Blood pressure measurement device, method, electronic device, storage medium, and program product

Abstract

The application relates to the technical field of sphygmomanometers, and discloses a blood pressure measuring device, a blood pressure measuring method, an electronic device, a storage medium and a program product.The blood pressure measuring device comprises a cuff, a piezoelectric sensor, an air pipe, a pressure sensor and a host computer.The cuff comprises a first cuff part and a second cuff part, the first cuff part and the second cuff part enclose an air storage chamber, the first cuff part and the second cuff part are integrally formed or are sealingly connected, an air nozzle is arranged on the cuff, the air nozzle is in communication with the air storage chamber, the piezoelectric sensor is fixed to the inside of the air storage chamber and is used for collecting Korotkoff sound signals, the air pipe has a first end and a second end, the first end is connected to the air nozzle, the air pipe is in communication with the air storage chamber, the pressure sensor is connected to the second end, the pressure sensor is used for collecting pressure signals, the pressure signals are used for representing the internal air pressure of the air storage chamber, and the host computer is used for predicting a blood pressure measurement result according to the Korotkoff sound signals and the pressure signals.Compared with conventional technologies, the application can improve the accuracy of blood pressure measurement results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sphygmomanometer, in particular to a blood pressure measuring device, method, electronic device, storage medium and program product. BACKGROUND

[0002] Electronic sphygmomanometers based on Korotkoff method have the advantages of simple operation, wide application range and reliable measurement results, and thus have been widely used. The conventional electronic sphygmomanometers based on Korotkoff method are provided with independent air bags on the cuffs, and piezoelectric sensors are arranged below the air bags and closely attached to the skin during use to collect signals. However, since the piezoelectric sensors are located below the air bags, the upper air bags are always impacted by blood flow, and the impact is transmitted to the lower piezoelectric sensors through the air bags, resulting in that the signals collected by the piezoelectric sensors are affected by the blood flow impact, thereby increasing the difficulty of judging the Korotkoff signals and affecting the accuracy of the blood pressure measurement results. SUMMARY

[0003] Therefore, the present application provides a blood pressure measuring device, method, electronic device, storage medium and program product to solve the problem that the blood pressure measurement results are easily affected by blood flow impact.

[0004] In a first aspect, the present application provides a blood pressure measuring device, which comprises:

[0005] a cuff comprising a first cuff part and a second cuff part, the first cuff part and the second cuff part surrounding a gas storage chamber, the first cuff part and the second cuff part being integrally formed or sealingly connected, the cuff being provided with an air nozzle, the air nozzle being in communication with the gas storage chamber;

[0006] a piezoelectric sensor fixed in the interior of the gas storage chamber, the piezoelectric sensor being used for collecting Korotkoff signals;

[0007] an air pipe having a first end and a second end, the first end being connected to the air nozzle, the air pipe being in communication with the gas storage chamber;

[0008] a pressure sensor connected to the second end, the pressure sensor being used for collecting pressure signals, the pressure signals being used for representing the internal pressure of the gas storage chamber;

[0009] a host configured to acquire the Korotkoff signals and the pressure signals, and to predict blood pressure measurement results according to the Korotkoff signals and the pressure signals, the piezoelectric sensor and the pressure sensor being respectively in communication connection with the host.

[0010] The present application does not separately arrange the air bag, provides a sleeve design scheme without air bag, arranges the piezoelectric sensor in the sleeve, and specifically arranges the piezoelectric sensor in the gas storage chamber surrounded by the first sleeve part and the second sleeve part, so that the influence of the air bag pressure generated by the blood flow impact on the collection of the Korotkoff sound signal in the blood pressure measurement process is reduced or even avoided, the precision of the Korotkoff sound collection is improved, compared with the conventional technology, the present application can not only improve the accuracy of the blood pressure measurement result, but also can help to reduce the material, reduce the manufacturing cost of the blood pressure measurement device, the assembly process of the blood pressure measurement device is simpler, and the production and manufacturing of the blood pressure measurement device are facilitated.

[0011] In a second aspect, the present application provides a blood pressure measurement method, which comprises:

[0012] The Korotkoff sound signal collected by the piezoelectric sensor fixed in the gas storage chamber and the pressure signal collected by the pressure sensor are obtained, the gas storage chamber is surrounded by the first sleeve part and the second sleeve part in the sleeve, the first sleeve part and the second sleeve part are integrally formed or sealingly connected, the air nozzle communicating with the gas storage chamber is arranged on the sleeve, the air nozzle is used for connecting the first end of the air pipe, the air pipe communicates with the gas storage chamber, the pressure sensor is connected to the second end of the air pipe, and the pressure signal is used for representing the internal pressure of the gas storage chamber.

[0013] According to the Korotkoff sound signal and the pressure signal, the blood pressure measurement result is predicted.

[0014] In the blood pressure measurement process of the blood pressure measurement device of the present application, the piezoelectric sensor is arranged in the gas storage chamber surrounded by the first sleeve part and the second sleeve part, which can reduce or even avoid the influence of the air bag pressure generated by the blood flow impact on the collection of the Korotkoff sound signal in the blood pressure measurement process, improve the precision of the Korotkoff sound collection, and improve the accuracy of the blood pressure measurement result.

[0015] In a third aspect, the present application provides an electronic device, which comprises a memory and a processor, the memory and the processor are connected in communication with each other, the memory stores computer instructions, and the processor executes the blood pressure measurement method of the first aspect or any one of the corresponding embodiments thereof by executing the computer instructions.

[0016] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used for making the computer execute the blood pressure measurement method of the first aspect or any one of the corresponding embodiments thereof.

[0017] In a fifth aspect, the present application provides a computer program product, which comprises computer instructions, and the computer instructions are used for making the computer execute the blood pressure measurement method of the first aspect or any one of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the specific embodiments or the related art of the present application, the drawings needed to be used in the specific embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0019] Figure 1 is a structural schematic diagram of a blood pressure measuring device according to an embodiment of the present application.

[0020] Figure 2 is a structural schematic diagram of an air nozzle according to an embodiment of the present application.

[0021] Figure 3 is a curve schematic diagram of a pressure signal according to an embodiment of the present application.

[0022] Figure 4 is a curve schematic diagram of a Korotkoff signal according to an embodiment of the present application.

[0023] Figure 5 is a curve schematic diagram of a pressure signal in a pressure drop phase according to an embodiment of the present application.

[0024] Figure 6 is a curve schematic diagram of a shock wave signal according to an embodiment of the present application.

[0025] Figure 7 is a curve schematic diagram of a Korotkoff signal in a pressure drop phase according to an embodiment of the present application.

[0026] Figure 8 is a schematic diagram of a Korotkoff signal locked according to a shock wave signal according to an embodiment of the present application.

[0027] Figure 9 is a schematic diagram of a spectrum of a Korotkoff signal according to an embodiment of the present application.

[0028] Figure 10 is a schematic diagram of a convolutional bidirectional long short-term memory neural network according to an embodiment of the present application.

[0029] Figure 11 is a schematic diagram of a signal frequency mean and a signal frequency variance according to an embodiment of the present application.

[0030] Figure 12 is a flow schematic diagram of a blood pressure measuring method according to an embodiment of the present application.

[0031] Figure 13 is a flow schematic diagram of another blood pressure measuring method according to an embodiment of the present application.

[0032] Figure 14 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention.

