Blood pressure measurement method and apparatus, blood pressure measurement device, and storage medium

Abstract

Embodiments of the present application relate to the field of wearable devices, and disclose a blood pressure measurement method and apparatus, a blood pressure measurement device, and a storage medium. The blood pressure measurement method comprises: in a measurement state, obtaining a pressure signal acquired by a pressure sensor, the pressure signal being used for characterizing the pressure corresponding to a plurality of sampling points in a blood pressure measurement process; extracting a first site pulse wave signal from the pressure signal, the first site pulse wave signal being used for characterizing a pulse wave amplitude corresponding to the sampling point; on the basis of the first site pulse wave signal, determining a signal correction amount of the pressure signal, the signal correction amount being used for characterizing a difference between the pressure signal measured by a wrist blood pressure measurement device and a pressure signal measured by a second blood pressure measurement device; performing correction on the pressure signal on the basis of the signal correction amount, to obtain a pressure correction signal; and determining a blood pressure measurement value on the basis of the pressure correction signal and the first site pulse wave signal. By using the method of the present application, the accuracy of blood pressure measurement can be improved.

Description

Blood pressure measurement method, device, blood pressure measurement equipment and storage medium Technical Field

[0001] The embodiments of the present application relate to the field of wearable devices, and in particular to a blood pressure measurement method, apparatus, blood pressure measurement device, and storage medium. Background Art

[0002] With the popularization of health electronic products, more and more users will choose to use wearable smart devices such as smart watches and smart bracelets to monitor physiological indicators such as heart rate, pulse, blood pressure, and use data to guide healthy living.

[0003] In related technologies, traditional upper-arm blood pressure monitors typically use the oscillometric coefficient method to measure blood pressure. During the inflation or deflation process, a pressure sensor measures the air pressure within the airbag to obtain raw data. This raw data is then processed to obtain pulse wave data. Blood pressure is estimated based on the relationship between the pulse wave amplitude and the air pressure within the airbag. The maximum pulse wave amplitude is typically assigned to mean arterial pressure (MAP), and systolic blood pressure (SBP) and diastolic blood pressure (DBP) are determined based on certain empirical coefficients.

[0004] Summary of the Invention

[0005] The present invention provides a blood pressure measurement method, apparatus, blood pressure measurement device, and storage medium. The technical solution is as follows:

[0006] In one aspect, an embodiment of the present application provides a blood pressure measurement method, which is used with a first blood pressure measurement device. The first blood pressure measurement device is worn at a first location to measure blood pressure. The first blood pressure measurement device includes a pressure sensor, an air pump, and an air bag. The pressure sensor is configured to measure the pressure of the air bag in a measurement state. In the measurement state, the air pump inflates the air bag so that the air bag presses against the wrist. The method includes:

[0007] In the measurement state, a pressure signal collected by the pressure sensor is obtained, wherein the pressure signal is used to represent the pressure corresponding to multiple sampling points during the blood pressure measurement process;

[0008] Extracting a first-site pulse wave signal from the pressure signal, where the first-site pulse wave signal is used to represent the pulse wave amplitude corresponding to the sampling point;

[0009] determining, based on the first-site pulse wave signal, a signal correction amount for the pressure signal, the signal correction amount being used to characterize a difference between the pressure signal measured by the first blood pressure measurement device and a pressure signal measured by a second blood pressure measurement device, the second blood pressure measurement device being worn at a second site for blood pressure measurement;

[0010] Correcting the pressure signal based on the signal correction amount to obtain a pressure correction signal;

[0011] A blood pressure measurement is determined based on the pressure-corrected signal and the first site pulse wave signal.

[0012] On the other hand, an embodiment of the present application provides a blood pressure measurement device, which is used for a first blood pressure measurement device. The first blood pressure measurement device is worn at a first location to measure blood pressure. The first blood pressure measurement device includes a pressure sensor, an air pump, and an air bag. The pressure sensor is used to measure the pressure of the air bag in a measurement state, and the air pump inflates the air bag in the measurement state so that the air bag presses the wrist. The device includes:

[0013] A signal acquisition module, configured to acquire a pressure signal collected by the pressure sensor in a measurement state, wherein the pressure signal is used to represent the pressure corresponding to multiple sampling points during the blood pressure measurement process;

[0014] a signal extraction module, configured to extract a first-site pulse wave signal from the pressure signal, wherein the first-site pulse wave signal is used to represent the pulse wave amplitude corresponding to the sampling point;

[0015] a correction prediction module, configured to determine a signal correction amount for the pressure signal based on the first-site pulse wave signal, the signal correction amount being used to characterize a difference between the pressure signal measured by the first blood pressure measurement device and a pressure signal measured by a second blood pressure measurement device, the second blood pressure measurement device being worn at a second site for blood pressure measurement;

[0016] a correction execution module, configured to correct the pressure signal based on the signal correction amount to obtain a pressure correction signal;

[0017] The blood pressure measurement module is used to determine a blood pressure measurement value based on the pressure correction signal and the first part pulse wave signal.

[0018] On the other hand, an embodiment of the present application provides a blood pressure measuring device, which includes a pressure sensor, an air pump, an airbag, a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement the method described in the above aspect.

[0019] On the other hand, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and the instruction is loaded and executed by a processor to implement the method described in the above aspects.

[0020] In another aspect, an embodiment of the present application provides a computer program product, comprising computer instructions stored in a computer-readable storage medium. A processor of a terminal reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the terminal to perform the methods provided in various optional implementations of the above aspects.

[0021] In an embodiment of the present application, a signal correction amount of the pressure signal is determined based on the pulse wave signal of the first part, the pressure signal is corrected based on the signal correction amount to obtain a pressure correction signal, and the blood pressure measurement value is determined based on the pressure correction signal and the pulse wave signal of the first part. This can eliminate errors caused by factors such as the air bag width of the first blood pressure measuring device and the differences in the physiological structures of the first and second parts, thereby improving the accuracy of blood pressure measurement based on the first blood pressure measuring device. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] FIG1 is a flow chart of a blood pressure measurement method provided by an exemplary embodiment of the present application;

[0024] FIG2 is a schematic diagram of extracting a first-site pulse wave signal from a pressure signal according to an exemplary embodiment of the present application;

[0025] FIG3 is a schematic diagram showing a deviation of a pressure signal collected by a pressure sensor according to an exemplary embodiment of the present application;

[0026] FIG4 is a schematic diagram of determining a pressure correction signal and a blood pressure measurement value provided by an exemplary embodiment of the present application;

[0027] FIG5 is a schematic diagram of determining a signal correction amount provided by an exemplary embodiment of the present application;

[0028] FIG6 is a flow chart of a blood pressure measurement method provided by another exemplary embodiment of the present application;

[0029] FIG7 is a schematic diagram of the external structure and internal structure of a first blood pressure measurement device provided by an exemplary embodiment of the present application;

[0030] FIG8 is a structural block diagram of a blood pressure measurement device provided by an exemplary embodiment of the present application;

[0031] FIG9 is a schematic structural diagram of a first blood pressure measurement device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0033] To measure blood pressure, the related art generally uses an air bag and a pressure sensor in an upper arm blood pressure measuring device (eg, an upper arm electronic blood pressure monitor) to detect arterial blood pressure and display the result on a screen.

