signal characteristic corresponding to the value is taken as a second signal characteristic.

Next, a high pressure measurement of the user may be obtained from the pressure signal generated by the corresponding brachial artery pulse in the first signal feature. For example, the pressure signal acquisition time t corresponding to the acquisition time characteristic in the first signal characteristic can be obtained ₁ The pressure signal acquisition time t is obtained from the pressure signal acquired in step 110 ₁ And obtaining a corresponding pressure signal value to obtain a high-pressure measurement result of the user. Similarly, the pressure signal corresponding to the acquisition time characteristic in the second signal characteristic can be obtainedAcquisition time t ₂ The pressure signal acquisition time t is obtained from the pressure signal acquired in step 110 ₂ And obtaining a low-pressure measurement result of the user according to the corresponding pressure signal value.

In order to make the scheme clearer, the training process of the blood pressure prediction model is further described below.

As described above, the blood pressure prediction model is constructed based on a long-short-term memory network, and the blood pressure prediction model is trained by the following method: obtaining a plurality of training samples, wherein sample data of each training sample is as follows: the signal characteristic sequence obtained after processing the pressure signal and the piezoelectric signal acquired based on single blood pressure measurement is as follows: marking a sequence of real values corresponding to the corresponding relation between the signal characteristics and a target blood pressure value, wherein the target blood pressure value is a blood pressure value corresponding to the change process from a high pressure value to a low pressure value; for each training sample, sequentially inputting sample data of the training sample into the blood pressure prediction model to respectively obtain a sequence of predicted values of the corresponding relation between each signal characteristic in the sample data and the target blood pressure value; calculating the loss of the blood pressure prediction model according to the sequence of the corresponding relation predicted values obtained for each training sample and the corresponding sample label; and carrying out iterative training on the blood pressure prediction model by optimizing the loss.

Each training sample for training the blood pressure prediction model may be a sequence of signal features obtained by processing a pressure signal and a piezoelectric signal acquired by using the blood pressure measurement device disclosed in the embodiment of the present application in a blood pressure measurement process of a user, and according to a pressure signal corresponding to each acquisition time in the sequence, a sample label is set for the sequence, the signal features corresponding to a blood pressure value between high and low pressure values are marked as "1", and the signal features corresponding to blood pressure values other than high and low pressure values are marked as "0", so as to obtain a sequence of true corresponding relation values between the signal features and a target blood pressure value.

For example, a training sample is processed into a sequence of signal features with a sequence length of 10, each sequence value is composed of 4-dimensional features, a high voltage value corresponds to the signal feature at the 3 rd sequence position, and a low voltage value corresponds to the signal feature at the 7 th sequence position, and then the sample label can be denoted as "0011111000".

In the process of training the blood pressure prediction model, after the sequence of signal features in each training sample is input into the blood pressure prediction model, the blood pressure prediction model outputs a sequence of corresponding relation predicted values of the corresponding signal features and the target blood pressure value. Further, for each training sample, according to the sequence of the predicted value of the corresponding relation of the corresponding training sample and the sample label of each training sample, that is, the sequence of the true value of the corresponding relation between the signal characteristic of the training sample and the target blood pressure value, model loss corresponding to the corresponding training sample can be obtained. Furthermore, according to model loss corresponding to all training samples, the loss of the blood pressure prediction model can be calculated. And then, adjusting model parameters of the blood pressure prediction model with the aim of optimizing the loss, and performing iterative training on the blood pressure prediction model until the loss of the blood pressure prediction model converges, thereby completing training. The blood pressure prediction model obtained at this time can be used in step 130 to predict the sequence of the signal characteristics obtained by processing the pressure signal and the piezoelectric signal acquired by the blood pressure signal disclosed in the embodiment of the present application, so as to obtain a blood pressure value category prediction result corresponding to the sequence.

According to the blood pressure measurement method disclosed by the embodiment of the application, the pressure signal and the piezoelectric signal which are acquired by the cuff worn by the arm of the user and generated by the brachial artery pulsation are acquired, wherein the pressure signal is the pressure signal in the air bag of the cuff, and the piezoelectric signal is acquired by the piezoelectric device arranged on one side of the cuff attached to the arm of the user; performing signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal characteristics corresponding to each brachial artery pulsation; inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence; and obtaining a blood pressure measurement result of the user according to the blood pressure value category prediction result and the pressure signal. According to the blood pressure measurement method disclosed by the embodiment of the application, the auscultation step in blood pressure measurement is improved to the step of predicting the blood pressure value through the neural network based on the characteristics of the brachial artery pulse signals, so that the accuracy of a blood pressure measurement result is effectively improved.

