A wearable blood pressure monitoring device and method of blood pressure monitoring

Abstract

The application relates to the technical field of wearable smart devices, and provides a wearable blood pressure monitoring device and a blood pressure monitoring method, the device comprising a pressure sensor, an acceleration sensor and a central processing unit; the pressure sensor is used for collecting a pressure signal of a user in a motion state; the acceleration sensor is used for collecting an acceleration signal of the user in the motion state; the central processing unit is used for: performing mode recognition based on a motion frequency signal and a motion amplitude signal to obtain a current motion mode, performing signal recognition on the pressure signal based on the current motion mode to obtain a motion interference signal in the pressure signal; performing signal filtering processing on the pressure signal based on the motion interference signal to obtain a blood pressure oscillation wave signal in the pressure signal; and determining a blood pressure parameter of the user in the motion state based on the blood pressure oscillation wave signal. The application improves the accuracy and reliability of blood pressure measurement in the motion state, and meets the demand of the user for precise blood pressure monitoring in the motion process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wearable smart devices, and relates to a wearable blood pressure monitoring device and a blood pressure monitoring method. BACKGROUND

[0002] At present, blood pressure monitoring technology based on the oscillometric method is widely used in various wearable devices. This method analyzes blood pressure values by measuring oscillation waves generated by pressure changes in a cuff or wristband. However, in a motion state, a large number of irregular interference signals are generated due to human limb movement, which are superimposed with real blood pressure oscillation waves, making it difficult for existing oscillometric blood pressure monitoring to accurately distinguish between effective signals and interference signals, thereby resulting in a large error in blood pressure measurement results and failing to meet the user's demand for accurate blood pressure monitoring during exercise. Therefore, how to effectively eliminate interference signals in a motion state and obtain accurate blood pressure measurement results has become a technical problem to be solved. SUMMARY

[0003] The present application provides a wearable blood pressure monitoring device and a blood pressure monitoring method, aiming to improve the accuracy and reliability of blood pressure measurement in a motion state and meet the user's demand for accurate blood pressure monitoring during exercise.

[0004] In a first aspect, the present application provides a wearable blood pressure monitoring device, comprising a pressure sensor, an acceleration sensor and a central processing unit; the central processing unit is connected with the pressure sensor and the acceleration sensor respectively;

[0005] The pressure sensor is used to collect pressure signals of a user in a motion state;

[0006] The acceleration sensor is used to collect acceleration signals of the user in the motion state; the acceleration signals include motion frequency signals and motion amplitude signals;

[0007] The central processing unit is used to:

[0008] Based on the motion frequency signals and the motion amplitude signals, pattern recognition is performed to obtain a current motion pattern, and based on the current motion pattern, signal recognition is performed on the pressure signals to obtain motion interference signals in the pressure signals;

[0009] Based on the motion interference signals, signal filtering processing is performed on the pressure signals to obtain blood pressure oscillation wave signals in the pressure signals;

[0010] Based on the blood pressure oscillation wave signals, blood pressure parameters of the user in the motion state are determined.

[0011] In a second aspect, the present application also provides a blood pressure monitoring method, which is implemented based on the wearable blood pressure monitoring device of the first aspect, and comprises the following steps:

[0012] collecting a pressure signal of the user in a motion state based on the pressure sensor, and collecting an acceleration signal of the user in the motion state based on the acceleration sensor; the acceleration signal comprises a motion frequency signal and a motion amplitude signal;

[0013] performing pattern recognition based on the motion frequency signal and the motion amplitude signal to obtain a current motion pattern, and performing signal recognition on the pressure signal based on the current motion pattern to obtain a motion interference signal in the pressure signal;

[0014] performing signal filtering processing on the pressure signal based on the motion interference signal to obtain a blood pressure oscillation wave signal in the pressure signal;

[0015] determining a blood pressure parameter of the user in the motion state based on the blood pressure oscillation wave signal.

[0016] In a third aspect, the present application also provides an electronic device, which comprises a memory for storing a computer software program, and a processor for reading and executing the computer software program, thereby implementing the blood pressure monitoring method according to any one of the above aspects.

[0017] In a fourth aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer software program, and the computer software program is executed by a processor to implement the blood pressure monitoring method according to any one of the above aspects.

[0018] In a fifth aspect, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the blood pressure monitoring method according to any one of the above aspects.

[0019] The wearable blood pressure monitoring device provided by the embodiments of the present application can accurately identify the current motion pattern of the user in the motion state by collecting the acceleration signal, can acquire the motion interference signal in different motion patterns, and can perform signal filtering processing on the pressure signal according to the motion interference signal, so as to accurately identify and remove the motion interference signal, thereby accurately filtering out the blood pressure oscillation wave signal in the pressure signal. Further, the blood pressure parameter of the user in the motion state is determined based on the blood pressure oscillation wave signal, the influence of the motion interference signal on the measurement result is effectively avoided, the accuracy and reliability of the blood pressure measurement in the motion state are improved, and the demand of the user for accurate blood pressure monitoring in the motion process is met. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 is a structural schematic diagram of the wearable blood pressure monitoring device provided by the present application;

[0021] Figure 2 is a flowchart of a blood pressure monitoring method provided by the present application;

[0022] Figure 3 is an embodiment diagram of an electronic device provided by an embodiment of the present application;

[0023] Figure 4 is an embodiment diagram of a computer readable storage medium provided by an embodiment of the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0025] In the description of the present application, the terms "first", "second" are used only for the purpose of description, 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 one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0026] In the description of the present application, the term "for example" is used to indicate "as an example, illustration or explanation". Any embodiment described as "for example" in the present application is not necessarily interpreted as more preferred or more advantageous than other embodiments. The following description is given in order to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that those skilled in the art can realize the present application without using these specific details. In other examples, well-known structures and processes will not be described in detail in order to avoid unnecessary details making the description of the present application obscure. Therefore, the present application is not intended to be limited to the shown embodiments, but is consistent with the broadest scope of principles and features disclosed.

[0027] Optionally, refer to Figure 1 shown, Figure 1 is a structural diagram of a wearable blood pressure monitoring device provided by the present application, which includes a pressure sensor, an acceleration sensor and a central processing unit. The central processing unit is connected with the pressure sensor and the acceleration sensor respectively.

[0028] Optionally, the pressure sensor is usually installed in the inner surface of the wristband or the cuff in contact with the human body, which is used to collect the pressure signal generated by the blood pressure change and the body movement of the user in the motion state. When the heart contracts and relaxes, the change of the pressure in the blood vessel is transmitted to the pressure sensor in contact with the skin; at the same time, the squeezing, friction and other pressure changes of the limbs during the movement of the human body will also be generated, and the pressure change will be converted into an electrical signal by the pressure sensor for output, so that the pressure sensor collects the pressure signal of the user in the motion state.

[0029] Optionally, the acceleration sensor is usually a three-axis accelerometer, which can measure the acceleration in three mutually perpendicular directions (X, Y, Z axes). The acceleration sensor is installed close to the human motion part, such as wrist, ankle, etc., which can collect the acceleration signal of the user in the motion state in real time. The motion frequency signal in the acceleration signal reflects the fast or slow rhythm of the user's movement, such as the step frequency when running; the motion amplitude signal reflects the intensity of the movement, such as the amplitude of the arm swing. The acceleration sensor converts the change of the inertial force into an electrical signal, so that the acceleration sensor collects the acceleration signal of the user in the motion state, and the acceleration signal includes the motion frequency signal and the motion amplitude signal.