[0033] Figure label:

[0034] 10. Cuff; 11. First cuff section; 12. Second cuff section; 101. Air chamber; 102. Air nozzle; 20. Piezoelectric sensor; 30. Air tube; 40. Pressure sensor; 50. Main unit. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] For non-invasive blood pressure measurement, the most accurate method is generally considered to be the Korotkoff method. The process of blood pressure measurement based on the Korotkoff method is generally as follows: a stethoscope is placed under the cuff and pressed firmly against the skin. The cuff is inflated until a certain pressure is reached, which blocks blood flow in the upper arm artery. Then, the gas in the cuff is released, allowing the pressure to slowly decrease. When the first pulse sound is heard through the stethoscope, the pressure value at this point is the systolic pressure. Pressure is continuously released until the last pulse sound disappears, at which point the pressure value at this point is the diastolic pressure. With the rapid development of non-invasive blood pressure measurement technology, electronic blood pressure monitors based on the Korotkoff method have emerged. Electronic blood pressure monitors generally include a cuff and a main unit. The cuff is used to collect piezoelectric and pressure signals, and the main unit is used to calculate the blood pressure measurement result based on the collected piezoelectric and pressure signals. A conventional cuff requires a cuff, with the piezoelectric sensor placed under the cuff and pressed firmly against the skin. However, since the piezoelectric sensor is located below the air bladder, the upper air bladder is constantly subjected to the impact of blocked blood flow. This impact is transmitted through the air bladder to the lower piezoelectric sensor, causing the signal collected by the piezoelectric sensor to be affected by the blood flow impact (i.e., the air bladder signal is interfered with by the blood flow impact). This increases the difficulty of interpreting Korotkoff sound signals and affects the accuracy of blood pressure measurement results.

[0037] like Figure 1 As shown, and can be combined Figure 2 This invention provides a blood pressure measuring device, which includes, but is not limited to, a cuff 10, a piezoelectric sensor 20, a trachea 30, a pressure sensor 40, and a main unit 50.

[0038] The cuff 10 comprises a first cuff part 11 and a second cuff part 12, which enclose a gas storage chamber 101, the first cuff part 11 and the second cuff part 12 are integrally formed or sealingly connected, the cuff 10 is provided with an air nozzle 102, which is in communication with the gas storage chamber 101. Of course, the cuff 10 can also comprise a third cuff part (the blank area on the right side of the gas storage chamber 101 in the figure, not marked), which can be a structure extended from the first cuff part 11 or the second cuff part 12, or a piece of non-woven fabric fixedly connected with the first cuff part 11 and / or the second cuff part 12, the third cuff part can be used to curl and cover the cuff 10 on the user's arm when using the cuff 10, and can ensure that the gas storage chamber 101 is attached to the user's skin (specifically the user's arm artery) through the magic tape and other fixing components provided on the cuff 10; wherein the gas storage chamber 101 can be used to store air.

[0039] Specifically, the first cuff part 11 and the second cuff part 12 are pressed together at the edges to sealingly connect the edges of the first cuff part 11 and the edges of the second cuff part 12, thereby forming the gas storage chamber 101; or the gas storage chamber 101 can also be formed inside the cuff 10 manufactured by integrally forming.

[0040] The piezoelectric sensor 20 is fixed inside the gas storage chamber 101, and is used to collect the Korotkoff sound signal; the piezoelectric sensor 20 is pressed inside the cuff 10, and the piezoelectric sheet in the piezoelectric sensor is specifically fixed inside the gas storage chamber 101, and the Korotkoff sound signal is a piezoelectric signal collected by the piezoelectric sensor 20.

[0041] The number of piezoelectric sensors 20 can be one or more, and one piezoelectric sensor can include at least one piezoelectric sheet, all piezoelectric sheets on the device of the embodiment collectively collect piezoelectric signals to obtain the above-mentioned Korotkoff sound signal, and transmit it to the host computer 50.

[0042] In some optional embodiments, the piezoelectric sensor 20 is in communication connection with the host computer 50 through the connecting line built in the air tube 30, and the piezoelectric sensor 20 can include a first piezoelectric sheet and a second piezoelectric sheet attached to the target inner wall of the gas storage chamber 101, and the target inner wall is the inner wall of the gas storage chamber 101 close to the inner side of the cuff 10.

[0043] Specifically, the front surface of the first piezoelectric sheet and the second piezoelectric sheet is attached to the side of the air chamber 101 facing the user's skin (when using the blood pressure measuring device), and the front surface of the first piezoelectric sheet and the second piezoelectric sheet is bonded to the inner wall of the air chamber 101 (for example, bonded with 3M double-sided tape), and the piezoelectric sensor 20 can be further bonded to the inner wall of the air chamber 101 by acetic acid cloth tape, which serves as a secondary reinforcement; the back surface of the first piezoelectric sheet and the second piezoelectric sheet is attached to the sensor shell, the connecting line is extended out through the sensor shell and connected to the host 50 through the air tube 30. By placing the connecting line in the air tube, the reuse of the air tube is realized, and the connecting line does not need to be separately led out, so that the host 50 and the cuff 10 only need to be connected through the air tube, simplifying the structure of the blood pressure measuring device, and the double piezoelectric sheets attached inside the air bag cuff and the air bag gas fluctuation jointly detect the Korotkoff sound signal, improving the detection accuracy of the Korotkoff sound signal.

[0044] Optionally, the first piezoelectric sheet and the second piezoelectric sheet are distributed on both sides of the air nozzle 102 and close to the air nozzle 102, and are symmetrically arranged along the cuff axis where the air nozzle 102 is located. The distance between the first piezoelectric sheet and the second piezoelectric sheet in the embodiment can be 100 mm.

[0045] Specifically, the first piezoelectric sheet and the second piezoelectric sheet are arranged in the lower half of the cuff 10, and during blood pressure measurement, the first piezoelectric sheet and the second piezoelectric sheet are respectively arranged on both sides of the artery.

[0046] The air tube 30 has a first end and a second end, the first end is connected to the air nozzle 102, and the air tube 30 communicates with the air chamber 101; in the embodiment, the second end of the air tube 30 is connected to the host 50, and the host 50 is used to control the inflation of the air chamber 101 through the air tube 30 or the deflation of the air chamber 101 through the air tube 30.

[0047] In combination Figure 2 As shown, the first cuff part 11 and the second cuff part 12 enclose the air chamber 101, which communicates with the air tube 30 through the air nozzle 102. The air nozzle 102 can be arranged on the air nozzle connector, and the air nozzle connector is used to fixedly connect the first end of the air tube 30 and make the air tube 30 communicate with the air chamber 101.

[0048] The pressure sensor 40 is connected to the second end, and the pressure sensor 40 is used to collect pressure signals, and the pressure signals are used to represent the internal pressure of the air chamber 101.

[0049] The host 50 is used to obtain the Korotkoff sound signal and the pressure signal, and the host 50 is used to predict the blood pressure measurement result according to the Korotkoff sound signal and the pressure signal. The piezoelectric sensor 20 and the pressure sensor 40 are respectively connected to the host 50 in communication.

[0050] The embodiment provides a cuff without a gas bag, a piezoelectric sensor is arranged in the cuff and specifically arranged in a gas storage chamber surrounded by a first cuff part and a second cuff part, so that the influence of the gas bag pressure caused by blood flow impact on the acquisition of Korotkoff sound signals in the blood pressure measurement process is reduced or even avoided, the accuracy of the acquisition of Korotkoff sound is improved, compared with the conventional technology, the accuracy of the blood pressure measurement result can be improved, and the embodiment can also help to reduce materials, reduce the manufacturing cost of the device, and the assembly process of the device is simpler, and the production and manufacturing of the blood pressure measurement device are facilitated.

[0051] In some optional embodiments, the host 50 comprises a preprocessing module, an intermediate processing module and a post-processing module connected in sequence.

[0052] The preprocessing module is configured to perform time-frequency transformation processing on the first time-domain feature corresponding to the arterial pulsation extracted from the Korotkoff sound signal to obtain a frequency-domain feature, and to splice the frequency-domain feature with the second time-domain feature extracted from the Korotkoff sound signal to obtain a target data feature.

[0053] The preprocessing module of the embodiment is configured to preprocess the collected pressure signal and the Korotkoff sound signal to obtain a target data feature required for a subsequent inference process.