[0034] Upper-arm blood pressure measurement devices typically use the oscillometric coefficient method to measure blood pressure. During balloon inflation and deflation, the balloon compresses the upper arm, and a pressure sensor measures the pressure within the balloon to generate a raw signal. This raw signal is then processed to generate a pulse wave signal, which is then used to estimate blood pressure based on the relationship between the pulse wave amplitude and the pressure within the balloon. The maximum pulse wave amplitude is typically assigned to mean arterial pressure (MAP), and systolic blood pressure (SBP) and diastolic blood pressure (DBP) are determined based on certain empirical coefficients.

[0035] In order to improve the portability of blood pressure measuring equipment, related technologies also use wrist blood pressure measuring equipment or first blood pressure measuring equipment (such as smart watches, smart bracelets, etc.) to measure blood pressure.

[0036] However, due to the different physiological structures of the wrist and upper arm, as well as the narrow width of the airbag in wrist blood pressure measurement equipment, if the traditional oscillometric coefficient method is still used to measure blood pressure through wrist blood pressure measurement equipment, the measurement results will be subject to large errors.

[0037] Therefore, an embodiment of the present application provides a blood pressure measurement method, which is used for a first blood pressure measuring device. Based on the pulse wave signal of the first part, the signal correction amount of the pressure signal is determined, and the pressure signal is corrected based on the signal correction amount to obtain a pressure correction signal. Then, based on the pressure correction signal and the pulse wave signal of the first part, the blood pressure measurement value is determined, which can improve the accuracy of blood pressure measurement.

[0038] Refer to FIG1 , which is a flow chart of a blood pressure measurement method provided by an exemplary embodiment of the present application. The flow chart includes the following steps.

[0039] Step 101: Under the measurement state, a pressure signal collected by a pressure sensor is obtained. The pressure signal is used to represent the pressure corresponding to multiple sampling points during the blood pressure measurement process.

[0040] The measurement state refers to a state in which the first blood pressure measurement device performs blood pressure measurement.

[0041] During measurement, the user wears a blood pressure measurement device (such as a smart bracelet) on their wrist, stretches their wrist and palm naturally to keep the smart bracelet level with their heart, and supports their elbow with their other hand to maintain a stable measurement posture. During measurement, the user's feet should be flat and uncrossed, and they should remain quiet and avoid talking to minimize disruption to the measurement process.

[0042] The first blood pressure measurement device is worn at a first location to measure blood pressure.

[0043] In some embodiments, the first part is the wrist, and the first blood pressure measurement device is a wrist blood pressure measurement device (e.g., a smart bracelet worn on the wrist). In some embodiments, the first part can also be other parts of the body, such as the ankle, etc., which is not limited in this embodiment of the present application.

[0044] It should be noted that the embodiment of the present application is described using the example of a smart bracelet worn on the wrist as the first blood pressure measuring device, but this is not limited to this. The first blood pressure measuring device can also include a blood pressure recorder, electronic blood pressure monitor, etc. worn on the first part. Such blood pressure measuring devices are all within the scope of protection of this application.

[0045] The first blood pressure measurement device includes a pressure sensor, an air pump, and an air bag, wherein the pressure sensor is configured to measure the pressure of the air bag in a measuring state, and the air pump is configured to inflate the air bag so that the air bag presses the wrist in the measuring state.

[0046] In some embodiments, the pressure of the airbag may include the pressure caused by the gas in the airbag and the pulse pressure formed by the airbag inflating and compressing the first site.

[0047] Optionally, the pressure sensor is a capacitive pressure sensor or a resistive pressure sensor.

[0048] Capacitive pressure sensors use air pressure to change the distance between the positive and negative electrodes of a capacitor, thereby altering its capacitance. This allows the accompanying oscillation circuit to generate an oscillation frequency that corresponds to the pressure. Resistive pressure sensors, composed of piezoresistors, change their resistance under the influence of air pressure, allowing the accompanying circuit to capture a signal that corresponds to the pressure.

[0049] Optionally, the pressure sensor may also be other types of pressure sensors, which is not limited in the embodiments of the present application.

[0050] Step 102: extracting a first-site pulse wave signal from the pressure signal. The first-site pulse wave signal is used to represent the pulse wave amplitude corresponding to the sampling point.

[0051] The first pulse wave signal is a signal collected at the wrist and generated as the heart beats propagate along the arteries and blood flow toward the periphery.

[0052] In some embodiments, the pressure signal collected by the pressure sensor may be baseline filtered to extract the first site pulse wave signal from the pressure signal.

[0053] Optionally, a straight line fitting may be performed on the pressure signal, and a baseline filtering may be performed on the pressure signal based on the fitted straight line. For example, the slope of the pressure signal may be restored to 0 based on the slope of the straight line.

[0054] Refer to FIG. 2 , which is a schematic diagram of extracting a first-site pulse wave signal from a pressure signal according to an exemplary embodiment of the present application.

[0055] As shown in Figure 2(a), the pressure sensor collects pressure data corresponding to 2000 sampling points.

[0056] In one possible implementation, the first blood pressure measurement device can perform linear fitting on the pressure data in Figure 2(a) to determine the slope of the fitting line, and then perform baseline filtering on the pressure data based on the slope to obtain an oscillation curve corresponding to the pulse wave signal of the first part as shown in Figure 2(b).

[0057] In another possible implementation, the first blood pressure measurement device may also use other filtering means to obtain the oscillation curve corresponding to the pulse wave signal of the first part.

[0058] Step 103: Determine a signal correction amount of the pressure signal based on the pulse wave signal at the first site. The signal correction amount is used to characterize the difference between the pressure signal measured by the first blood pressure measuring device and the pressure signal measured by the second blood pressure measuring device. The second blood pressure measuring device is worn at the second site to perform blood pressure measurement.

[0059] In some embodiments, the second part is the upper arm, and the second blood pressure measuring device is an upper arm blood pressure measuring device. In some embodiments, the second part can also be other parts of the body, such as the ankle, etc., which is not limited in this embodiment of the present application.

[0060] It should be noted that the second part can refer to a part of the human body, and is not necessarily the first and second parts of the same user. It can be the second parts of other users, for example, by previously collecting pressure signals corresponding to the second parts of a large number of people to obtain relevant data. Of course, in some embodiments, the first and second parts of the same user can also be collected.

[0061] The second blood pressure measuring device is a device worn at a second location and uses an oscillometric method to measure blood pressure, such as an upper arm electronic blood pressure monitor.

[0062] In some embodiments, because the airbag width of the first blood pressure measurement device is narrower than that of the second blood pressure measurement device, the compression efficiency of the airbag is low, which is reflected in the impact on the pressure signal and affects the accuracy of the pressure signal collected by the pressure sensor. At the same time, due to the different physiological structures of the first and second parts (such as the wrist and upper arm), there may also be differences between the pressure signal measured by the first blood pressure measurement device and the pressure signal measured by the second blood pressure measurement device. For example, the pressure signal collected by the pressure sensor may be offset to a certain extent.

[0063] Referring to FIG. 3 , FIG. 3 is a schematic diagram showing an offset of a pressure signal collected by a pressure sensor provided by an exemplary embodiment of the present application.