According to the blood pressure measurement method disclosed by the embodiment of the application, through improving blood pressure measurement equipment in the prior art, the piezoelectric device is arranged in the cuff to collect piezoelectric signals generated by beating of the brachial artery each time, the pressure signals collected by the pressure detection device arranged in the cuff air bag are combined, the collected piezoelectric signals and the pressure signals are subjected to characteristic extraction, and then, the extracted characteristics are predicted through the pre-trained neural network model, so that a blood pressure measurement result is obtained, the problem that when the Korotkoff sound method is adopted for blood pressure measurement in the prior art, auscultation links are easily influenced by surrounding environment sounds to cause high-pressure value or low-pressure value judgment error conditions is effectively avoided, and the accuracy of the blood pressure measurement result is effectively improved.

The results of clinical tests show that the average deviation of the systolic blood pressure measured by the blood pressure measuring method disclosed in the embodiment of the application is-0.9652 mmHg, the standard deviation is 2.5409mmHg, the average deviation of the diastolic blood pressure measured by the blood pressure measuring method is-0.3550 mmHg, and the standard deviation is 2.6816mmHg. It can be seen that the mean deviation and standard deviation of systolic and diastolic blood pressure meet the clinical test objectives and meet the YY0670-2008 requirements at high standards.

Furthermore, because the signal acquisition capacity of the double piezoelectric sheets is higher than the air bag pressure, the blood pressure measuring method disclosed by the embodiment of the application has higher accuracy compared with the traditional blood pressure measuring method.

The embodiment of the application also discloses a blood pressure measuring device, as shown in fig. 8, the device includes:

the signal acquisition module 810 is configured to acquire a pressure signal and a piezoelectric signal, which are acquired by a cuff worn by an arm of a user and generated by a brachial artery pulsation, wherein the pressure signal is a pressure signal in an air bag of the cuff, and the piezoelectric signal is a piezoelectric signal acquired by a piezoelectric device arranged on one side of the cuff attached to the arm of the user;

the feature extraction module 820 is configured to perform signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal features corresponding to each brachial artery pulse;

The prediction module 830 is configured to input the sequence to a pre-trained blood pressure prediction model, so as to obtain a blood pressure value class prediction result corresponding to the sequence;

and the measurement result obtaining module 840 is configured to obtain a blood pressure measurement result of the user according to the blood pressure value type prediction result and the pressure signal.

Optionally, the signal features include: the feature extraction module 820 is further configured to:

Optionally, the blood pressure prediction model includes: the prediction module 830 is further configured to:

Optionally, the measurement result obtaining module 840 is further configured to:

The embodiment of the module of the blood pressure measuring device disclosed in the embodiment of the present application is not described again, and reference may be made to the specific implementation of the corresponding steps in the embodiment of the method.

According to the blood pressure measuring device disclosed by the embodiment of the application, the pressure signal and the piezoelectric signal which are acquired by the cuff worn by the arm of the user and generated by the brachial artery pulsation are acquired, wherein the pressure signal is the pressure signal in the air bag of the cuff, and the piezoelectric signal is acquired by the piezoelectric device arranged on one side of the cuff attached to the arm of the user; performing signal processing on the pressure signal and the piezoelectric signal to obtain a sequence of signal characteristics corresponding to each brachial artery pulsation; inputting the sequence into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence; and obtaining a blood pressure measurement result of the user according to the blood pressure value category prediction result and the pressure signal. According to the blood pressure measuring device disclosed by the embodiment of the application, the auscultation process during blood pressure measurement is improved to be based on the characteristics of the brachial artery pulse signals, and the blood pressure value is predicted through the neural network, so that the accuracy of a blood pressure measuring result is effectively improved.