[0030] Optionally, the central processing unit performs pattern recognition according to the motion frequency signal and the motion amplitude signal to obtain the current motion pattern, as described in steps 201 to 204.

[0031] Further, the central processing unit performs signal recognition on the pressure signal according to the current motion pattern to obtain the motion interference signal in the pressure signal in the current motion pattern, as described in steps 205 to 217.

[0032] Further, the central processing unit performs signal filtering processing on the pressure signal according to the motion interference signal to obtain the blood pressure oscillation wave signal in the pressure signal, wherein the commonly used filtering methods include low-pass filtering, band-pass filtering, adaptive filtering, etc. The low-pass filtering can remove the high-frequency motion interference signal in the pressure signal and retain the low-frequency blood pressure oscillation wave signal, because the frequency of the blood pressure oscillation wave signal is generally around 0.5-15 Hz; the band-pass filtering can only allow the signal in a specific frequency range to pass according to the frequency range of the blood pressure oscillation wave signal, further enhancing the extraction effect of the blood pressure oscillation wave signal; the adaptive filtering can automatically adjust the filtering parameters according to the change of the signal, and more effectively remove the motion interference signal in the complex motion environment.

[0033] In practical applications, a combination of multiple filtering methods is usually used for processing. First, a low-pass filter is used to preliminarily filter the pressure signal to remove most high-frequency motion interference signals. Then, a band-pass filter is used to further process the preliminarily filtered signal to retain signals within the frequency range of the blood pressure oscillatory wave signal. Finally, an adaptive filter is used to fine-tune the signal and further optimize the filtering effect according to the real-time signal changes, thereby obtaining a relatively pure blood pressure oscillatory wave signal.

[0034] Further, the central processing unit determines the blood pressure parameters of the user in the motion state based on the blood pressure oscillatory wave signal. The blood pressure oscillatory wave signal contains rich information related to blood pressure. Determining the blood pressure parameters of the user in the motion state based on the blood pressure oscillatory wave signal mainly involves calculating the systolic pressure, diastolic pressure, and mean arterial pressure. A common calculation method is based on the principle of the oscillometric method. This method determines the blood pressure value by analyzing the relationship between the amplitude of the blood pressure oscillatory wave and the cuff pressure. Specifically, feature extraction is performed on the blood pressure oscillatory wave signal, such as finding the peak value, valley value, and slope of the waveform, etc. Generally, as the cuff pressure gradually decreases, the amplitude of the blood pressure oscillatory wave gradually increases. When the cuff pressure equals the mean arterial pressure, the amplitude of the oscillatory wave reaches a maximum value. When the cuff pressure approaches the systolic pressure, the amplitude of the oscillatory wave begins to significantly increase. When the cuff pressure approaches the diastolic pressure, the amplitude of the oscillatory wave begins to decrease. By establishing a mathematical model between the feature parameters of the blood pressure oscillatory wave and the blood pressure value, the systolic pressure, diastolic pressure, and mean arterial pressure are calculated. For example, an empirical formula or a regression model trained based on machine learning can be used, with the extracted feature parameters as input and the corresponding blood pressure parameter values as output.

[0035] In an embodiment, taking a wrist-wearable blood pressure monitoring device as an example, after obtaining a relatively pure blood pressure oscillatory wave signal, feature extraction is performed on the blood pressure oscillatory wave signal. Peak detection algorithms are used to find each peak in the blood pressure oscillatory wave signal and record the amplitude and time point corresponding to each peak. At the same time, the slope change between adjacent peaks is calculated. For example, based on a large amount of clinical trial data, a blood pressure calculation model is established using a linear regression algorithm based on machine learning. The peak amplitude and slope of the extracted blood pressure oscillatory wave signal are input into the model, and the model outputs the blood pressure parameters of the user in the motion state after calculation, such as a systolic pressure of 130 mmHg, a diastolic pressure of 85 mmHg, and a mean arterial pressure of 100 mmHg, providing the user with blood pressure health reference data in the motion state.

[0036] The embodiment of the present application can accurately identify the current motion mode of the user in the motion state, and can obtain the motion interference signal in different motion modes, and then filter the pressure signal according to the motion interference signal, accurately identify and remove the motion interference signal, so as to accurately filter out the blood pressure oscillation wave signal in the pressure signal. Further, the blood pressure parameter of the user in the motion state is determined according to the blood pressure oscillation wave signal, the influence of the motion interference signal on the measurement result is effectively avoided, the accuracy and reliability of the blood pressure measurement in the motion state are improved, and the demand of the user for accurate blood pressure monitoring in the motion process is met.

[0037] In an embodiment, steps 201 to 204 are described as follows:

[0038] In step 201, the frequency characteristic index is determined based on the number of motion frequencies in the motion frequency signal and the ratio between the square of each motion frequency and the mean of the motion frequencies.

[0039] Optionally, in the motion frequency signal, different motion modes show unique frequency distribution characteristics. The embodiment of the present application determines the frequency characteristic index by calculating the number of motion frequencies, the ratio between the square of each motion frequency and the mean of the motion frequencies, quantifies the characteristics of the motion frequency signal, and specifically: the number of different motion frequencies in the motion frequency signal is counted, the square of each motion frequency is calculated, then the mean of all motion frequencies is calculated, and finally the square of each motion frequency is compared with the mean to obtain the frequency characteristic index, wherein the frequency characteristic index reflects the dispersion degree and distribution characteristics of the motion frequencies.

[0040] Taking the wrist blood pressure monitoring device as an example, for example, in the motion frequency signal collected by the acceleration sensor within 10 seconds, the motion frequencies f1=2Hz, f2=2.1Hz, f3=1.9Hz are detected, and there are 3 different motion frequencies. First, the mean of the motion frequencies is calculated Then the square of each motion frequency is calculated, which is (f1) 2 =4, (f2) 2 =4.41, (f3) 2 =3.61. Finally, the frequency characteristic index k1=4 / 2=2, k2=4.41 / 2=2.205, k3=3.61 / 2=1·805 is calculated, which constitutes the frequency characteristic index of the motion frequency signal.

[0041] In step 202, the frequency interval identifier of each frequency characteristic index is determined based on the frequency interval where each frequency characteristic index is located.

[0042] Furthermore, based on the frequency range in which each frequency characteristic indicator is located, the frequency range identifier for each frequency characteristic indicator is determined. Different frequency ranges are pre-divided, such as low frequency range, medium frequency range, and high frequency range. Then, it is determined which range each frequency characteristic indicator falls into and assigned a corresponding identifier, such as "low", "medium", or "high". The frequency range identifier can intuitively reflect the relative magnitude and distribution characteristics of the motion frequency.

[0043] Continuing with the above embodiment, the pre-defined frequency range identification rules are as follows: frequency characteristic indices less than 1.5 are classified as "low" range, 1.5-2.5 as "medium" range, and greater than 2.5 as "high" range. For the calculated frequency characteristic indices, k1 = 2, k2 = 2.205, and k3 = 1.805. k1, k2, and k3 all fall within the "medium" range; therefore, the frequency range identification is "medium".

[0044] Step 203: Determine the amplitude change index based on the sum of the absolute values ​​of the amplitude differences between adjacent time points in the motion amplitude signal and the maximum value of the amplitude.