[0064] As shown in Figure 3, curve S31 is the fitting curve corresponding to the pressure signal measured by the wrist blood pressure measurement device, and curve S32 is the fitting curve corresponding to the pressure signal measured by the upper arm blood pressure measurement device. It can be seen that there is a certain degree of offset between the pressure signals corresponding to curve S31 and curve S32.

[0065] In one possible scenario, the offset between curve S31 and curve S32 is manifested as a difference in slope between curve S31 and curve S32. In other possible scenarios, the offset between curve S31 and curve S32 may also be manifested as a difference in intercept, or a difference in curve shape, etc.

[0066] The signal correction amount refers to the correction amount required to correct the pressure signal measured by the first blood pressure measurement device to the pressure signal measured by the second blood pressure measurement device.

[0067] Optionally, the signal correction amount may include a slope correction amount, an intercept correction amount, or other types of correction amounts.

[0068] In some embodiments, the pulse wave feature corresponding to the pulse wave signal at the first site may be extracted based on the pulse wave signal at the first site, and the signal correction amount of the pressure signal may be predicted based on the pulse wave feature.

[0069] Regarding the specific method of determining the signal correction amount of the pressure signal based on the pulse wave signal of the first part, please refer to Figure 5 and its related description, which will not be repeated here.

[0070] Step 104 : Correct the pressure signal based on the signal correction amount to obtain a pressure correction signal.

[0071] In some embodiments, when the signal correction amount is a slope correction amount, the slope of the fitting straight line of the pressure signal can be corrected to obtain a pressure correction signal.

[0072] As shown in FIG3 , the slope of the curve S31 corresponding to the pressure signal obtained by the first blood pressure measurement device may be corrected to obtain a curve S32 .

[0073] In some embodiments, when the signal correction amount is an intercept correction amount, the intercept of the fitting line of the pressure signal may also be corrected.

[0074] Step 105: Determine a blood pressure measurement value based on the pressure correction signal and the first site pulse wave signal.

[0075] Optionally, the blood pressure measurement value includes at least one of a mean arterial pressure measurement value, a systolic pressure measurement value, and a diastolic pressure measurement value.

[0076] For the specific method of determining the mean arterial pressure measurement value, the systolic pressure measurement value and the diastolic pressure measurement value, please refer to Figure 4 and its related description, which will not be repeated here.

[0077] To summarize, in the embodiment of the present application, the signal correction amount of the pressure signal is determined based on the pulse wave signal of the first part, the pressure signal is corrected based on the signal correction amount to obtain a pressure correction signal, and the blood pressure measurement value is determined based on the pressure correction signal and the pulse wave signal of the first part. This can eliminate the deviation of the pressure signal caused by factors such as the air bag width of the first blood pressure measuring device and the differences in the physiological structures of the wrist and upper arm, thereby improving the accuracy of blood pressure measurement based on the first blood pressure measuring device.

[0078] In some embodiments, the signal correction value corresponding to the pressure signal is a slope correction value.

[0079] In some embodiments, the signal correction amount is the difference between the slopes of a first fitted straight line and a second fitted straight line, where the first fitted straight line is a fitted straight line corresponding to the pressure signal measured by the second blood pressure measurement device, and the second fitted straight line is a fitted straight line corresponding to the pressure signal measured by the first blood pressure measurement device.

[0080] In some embodiments, the first blood pressure measurement device performs linear fitting on the pressure signal to obtain a second fitting straight line, and determines the first fitting straight line based on the signal correction amount and the second fitting straight line.

[0081] Refer to FIG4 , which is a schematic diagram of determining a pressure correction signal and a blood pressure measurement value provided by an exemplary embodiment of the present application.

[0082] As shown in FIG4( a ), the first blood pressure measurement device performs linear fitting on the pressure data collected by the pressure sensor to obtain a second fitting straight line S41 , wherein the slope of the second fitting straight line S41 is k1 , and the equation of the second fitting straight line S41 is y=k1*x+b.

[0083] In some embodiments, the first blood pressure measurement device may perform feature extraction on the pulse wave signal at the first site to obtain pulse wave features, and predict a signal correction amount corresponding to the pressure data based on the pulse wave features.

[0084] For example, assuming that the predicted signal correction amount is the slope correction amount kb, the equation of the first fitting line S42 obtained by correcting the second fitting line S41 based on the slope correction amount kb is yb=(k1+kb)*x+b, where k1+kb=k2.

[0085] In some embodiments, a pressure correction signal can be determined based on the first fitted line S42 and the pressure signal. For example, the pressure signal can be corrected based on the slope k2 of the first fitted line S42 to obtain the pressure correction signal. In some embodiments, the first fitted line S42 can also be used as the pressure correction signal.

[0086] After the pressure correction signal is determined, at least one of a mean arterial pressure measurement value, a systolic pressure measurement value, and a diastolic pressure measurement value may be determined based on the pressure correction signal and the first site pulse wave signal.

[0087] In some embodiments, the first blood pressure measurement device may determine a pulse wave envelope of the first site pulse wave signal.

[0088] As shown in FIG4( b ), the difference between the upper envelope curve and the lower envelope curve of the pulse wave signal at the first site may be determined as the pulse wave envelope.

[0089] In some embodiments, the first blood pressure measurement device determines the sampling point corresponding to the highest amplitude in the pulse wave envelope as the highest sampling point. For example, in FIG4(b), approximately the 1900th sampling point corresponds to the highest amplitude Am, and thus the highest sampling point is the 1900th sampling point.

[0090] In some embodiments, the first blood pressure measurement device determines a first amplitude in the positive envelope of the pulse wave based on the highest amplitude and the systolic pressure coefficient, and determines a second amplitude in the positive envelope of the pulse wave based on the highest amplitude and the diastolic pressure coefficient.

[0091] The systolic pressure coefficient is the coefficient used to determine the systolic pressure measurement value, recorded as Ks; the diastolic pressure coefficient is the coefficient used to determine the diastolic pressure measurement value, recorded as Kd.

[0092] Exemplarily, the maximum amplitude is Am, then the first amplitude is the product of the maximum amplitude and the systolic pressure coefficient Am*Ks; the second amplitude is the product of the maximum amplitude and the diastolic pressure coefficient Am*Kd.

[0093] In some embodiments, the systolic and diastolic coefficients are fixed values. For example, the systolic coefficient is 0.55 and the diastolic coefficient is 0.45. Alternatively, the systolic and diastolic coefficients can be determined based on empirical values ​​or by fitting multiple samples.

[0094] In other embodiments, the systolic pressure coefficient and the diastolic pressure coefficient are not fixed values, and different systolic pressure coefficients and diastolic pressure coefficients can be determined based on different pulse wave characteristics.

[0095] Regarding how to determine the systolic and diastolic pressure coefficients, please refer to the relevant instructions below and will not be repeated here.

[0096] In some embodiments, the first blood pressure measurement device can determine the mean arterial pressure measurement value based on the pressure corresponding to the highest sampling point in the pressure-corrected signal. For example, in FIG4 , the highest sampling point is the 1900th sampling point, and the pressure corresponding to the first fitted line S42 is 85.55 mmHg. Therefore, the mean arterial pressure measurement value is 85.55 mmHg.