[0054] The intermediate processing module is configured to perform inference according to the target data feature to predict a blood pressure category classification result corresponding to the Korotkoff sound signal.

[0055] The intermediate processing module of the embodiment is configured to classify the screened Korotkoff sound signal according to the target data feature to infer a blood pressure category corresponding to the Korotkoff sound signal.

[0056] The post-processing module is configured to determine a blood pressure measurement result according to the blood pressure category classification result and the pressure signal.

[0057] The post-processing module of the embodiment screens a low-pressure signal and a high-pressure signal from the pressure signal according to the blood pressure category to realize measurement of high blood pressure and low blood pressure.

[0058] The present application can more accurately capture the change characteristics related to systolic pressure and diastolic pressure through analysis and processing of the frequency domain of the Korotkoff sound signal, and through splicing of the frequency domain feature and the time domain feature, the expression of comprehensive useful information is ensured, so that the accuracy of blood pressure measurement is further improved based on the principle of the Korotkoff sound method.

[0059] In some optional embodiments, the preprocessing module comprises a band-pass filter unit, a signal extraction unit, a time-frequency transformation unit, a signal sampling unit and a feature splicing unit.

[0060] The bandpass filter unit is used to perform bandpass filtering on the pressure signal to obtain an oscillating wave signal that reflects the arterial pulsation.

[0061] The bandpass filter unit is specifically used to perform bandpass filtering on pressure signals based on pulse characteristics to obtain oscillating wave signals, and achieves the function of signal denoising during the filtering process.

[0062] like Figure 3 As shown, the pressure signal collected by pressure sensor 40 is illustrated. Figure 3 The horizontal axis represents time, with units of seconds (s), and the vertical axis represents pressure, with units of millimeters of mercury (mmHg). Figure 3 It can be seen that during the process of inflating and pressurizing the gas chamber in the cuff, the blood flow in the user's upper arm artery is gradually blocked, and the amplitude of the pressure signal increases. Then, during the process of slowly releasing the gas in the gas chamber at a preset speed (e.g., 2-4 mmHg), the amplitude of the pressure signal gradually decreases.

[0063] Combination Figure 4 As shown, during the process of filling the gas storage chamber with gas, the piezoelectric sensor will detect the piezoelectric signal, and during the process of releasing gas, the piezoelectric sensor will detect the Korotkoff sound signal generated by the arterial pulsation.

[0064] like Figure 5 As shown, the horizontal axis represents time, and the unit can be seconds (s). The vertical axis represents pressure, and the unit can be millimeters of mercury (mmHg). In this embodiment, the focus of blood pressure measurement is on the process of the decrease in the amplitude of the pressure signal, that is, the pressure curve of the pressure decrease segment.

[0065] like Figure 6 As shown, the horizontal axis represents time, with the unit being seconds (s), and the vertical axis represents the pressure change value, with the unit being millimeters of mercury (mmHg). The points in the figure are used to indicate the location of the maximum value.

[0066] The signal extraction unit is used to extract the first time-domain feature corresponding to the arterial pulsation from the Korotkoff sound signal, using the sampling time corresponding to the maximum value in the oscillation wave signal as the reference time point.

[0067] The signal extraction unit is specifically used to locate the position of the Korotkoff sound signal in the dual pressure sensor data (i.e., Korotkoff sound signal) based on the maximum value of the oscillation wave. In this embodiment, each pulse beat is taken as a moment, and a total of 512 data points (or feature points) before and after the position of the Korotkoff sound signal at each moment are extracted.

[0068] like Figure 7 As shown, the horizontal axis represents time, with the unit being seconds (s), and the vertical axis represents the amplitude of the Korotkoff tone signal, with the unit being volts (V). Figure 7On this basis, the accurate position of the click signal is locked through the time point corresponding to the maximum value in the shock wave signal.

[0069] As shown in Figure 8 25 first time domain features are shown, and each first time domain feature includes 512 data points.

[0070] The time-frequency conversion unit is configured to perform time-frequency conversion processing on the first time domain feature to obtain a frequency domain feature.

[0071] The time-frequency conversion unit is specifically configured to obtain 256 data points as the frequency domain feature after performing time-frequency conversion processing on the time sequence signal composed of the above-mentioned 512 data points.

[0072] The signal sampling unit is configured to perform sampling processing on the click signal to extract a second time domain feature from the click signal.

[0073] The feature splicing unit is configured to splice the frequency domain feature and the second time domain feature into a target data feature.

[0074] In this embodiment, the shock wave signal is obtained by filtering the pressure signal, so that the position of the click signal is identified through the maximum value of the shock wave signal, and then time-frequency conversion can be performed on the locked click signal, so that the target data feature used for subsequent identification is obtained through the splicing of the frequency domain signal and the frequency domain signal. The processing mode of the pressure signal and the click signal in the above process can help to significantly improve the accuracy and reliability of the high-low pressure judgment result.

[0075] In some optional embodiments, the signal extraction unit is configured to determine a first preset number of first feature points before and after a reference time point extracted from the click signal as the first time domain feature.

[0076] The first preset number is 512, for example.

[0077] The time-frequency conversion unit is configured to determine a second preset number of second feature points obtained by performing time-frequency conversion processing on the first time domain feature as the frequency domain feature.

[0078] The second preset number is less than the first preset number; the second preset number is 256, for example.

[0079] In this embodiment, the number of feature points is reduced in the time-frequency conversion process, which can reduce the requirement for hardware in the subsequent processing process on the basis of retaining key information, and can improve the processing efficiency of the subsequent process.

[0080] Specifically, the signal sampling unit is configured to determine a third preset number of third feature points sampled from the click sound signal as the second time domain feature; the third preset number is less than the first preset number, and the third preset number is the same as or different from the second preset number; for example, the third preset number is 256.

[0081] The signal sampling unit can be specifically configured to perform downsampling processing on the timing signal composed of the 512 data points, so as to obtain 256 data points.

[0082] The feature splicing unit is configured to splice the third preset number of third feature points and the second preset number of second feature points into the target data feature.

[0083] The feature splicing unit can be specifically configured to splice the frequency domain signal represented by the 256 data points obtained through the time domain transformation and the time domain signal represented by the 256 data points obtained through the downsampling, to obtain the target data feature represented by the 512 data points obtained through the splicing.

[0084] The third preset number of third feature points and the second preset number of second feature points are spliced in the embodiment, so that the time domain key information and the frequency domain key information are retained, and sufficient and reliable data support is provided for accurate identification of the high and low pressure categories.

[0085] In some optional embodiments, the intermediate processing module is a trained convolutional bidirectional long short-term memory neural network, and the trained convolutional bidirectional long short-term memory neural network comprises a convolutional neural network and a bidirectional long short-term memory network connected in sequence.

[0086] The convolutional neural network is configured to perform convolution operation on the target data feature to extract spatial features from the target data feature.

[0087] The bidirectional long short-term memory network is configured to output a fourth preset number of blood pressure category classification results according to the spatial features, the blood pressure category classification results comprising a classification result between high and low pressure and a classification result not between high and low pressure, and the fourth preset number being the sum of the third preset number and the second preset number.

[0088] The embodiment inputs the extracted target data features into the trained convolutional bidirectional long short-term memory neural network including the convolutional neural network and the bidirectional long short-term memory network connected in sequence, so as to learn the deep connection between the pressure signal and the Korotkoff tone high and low pressure signal through the convolutional bidirectional long short-term memory neural network. The method can greatly improve the accuracy of the blood pressure category classification result judgment while retaining the original characteristics of the signal, and further improve the accuracy of the high and low pressure recognition by converting the extracted Korotkoff tone signal to the frequency domain for high and low pressure judgment. Moreover, compared with the manual judgment method in the conventional scheme, the convolutional bidirectional long short-term memory neural network used in the application can also eliminate the problem of inaccurate blood pressure measurement results caused by human subjective factors.