[0045] Furthermore, the motion amplitude signal reflects the intensity and changes in motion. In this embodiment of the invention, the amplitude change index is determined by calculating the ratio of the sum of the absolute values ​​of the amplitude differences between adjacent time points in the motion amplitude signal to the maximum amplitude value. Specifically, the differences in the motion amplitude signals at adjacent time points are first calculated and their absolute values ​​are taken. These absolute values ​​are then summed to obtain a total value. Next, the maximum value in the motion amplitude signal is found, and finally, the ratio of the two is calculated. The amplitude change index measures the degree of change in motion amplitude.

[0046] Continuing with the above embodiment, for example, within a certain period of time, the amplitude values ​​of the motion amplitude signal collected by the accelerometer at adjacent time points are A1 = 5 m / s. 2 A2 = 7 m / s 2 A3 = 6 m / s 2 A4 = 8 m / s 2 First, calculate the absolute values ​​of the amplitude differences between adjacent time points: |A2-A1|=|7-5|=2, |A3-A2|=|6-7|=1, |A4-A3|=|8-6|=2, and their sum is S=2+1+2=5. The maximum value in the motion amplitude signal is A4=8m / s. 2 Therefore, the amplitude change index I = S / A max =5 / 8=0.625.

[0047] Step 204: Perform pattern recognition based on frequency range identifier and amplitude change index to obtain the current motion pattern.

[0048] Further, the mode recognition is performed according to the frequency interval identifier and the amplitude change index to obtain the current motion mode, as described in steps 2041 to 2043.

[0049] The embodiment of the present application extracts the characteristic index with distinguishability from the motion frequency signal and the motion amplitude signal, and thus the current motion mode of the user in the motion state can be accurately recognized through the characteristic index, the motion interference signal filtering can be performed on the pressure signals in different motion modes, and thus the blood pressure oscillation wave signal in the pressure signal can be accurately filtered out, the influence of the motion interference signal on the measurement result is effectively avoided, the accuracy and reliability of the blood pressure measurement in the motion state are improved, and the demand of the user for the accurate blood pressure monitoring in the motion process is met.

[0050] In an embodiment, steps 2041 to 2043 are described as follows:

[0051] In step 2041, if the frequency interval identifier is the first interval identifier and the amplitude change index is less than the first preset amplitude change threshold, it is determined that the current motion mode is the cycling mode.

[0052] Optionally, the first interval identifier, the second interval identifier and the third interval identifier in the embodiment of the present application are different identifiers. When the frequency interval identifier is the first interval identifier (representing that the motion frequency is in a specific lower range) and the amplitude change index is less than the first preset amplitude change threshold (indicating that the motion amplitude change is relatively small), it is determined that the current motion mode is the cycling mode, because in the cycling process, the body mainly rotates around the regular motion parts of the bicycle, the motion frequency is relatively stable and low, and the body amplitude change is relatively flat, which meets the characteristics set by the judgment condition.

[0053] In an embodiment, the first interval identifier corresponds to a “low” frequency interval in which the frequency characteristic index is less than 1.2, and the first preset amplitude change threshold is set to 0.3. The frequency characteristic index is k1=1.1, k2=1.05 and k3=1.15, and the frequency interval identifiers of the three are all “low”, i.e. the first interval identifier; the amplitude change index I=0.25, which is less than the first preset amplitude change threshold 0.3, and thus it is determined that the current motion mode is the cycling mode.

[0054] In step 2042, if the frequency interval identifier is the second interval identifier, and the amplitude change index is greater than or equal to the first preset amplitude change threshold and less than the second preset amplitude change threshold, it is determined that the current motion mode is the running mode.

[0055] Further, when the frequency interval identifier is the second interval identifier (corresponding to a medium motion frequency range), and the amplitude variation index is between the first preset amplitude variation threshold and the second preset amplitude variation threshold, it is determined that the current motion mode is a running mode. Since the feet are alternately landed to generate periodic motion during running, the frequency is moderate, and the body is up and down and the arms are swung to cause the motion amplitude to have a certain variation, but not as large as that of some intense motions.

[0056] In an embodiment, the second interval identifier corresponds to a "medium" frequency interval of the frequency characteristic index of 1.2-2.2, the first preset amplitude variation threshold is 0.3, and the second preset amplitude variation threshold is 0.6. The frequency characteristic index is k1=1.8, k2=2.0, and k3=1.9, the frequency interval identifier is "medium", that is, the second interval identifier, the amplitude variation index I=0.45, and the condition of being greater than or equal to the first preset amplitude variation threshold 0.3 and less than the second preset amplitude variation threshold 0.6 is met, and therefore, it is determined that the current motion mode is a running mode.

[0057] In step 2043, if the frequency interval identifier is the third interval identifier, and the amplitude variation index is greater than or equal to the second preset amplitude variation threshold, it is determined that the current motion mode is a swimming mode.

[0058] Further, when the frequency interval identifier is the third interval identifier (representing a higher motion frequency range), and the amplitude variation index is greater than or equal to the second preset amplitude variation threshold (meaning that the motion amplitude variation is large), it is determined that the current motion mode is a swimming mode. Since the limbs are swum, the body is swung, and the motion frequency is high during swimming, and the motion amplitude is greatly changed due to the influence of water resistance and other factors in water.

[0059] In an embodiment, the third interval identifier corresponds to a "high" frequency interval of the frequency characteristic index greater than 2.2, and the second preset amplitude variation threshold is 0.6. The frequency characteristic index is k1=2.5, k2=2.6, and k3=2.4, the frequency interval identifier is "high", that is, the third interval identifier, the amplitude variation index I=0.7, and the second preset amplitude variation threshold 0.6 is greater than or equal to, and therefore, it is determined that the current motion mode is a swimming mode.

[0060] The embodiment of the present application constructs a specific motion mode recognition rule system based on the frequency interval identification and amplitude change index obtained through motion signal processing, so that the differences in frequency and amplitude change characteristics of different motion modes can be utilized to quickly and accurately recognize common motion modes such as cycling, running, swimming and the like in a complex motion scene, and thus the pressure signals under different motion modes can be filtered in a targeted manner, so that the blood pressure oscillation wave signals in the pressure signals are accurately filtered out, the influence of the motion interference signals on the measurement results is effectively avoided, the accuracy and reliability of the blood pressure measurement in the motion state are improved, and the demand of the user for accurate blood pressure monitoring during the motion process is met.

[0061] In an embodiment, steps 2044 to 2047 are described as follows:

[0062] In step 2044, the running direction angle difference between adjacent time points in the running direction signal is compared with a preset direction change rate threshold.

[0063] Optionally, the acceleration signals collected by the embodiment of the present application also include a running direction signal. Therefore, the running direction signal is processed to calculate the running direction angle difference between adjacent time points. Specifically, the running direction angles θ i and θ i+1 of adjacent two time points t i and t i+1 are obtained, and the angle difference is calculated through the formula Δθ = |θ i+1 - θ i |. Then, the calculated angle difference is compared with a preset direction change rate threshold, wherein the preset direction change rate threshold is set according to the reasonable range of direction change in the normal motion process, and is used to judge whether the direction change is abnormal.

[0064] In an embodiment, the preset direction change rate threshold is 30°. When the user rides a bicycle, the running direction angles collected at two adjacent time points t1 and t2 are θ1 = 45° and θ2 = 60° respectively, and the running direction angle difference Δθ = |60°-45°| = 15°, which is compared with the preset direction change rate threshold 30°, and 15° < 30°.

[0065] In step 2045, if the running direction angle difference is greater than the preset direction change rate threshold, it is determined that there is a direction mutation at the current time point, the mutation number is recorded, and the direction mutation number is obtained.