[0097] In some embodiments, the first blood pressure measurement device can determine a systolic pressure measurement value based on the pressure at the sampling point corresponding to the first amplitude in the pressure-corrected signal; and determine a diastolic pressure measurement value based on the pressure at the sampling point corresponding to the second amplitude. For example, if the sampling point corresponding to the first amplitude Am*Ks in FIG4 is approximately the 2300th sampling point, the pressure at the first fitting line S42 corresponding to the 2300th sampling point can be used as the systolic pressure measurement value; if the sampling point corresponding to the second amplitude Am*Kd is approximately the 1700th sampling point, the pressure at the first fitting line S42 corresponding to the 1700th sampling point can be used as the systolic pressure measurement value.

[0098] For example, assuming that the oscillometric coefficient method is represented by function F, the first-part pulse wave signal extracted from the pressure signal is S, and the pressure correction signal is yb, the calculation formula for the systolic pressure measurement value can be expressed as: SBP=F(Ks, S, yb), and the calculation formula for the diastolic pressure measurement value can be expressed as: DBP=F(Kd, S, yb).

[0099] In order to predict the signal correction amount corresponding to the pressure signal, in some embodiments, the first blood pressure measurement device can extract the pulse wave characteristics of the pulse wave signal of the first part, and input the pulse wave characteristics into the signal correction amount prediction model to obtain the signal correction amount output by the signal correction amount prediction model.

[0100] The pulse wave feature is used to characterize at least one of the morphological information, time domain information and frequency domain information of the pulse wave signal of the first part.

[0101] Regarding the method of extracting the pulse wave feature of the first site pulse wave signal, at least one of the following methods may be included.

[0102] (1) Extract features from the pulse wave signal of the first part.

[0103] Exemplarily, the characteristics of the first-part pulse wave signal itself may include the number of sampling points, the number of pulse waves, the pulse wave amplitude, the pulse wave frequency, the first-order derivative of the curve, the second-order derivative of the curve, the area under the curve... and other characteristics directly extracted from the first-part pulse wave signal.

[0104] (2) performing signal conversion on the pulse wave signal of the first part to obtain a converted signal, and then performing feature extraction on the converted signal to obtain features.

[0105] Exemplarily, the signal conversion may be one or more of time domain conversion, frequency domain conversion, or other mathematical conversions.

[0106] Optionally, signal conversion includes but is not limited to Fourier transform, Laplace transform, Z transform, etc.

[0107] Optionally, the conversion signal may include features such as time domain information and frequency domain information.

[0108] (3) Envelope extraction is performed on the pulse wave signal of the first part to obtain a pulse wave envelope, and then feature extraction is performed on the pulse wave envelope to obtain features.

[0109] Optionally, the pulse wave envelope is the difference between an upper envelope curve and a lower envelope curve of the pulse wave signal at the first part.

[0110] Optionally, the features obtained by extracting features from the pulse wave envelope include features reflecting morphological information, such as amplitude features and frequency features of the pulse wave envelope.

[0111] (4) Extracting features from the pressure signal corresponding to the pulse wave signal at the first site.

[0112] Exemplarily, the pressure signal corresponding to each sampling point may also be used as a pulse wave feature.

[0113] In addition to the above methods, those skilled in the art will appreciate that pulse wave features can also be extracted based on other factors related to the pulse wave signal at the first site, and the embodiments of the present application are not limited thereto.

[0114] Refer to FIG. 5 , which is a schematic diagram of determining a signal correction amount provided by an exemplary embodiment of the present application.

[0115] As shown in FIG5 , the first blood pressure measurement device may perform feature extraction on the first site pulse wave signal 501 to obtain a pulse wave feature 520 .

[0116] Among them, feature extraction includes extracting the characteristics of the first-part pulse wave signal 501 itself, or extracting the characteristics of the converted signal 511 obtained by signal conversion of the first-part pulse wave signal 501, or extracting the characteristics of the pulse wave envelope 512 obtained by envelope extraction of the first-part pulse wave signal 501.

[0117] In some embodiments, the server may obtain multiple groups of samples and divide the data sets into a training set 531 and a test set 532 to train and evaluate the signal correction amount prediction model 540 .

[0118] In some embodiments, the pulse wave feature 520 may be input into the signal correction amount prediction model 540 to obtain a signal correction amount corresponding to the pressure signal.

[0119] In some embodiments, the signal correction amount prediction model 540 is deployed in the first blood pressure measurement device, and the first blood pressure measurement device can directly input the pulse wave feature 520 into the signal correction amount prediction model 540 to obtain the signal offset 550.

[0120] In other embodiments, the signal correction amount prediction model 540 is deployed in a server corresponding to the first blood pressure measurement device, and the first blood pressure measurement device can send a prediction request to the server, wherein the prediction request carries the pulse wave feature 520, so that the server inputs the pulse wave feature 520 into the signal correction amount prediction model 540 and returns the output signal correction amount 550 to the first blood pressure measurement device.

[0121] The signal correction amount prediction model 540 may be a machine learning model trained based on a server or other devices.

[0122] Regarding the training process of the signal correction amount prediction model, in some embodiments, the signal correction amount prediction model is obtained by the server extracting the sample first-part pulse wave signal from the sample pressure signal, performing feature extraction on the sample first-part pulse wave signal to obtain the sample pulse wave feature, inputting the sample pulse wave feature into the signal correction amount prediction model to obtain the predicted correction amount, and using the correction amount gold standard as the supervision of the predicted correction amount to train the signal correction amount prediction model.

[0123] The correction amount gold standard is determined based on the pressure signal of the second part of the sample and the sample pressure signal, and the pressure signal of the second part of the sample is measured by a second blood pressure measurement device.

[0124] For example, the sample wrist pressure signals corresponding to multiple groups of samples can be obtained through the first blood pressure measurement device, and the corresponding sample second-part pressure signals can be obtained through the second blood pressure measurement device, and the correction amount gold standard can be determined based on the difference between the sample wrist pressure signals and the sample second-part pressure signals.

[0125] For example, the correction amount gold standard may be the slope correction amount kb.

[0126] In addition to predicting the signal correction amount through the signal correction amount prediction model, prediction can also be performed based on other methods (such as fitting functions, etc.).

[0127] In some embodiments, the first blood pressure measurement device can extract the pulse wave characteristics of the pulse wave signal at the first part, wherein the pulse wave characteristics are used to characterize at least one of the morphological information, time domain information and frequency domain information of the pulse wave signal at the first part, and based on the pulse wave characteristics, determine the signal correction amount through a fitting function.

[0128] In some embodiments, the fitting function may include at least one of a linear fitting function, a polynomial fitting function, and an exponential fitting function.

[0129] Since the signal correction amount of the pressure signal is also related to the physiological structure of the wrist, for different users, the signal correction amount prediction model can be fine-tuned based on the signal correction amount prediction model and combined with the user's sample pressure signal, so that the signal correction amount prediction model can better predict the user himself, thereby obtaining more accurate signal correction amount prediction results.

[0130] In some embodiments, the user may obtain a local upper arm pressure signal through an upper arm blood pressure measurement device and a local wrist pressure signal through a first blood pressure measurement device within a target time period.

[0131] Optionally, the target duration is a fixed shorter time value, such as 2 minutes.

[0132] In some embodiments, the first blood pressure measurement device may determine a local correction gold standard based on the local wrist pressure signal and the local upper arm pressure signal, and extract a local first-site pulse wave signal from the local wrist pressure signal.