[0089] In some optional embodiments, the bidirectional long short-term memory network includes a long short-term memory network layer and a fully connected layer connected in sequence.

[0090] The long short-term memory network layer is used to extract context features from the spatial features.

[0091] The fully connected layer is used to output a fourth preset number of blood pressure category classification results according to the context features.

[0092] The application comprehensively considers the spatial features and context features in the target data features, thereby fully analyzing and learning the conditions of the pressure signal and the Korotkoff tone high and low pressure signal and the connection therebetween, to obtain a blood pressure category classification result with higher accuracy.

[0093] In some optional embodiments, the post-processing module is used to determine the pressure signal corresponding to the blood pressure category classification result between the high and low pressures as the high pressure signal, and is used to determine the pressure signal corresponding to the blood pressure category classification result between the high and low pressures as the low pressure signal.

[0094] The embodiment can determine the high pressure signal and the low pressure signal according to the relationship between the blood pressure category classification result and the pressure signal, that is, to accurately measure the high pressure value and the low pressure value.

[0095] In some optional embodiments, the host 50 includes an analysis module, an identification module and a judgment module connected in sequence.

[0096] The analysis module is used to extract target time domain features corresponding to the arterial pulsation from the Korotkoff tone signal according to the pressure signal, and is used to determine the signal frequency mean and the signal frequency variance corresponding to the target time domain features;

[0097] The identification module is used to determine the signal change trend according to the signal frequency mean and the signal frequency variance, and is used to determine the high pressure change trend and the low pressure change trend according to the signal change trend;

[0098] The judging module is configured to determine the pressure signal corresponding to the high-pressure change trend as a high-pressure signal and to determine the pressure signal corresponding to the low-pressure change trend as a low-pressure signal.

[0099] The embodiment can also determine the signal change trend by using the signal frequency mean and signal frequency variance corresponding to the target time domain feature extracted from the Korotkoff signal, thereby identifying the high-pressure signal and the low-pressure signal from the pressure signal according to the signal change trend, so as to quickly and accurately determine the high-pressure value and the low-pressure value, and compared with the manual identification in the conventional scheme, the analysis module, the identification module and the judging module can eliminate the problem of inaccurate blood pressure measurement results caused by human subjective factors.

[0100] According to the embodiment of the present application, a blood pressure measurement method is provided, and it should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0101] In the embodiment, a blood pressure measurement method is provided, which can be used in the host computer described above, Figure 12 is a flowchart of the blood pressure measurement method according to the embodiment of the present application, as Figure 12 shown, the flow includes the following steps:

[0102] In step S1201, the Korotkoff signal collected by the piezoelectric sensor fixed inside the gas chamber and the pressure signal collected by the pressure sensor are obtained, the gas chamber is surrounded by the first sleeve part and the second sleeve part in the sleeve, the first sleeve part is integrally formed or sealingly connected with the second sleeve part, the air nozzle communicating with the gas chamber is arranged on the sleeve, the air nozzle is used to connect the first end of the air pipe, the air pipe communicates with the gas chamber, the pressure sensor is connected to the second end of the air pipe, and the pressure signal is used to represent the internal pressure of the gas chamber.

[0103] In some optional embodiments, the piezoelectric sensor is in communication connection with the host computer through the connecting line built in the air pipe, the piezoelectric sensor includes the first piezoelectric sheet and the second piezoelectric sheet attached to the target inner wall of the gas chamber, and the target inner wall is the inner wall of the gas chamber close to the inner side of the sleeve.

[0104] Specifically, the Korotkoff signal of the embodiment is the double-piezoelectric sensor data collected by the first piezoelectric sheet and the second piezoelectric sheet.

[0105] In step S1202, the blood pressure measurement result is predicted according to the Korotkoff signal and the pressure signal.

[0106] Specifically, the blood pressure measurement method based on the Korotkoff sound method selects a high pressure signal and a low pressure signal from the pressure signal according to the Korotkoff sound signal, so as to obtain a blood pressure measurement result, that is, a high pressure value corresponding to the high pressure signal and a low pressure value corresponding to the low pressure signal.

[0107] In the embodiment, a blood pressure measurement method is provided, which can be used for the host computer, Figure 13 is a flowchart of the blood pressure measurement method according to the embodiment of the present application, as Figure 13 shown, the flow includes the following steps:

[0108] In step S1301, a Korotkoff sound signal collected by a piezoelectric sensor fixed inside a gas storage chamber and a pressure signal collected by a pressure sensor are obtained, the gas storage chamber is surrounded by a first cuff part and a second cuff part in a cuff, the first cuff part and the second cuff part are integrally formed or sealingly connected, an air nozzle communicating with the gas storage chamber is arranged on the cuff, the air nozzle is used to connect a first end of an air tube, the air tube communicates with the gas storage chamber, and the pressure sensor is connected to a second end of the air tube, the pressure signal is used to represent the internal pressure of the gas storage chamber. For details, see step S1201 of the embodiment shown in Figure 12 , which will not be repeated here.

[0109] In step S1302, the blood pressure measurement result is predicted according to the Korotkoff sound signal and the pressure signal.

[0110] The embodiment provides a blood pressure measurement method based on a cuff without air bag design scheme, the piezoelectric sensor is arranged in the cuff and specifically arranged in the gas storage chamber surrounded by the first cuff part and the second cuff part, so as to reduce or even avoid the influence of the air bag pressure caused by the blood flow impact on the Korotkoff sound signal collection in the blood pressure measurement process, improve the accuracy of the Korotkoff sound collection, and the present application can obviously improve the accuracy of the blood pressure measurement result compared with the conventional technology.

[0111] Specifically, the above-mentioned step S1302 includes:

[0112] In step S13021, the first time domain feature corresponding to the arterial pulsation extracted from the Korotkoff sound signal is subjected to time-frequency transformation processing to obtain a frequency domain feature.

[0113] In some optional embodiments, step S13021 includes but is not limited to steps a1 and a2.

[0114] In step a1, the pressure signal is subjected to band-pass filtering processing to obtain a shock wave signal reflecting the arterial pulsation.

[0115] Specifically, the pressure signal is subjected to band-pass filtering processing according to the pulse characteristics to obtain the shock wave signal.

[0116] As Figure 3As shown, the horizontal axis represents time, the unit can be seconds (s), and the vertical axis represents the pressure signal collected by the pressure sensor 40, Figure 3 The horizontal axis represents time, the unit can be seconds (s), and the vertical axis represents pressure, the unit can be millimeters of mercury (mmHg). Figure 3 As can be seen, the blood flow of the user's upper arm artery is gradually blocked during the process of inflating the gas chamber in the cuff, and the amplitude of the pressure signal is increasing. Then, during the process of slowly releasing the gas in the gas chamber at a preset speed (for example, 2-4 mmHg), the amplitude of the pressure signal is gradually decreasing.

[0117] As shown in Figure 4 During the process of inflating the gas chamber, the piezoelectric sensor will detect the piezoelectric signal, and during the process of releasing the gas, the piezoelectric sensor will detect the Korotkoff signal generated by the arterial pulsation.

[0118] As shown in Figure 5 The horizontal axis represents time, the unit can be seconds (s), and the vertical axis represents pressure, the unit can be millimeters of mercury (mmHg). The amplitude of the pressure signal is decreasing during the blood pressure measurement, that is, the pressure curve in the pressure drop section.

[0119] As shown in Figure 6 The horizontal axis represents time, the unit can be seconds (s), and the vertical axis represents the pressure change value, the unit can be millimeters of mercury (mmHg). The dots in the figure are used to represent the position of the maximum value.

[0120] Step a2, taking the sampling time corresponding to the maximum value in the shock wave signal as the reference time point, extracting the first time domain feature corresponding to the arterial pulsation from the Korotkoff signal.