[0066] Further, if the angle difference is greater than the preset direction change rate threshold, it indicates that the motion direction of the user at the current time point has changed abruptly, and the condition of the direction change is recorded. Each time a direction change that meets the condition occurs, the number of changes is increased by 1. By continuously recording the number of direction changes, the overall situation of the direction changes of the user's motion in a period of time can be obtained.

[0067] Continuing the above embodiment, if the running direction angle collected at time point t3 in the subsequent collection process is θ3=120°, then the running direction angle difference Δθ between t2 and t3 is Δθ=|120°-60°|=60°, because 60°>30°, it is determined that there is a direction change at time point t3, and the number of direction changes is recorded as 1. With the continuation of the motion, if multiple direction changes occur, the count of the number of changes is correspondingly increased.

[0068] Step 2046, if the current motion mode is the cycling mode and the number of direction changes is greater than the first upper limit of the number of direction changes in the cycling mode, the current motion mode is corrected from the cycling mode to the running mode.

[0069] Further, if the current motion mode is the cycling mode, the number of direction changes is further judged, wherein the first upper limit of the number of direction changes in the cycling mode is set according to the frequency and amplitude of the direction change in the normal cycling process. If the number of direction changes is greater than the first upper limit of the number of direction changes, it indicates that the direction change in the current motion process does not conform to the normal characteristics of the cycling mode, and more conforms to the direction change characteristics of the running mode (the direction is more likely to change frequently when running). At this time, the current motion mode is corrected from the cycling mode to the running mode. In an embodiment, the first upper limit of the number of direction changes in the cycling mode is 5 times. In the cycling process, after a period of monitoring, the recorded number of direction changes is 7 times, because 7>5, and the current motion mode has been determined to be the cycling mode, the current motion mode is corrected to the running mode.

[0070] Step 2047, if the current motion mode is the swimming mode and the number of direction changes is greater than the second upper limit of the number of direction changes in the swimming mode, the current motion mode is corrected from the swimming mode to the running mode.

[0071] Further, when the current motion mode is the swimming mode, the number of direction mutations is compared with a second upper limit of the number of direction mutations in the swimming mode, wherein the second upper limit of the number of direction mutations in the swimming mode is set based on a normal direction change rule of swimming. If the number of direction mutations is greater than the second upper limit of the number of direction mutations, it is indicated that the current direction change condition is out of the normal range of the swimming mode, and the running mode has a relatively more frequent direction change in the motion process, and therefore, the current motion mode is corrected from the swimming mode to the running mode. In an embodiment, the second upper limit of the number of direction mutations in the swimming mode is 3. The user records the number of direction mutations in the swimming process, and the number of direction mutations reaches 4, because 4>3, and the current motion mode is the swimming mode, the current motion mode is corrected to the running mode.

[0072] The embodiment of the present application preliminarily identifies the motion mode based on the frequency interval identifier and the amplitude change index, effectively captures the direction mutation condition in the motion process through accurate calculation of the running direction angle difference value and comparison with the threshold value, and corrects the preliminarily identified motion mode in combination with reasonable range setting of the number of direction mutations in different motion modes, so as to fully consider the motion direction change, effectively correct the motion mode misjudgment caused by special motion states or interference, improve the accuracy of motion mode recognition in a complex motion scene, and therefore, the pressure signal in different motion modes can be targeted for motion interference signal filtering, so that the blood pressure oscillation wave signal in the pressure signal is accurately filtered out, the influence of the motion interference signal on the measurement result is effectively avoided, the accuracy and reliability of the blood pressure measurement in the motion state are improved, and the demand of the user for accurate blood pressure monitoring in the motion process is met.

[0073] In an embodiment, steps 205 to 209 are described as follows:

[0074] In step 205, if the current motion mode is the running mode, the pressure signal is divided based on a preset size of a time window, and a first target time window and a second target time window are determined based on a preset mean value threshold and a pressure signal value of each sampling point in each time window.

[0075] Optionally, after determining that the current motion mode is the running mode, in order to identify the motion interference signal from the pressure signal, the pressure signal is first divided based on a preset size of a time window, wherein the size of the time window is set according to the periodic characteristics of the pressure signal change in the running motion and the sampling frequency, and the continuous pressure signal is divided into multiple equal-length sub-signal segments.

[0076] Furthermore, a preset mean threshold is set, and time windows that meet specific conditions are selected by comparing the pressure signal value of each sampling point in the sub-signal within each time window with this threshold. Specifically, time windows where the average pressure signal value is higher than the preset mean threshold are determined as the first target time window, and time windows where the average pressure signal value is lower than the preset mean threshold are determined as the second target time window.

[0077] In one embodiment, the pressure signal sampling frequency is 1000Hz, the preset time window size is 500 sampling points (i.e., 0.5 seconds), and the preset average threshold is 5mV. When the user is in running mode, the pressure signal is a series of continuous voltage values. The pressure signal is divided into multiple sub-signal segments by dividing the time window into 500 sampling points. For a sub-signal within one time window, the pressure signal values ​​of its 500 sampling points are {p1, p2, ..., p...} 500} Calculate the mean value of the pressure signal within this time window. For example, if the value is 6mV, since 6mV > 5mV, this time window is determined as the first target time window; if the calculated mean value is 4mV < 5mV in another time window, then this is determined as the second target time window.

[0078] Step 206: For each first target time window, determine the local maxima and local minima, and determine the time interval between adjacent local maxima.

[0079] Furthermore, for each sub-signal within the first target time window, the fluctuation characteristics of the signal are analyzed by finding local maxima and local minima. A local maximum is a pressure signal value at a sampling point and its neighborhood that is greater than the values ​​at surrounding points; a local minimum is a pressure signal value that is less than the values ​​at surrounding points. After finding the local maxima and local minimum, the time interval between adjacent local maxima is calculated, where the time interval reflects the periodicity of the pressure signal fluctuation.

[0080] Continuing with the above embodiments, for example, there is a local maximum point p in the sub-signal. max1 ,p max2 ... and the local minimum point p min1 ,p min2 ...。 Among them, p max1 The corresponding sampling point number is n1, p max2 The corresponding sampling point number is n2. Since the sampling frequency is 1000Hz, the adjacent local maxima p max1 and p max2 Time interval T 12= (n2-n1) / 1000 (unit: seconds). By traversing the sub-signals within the entire first target time window, the time interval between all adjacent local maxima is determined.

[0081] Step 207: For each local maximum, determine the time correlation parameter of each local maximum based on the difference between the rise time from the preceding local minimum to each local maximum and the fall time from each local maximum to the subsequent local minimum.

[0082] Furthermore, for each local maximum, the rise time from the preceding local minimum to that local maximum and the fall time from that local maximum to the subsequent local minimum are calculated. The difference between these two times is then used as the time correlation parameter for that local maximum. This time correlation parameter reflects the asymmetry of the pressure signal during local fluctuations; different motion disturbances will cause the time correlation parameter to exhibit different characteristics.

[0083] In one embodiment, a local maximum p max The local minimum value before it is p min1 The corresponding sampling point numbers are n max and n min1 The subsequent local minimum is p. min2 The corresponding sampling point number is n min2 Then from p min1 to p max rise time t up =(n max -n min1 ) / 1000 (unit: seconds), from p max to p min2 descent time t down =(n min2 -n max ) / 1000 (unit: seconds). The time-related parameter of this local maximum is Δt = t up -t down By calculating the time correlation parameters of each local maximum, a set of data reflecting the time characteristics of local fluctuations in the pressure signal is obtained.