[0133] In some embodiments, the first blood pressure measurement device can report a model fine-tuning request including the local first-site pulse wave signal and the local correction amount gold standard to the server, so that the server can fine-tune the model parameters of the signal correction amount prediction model based on the local first-site pulse wave signal and the local correction amount gold standard.

[0134] In some embodiments, the first blood pressure measurement device receives the updated signal correction amount prediction model sent by the server, and uses the updated signal correction amount prediction model to predict the signal correction amount of the pressure signal during subsequent blood pressure measurement of the user.

[0135] In this embodiment, the signal correction amount prediction model is fine-tuned through the local first-part pulse wave signal and the local correction amount gold standard, so that the model's prediction results can be more targeted to the user of the first blood pressure measurement device, thereby making the signal correction amount prediction more accurate and further improving the accuracy of the blood pressure measurement value.

[0136] Regarding the method for determining the systolic pressure coefficient and the diastolic pressure coefficient, in one possible implementation, they can be obtained by performing an average fitting based on multiple samples. In this case, the systolic pressure coefficient and the diastolic pressure coefficient are fixed values.

[0137] In some embodiments, the server may obtain pressure signals and pulse wave signals corresponding to multiple groups of samples in advance through a first blood pressure measurement device, and obtain corresponding systolic pressure gold standard and diastolic pressure gold standard through an upper arm blood pressure measurement device.

[0138] Optionally, the systolic blood pressure gold standard and the diastolic blood pressure gold standard may also be obtained based on invasive blood pressure measurement equipment.

[0139] The server uses the sampling point corresponding to the systolic pressure gold standard in the pressure signal as the systolic pressure sampling point, and uses the sampling point corresponding to the diastolic pressure gold standard in the pressure signal as the diastolic pressure sampling point.

[0140] The server determines the amplitude corresponding to the systolic pressure sampling point in the pulse wave envelope as the first sample amplitude, and determines the amplitude corresponding to the diastolic pressure sampling point in the pulse wave envelope as the second sample amplitude.

[0141] The server can calculate the average of the ratios of the first amplitudes of multiple samples corresponding to multiple groups of samples to the multiple highest amplitudes as the systolic pressure coefficient; and calculate the average of the ratios of the second amplitudes of multiple samples corresponding to multiple groups of samples to the multiple highest amplitudes as the diastolic pressure coefficient.

[0142] In this embodiment, by performing average fitting on multiple samples, the appropriate systolic pressure coefficient and diastolic pressure coefficient can be determined for the first blood pressure measurement device, thereby improving the accuracy of the blood pressure measurement value.

[0143] However, for different users, the appropriate systolic and diastolic blood pressure coefficients may be different. Even for the same user, the appropriate systolic and diastolic blood pressure coefficients may be different when measured at different time points.

[0144] Therefore, in some embodiments, the systolic pressure coefficient and the diastolic pressure coefficient may also be predicted based on the pulse wave characteristics of the pulse wave signal obtained in each measurement.

[0145] Referring to Figure 6, Figure 6 is a flow chart of a blood pressure measurement method provided by another exemplary embodiment of the present application. The flow chart includes the following steps.

[0146] Step 601: extracting a first-site pulse wave signal from a pressure signal.

[0147] Exemplarily, assuming there are n sampling points in total, the first-site pulse wave signal S is extracted from the pressure signal and recorded as: S={x1, x2, . . . , xn}.

[0148] Step 602: Extract pulse wave features.

[0149] For example, assuming that the dimension of the pulse wave feature is m, the pulse wave feature f → Denoted as: f → ={f_1,f_2,f_3,...,f_m}.

[0150] Step 603: Determine the signal correction amount of the pressure signal through the signal correction amount prediction model.

[0151] In some embodiments, the signal correction amount prediction model is deployed in the first blood pressure measurement device, and the first blood pressure measurement device inputs the pulse wave characteristics into the signal correction amount prediction model to obtain an output signal correction amount.

[0152] In some embodiments, the signal correction amount prediction model is deployed in the server, and the first blood pressure measurement device sends a correction prediction request to the server, so that the server inputs the pulse wave characteristics into the signal correction amount prediction model, obtains the output signal correction amount, and returns it to the first blood pressure measurement device.

[0153] For example, assuming that the signal correction amount prediction model is h, the signal correction amount kb can be expressed as: kb = h(f → ).

[0154] Step 604: Determine the systolic pressure coefficient and the diastolic pressure coefficient through the coefficient prediction model.

[0155] In some embodiments, the first blood pressure measurement device determines the pulse wave characteristics based on the pulse wave signal at the first site, and inputs the pulse wave characteristics into a coefficient prediction model to obtain the systolic pressure coefficient and the diastolic pressure coefficient.

[0156] The pulse wave feature is used to characterize at least one of the morphological information, time domain information, and frequency domain information of the pulse wave signal of the first part.

[0157] In some embodiments, the coefficient prediction model is deployed in the first blood pressure measurement device, and the first blood pressure measurement device inputs the pulse wave characteristics into the coefficient prediction model to obtain output systolic pressure coefficient and diastolic pressure coefficient.

[0158] In some embodiments, the coefficient prediction model is deployed in a server, and the first blood pressure measurement device sends a coefficient prediction request to the server, so that the server inputs the pulse wave characteristics into the coefficient prediction model, obtains the output systolic pressure coefficient and diastolic pressure coefficient, and returns them to the first blood pressure measurement device.

[0159] In some embodiments, the coefficient prediction model is performed by the server to extract the sample first-part pulse wave signal from the sample pressure signal, perform feature extraction on the sample first-part pulse wave signal to obtain the sample pulse wave feature, input the sample pulse wave feature into the coefficient prediction model to obtain the predicted systolic pressure coefficient and the predicted diastolic pressure coefficient, and use the systolic pressure coefficient gold standard and the diastolic pressure coefficient gold standard as supervision respectively to train the coefficient prediction model.

[0160] The systolic pressure coefficient gold standard and the diastolic pressure coefficient gold standard are determined based on the sample second site pressure signal and the sample pressure signal, and the sample second site pressure signal is measured by a second blood pressure measurement device.

[0161] For example, the first blood pressure measurement device can be used to obtain the sample first-part pulse wave signals and pulse wave envelopes corresponding to multiple groups of samples, and the second blood pressure measurement device can be used to obtain the corresponding sample upper arm pulse wave signals, and the systolic pressure gold standard and diastolic pressure gold standard can be determined from the sample upper arm pulse wave signals.

[0162] Optionally, the systolic blood pressure gold standard and the diastolic blood pressure gold standard may also be obtained based on invasive blood pressure measurement equipment.

[0163] The server can determine the systolic pressure coefficient gold standard based on the ratio between the amplitude of the pulse wave envelope at the sampling time point corresponding to the systolic pressure gold standard and the highest amplitude in the pulse wave envelope; and determine the diastolic pressure coefficient gold standard based on the ratio between the amplitude of the pulse wave envelope at the sampling time point corresponding to the diastolic pressure gold standard and the highest amplitude in the pulse wave envelope.

[0164] For example, if the amplitude of the pulse wave envelope at the sampling time point corresponding to the systolic pressure gold standard is 3, the amplitude of the pulse wave envelope at the sampling time point corresponding to the diastolic pressure gold standard is 2, and the highest amplitude in the pulse wave envelope is 4, then the systolic pressure coefficient gold standard is 0.75, and the diastolic pressure coefficient gold standard is 0.5.