[0121] Specifically, step a2 includes: determining the first preset number of first feature points before and after the reference time point extracted from the Korotkoff signal as the first time domain feature.

[0122] For example, the first preset number is 512.

[0123] This embodiment locks the position of the Korotkoff signal in the double pressure sensor data (i.e. the Korotkoff signal) according to the maximum value of the shock wave. This embodiment takes each pulse as a time point, and extracts 512 data points (or feature points) before and after the position of the Korotkoff signal at each time point.

[0124] As shown in Figure 7 The horizontal axis represents time, the unit can be seconds (s), and the vertical axis represents the amplitude of the Korotkoff signal, the unit can be volts (V). Based on Figure 7 The accurate position of the Korotkoff signal is locked through the time point corresponding to the maximum value in the shock wave signal.

[0125] As shown in Figure 8 25 first time domain features are shown, and each first time domain feature includes 512 data points.

[0126] Step a3, time-frequency transformation processing is performed on the first time domain feature to obtain a frequency domain feature.

[0127] Specifically, step a3 includes: determining the second preset number of second feature points obtained by performing time-frequency transformation processing on the first time domain feature as the frequency domain feature; wherein the second preset number is less than the first preset number.

[0128] For example, the second preset number is 256.

[0129] In this embodiment, the time series signal composed of the above-mentioned 512 data points is processed by time-frequency transformation to obtain 256 data points as the frequency domain feature. In this embodiment, the number of feature points is reduced in the time-frequency transformation process. This way can reduce the hardware requirements of the subsequent processing process on the basis of preserving key information, and can improve the processing efficiency of the subsequent process.

[0130] Step S13022, splicing the frequency domain feature and the second time domain feature extracted from the click signal to obtain a target data feature.

[0131] In some optional embodiments, step S13022 includes:

[0132] Step b1, sampling processing is performed on the click signal to extract a second time domain feature from the click signal.

[0133] Specifically, step b1 includes: determining the third preset number of third feature points sampled from the click signal as the second time domain feature; wherein the third preset number is less than the first preset number, and the third preset number is the same as or different from the second preset number.

[0134] For example, the third preset number is 256.

[0135] This embodiment can also perform down-sampling processing on the time series signal composed of the above-mentioned 512 data points, thereby obtaining 256 data points.

[0136] Step b2, splicing the frequency domain feature and the second time domain feature into a target data feature.

[0137] Specifically, step b2 includes: splicing the third preset number of third feature points and the second preset number of second feature points into the target data feature.

[0138] In this embodiment, the frequency domain signal represented by 256 data points obtained through time domain transformation and the time domain signal represented by 256 data points obtained through downsampling are spliced ​​together to obtain the target data features represented by 512 data points obtained through splicing.

[0139] This embodiment obtains an oscillation wave signal by filtering the pressure signal. The location of the Korotkoff sound signal is then identified by the maximum value of the oscillation wave signal. A time-frequency transformation is then performed on the locked Korotkoff sound signal, and target data features for subsequent identification are obtained by concatenating frequency domain signals. The processing method for the pressure signal and Korotkoff sound signal described above significantly improves the accuracy and reliability of high and low pressure identification results. This embodiment preserves key time-domain and frequency-domain information by concatenating a third preset number of third feature points and a second preset number of second feature points, providing sufficient and reliable data support for accurate identification of high and low pressure categories.

[0140] Step S13023: Based on the characteristics of the target data, reasoning is performed to predict the blood pressure category classification result corresponding to the Korotkoff sound signal.

[0141] Specifically, step S13023 includes:

[0142] Step c1 involves performing convolution operations on the target data features using the convolutional neural network within the trained bidirectional long short-term memory neural network to extract spatial features from the target data features.

[0143] Specifically, a convolutional neural network may include convolutional layers, pooling layers, and activation function layers; convolutional layers are used to perform convolution operations on input data using multiple convolutional kernels to extract local features; pooling layers are used to perform pooling operations on the output of convolutional layers to reduce data dimensionality while retaining important features; activation function layers are used to introduce nonlinear factors to enhance the expressive power of the model.

[0144] Step c2: The bidirectional long short-term memory network in the trained convolutional bidirectional long short-term memory neural network outputs a fourth preset number of blood pressure category classification results based on spatial features. The blood pressure category classification results include classification results between high and low blood pressure and classification results not between high and low blood pressure. The fourth preset number is the sum of the third preset number and the second preset number.

[0145] like Figure 10 As shown, in this embodiment, the number of pulses corresponding to the input target data feature W is N=25, H represents 512-dimensional features, which is the aforementioned fourth preset number, and the number of channels C is 1. The data is input into a bidirectional long short-term memory network to distinguish each pulse wave.

[0146] Specifically, the bidirectional long short-term memory network can include a forward long short-term memory network layer (forward LSTM layer) and a backward long short-term memory network layer (backward LSTM layer) and an output layer; the forward long short-term memory network layer is used for processing forward propagation of sequence data and capturing past information; the backward long short-term memory network layer is used for processing backward propagation of sequence data and capturing future information; and the output layer is used for making a prediction or classification according to outputs of the forward LSTM layer and the backward LSTM layer. In the embodiment, whether the Korotkoff signal is between the high and low pressure values (including the high pressure value point and the low pressure value point) is outputted, and the bidirectional long short-term memory network is trained in advance, and the training sample is labeled, if it is between the high and low pressure values, the output is 1, and if it is between the high and low pressure values, the output is 0.

[0147] Specifically, the convolutional bidirectional long short-term memory neural network (CNN-BiLSTM) is a deep learning model, which specifically combines the advantages of the convolutional neural network (CNN) and the bidirectional long short-term memory network (BiLSTM).

[0148] In the embodiment, the extracted target data features are input into the trained convolutional bidirectional long short-term memory neural network including the convolutional neural network and the bidirectional long short-term memory network connected in sequence, so as to learn the deep connection between the pressure signal and the Korotkoff high and low pressure signal through the convolutional bidirectional long short-term memory neural network. This way can greatly improve the accuracy of the blood pressure category classification result judgment while retaining the original features of the signal, and further improve the accuracy of the high and low pressure recognition by converting the extracted Korotkoff signal to the frequency domain for high and low pressure judgment. Moreover, compared with the manual discrimination method in the conventional scheme, the convolutional bidirectional long short-term memory neural network used in the present application can also eliminate the problem of inaccurate blood pressure measurement results caused by human subjective factors.

[0149] In the embodiment, the convolutional neural network and the bidirectional long short-term memory network are combined, which can make full use of the advantages of the convolutional neural network in better extracting spatial features in the data, and make full use of the advantages of the bidirectional long short-term memory network in better extracting temporal features in the data, better process the target data features in the form of sequence data, and determine more accurate blood pressure category classification results corresponding to the Korotkoff signal based on the temporal features and the spatial features.

[0150] Specifically, step c2 includes:

[0151] Step d1, extracting context features from the spatial features through the long short-term memory network layer in the bidirectional long short-term memory network.

[0152] Step d2, outputting a fourth preset number of blood pressure category classification results according to the context features through the fully connected layer in the bidirectional long short-term memory network.

[0153] Step S13024, according to the blood pressure category classification result and the pressure signal, determine the blood pressure measurement result.

[0154] Specifically, step S13024 includes: determining the pressure signal corresponding to the blood pressure category classification result between the first high and low pressure as the high pressure signal, and determining the pressure signal corresponding to the blood pressure category classification result between the last high and low pressure as the low pressure signal.

[0155] The present application can more accurately capture the change characteristics related to systolic pressure and diastolic pressure through analysis and processing of the frequency domain of the Korotkoff signal, and can ensure the expression of comprehensive useful information through the splicing of frequency domain characteristics and time domain characteristics, thereby further improving the accuracy of blood pressure measurement based on the principle of Korotkoff method.