[0084] Step 208: Determine the strength of the first interference signal based on the mean of the time interval between adjacent local maxima, the mean of the peak-to-peak values ​​of adjacent local maxima, and the mean of the time correlation parameter of each local maximum.

[0085] Furthermore, the mean of the time intervals between adjacent local maxima is calculated. This reflects the average period of pressure signal fluctuations; then, the mean of the peak-to-peak values ​​of adjacent local maxima (i.e., the difference between adjacent local maxima and local minima) is calculated. embodies the average amplitude of the fluctuation of the pressure signal; the mean value of the time correlation parameter of each local maximum is recalculated Further, the above three parameters are fused to obtain a first interference signal strength S1. The formula adopted by the embodiment of the present application is Wherein, α, β, γ are coefficients adjusted according to actual conditions, and α+β+γ=1, for example, α=0.3, β=0.5, γ=0.2.

[0086] Step 209, the sub-signals in the first target time window and the sub-signals in the second target time window whose interference signal strength is greater than or equal to the first preset strength threshold are determined as motion interference signals.

[0087] Further, the first preset strength threshold is set, and the first interference signal strength calculated in each first target time window is compared with the threshold. If the first interference signal strength is greater than or equal to the first preset strength threshold, it is considered that the sub-signals in the first target time window contain strong motion interference signals; at the same time, the second target time window is also considered due to the particularity of the mean value of the pressure signal. Finally, the sub-signals in the first target time window and the sub-signals in the second target time window that meet the conditions are determined as motion interference signals, and the motion interference component is accurately extracted from the pressure signal.

[0088] In an embodiment, the first preset strength threshold is 1.2. For the first target time window whose first interference signal strength S1=1.57 is calculated above, because 1.57>1.2, the sub-signals in the first target time window are determined as motion interference signals. At the same time, the sub-signals in all the second target time windows are also determined as motion interference signals, and these determined sub-signals jointly constitute the motion interference signals in the pressure signal in the running mode.

[0089] The embodiment of the present application comprehensively considers the mean value, fluctuation period, amplitude and time characteristics of the pressure signal in the running mode, can more accurately and comprehensively identify the motion interference signals in the pressure signal in the running mode, effectively removes the influence of the motion interference on the blood pressure signal, obtains the blood pressure oscillation wave signal in the pressure signal in the running mode, effectively avoids the influence of the motion interference signal on the measurement result, improves the accuracy and reliability of the blood pressure measurement in the running mode, and meets the demand of the user for accurate monitoring of blood pressure during exercise.

[0090] In an embodiment, steps 210 to 213 are described as follows:

[0091] In step 210, if the current exercise mode is the cycling mode, the pressure signal is subjected to a fast Fourier transform to obtain a frequency domain representation of the pressure signal, and a first target frequency interval and a second target frequency interval are determined based on a preset energy proportion and an energy distribution of the frequency intervals in the frequency domain representation.

[0092] Optionally, when it is determined that the current exercise mode is the cycling mode, in order to identify the motion interference signal in the pressure signal, the pressure signal is subjected to a fast Fourier transform (FFT), where the FFT can convert the pressure signal from the time domain to the frequency domain, so that the signal is displayed in the form of frequency components.

[0093] Further, the first target frequency interval and the second target frequency interval are determined according to the energy distribution of each frequency interval in the frequency domain representation and in combination with the preset energy proportion, where the preset energy proportion is a standard preset for measuring which frequency intervals contain more energy, and the motion interference signal is usually concentrated in some frequency intervals with a higher energy proportion. Therefore, it can be understood that the energy proportions of the first target frequency interval and the second target frequency interval are both greater than or equal to the preset energy proportion, and the frequency of the second target frequency interval is higher than the frequency of the first target frequency interval.

[0094] In an embodiment, the length of the collected pressure signal is 10 seconds, the sampling frequency is 1000 Hz, the pressure signal of the 10000 sampling points is subjected to the FFT transform to obtain the frequency domain representation. The frequency domain range is divided into multiple frequency intervals, such as 0-10 Hz, 10-20 Hz, 20-30 Hz, etc. The energy proportion in each frequency interval is calculated, and the preset energy proportion is set to 10%. It is found through calculation that the energy proportion of the 20-30 Hz frequency interval is 15%, and the energy proportion of the 50-60 Hz frequency interval is 12%. Therefore, the 20-30 Hz is determined as the first target frequency interval, and the 50-60 Hz is determined as the second target frequency interval.

[0095] In step 211, a frequency screening range is determined based on the cycling speed collected by the speed sensor, and the signal frequencies in the first target frequency interval are screened based on the frequency screening range to obtain a first target signal frequency and a second target signal frequency in the first target frequency interval.

[0096] Further, the cycling speed is collected by the speed sensor, and the cycling speed is related to the frequency of the motion interference signal. Therefore, a frequency screening range is determined according to the collected cycling speed, where the frequency screening range can screen the signal frequencies in the first target frequency interval, and exclude those frequency components that are not related to the current cycling speed, so that the screened frequencies are more likely to be the frequencies of the motion interference signal. After screening, a first target signal frequency and a second target signal frequency in the first target frequency interval are obtained.

[0097] In an embodiment, the speed sensor collects the cycling speed of 20km / h, and through experimental data or empirical formula, it is determined that the frequency filtering range at this speed is 22-28Hz. For the first target frequency range 20-30Hz determined above, the signal frequencies in the range of 22-28Hz are filtered out as the first target signal frequencies, and the signal frequencies not in the range but still in the range of 20-30Hz are filtered out as the second target signal frequencies, for example, 23Hz, 25Hz, and 27Hz are determined as the first target signal frequencies, and 21Hz and 29Hz are determined as the second target signal frequencies.

[0098] In step 212, for each first target signal frequency in each first target frequency range, the second interference signal strength is determined based on the average of the difference between each signal frequency peak value and the center signal frequency, and the average of the difference between each signal frequency peak value and the two signal frequency valley values before and after it.

[0099] Further, for each first target signal frequency in each first target frequency range, the average of the difference between each signal frequency peak value and the center signal frequency, which is the center value of the frequency range, and the average of the difference between each signal frequency peak value and the two signal frequency valley values before and after it are calculated.

[0100] Further, the two parameters are weighted and summed to obtain the second interference signal strength, wherein the second interference signal strength reflects to what extent the frequency component is a motion interference signal.

[0101] In an embodiment, taking the first target signal frequency 23Hz as an example, for example, the center signal frequency of the frequency range is 25Hz. The signal peak values of the frequency collected in a period of time are P1, P2, and P3, and the corresponding two signal frequency valley values before and after them are V 11 ,V 12 ,V 21 ,V 22 ,V 31 ,V 32 . The differences between the signal frequency peak values and the center signal frequency are |P1-25|, |P2-25|, and |P3-25|, and the average is The differences between the signal frequency peak values and the two signal frequency valley values before and after them are P1-V 11 ,P1-V 12 ,P2-V 21 ,P2-V 22 ,P3-V 31 ,P3-V 32 , and the average is The second interference signal strength calculation formula is wherein w1, w2 are weight coefficients, and w1+w2=1, for example w1=0.4, w2=0.6, the second interference signal strength of the first target signal frequency is obtained by substituting the calculated mean value into the formula.