[0165] In addition to predicting the systolic pressure coefficient and the diastolic pressure coefficient through the coefficient prediction model, prediction can also be made based on other methods (such as fitting functions, etc.).

[0166] In some embodiments, the first blood pressure measurement device may extract a pulse wave feature of the pulse wave signal at the first site, and determine a signal offset by a fitting function based on the pulse wave feature.

[0167] In some embodiments, the fitting function may include at least one of a linear fitting function, a polynomial fitting function, and an exponential fitting function.

[0168] For example, the systolic pressure coefficient is recorded as Ks, and the diastolic pressure coefficient is recorded as Kd.

[0169] Step 605: Determine a pressure correction signal based on the signal correction amount.

[0170] For example, assuming that the signal correction amount is the slope correction amount kb, and the fitting straight line equation corresponding to the pressure signal is y=k1*x+b, then the fitting straight line equation corresponding to the pressure correction signal is yb=(k1+kb)*x+b.

[0171] Step 606: Determine a blood pressure measurement value based on the pressure correction signal and the first site pulse wave signal.

[0172] For example, assuming that the oscillometric method is represented by a function F, the systolic pressure measurement value and the diastolic pressure measurement value can be expressed as: SBP=F(Ks, S, yb); DBP=F(Kd, S, yb).

[0173] In this embodiment, the systolic pressure coefficient and the diastolic pressure coefficient are predicted based on the pulse wave characteristics through a coefficient prediction model or a fitting function. This can achieve the prediction of different systolic pressure coefficients and diastolic pressure coefficients based on the pulse wave characteristics in each measurement, rather than using a unified fixed coefficient for blood pressure estimation. Therefore, the measurement of systolic pressure and diastolic pressure can be more accurate, thereby improving the measurement quality of the first blood pressure measurement device.

[0174] Referring to FIG. 7 , FIG. 7 is a schematic diagram of the external structure and internal structure of a first blood pressure measurement device provided by an exemplary embodiment of the present application.

[0175] As shown in FIG. 7( a ), the external structure of the first blood pressure measurement device includes a wristband 710 , a measurement body 720 , and an air bag 730 .

[0176] The wristband 710 is used to fix the first blood pressure measurement device on the wrist, the measurement body 720 is used to measure blood pressure, and the airbag 730 is used to compress the wrist in the measurement state.

[0177] As shown in FIG. 7( b ), in the internal structure of the first blood pressure measurement device, a measurement body 720 includes an air pump 721 , a pressure sensor 722 , a storage device 723 , and an air path 724 .

[0178] The air pump 721 is used to inflate the airbag 730 via the air path 724 during measurement so that the airbag 730 compresses the wrist. The pressure sensor 722 is used to collect pressure signals via the air path 724 during blood pressure measurement. The storage device 723 is used to store the pressure signals collected by the pressure sensor 722.

[0179] Optionally, the pressure sensor 722 is a capacitive pressure sensor or a resistive pressure sensor, or other types of pressure sensors, which is not limited in the embodiment of the present application.

[0180] In some embodiments, during measurement, air pump 721 inflates airbag 730 to compress the wrist. Pressure sensor 722 collects a pressure signal via air path 724, and storage device 723 stores the pressure signal. In some embodiments, the first blood pressure measurement device can extract a first-site pulse wave signal from the pressure signal and, based on the pulse wave characteristics of the first-site pulse wave signal, predict a signal correction amount for the pressure signal to determine a more accurate blood pressure measurement value.

[0181] It should be noted that the above embodiment only describes the general structure of the first blood pressure measurement device. This structure may include more or fewer components, or combinations of certain components, and this embodiment does not limit this. For example, the first blood pressure measurement device may also include a chip for controlling a blood pressure measurement algorithm, a display for displaying blood pressure measurement results, and so on. Such structures are all within the scope of protection of this application.

[0182] Referring to FIG8 , FIG8 is a block diagram of a blood pressure measurement device provided by an exemplary embodiment of the present application. The device is used for a first blood pressure measurement device, which is worn at a first location to measure blood pressure. The first blood pressure measurement device includes a pressure sensor, an air pump, and an air bag. The pressure sensor is used to measure the pressure of the air bag during measurement, and the air pump inflates the air bag to compress the wrist during measurement. The device includes:

[0183] The signal acquisition module 801 is used to acquire the pressure signal collected by the pressure sensor in the measurement state, wherein the pressure signal is used to represent the pressure corresponding to multiple sampling points during the blood pressure measurement process;

[0184] A signal extraction module 802 is configured to extract a first-site pulse wave signal from the pressure signal, wherein the first-site pulse wave signal is used to represent the pulse wave amplitude corresponding to the sampling point;

[0185] a correction prediction module 803 for determining, based on the first-site pulse wave signal, a signal correction amount for the pressure signal, the signal correction amount being used to represent a difference between the pressure signal measured by the first blood pressure measurement device and a pressure signal measured by a second blood pressure measurement device, the second blood pressure measurement device being worn at a second site for blood pressure measurement;

[0186] a correction execution module 804, configured to correct the pressure signal based on the signal correction amount to obtain a pressure correction signal;

[0187] The blood pressure measurement module 805 is configured to determine a blood pressure measurement value based on the pressure correction signal and the first-site pulse wave signal.

[0188] Optionally, the modified prediction module 803 is configured to:

[0189] extracting a pulse wave feature of the pulse wave signal at the first site, wherein the pulse wave feature is used to characterize at least one of morphological information, time domain information, and frequency domain information of the pulse wave signal at the first site;

[0190] The pulse wave feature is input into a signal correction amount prediction model to obtain the signal correction amount output by the signal correction amount prediction model.

[0191] Optionally, the modified prediction module 803 is configured to:

[0192] Determining a pulse wave envelope of the pulse wave signal at the first part; performing feature extraction on the pulse wave envelope to obtain the pulse wave feature;

[0193] Performing signal conversion on the pulse wave signal of the first part to obtain a converted signal, wherein the signal conversion method includes at least one of time domain conversion and frequency domain conversion; performing feature extraction on the converted signal to obtain the pulse wave feature.

[0194] Optionally, the signal correction amount prediction model is obtained by extracting a sample first-site pulse wave signal from a sample pressure signal by a server, performing feature extraction on the sample first-site pulse wave signal to obtain a sample pulse wave feature, inputting the sample pulse wave feature into the signal correction amount prediction model to obtain a predicted correction amount, and training the signal correction amount prediction model using a correction amount gold standard as supervision of the predicted correction amount;

[0195] The correction amount gold standard is determined based on the pressure signal of the second part of the sample and the sample pressure signal, and the pressure signal of the second part of the sample is measured by a second blood pressure measurement device.

[0196] Optionally, the device further includes a model fine-tuning module, configured to:

[0197] Obtaining a local first-site pulse wave signal and a local correction gold standard, the local correction gold standard being determined based on a local upper arm pressure signal and a local wrist pressure signal, the local upper arm pressure signal and the local wrist pressure signal being measured sequentially within a target duration;

[0198] Reporting a model fine-tuning request including the local first-site pulse wave signal and the local correction amount gold standard to the server, so that the server fine-tunes model parameters of the signal correction amount prediction model based on the local first-site pulse wave signal and the local correction amount gold standard;

[0199] Receive the updated signal correction amount prediction model sent by the server.