[0156] In some optional embodiments, in step S1302, the blood pressure measurement result is predicted according to the Korotkoff signal and the pressure signal, including but not limited to steps e1 to e3.

[0157] Step e1, extracting the target time domain feature corresponding to the arterial pulsation from the Korotkoff signal according to the pressure signal, and determining the signal frequency mean and signal frequency variance corresponding to the target time domain feature.

[0158] Specifically, the pressure signal is filtered in this embodiment, for example, a first-order Butterworth band-pass filter is used to extract the pulsatile signal, and the maximum value of the pulsatile signal is obtained, and the point where the maximum value is located is the pulse time, that is, the time of each pulse is obtained, for example Figure 6 As shown; next, the pulse time is used to locate the corresponding time of the Korotkoff signal, that is, the corresponding time of the piezoelectric signal, wherein, since there may be a difference between the sampling frequencies of the piezoelectric signal and the pressure signal, in order to avoid the deviation caused by direct correspondence, this embodiment finds the position of the maximum value between the first preset time period (for example, 0.2 seconds) and the second preset time period (for example, 0.1 seconds) before and after the corresponding piezoelectric signal as the position of the Korotkoff signal, for example Figure 7 As shown; according to the position of the Korotkoff signal, 256 points before and after are taken as the target time domain feature corresponding to the arterial pulsation, for example Figure 8 26 target time domain features shown in FIG. 26, the extracted Korotkoff signal is processed by a windowing function, so that the edges of the signal are smoothed to a certain extent, and the signal will not produce too large mutation when being intercepted; then the Korotkoff signal processed by the windowing function is subjected to short-time Fourier transform to obtain the corresponding frequency spectrum. This embodiment can realize the visualization of the energy distribution of the Korotkoff signal at different frequencies through the frequency spectrum, for example Figure 9 As shown, the data preprocessing is completed.

[0159] In this embodiment, after the window function processing and the short-time Fourier transform are performed on the target time domain features, frequency domain features are obtained. By processing the frequency domain features, the signal frequency mean and the signal frequency variance corresponding to each target time domain feature can be directly calculated. The signal frequency mean and the signal frequency variance are combined to determine the signal change trend. Figure 11 As shown in the figure, the horizontal coordinate represents each target time domain feature, and the vertical coordinate represents the mean and the variance. The vertical bars in the figure represent the mean, the vertical lines represent the variance, and the intersection of the vertical bars and the vertical lines represents the difference between the mean and the variance.

[0160] Step e2, determining the signal change trend according to the signal frequency mean and the signal frequency variance, and determining the high-pressure change trend and the low-pressure change trend according to the signal change trend.

[0161] Specifically, the signal change trend is determined according to the difference between the signal frequency mean and the signal frequency variance or the sum of the signal frequency mean and the signal frequency variance. Figure 11 As shown in the figure, the curve formed by the connection between the intersection points of the vertical bars and the vertical lines represents the change trend of the difference between the mean and the variance.

[0162] In this embodiment, the signal change trend is the change trend of the difference between the mean and the variance, or the change trend of the sum of the mean and the variance. The high-pressure change trend refers to the change trend between the first (i.e., the first) two target time domain features in the signal change trend, in which the signal frequency mean and the signal frequency variance both change most obviously. The low-pressure change trend refers to the change trend between the last (i.e., the last) two target time domain features in the signal change trend, in which the signal frequency mean and the signal frequency variance both change most obviously.

[0163] Step e3, determining the pressure signal corresponding to the high-pressure change trend as the high-pressure signal, and determining the pressure signal corresponding to the low-pressure change trend as the low-pressure signal.

[0164] In combination with Figure 11 As shown in the figure, according to the time sequence of signal acquisition, it can be judged from the slope of the curve in the figure that the target time domain feature 13 to the target time domain feature change most obviously. Therefore, the pressure signal corresponding to the target time domain feature 14 is the high-pressure signal. After the target time domain feature 23, the mean and the variance of the target time domain feature 24 and the target time domain feature 25 tend to be moderate, so the pressure signal corresponding to the target time domain feature 23 is the low-pressure signal.

[0165] In this embodiment, a host 50 is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and has been described above. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware or a combination of software and hardware is also possible and contemplated.

[0166] The embodiment provides a host 50, which is combined with Figure 1 As shown, the host 50 comprises a preprocessing module, an intermediate processing module and a post-processing module connected in sequence.

[0167] The preprocessing module is configured to perform time-frequency transformation processing on the first time-domain feature corresponding to the arterial pulse extracted from the Korotkoff signal to obtain a frequency-domain feature, and splice the frequency-domain feature with the second time-domain feature extracted from the Korotkoff signal to obtain a target data feature.

[0168] The intermediate processing module is configured to perform inference according to the target data feature to predict a blood pressure category classification result corresponding to the Korotkoff signal.

[0169] The post-processing module is configured to determine a blood pressure measurement result according to the blood pressure category classification result and the pressure signal.

[0170] In some optional embodiments, the preprocessing module comprises a band-pass filtering unit, a signal extraction unit, a time-frequency transformation unit, a signal sampling unit and a feature splicing unit.

[0171] The band-pass filtering unit is configured to perform band-pass filtering processing on the pressure signal to obtain an oscillation wave signal reflecting the arterial pulse.

[0172] The signal extraction unit is configured to extract the first time-domain feature corresponding to the arterial pulse from the Korotkoff signal with a sampling time point corresponding to a maximum value in the oscillation wave signal as a reference time point.

[0173] The time-frequency transformation unit is configured to perform time-frequency transformation processing on the first time-domain feature to obtain a frequency-domain feature.

[0174] The signal sampling unit is configured to perform sampling processing on the Korotkoff signal to extract the second time-domain feature from the Korotkoff signal.

[0175] The feature splicing unit is configured to splice the frequency-domain feature and the second time-domain feature into the target data feature.

[0176] In some optional embodiments, the signal extraction unit is configured to determine a first preset number of first feature points before and after the reference time point extracted from the Korotkoff signal as the first time-domain feature. The time-frequency transformation unit is configured to determine a second preset number of second feature points obtained by performing time-frequency transformation processing on the first time-domain feature as the frequency-domain feature. The second preset number is less than the first preset number.

[0177] In some optional embodiments, the signal sampling unit is configured to determine a third preset number of third feature points sampled from the Korotkoff signal as the second time-domain feature. The third preset number is less than the first preset number, and the third preset number is the same as or different from the second preset number.

[0178] The feature splicing unit is configured to splice the third preset number of third feature points and the second preset number of second feature points into the target data feature.

[0179] In some optional embodiments, the intermediate processing module is a trained convolutional bidirectional long short-term memory neural network, and the trained convolutional bidirectional long short-term memory neural network comprises a convolutional neural network and a bidirectional long short-term memory network connected in sequence.

[0180] The convolutional neural network is configured to perform a convolution operation on the target data feature to extract a spatial feature from the target data feature.

[0181] The bidirectional long short-term memory network is configured to output a fourth preset number of blood pressure category classification results according to the spatial feature, the blood pressure category classification results comprising a classification result between high and low pressures and a classification result not between high and low pressures, and the fourth preset number being a sum of the third preset number and the second preset number.

[0182] In some optional embodiments, the bidirectional long short-term memory network comprises a long short-term memory network layer and a fully connected layer connected in sequence; the long short-term memory network layer is configured to extract a context feature from the spatial feature; and the fully connected layer is configured to output the fourth preset number of blood pressure category classification results according to the context feature.

[0183] In some optional embodiments, the post-processing module is configured to determine a pressure signal corresponding to a first blood pressure category classification result between high and low pressures as a high pressure signal, and to determine a pressure signal corresponding to a last blood pressure category classification result between high and low pressures as a low pressure signal.