[0102] In step 213, the signals in the first target frequency interval with the second interference signal strength greater than or equal to the second preset strength threshold, the signals corresponding to the second target frequency interval, and the signals corresponding to the second target signal frequency are determined as motion interference signals.

[0103] Further, the second preset strength threshold is set, and the second interference signal strength calculated for the first target signal frequency in each first target frequency interval is compared with the threshold. If the second interference signal strength is greater than or equal to the second preset strength threshold, the corresponding signal in the first target frequency interval is considered as a motion interference signal. At the same time, the signals corresponding to the second target frequency interval and the second target signal frequency are also identified as motion interference signals due to their own characteristics. Finally, these signals that meet the conditions are determined as motion interference signals in the pressure signal in the cycling mode. In an embodiment, the second preset strength threshold is 0.8. For the first target signal frequency 23 Hz with the second interference signal strength S2=1.2 calculated above, since 1.2>0.8, the signal corresponding to the frequency is determined as a motion interference signal. At the same time, the signals corresponding to the second target frequency interval 50-60 Hz and the second target signal frequencies 21 Hz and 29 Hz in the first target frequency interval are also determined as motion interference signals.

[0104] The embodiment of the present application comprehensively considers the relationship between the signal frequency peak value and the center frequency and the signal frequency valley value, can more comprehensively and accurately identify the motion interference signals in the pressure signal in the cycling mode, effectively avoids the influence of the motion interference signals on the measurement results, obtains the blood pressure oscillation wave signal in the pressure signal in the cycling mode, effectively avoids the influence of the motion interference signals on the measurement results, improves the accuracy and reliability of the blood pressure measurement in the cycling mode, and meets the demand of the user for precise monitoring of blood pressure during exercise.

[0105] In an embodiment, steps 214 to 217 are described as follows:

[0106] In step 214, if the current motion mode is the swimming mode, the motion period is determined based on the attitude information collected by the gyroscope, and the pressure signal is split based on the motion period to obtain a plurality of signal sub-sequences.

[0107] Optionally, when the current exercise mode is determined as the swimming mode, the posture information of the user during swimming is collected by using the built-in gyroscope. The posture of the human body changes periodically during swimming, such as the stroke and turning of the human body. Therefore, the exercise period can be determined by analyzing the posture data (such as angular velocity and angle change) collected by the gyroscope.

[0108] Further, the pressure signal is split into multiple signal subsequences with the same time length by taking the exercise period as the time interval, and each subsequence corresponds to the pressure change in one exercise period.

[0109] In an embodiment, the built-in gyroscope collects the posture information at a frequency of 100 Hz. By analyzing the angular velocity data collected by the gyroscope, it is found that the angular velocity changes periodically for one complete stroke during swimming. The exercise period T is calculated to be 0.8 seconds. The sampling frequency of the pressure signal is 500 Hz. The pressure signal is split into multiple signal subsequences Q1, Q2,... by taking T = 0.8 seconds as the time interval. Since the number of sampling points of the pressure signal in 0.8 seconds is 0.8*500 = 400, the pressure signal is split into multiple signal subsequences Q1, Q2,... containing 400 sampling points.

[0110] Step 215, based on the preset period threshold and the preset amplitude threshold, the signal subsequence is screened based on the fluctuation period and amplitude change of the signal in each signal subsequence, to obtain the first target signal subsequence and the second target signal subsequence containing water wave interference.

[0111] Further, the preset period threshold and the preset amplitude threshold are set to screen the signal subsequence. The preset period threshold is used to determine whether the signal fluctuation period in the signal subsequence meets the normal period range of swimming exercise, and the preset amplitude threshold is used to determine whether the amplitude change of the signal in the signal subsequence is within a reasonable range. Therefore, the signal subsequence whose signal fluctuation period meets the preset period threshold and whose amplitude change meets the preset amplitude threshold is determined as the first target signal subsequence. Such signal subsequence is likely to contain normal exercise-related pressure changes. The signal subsequence whose fluctuation period or / and amplitude change is abnormal, which may be affected by water wave interference and other factors, is determined as the second target signal subsequence.

[0112] In an embodiment, the preset period threshold is 0.7-0.9 seconds, and the preset amplitude threshold is 3-8 mV. For the signal subsequence Q1, the calculated signal fluctuation period thereof is 0.82 seconds, and the signal amplitude in the subsequence is between 3.5-7 mV, satisfying the preset period threshold and the preset amplitude threshold conditions, and Q1 is determined as the first target signal subsequence; while the signal subsequence Q2, although the signal fluctuation period thereof is 0.8 seconds, the amplitude is between 2-10 mV, and the amplitude variation exceeds the preset amplitude threshold, Q2 is determined as the second target signal subsequence containing water wave interference.

[0113] In step 216, for each first target signal subsequence, the third interference signal strength is determined based on the mean of the difference between the signal peak value and the amplitude value of each signal, the mean of the difference between the signal valley value and the amplitude value of each signal, and the mean of the amplitude standard deviation of each signal.

[0114] Further, for each first target signal subsequence, the mean of the difference between the signal peak value and the amplitude value of each signal is calculated, reflecting the degree of deviation of the signal peak value from the average amplitude, and the mean of the difference between the signal valley value and the amplitude value of each signal is calculated, reflecting the deviation of the signal valley value from the average amplitude, and the mean of the amplitude standard deviation of each signal is calculated, for measuring the dispersion degree of the signal amplitude.

[0115] Further, the above three means are weighted and summed to obtain the third interference signal strength, wherein the third interference signal strength quantifies the strength of the motion interference signal in each first target signal subsequence. The specific formula can refer to the calculation formula in the running mode, which is not described here.

[0116] In step 217, the signals corresponding to the first target signal subsequences and the second target signal subsequences whose third interference signal strength is greater than or equal to the third preset strength threshold are determined as the motion interference signals.

[0117] Further, the third interference signal strength calculated for each first target signal subsequence is compared with the set third preset strength threshold. If the third interference signal strength is greater than or equal to the third preset strength threshold, it is considered that the signal corresponding to the first target signal subsequence contains strong motion interference signals; at the same time, the second target signal subsequence is also determined as the motion interference signal because it has been determined to contain water wave interference and other abnormal conditions. Finally, the signals corresponding to the first target signal subsequences and the second target signal subsequences that meet the conditions are determined as the motion interference signals in the pressure signals in the swimming mode.

[0118] In an embodiment, the third preset intensity threshold is 0.6. For the first target signal subsequence R1, the calculated third interference signal intensity is 0.7, and since 0.7>0.6, the signal corresponding to the first target signal subsequence R is determined as a motion interference signal; and the second target signal subsequence R2 is directly determined as a motion interference signal due to its own characteristics, obtaining the motion interference signal in the pressure signal in the swimming mode.

[0119] The embodiment of the present application fully considers the periodicity of swimming and water wave interference, can more comprehensively and accurately identify the motion interference signal in the pressure signal in the swimming mode, effectively avoids the influence of the motion interference signal on the measurement result, obtains the blood pressure oscillation wave signal in the pressure signal in the swimming mode, effectively avoids the influence of the motion interference signal on the measurement result, improves the accuracy and reliability of blood pressure measurement in the swimming mode, and meets the demand of the user for precise blood pressure monitoring during exercise.

[0120] Optionally, with reference to Figure 2 , Figure 2 is a flowchart of the blood pressure monitoring method provided by the present application. The execution subject of the blood pressure monitoring method in the embodiment of the present application is a blood pressure monitoring device, and the blood pressure monitoring method comprises:

[0121] Step 10, acquiring the pressure signal of the user in the motion state based on the pressure sensor, and acquiring the acceleration signal of the user in the motion state based on the acceleration sensor; the acceleration signal comprises a motion frequency signal and a motion amplitude signal.