[0200] Optionally, the modification execution module 804 is configured to:

[0201] Performing a linear fit on the pressure signal to obtain a second fitting straight line;

[0202] determining the first fitting straight line based on the signal correction amount and the second fitting straight line;

[0203] The pressure correction signal is determined based on the first fitting straight line and the pressure signal.

[0204] Optionally, the blood pressure measurement module 805 is used to:

[0205] determining a pulse wave envelope of the pulse wave signal at the first site;

[0206] Determining the sampling point corresponding to the highest amplitude in the pulse wave envelope as the highest sampling point;

[0207] determining a first amplitude in the positive envelope of the pulse wave based on the highest amplitude and a systolic pressure coefficient, and determining a second amplitude in the positive envelope of the pulse wave based on the highest amplitude and a diastolic pressure coefficient;

[0208] determining a mean arterial pressure measurement value based on the pressure corresponding to the highest sampling point in the pressure-corrected signal;

[0209] The systolic pressure measurement value is determined based on the pressure at the sampling point corresponding to the first amplitude in the pressure correction signal; and the diastolic pressure measurement value is determined based on the pressure at the sampling point corresponding to the second amplitude.

[0210] Optionally, the blood pressure measurement module 805 is used to:

[0211] determining a pulse wave feature based on the pulse wave signal at the first site, the pulse wave feature being used to characterize at least one of morphological information, time domain information, and frequency domain information of the pulse wave signal at the first site;

[0212] The pulse wave characteristics are input into a coefficient prediction model to obtain the systolic pressure coefficient and the diastolic pressure coefficient.

[0213] Optionally, the coefficient prediction model is obtained by extracting a sample first-site pulse wave signal from a sample pressure signal by a server, performing feature extraction on the sample first-site pulse wave signal to obtain a sample pulse wave feature, inputting the sample pulse wave feature into the coefficient prediction model to obtain a predicted systolic pressure coefficient and a predicted diastolic pressure coefficient, and respectively training the coefficient prediction model using a gold standard for the systolic pressure coefficient and a gold standard for the diastolic pressure coefficient as supervision;

[0214] The systolic pressure coefficient gold standard and the diastolic pressure coefficient gold standard are determined based on the sample second site pressure signal and the sample pressure signal, and the sample second site pressure signal is measured by a second blood pressure measurement device.

[0215] Optionally, the modified prediction module 803 is configured to:

[0216] extracting a pulse wave feature of the pulse wave signal at the first site, wherein the pulse wave feature is used to characterize at least one of morphological information, time domain information, and frequency domain information of the pulse wave signal at the first site;

[0217] Based on the pulse wave characteristics, the signal correction amount is determined by a fitting function, wherein the fitting function includes at least one of a linear fitting function, a polynomial fitting function, and an exponential fitting function.

[0218] Refer to FIG9 , which is a schematic structural diagram of a first blood pressure measurement device provided by an exemplary embodiment of the present application.

[0219] The first blood pressure measurement device can perform the blood pressure measurement method of the above embodiment. The first blood pressure measurement device is provided with a pressure sensor 930, an air pump 940, and an air bag 950. The first blood pressure measurement device is a wrist device that can perform blood pressure measurement, such as a smart bracelet, a smart watch, a wrist blood pressure recorder, a wrist electronic blood pressure monitor, etc.

[0220] The pressure sensor 930 is used to measure the pressure of the airbag 940 in a measuring state.

[0221] Optionally, the pressure sensor 930 is a capacitive pressure sensor or a resistive pressure sensor, or other types of pressure sensors.

[0222] The air pump 940 is used to inflate the airbag 950 through the air path in a measuring state so that the airbag 950 presses the wrist.

[0223] Optionally, the air pump 940 is an air pump that provides smooth inflation and less noise interference.

[0224] Airbag 950 is the airbag that contacts and compresses the wrist during blood pressure measurement. As air pump 940 inflates airbag 950, the air pressure within the airbag varies within a certain range. These varying air pressures interact with the blood vessels, generating varying pressure fluctuations that are captured by pressure sensor 930 connected to the airbag.

[0225] In some embodiments, during measurement, air pump 940 inflates airbag 950 to compress the wrist. Pressure sensor 930 collects a pressure signal via the air path, and memory 920 stores the pressure signal. In some embodiments, the first blood pressure measurement device can extract a first-site pulse wave signal from the pressure signal, perform feature extraction on the first-site pulse wave signal to obtain pulse wave features, and predict a signal correction corresponding to the pressure signal based on the pulse wave features to determine a more accurate blood pressure measurement value.

[0226] The first blood pressure measurement device may further include one or more of the following components: a processor 910 and a memory 920 .

[0227] Optionally, the processor 910 uses various interfaces and lines to connect various parts of the entire electronic device, and performs various functions of the electronic device and processes signals by running or executing instructions, programs, code sets or instruction sets stored in the memory 920, and calling signals stored in the memory 920. Optionally, the processor 910 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 910 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a neural network processing unit (NPU), and a baseband chip. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content required to be displayed on the touch screen; the NPU is used to implement artificial intelligence (AI) functions; and the baseband chip is used to handle wireless communications. It is understandable that the above-mentioned baseband chip may not be integrated into the processor 910, but may be implemented by a separate chip.

[0228] The memory 920 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 920 includes a non-transitory computer-readable storage medium. The memory 920 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 920 may include a program storage area and a signal storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the signal storage area may store signals created according to the use of the first blood pressure measurement device (such as a pressure signal collected by a pressure sensor, or a pulse wave signal extracted from the pressure signal), etc.

[0229] In addition, those skilled in the art will understand that the structure of the electronic device shown in the above figures does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figures, or combine certain components, or arrange the components differently.

[0230] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement the method described in the above embodiment. Optionally, the computer-readable storage medium may include: ROM, RAM, solid-state drives (SSDs), or optical disks. Among them, RAM may include resistance random access memory (ReRAM) and dynamic random access memory (DRAM).

[0231] The present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in various optional implementations of the above aspects.

[0232] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A blood pressure measurement method, characterized in that: The method is used for a first blood pressure measurement device, which is worn at a first location to measure blood pressure, and includes a pressure sensor, an air pump, and an air bag, wherein the pressure sensor is configured to measure the pressure of the air bag in a measuring state, and the air pump is configured to inflate the air bag so that the air bag presses the wrist in the measuring state, and the method includes: In the measurement state, a pressure signal collected by the pressure sensor is obtained, wherein the pressure signal is used to characterize the pressure corresponding to multiple sampling points during the blood pressure measurement process; Extracting a first-site pulse wave signal from the pressure signal, wherein the first-site pulse wave signal is used to characterize the pulse wave amplitude corresponding to the sampling point; Based on the pulse wave signal at the first site, determining a signal correction amount of the pressure signal, the signal correction amount being used to characterize a difference between the pressure signal measured by the first blood pressure measurement device and the pressure signal measured by a second blood pressure measurement device, the second blood pressure measurement device being worn at a second site to perform blood pressure measurement; Correcting the pressure signal based on the signal correction amount to obtain a pressure correction signal; A blood pressure measurement is determined based on the pressure-corrected signal and the first site pulse wave signal.