[0184] In some optional embodiments, the host 50 comprises an analysis module, an identification module and a judgment module connected in sequence; the analysis module is configured to extract a target time domain feature corresponding to arterial pulsation from the Korotkoff sound signal according to the pressure signal, and to determine a signal frequency mean value and a signal frequency variance corresponding to the target time domain feature; the identification module is configured to determine a signal change trend according to the signal frequency mean value and the signal frequency variance, and to determine a high pressure change trend and a low pressure change trend according to the signal change trend; and the judgment module is configured to determine a pressure signal corresponding to the high pressure change trend as a high pressure signal, and to determine a pressure signal corresponding to the low pressure change trend as a low pressure signal.

[0185] Further function descriptions of the above-mentioned various modules and / or units are the same as those of the above-mentioned corresponding embodiments, and will not be described here again.

[0186] In this embodiment, the host 50 is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0187] This invention also provides an electronic device having the above-described features. Figure 14 The host computer 50 is shown.

[0188] Please see Figure 14 , Figure 14 This is a schematic diagram of the structure of an electronic device provided in an optional embodiment of the present invention, such as... Figure 14 As shown, the electronic device includes one or more processors 1410, a memory 1420, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise as required. The processors can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 14 Take the 1410 processor as an example.

[0189] Processor 1410 may be a central processing unit, a network processor, or a combination thereof. Processor 1410 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0190] The memory 1420 stores instructions executable by at least one processor 1410 to cause at least one processor 1410 to perform the method shown in the above embodiments.

[0191] The memory 1420 can include a program storage area and a data storage area. The program storage area can store an operating system, application programs, and / or data required by at least one function. The data storage area can store data created by the electronic device, etc. In addition, the memory 1420 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk memory device, a flash memory device, or other non-volatile solid state memory device. In some alternative embodiments, the memory 1420 can optionally include a memory that is remotely located from the processor 1410, and can be connected to the electronic device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0192] The memory 1420 can include a volatile memory, such as a random access memory, and can also include a non-volatile memory, such as at least one disk memory device, a flash memory device, or other non-volatile solid state memory device. The memory 1420 can also include a combination of the above-mentioned types of memory.

[0193] The electronic device also includes a communication interface 1430 for communication of the electronic device with other devices or communication networks.

[0194] The embodiments of the present application also provide a computer readable storage medium, and the above-mentioned method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or implemented through computer code originally stored in a remote storage medium or non-transitory machine readable storage medium and downloaded to a local storage medium, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that the computer, processor, microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, processor, or hardware, the method shown in the above embodiments is implemented.

[0195] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, through the operation of the computer, can call or provide the method and / or technical solutions according to the present application. Those skilled in the art should understand that the form of computer program instructions in computer readable medium includes but is not limited to source file, executable file, installation package file and the like, and accordingly, the way of computer program instructions executed by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0196] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0197] In the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connection", "fixing" and the like should be understood broadly, for example, it can be fixed connection, or detachable connection, or integral; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through intermediate medium, it can be the internal communication of two elements or the interaction relationship of two elements, unless otherwise explicitly limited. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0198] It should be understood that various parts of the present application can be implemented in hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following technologies known in the art or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0199] In the description of the present specification, the description of the terms "the present embodiment", "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0200] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise explicitly specified.

[0201] Although the embodiments of the present application are described in conjunction with the drawings, various modifications and variations can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A blood pressure measuring device, characterized in that, The device includes: The cuff (10) includes a first cuff portion (11) and a second cuff portion (12), the first cuff portion (11) and the second cuff portion (12) forming an air storage chamber (101), the first cuff portion (11) and the second cuff portion (12) are integrally formed or sealed together, and an air nozzle (102) is provided on the cuff (10), the air nozzle (102) is connected to the air storage chamber (101); A piezoelectric sensor (20) is fixed inside the gas storage chamber (101), and the piezoelectric sensor (20) is used to collect Korotkoff sound signals; The air tube (30) has a first end and a second end, the first end being connected to the air nozzle (102), and the air tube (30) being connected to the air storage chamber (101); A pressure sensor (40) is connected to the second end. The pressure sensor (40) is used to collect pressure signals, which are used to characterize the internal air pressure of the gas storage chamber (101). The host (50) is used to acquire the Korotkoff sound signal and the pressure signal, and to predict the blood pressure measurement result based on the Korotkoff sound signal and the pressure signal. The piezoelectric sensor (20) and the pressure sensor (40) are respectively connected to the host (50) in communication. The host (50) includes an analysis module, an identification module and a judgment module connected in sequence; The analysis module is used to extract target time-domain features corresponding to arterial pulsation from the Korotkoff sound signal based on the pressure signal, and to determine the signal frequency mean and signal frequency variance corresponding to the target time-domain features; The identification module is used to determine the signal change trend based on the signal frequency mean and the signal frequency variance, and to determine the high-voltage change trend and the low-voltage change trend based on the signal change trend; the signal change trend is the change trend of the difference between the signal frequency mean and the signal frequency variance, or the change trend of the sum of the signal frequency mean and the signal frequency variance; the high-voltage change trend refers to the change trend between the two adjacent target time-domain features in the signal change trend where the first change in both the signal frequency mean and the signal frequency variance is most significant, and the low-voltage change trend refers to the change trend between the two adjacent target time-domain features in the signal change trend where the last change in both the signal frequency mean and the signal frequency variance is most significant; The judgment module is used to determine the pressure signal corresponding to the high pressure change trend as a high pressure signal, and to determine the pressure signal corresponding to the low pressure change trend as a low pressure signal.

2. The apparatus according to claim 1, characterized in that, The piezoelectric sensor (20) is connected to the host (50) via a connecting line built into the air tube (30). The piezoelectric sensor (20) includes a first piezoelectric piece and a second piezoelectric piece attached to the inner wall of the target of the air storage chamber (101). The inner wall of the target is the inner wall of the air storage chamber (101) near the inner side of the cuff (10).

3. The apparatus according to claim 1 or 2, characterized in that, The host (50) includes a preprocessing module, an intermediate processing module and a postprocessing module connected in sequence; The preprocessing module is used to perform time-frequency transformation processing on the first time-domain feature corresponding to the arterial pulsation extracted from the Korotkoff sound signal to obtain the frequency-domain feature, and to concatenate the frequency-domain feature with the second time-domain feature extracted from the Korotkoff sound signal to obtain the target data feature. The intermediate processing module is used to perform reasoning based on the target data features to predict the blood pressure category classification result corresponding to the Korotkoff sound signal; The post-processing module is used to determine the blood pressure measurement result based on the blood pressure category classification result and the pressure signal.

4. The apparatus according to claim 3, characterized in that, The preprocessing module includes a bandpass filtering unit, a signal extraction unit, a time-frequency transformation unit, a signal sampling unit, and a feature splicing unit; The bandpass filter unit is used to perform bandpass filtering on the pressure signal to obtain an oscillating wave signal that reflects the arterial pulsation. The signal extraction unit is used to extract the first time-domain feature corresponding to the arterial pulsation from the Korotkoff sound signal, taking the sampling time corresponding to the maximum value in the oscillation wave signal as the reference time point; The time-frequency transformation unit is used to perform time-frequency transformation processing on the first time-domain features to obtain frequency-domain features; The signal sampling unit is used to sample the Korotkoff tone signal to extract the second time-domain feature from the Korotkoff tone signal; The feature splicing unit is used to splice the frequency domain feature and the second time domain feature into the target data feature.

5. The apparatus according to claim 4, characterized in that, The signal extraction unit is used to determine the first preset number of first feature points before and after the reference time point extracted from the Korotkoff sound signal as the first time domain feature; The time-frequency transformation unit is used to determine the second preset number of second feature points obtained by performing time-frequency transformation on the first time-domain feature as the frequency-domain feature; The second preset quantity is less than the first preset quantity.