[0122] Optionally, the blood pressure monitoring device acquires the pressure signal of the user in the motion state through the pressure sensor, and acquires the acceleration signal of the user in the motion state through the acceleration sensor, wherein the acceleration signal comprises a motion frequency signal and a motion amplitude signal.

[0123] Step 20, performing mode recognition based on the motion frequency signal and the motion amplitude signal to obtain the current motion mode, and performing signal recognition on the pressure signal based on the current motion mode to obtain the motion interference signal in the pressure signal.

[0124] Further, the blood pressure monitoring device performs mode recognition based on the motion frequency signal and the motion amplitude signal to obtain the current motion mode, and performs signal recognition on the pressure signal based on the current motion mode to obtain the motion interference signal in the pressure signal in the current motion mode.

[0125] Step 30, performing signal filtering processing on the pressure signal based on the motion interference signal to obtain the blood pressure oscillation wave signal in the pressure signal.

[0126] Further, the blood pressure monitoring device performs signal filtering processing on the pressure signal according to the motion interference signal to obtain a blood pressure oscillatory wave signal in the pressure signal. Common filtering methods include low-pass filtering, band-pass filtering, and adaptive filtering. Low-pass filtering can remove high-frequency motion interference signals in the pressure signal and retain low-frequency blood pressure oscillatory wave signals, because the frequency of the blood pressure oscillatory wave signal is generally around 0.5-15 Hz. Band-pass filtering can allow only signals within a specific frequency range to pass, further enhancing the extraction effect of the blood pressure oscillatory wave signal. Adaptive filtering can automatically adjust filtering parameters according to signal changes, more effectively removing motion interference signals in complex motion environments.

[0127] In actual applications, multiple filtering methods are usually combined for processing. First, a low-pass filter is used to preliminarily filter the pressure signal to remove most high-frequency motion interference signals. Then, a band-pass filter is used to further process the preliminarily filtered signal to retain signals within the frequency range of the blood pressure oscillatory wave signal. Finally, an adaptive filter is used to fine-tune the signal and further optimize the filtering effect according to real-time signal changes, thereby obtaining a relatively pure blood pressure oscillatory wave signal.

[0128] Step 40: determining blood pressure parameters of the user in the motion state based on the blood pressure oscillatory wave signal.

[0129] Further, the blood pressure oscillatory wave signal contains rich information related to blood pressure. Determining blood pressure parameters of the user in the motion state based on the blood pressure oscillatory wave signal mainly involves calculating systolic pressure, diastolic pressure, and mean arterial pressure. A common calculation method is based on the principle of oscillography. This method determines blood pressure values by analyzing the relationship between the amplitude of the blood pressure oscillatory wave and the cuff pressure. Specifically, feature extraction is performed on the blood pressure oscillatory wave signal, such as finding the peak value, valley value, and slope of the waveform, etc. Generally, as the cuff pressure gradually decreases, the amplitude of the blood pressure oscillatory wave gradually increases. When the cuff pressure equals the mean arterial pressure, the amplitude of the oscillatory wave reaches a maximum value. When the cuff pressure approaches the systolic pressure, the amplitude of the oscillatory wave begins to significantly increase. When the cuff pressure approaches the diastolic pressure, the amplitude of the oscillatory wave begins to decrease. By establishing a mathematical model between the blood pressure oscillatory wave feature parameters and the blood pressure values, the systolic pressure, diastolic pressure, and mean arterial pressure can be calculated. For example, an empirical formula or a regression model trained based on machine learning can be used, with the extracted feature parameters as input and the corresponding blood pressure parameter values as output.

[0130] The embodiment of the present application can accurately identify the current motion mode of the user in the motion state, can acquire the motion interference signal in different motion modes, can perform signal filtering processing on the pressure signal according to the motion interference signal, can accurately identify and remove the motion interference signal, and can accurately filter out the blood pressure oscillation wave signal in the pressure signal. Further, the blood pressure parameter of the user in the motion state is determined according to the blood pressure oscillation wave signal, the influence of the motion interference signal on the measurement result is effectively avoided, the accuracy and reliability of the blood pressure measurement in the motion state are improved, and the demand of the user for accurate blood pressure monitoring in the motion process is met.

[0131] Please refer to Figure 3 , Figure 3 The embodiment of the electronic device provided by the present application is shown in the figure. As shown in the figure, the present application provides an electronic device 300, which comprises a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented: Figure 3

[0132] The pressure signal of the user in the motion state is collected based on the pressure sensor, and the acceleration signal of the user in the motion state is collected based on the acceleration sensor; the acceleration signal comprises a motion frequency signal and a motion amplitude signal;

[0133] The motion frequency signal and the motion amplitude signal are used for pattern recognition to obtain a current motion mode, and the pressure signal is used for signal recognition based on the current motion mode to obtain a motion interference signal in the pressure signal;

[0134] The pressure signal is used for signal filtering processing based on the motion interference signal to obtain a blood pressure oscillation wave signal in the pressure signal;

[0135] The blood pressure parameter of the user in the motion state is determined based on the blood pressure oscillation wave signal.

[0136] Please refer to Figure 4 , Figure 4 The embodiment of the computer readable storage medium provided by the present application is shown in the figure. As shown in the figure, the present embodiment provides a computer readable storage medium 400, which stores a computer program 311. When the computer program 311 is executed by a processor, the following steps are implemented: Figure 4

[0137] The pressure signal of the user in the motion state is collected based on the pressure sensor, and the acceleration signal of the user in the motion state is collected based on the acceleration sensor; the acceleration signal comprises a motion frequency signal and a motion amplitude signal;

[0138] ​​The motion frequency signal and the motion amplitude signal are used for pattern recognition to obtain a current motion pattern, and the pressure signal is subjected to signal recognition based on the current motion pattern to obtain a motion interference signal in the pressure signal;

[0139] The pressure signal is subjected to signal filtering based on the motion interference signal to obtain a blood pressure oscillation wave signal in the pressure signal;

[0140] The blood pressure parameter of the user in the motion state is determined based on the blood pressure oscillation wave signal.

[0141] In another aspect, the present application also provides a computer program product, which comprises a computer program that can be stored on a non-transitory computer readable storage medium, and the computer program can be executed by a processor to enable a computer to perform the blood pressure monitoring method provided by the above-mentioned methods, the blood pressure monitoring method comprising:

[0142] The pressure signal of the user in the motion state is collected based on a pressure sensor, and the acceleration signal of the user in the motion state is collected based on an acceleration sensor; the acceleration signal comprises a motion frequency signal and a motion amplitude signal;

[0143] The motion frequency signal and the motion amplitude signal are used for pattern recognition to obtain a current motion pattern, and the pressure signal is subjected to signal recognition based on the current motion pattern to obtain a motion interference signal in the pressure signal;

[0144] The pressure signal is subjected to signal filtering based on the motion interference signal to obtain a blood pressure oscillation wave signal in the pressure signal;

[0145] The blood pressure parameter of the user in the motion state is determined based on the blood pressure oscillation wave signal.