2. The method according to claim 1, characterized in that The step of determining the signal correction amount of the pressure signal based on the first part pulse wave signal comprises: Extracting a pulse wave feature of the pulse wave signal at the first site, wherein the pulse wave feature is used to characterize at least one of morphological information, time domain information, and frequency domain information of the pulse wave signal at the first site; The pulse wave feature is input into a signal correction amount prediction model to obtain the signal correction amount output by the signal correction amount prediction model.

3. The method according to claim 2, characterized in that The extracting of the pulse wave feature corresponding to the pulse wave signal of the first part includes at least one of the following methods: Determine the pulse wave envelope of the pulse wave signal of the first part; extract features of the pulse wave envelope to obtain the pulse wave features; Perform signal conversion on the pulse wave signal of the first part to obtain a converted signal, wherein the signal conversion method includes at least one of time domain conversion and frequency domain conversion; perform feature extraction on the converted signal to obtain the pulse wave feature.

4. The method according to claim 2, characterized in that: The signal correction amount prediction model is obtained by extracting the sample first-site pulse wave signal from the sample pressure signal by the server, performing feature extraction on the sample first-site pulse wave signal to obtain sample pulse wave features, inputting the sample pulse wave features into the signal correction amount prediction model to obtain a predicted correction amount, and using the correction amount gold standard as the supervision of the predicted correction amount to train the signal correction amount prediction model; The correction amount gold standard is determined based on the pressure signal of the second part of the sample and the pressure signal of the sample, and the pressure signal of the second part of the sample is measured by a second blood pressure measurement device.

5. The method according to claim 4, characterized in that The method further comprises: Acquire a local first-site pulse wave signal and a local correction gold standard, wherein the local correction gold standard is determined based on a local upper arm pressure signal and a local wrist pressure signal, wherein the local upper arm pressure signal and the local wrist pressure signal are measured successively within a target duration; Reporting a model fine-tuning request including the local first-site pulse wave signal and the local correction amount gold standard to the server, so that the server fine-tunes the model parameters of the signal correction amount prediction model based on the local first-site pulse wave signal and the local correction amount gold standard; Receive the updated signal correction amount prediction model sent by the server.

6. The method according to claim 1, characterized in that The signal correction amount is the difference between the slopes of a first fitting straight line and a second fitting straight line, wherein the first fitting straight line is a fitting straight line corresponding to the pressure signal measured by the second blood pressure measurement device, and the second fitting straight line is a fitting straight line corresponding to the pressure signal measured by the first blood pressure measurement device; The step of correcting the pressure signal based on the signal correction amount to obtain a pressure correction signal includes: Performing a linear fit on the pressure signal to obtain the second fitting straight line; Determine the first fitting straight line based on the signal correction amount and the second fitting straight line; The pressure correction signal is determined based on the first fitting straight line and the pressure signal.

7. The method according to claim 1, characterized in that The step of determining the blood pressure measurement value based on the pressure correction signal and the first part pulse wave signal comprises: determining a pulse wave envelope of the pulse wave signal at the first part; Determining the sampling point corresponding to the highest amplitude in the pulse wave envelope as the highest sampling point; determining a first amplitude in the positive envelope of the pulse wave based on the highest amplitude and the systolic pressure coefficient, and determining a second amplitude in the positive envelope of the pulse wave based on the highest amplitude and the diastolic pressure coefficient; Determining a mean arterial pressure measurement value based on the pressure corresponding to the highest sampling point in the pressure correction signal; The systolic pressure measurement value is determined based on the pressure at the sampling point corresponding to the first amplitude in the pressure correction signal; and the diastolic pressure measurement value is determined based on the pressure at the sampling point corresponding to the second amplitude.

8. The method according to claim 7, characterized in that Before determining the first amplitude in the positive envelope of the pulse wave based on the maximum amplitude and the systolic pressure coefficient, and determining the second amplitude in the positive envelope of the pulse wave based on the maximum amplitude and the diastolic pressure coefficient, the method further includes: Determine a pulse wave feature based on the pulse wave signal of the first part, wherein the pulse wave feature is used to characterize at least one of morphological information, time domain information, and frequency domain information of the pulse wave signal of the first part; The pulse wave characteristics are input into a coefficient prediction model to obtain the systolic pressure coefficient and the diastolic pressure coefficient.

9. The method according to claim 8, characterized in that The coefficient prediction model is obtained by extracting a sample first-site pulse wave signal from a sample pressure signal by a server, performing feature extraction on the sample first-site pulse wave signal to obtain a sample pulse wave feature, inputting the sample pulse wave feature into the coefficient prediction model to obtain a predicted systolic pressure coefficient and a predicted diastolic pressure coefficient, and respectively using a systolic pressure coefficient gold standard and a diastolic pressure coefficient gold standard as supervision to train the coefficient prediction model; The systolic pressure coefficient gold standard and the diastolic pressure coefficient gold standard are determined based on the sample second site pressure signal and the sample pressure signal, and the sample second site pressure signal is measured by a second blood pressure measurement device.

10. The method according to claim 1, characterized in that The determining the signal correction amount of the pressure signal based on the first part pulse wave signal further includes: Extracting a pulse wave feature of the pulse wave signal at the first site, wherein the pulse wave feature is used to characterize at least one of morphological information, time domain information, and frequency domain information of the pulse wave signal at the first site; Based on the pulse wave feature, the signal correction amount is determined by a fitting function, wherein the fitting function includes at least one of a linear fitting function, a polynomial fitting function and an exponential fitting function.

11. The method according to claim 1, characterized in that: The first part is the wrist, and the first blood pressure measurement device is a wrist blood pressure measurement device; the second part is the upper arm, and the second blood pressure measurement device is an upper arm blood pressure measurement device.

12. A blood pressure measuring device, characterized in that: The device is used for a first blood pressure measurement device, which is worn at a first position to measure blood pressure, and comprises a pressure sensor, an air pump and an air bag, wherein the pressure sensor is configured to measure the pressure of the air bag in a measuring state, and the air pump is configured to inflate the air bag so that the air bag presses the wrist in the measuring state, and the device comprises: A signal acquisition module, used to acquire the pressure signal collected by the pressure sensor in the measurement state, wherein the pressure signal is used to characterize the pressure corresponding to multiple sampling points during the blood pressure measurement process; A signal extraction module, used to extract a first-site pulse wave signal from the pressure signal, wherein the first-site pulse wave signal is used to characterize the pulse wave amplitude corresponding to the sampling point; a correction prediction module, for determining a signal correction amount of the pressure signal based on the first-site pulse wave signal, the signal correction amount being used to characterize a difference between the pressure signal measured by the first blood pressure measurement device and the pressure signal measured by a second blood pressure measurement device, the second blood pressure measurement device being worn at a second site to perform blood pressure measurement; A correction execution module, used for correcting the pressure signal based on the signal correction amount to obtain a pressure correction signal; The blood pressure measurement module is used to determine the blood pressure measurement value based on the pressure correction signal and the first part pulse wave signal.

13. A blood pressure measuring device, characterized in that: The blood pressure measuring device comprises a pressure sensor, an air pump, an air bag, a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement the blood pressure measurement method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, which is loaded and executed by a processor to implement the blood pressure measurement method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium; the processor of the blood pressure measurement device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the blood pressure measurement device performs the blood pressure measurement method as described in any one of claims 1 to 11.

Images