6. The apparatus according to claim 5, characterized in that, The signal sampling unit is used to determine a third feature point of a third preset number sampled from the Korotkoff tone signal as a second time-domain feature; wherein the third preset number is less than the first preset number, and the third preset number is the same as or different from the second preset number; The feature splicing unit is used to splice the third preset number of third feature points and the second preset number of second feature points into the target data feature.

7. The apparatus according to claim 6, characterized in that, The intermediate processing module is a trained convolutional bidirectional long short-term memory neural network, which includes a convolutional neural network and a bidirectional long short-term memory network connected in sequence. The convolutional neural network is used to perform convolution operations on the target data features in order to extract spatial features from the target data features; The bidirectional long short-term memory network is used to output a fourth preset number of blood pressure category classification results based on the spatial features. The blood pressure category classification results include classification results between high and low blood pressure and classification results not between high and low blood pressure. The fourth preset number is the sum of the third preset number and the second preset number.

8. The apparatus according to claim 7, characterized in that, The bidirectional long short-term memory network includes a long short-term memory network layer and a fully connected layer connected in sequence; The long short-term memory network layer is used to extract contextual features from the spatial features; The fully connected layer is used to output the fourth preset number of blood pressure category classification results based on the context features.

9. The apparatus according to claim 7, characterized in that, The post-processing module is used to determine the pressure signal corresponding to the first blood pressure category classification result between high and low pressure as a high pressure signal, and to determine the pressure signal corresponding to the last blood pressure category classification result between high and low pressure as a low pressure signal.

10. A method for measuring blood pressure, characterized in that, The method includes: The gas storage chamber (101) is equipped with a piezoelectric sensor (20) fixed inside the gas storage chamber (101) and a pressure signal collected by a pressure sensor (40). The gas storage chamber (101) is surrounded by a first cuff part (11) and a second cuff part (12) in a cuff (10). The first cuff part (11) and the second cuff part (12) are integrally formed or sealed together. The cuff (10) is provided with a nozzle (102) that communicates with the gas storage chamber (101). The nozzle (102) is used to connect to the first end of the air tube (30). The air tube (30) communicates with the gas storage chamber (101). The pressure sensor (40) is connected to the second end of the air tube (30). The pressure signal is used to characterize the internal air pressure of the gas storage chamber (101). Based on the Korotkoff sound signal and the pressure signal, the blood pressure measurement result is predicted; The step of predicting blood pressure measurement results based on the Korotkoff sound signal and the pressure signal includes: extracting target time-domain features corresponding to arterial pulsation from the Korotkoff sound signal based on the pressure signal, and determining the mean signal frequency and variance of the signal frequency corresponding to the target time-domain features; determining the signal change trend based on the mean signal frequency and the variance of the signal frequency, and determining the systolic and diastolic pressure change trends based on the signal change trends; the signal change trend is the change trend of the difference between the mean signal frequency and the variance of the signal frequency, or the change trend of the sum of the mean signal frequency and the variance of the signal frequency; the systolic pressure change trend refers to the change trend between the two adjacent target time-domain features where the first mean signal frequency and the variance of the signal frequency both change most significantly, and the diastolic pressure change trend refers to the change trend between the two adjacent target time-domain features where the last mean signal frequency and the variance of the signal frequency both change most significantly; determining the pressure signal corresponding to the systolic pressure change trend as the systolic pressure signal, and determining the pressure signal corresponding to the diastolic pressure change trend as the diastolic pressure signal.

11. The blood pressure measurement method according to claim 10, characterized in that, The prediction of blood pressure measurement results based on the Korotkoff sound signal and the pressure signal includes: The first time-domain feature corresponding to the arterial pulsation extracted from the Korotkoff sound signal is subjected to time-frequency transformation to obtain the frequency-domain feature; The frequency domain features are concatenated with the second time domain features extracted from the Korotkoff tone signal to obtain the target data features; Based on the target data features, inference is performed to predict the blood pressure category classification result corresponding to the Korotkoff sound signal; The blood pressure measurement result is determined based on the blood pressure category classification result and the pressure signal.

12. The blood pressure measurement method according to claim 11, characterized in that, The step of performing time-frequency transformation on the first time-domain feature corresponding to the arterial pulsation extracted from the Korotkoff sound signal to obtain the frequency-domain feature includes: The pressure signal is bandpass filtered to obtain an oscillating wave signal that reflects the arterial pulsation. Using the sampling time corresponding to the maximum value in the oscillation wave signal as a reference time point, the first time-domain feature corresponding to the arterial pulsation is extracted from the Korotkoff sound signal; The first time-domain feature is subjected to time-frequency transformation to obtain the frequency-domain feature.

13. The blood pressure measurement method according to claim 12, characterized in that, The step of concatenating the frequency domain features with the second time domain features extracted from the Korotkoff tone signal to obtain the target data features includes: The Korotkoff tone signal is sampled to extract the second time-domain feature from the Korotkoff tone signal; The frequency domain feature and the second time domain feature are concatenated to form the target data feature.

14. The blood pressure measurement method according to claim 13, characterized in that, The step of extracting the first time-domain feature corresponding to the arterial pulsation from the Korotkoff sound signal, using the sampling time corresponding to the maximum value in the oscillation wave signal as a reference time point, includes: determining a first preset number of first feature points before and after the reference time point extracted from the Korotkoff sound signal as the first time-domain feature. The step of performing time-frequency transformation processing on the first time-domain feature to obtain frequency-domain features includes: determining a second preset number of second feature points obtained after performing time-frequency transformation processing on the first time-domain feature as the frequency-domain feature; wherein the second preset number is less than the first preset number.

15. The blood pressure measurement method according to claim 14, characterized in that, The step of sampling the Korotkoff sound signal to extract the second time-domain feature from the Korotkoff sound signal includes: determining a third preset number of third feature points sampled from the Korotkoff sound signal as the second time-domain feature; wherein the third preset number is less than the first preset number, and the third preset number is the same as or different from the second preset number; The step of concatenating the frequency domain feature and the second time domain feature into the target data feature includes: concatenating the third preset number of third feature points and the second preset number of second feature points into the target data feature.

16. The blood pressure measurement method according to claim 15, characterized in that, The step of reasoning based on the target data features to predict the blood pressure category classification result corresponding to the Korotkoff sound signal includes: The target data features are convolved by the convolutional neural network in the trained bidirectional long short-term memory neural network to extract spatial features from the target data features. The bidirectional long short-term memory network in the convolutional bidirectional long short-term memory neural network, after training, outputs a fourth preset number of blood pressure category classification results based on the spatial features. The blood pressure category classification results include classification results between high and low blood pressure and classification results not between high and low blood pressure. The fourth preset number is the sum of the third preset number and the second preset number.

17. The blood pressure measurement method according to claim 16, characterized in that, The bidirectional long short-term memory network in the convolutional bidirectional long short-term memory neural network trained by the above outputs a fourth preset number of blood pressure category classification results based on the spatial features, including: Contextual features are extracted from the spatial features through the long short-term memory network layer in the bidirectional long short-term memory network; The fourth preset number of blood pressure category classification results are output through the fully connected layer in the bidirectional long short-term memory network based on the context features.

18. The blood pressure measurement method according to claim 16, characterized in that, The step of determining the blood pressure measurement result based on the blood pressure category classification result and the pressure signal includes: The pressure signal corresponding to the first blood pressure category classification result that falls between high and low pressure is determined as the high pressure signal, and the pressure signal corresponding to the last blood pressure category classification result that falls between high and low pressure is determined as the low pressure signal.

19. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the blood pressure measurement method according to any one of claims 10 to 18.

20. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the blood pressure measurement method according to any one of claims 10 to 18.

21. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the blood pressure measurement method according to any one of claims 10 to 18.

Images