According to the blood pressure measuring device disclosed by the embodiment of the application, through improving blood pressure measuring equipment in the prior art, the piezoelectric device is arranged in the cuff to collect piezoelectric signals generated by beating of the brachial artery each time, the pressure signals collected by the pressure detecting device arranged in the cuff air bag are combined, and the collected piezoelectric signals and the pressure signals are subjected to feature extraction, and then, the extracted features are predicted through the neural network model trained in advance, so that blood pressure measuring results are obtained, the auscultation link is easily affected by surrounding environment sounds to cause the occurrence of high-pressure value or low-pressure value judgment error conditions when the blood pressure measuring is carried out by adopting the Korotkoff sound method in the prior art, and the accuracy of the blood pressure measuring results is effectively improved.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

The foregoing has described in detail a blood pressure measurement method and apparatus provided herein, and specific examples have been presented herein to illustrate the principles and embodiments of the present application, the above examples being provided only to assist in understanding the method and core idea of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

Various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in an electronic device according to embodiments of the present application may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present application may also be embodied as an apparatus or device program (e.g., computer program and computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present application may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

For example, fig. 9 shows an electronic device in which a method according to the present application may be implemented. The electronic device may be a PC, a mobile terminal, a personal digital assistant, a tablet computer, etc. The electronic device conventionally comprises a processor 910 and a memory 920 and a program code 930 stored on said memory 920 and executable on the processor 910, said processor 910 implementing the method described in the above embodiments when said program code 930 is executed. The memory 920 may be a computer program product or a computer-readable medium. The memory 920 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 920 has a memory 9201 of program code 930 of a computer program for performing any of the method steps described above. For example, the memory space 9201 for the program code 930 may include individual computer programs for implementing the various steps in the above methods, respectively. The program code 930 is computer readable code. These computer programs may be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. The computer program comprises computer readable code which, when run on an electronic device, causes the electronic device to perform a method according to the above-described embodiments.

The embodiment of the application also discloses a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the blood pressure measurement method according to the embodiment of the application.

Such a computer program product may be a computer readable storage medium, which may have memory segments, memory spaces, etc. arranged similarly to the memory 920 in the electronic device shown in fig. 9. The program code may be stored in the computer readable storage medium, for example, in a suitable form. The computer readable storage medium is typically a portable or fixed storage unit as described with reference to fig. 10. In general, the memory unit comprises computer readable code 930', which computer readable code 930' is code that is read by a processor, which code, when executed by the processor, implements the steps of the method described above.

Reference herein to "one embodiment," "an embodiment," or "one or more embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Furthermore, it is noted that the word examples "in one embodiment" herein do not necessarily all refer to the same embodiment.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims

1. A method of measuring blood pressure, comprising:

2. The method of claim 1, wherein the signal characteristics comprise: the pressure wave difference, the first piezoelectric signal characteristic, the second piezoelectric signal characteristic and the acquisition time characteristic corresponding to the brachial artery pulsation, the signal processing is performed on the pressure signal and the piezoelectric signal, and a sequence of signal characteristics corresponding to each brachial artery pulsation is obtained, and the method comprises the following steps:

3. The method of claim 1, wherein the blood pressure prediction model comprises: the bidirectional long-short-time memory network and the full-connection layer, the sequence is input into a pre-trained blood pressure prediction model to obtain a blood pressure value category prediction result corresponding to the sequence, and the method comprises the following steps:

4. The method according to claim 1, wherein said deriving a blood pressure measurement of said user from said blood pressure value class prediction result and said pressure signal comprises:

5. The method according to any one of claims 1 to 4, wherein the blood pressure prediction model is built based on a long-short-term memory network, the blood pressure prediction model being trained by:

6. The method according to any one of claims 1 to 4, wherein the piezoelectric device comprises: and the piezoelectric sensing device is arranged integrally with the cuff and arranged on the inner side of the cuff, and is placed at a position close to the brachial artery of the tested user when the blood pressure of the user is measured.

7. The method of claim 6, wherein the piezoelectric device comprises at least two of the piezoelectric sensing devices, the piezoelectric signal being a superimposed piezoelectric signal of the at least two of the piezoelectric sensing devices.

8. A blood pressure measurement device, comprising:

9. A blood pressure measurement device comprising a cuff, wherein the cuff comprises: an air bag, a pressure detection device, a piezoelectric device, and a signal output device, wherein,

10. A blood pressure measurement device, comprising: a signal processing device, a cuff, and an air bag, a pressure detecting device and a piezoelectric device which are arranged on the cuff, wherein,

11. An electronic device comprising a memory, a processor and program code stored on the memory and executable on the processor, characterized in that the processor implements the blood pressure measurement method of any one of claims 1 to 7 when executing the program code.

12. A computer readable storage medium having stored thereon a program code, characterized in that the program code, when executed by a processor, implements the steps of the blood pressure measurement method of any of claims 1 to 7.