[0146] The apparatus embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0147] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0148] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A wearable blood pressure monitoring device, characterized in that, It includes a pressure sensor, an accelerometer, and a central processing unit; the central processing unit is connected to both the pressure sensor and the accelerometer. Pressure sensors are used to: collect pressure signals from users during movement; The accelerometer is used to: collect acceleration signals of a user in motion; the acceleration signals include motion frequency signals and motion amplitude signals; The central processing unit is used for: Pattern recognition is performed based on the motion frequency signal and the motion amplitude signal to obtain the current motion pattern, and signal recognition is performed on the pressure signal based on the current motion pattern to obtain the motion interference signal in the pressure signal; Based on the motion interference signal, the pressure signal is filtered to obtain the blood pressure oscillation wave signal in the pressure signal; The blood pressure parameters of the user during exercise are determined based on the blood pressure oscillation wave signal. The step of identifying the motion interference signal in the pressure signal based on the current motion mode includes: If the current exercise mode is running mode, the pressure signal is divided based on a time window of a preset size, and a first target time window and a second target time window are determined based on a preset mean threshold and the pressure signal value of each sampling point in the sub-signal within each time window. For each first target time window, determine the local maxima and local minima, and determine the time interval between adjacent local maxima; For each local maximum, the time-related parameters of each local maximum are determined based on the difference between the rise time from the preceding local minimum to each local maximum and the fall time from each local maximum to the subsequent local minimum. The strength of the first interference signal is determined based on the mean of the time interval between adjacent local maxima, the mean of the peak-to-peak values ​​of adjacent local maxima, and the mean of the time correlation parameter of each local maximum. The sub-signals within the first target time window and the sub-signals within the second target time window whose interference signal strength is greater than or equal to the first preset strength threshold are determined as the motion interference signal; The step of identifying the pressure signal based on the current motion mode to obtain the motion interference signal in the pressure signal includes: If the current exercise mode is cycling mode, then the pressure signal is subjected to fast Fourier transform to obtain the frequency domain representation of the pressure signal, and based on the preset energy ratio and the energy distribution of the frequency interval in the frequency domain representation, the first target frequency interval and the second target frequency interval are determined. The frequency filtering range is determined based on the riding speed collected by the speed sensor, and the signal frequencies in the first target frequency range are filtered based on the frequency filtering range to obtain the first target signal frequency and the second target signal frequency in the first target frequency range. For each target signal frequency in the first target frequency interval, the strength of the second interference signal is determined based on the average difference between the peak value of each signal frequency and the center signal frequency, and the average difference between the peak value of each signal frequency and the two preceding and following valley values ​​of the signal frequency. The signals within the first target frequency range whose second interference signal strength is greater than or equal to the second preset strength threshold, the signals corresponding to the second target frequency range, and the signals corresponding to the second target signal frequency are determined as the motion interference signals; The step of identifying the pressure signal based on the current motion mode to obtain the motion interference signal in the pressure signal includes: If the current motion mode is swimming mode, the motion cycle is determined based on the attitude information collected by the gyroscope, and the pressure signal is split based on the motion cycle to obtain multiple signal subsequences; Based on a preset period threshold and a preset amplitude threshold, combined with the fluctuation period and amplitude changes of the signal in each signal subsequence, the signal subsequences are filtered to obtain the first target signal subsequence and the second target signal subsequence containing water wave interference. For each first target signal subsequence, the intensity of the third interference signal is determined based on the mean of the difference between the signal peak and the amplitude value of each signal, the mean of the difference between the signal trough and the amplitude value of each signal, and the mean of the standard deviation of the amplitude of each signal. The signals corresponding to the first target signal subsequence and the second target signal subsequence, whose third interference signal strength is greater than or equal to the third preset strength threshold, are determined as the motion interference signals.

2. The wearable blood pressure monitoring device according to claim 1, characterized in that, The step of performing pattern recognition based on the motion frequency signal and the motion amplitude signal to obtain the current motion pattern includes: Frequency characteristic indicators are determined based on the number of motion frequencies in the motion frequency signal and the ratio between the square of each motion frequency and the mean of the motion frequencies. Based on the frequency range in which each frequency feature index is located, determine the frequency range identifier for each frequency feature index. The amplitude change index is determined based on the sum of the absolute values ​​of the amplitude differences between adjacent time points in the motion amplitude signal and the maximum value of the amplitude. The current motion pattern is obtained by performing pattern recognition based on the frequency range identifier and the amplitude change index.

3. The wearable blood pressure monitoring device according to claim 2, characterized in that, The process of obtaining the current motion pattern based on the frequency range identifier and the amplitude change index includes: If the frequency range identifier is the first range identifier, and the amplitude change index is less than the first preset amplitude change threshold, then the current exercise mode is determined to be cycling mode. If the frequency interval is identified as the second interval, and the amplitude change index is greater than or equal to the first preset amplitude change threshold and less than the second preset amplitude change threshold, then the current exercise mode is determined to be the running mode. If the frequency interval is identified as the third interval, and the amplitude change index is greater than or equal to the second preset amplitude change threshold, then the current exercise mode is determined to be the swimming mode. The first interval identifier, the second interval identifier, and the third interval identifier are different identifiers.

4. The wearable blood pressure monitoring device according to claim 2, characterized in that, The acceleration signal also includes a direction of travel signal; the central processing unit is further used for: The difference in the running direction angle between adjacent time points in the running direction signal is compared with a preset direction change rate threshold. If the difference in the running direction angle is greater than the preset direction change rate threshold, then it is determined that there is a sudden change in direction at the current time point, the number of sudden changes is recorded, and the number of direction sudden changes is obtained. If the current exercise mode is cycling mode, and the number of directional changes is greater than the upper limit of the first directional change number in cycling mode, then the current exercise mode is changed from cycling mode to running mode. If the current exercise mode is swimming mode, and the number of directional changes is greater than the upper limit of the second directional change number in swimming mode, then the current exercise mode is changed from swimming mode to running mode.

5. A blood pressure monitoring method, implemented based on the wearable blood pressure monitoring device as described in any one of claims 1 to 4, characterized in that, The blood pressure monitoring method includes: The system collects pressure signals from the user during movement using a pressure sensor and acceleration signals from the user during movement using an accelerometer; the acceleration signals include motion frequency signals and motion amplitude signals. Pattern recognition is performed based on the motion frequency signal and the motion amplitude signal to obtain the current motion pattern, and signal recognition is performed on the pressure signal based on the current motion pattern to obtain the motion interference signal in the pressure signal; Based on the motion interference signal, the pressure signal is filtered to obtain the blood pressure oscillation wave signal in the pressure signal; The blood pressure parameters of the user during exercise are determined based on the blood pressure oscillation wave signal. The step of identifying the motion interference signal in the pressure signal based on the current motion mode includes: If the current exercise mode is running mode, the pressure signal is divided based on a time window of a preset size, and a first target time window and a second target time window are determined based on a preset mean threshold and the pressure signal value of each sampling point in the sub-signal within each time window. For each first target time window, determine the local maxima and local minima, and determine the time interval between adjacent local maxima; For each local maximum, the time-related parameters of each local maximum are determined based on the difference between the rise time from the preceding local minimum to each local maximum and the fall time from each local maximum to the subsequent local minimum. The strength of the first interference signal is determined based on the mean of the time interval between adjacent local maxima, the mean of the peak-to-peak values ​​of adjacent local maxima, and the mean of the time correlation parameter of each local maximum. The sub-signals within the first target time window and the sub-signals within the second target time window whose interference signal strength is greater than or equal to the first preset strength threshold are determined as the motion interference signal; The step of identifying the pressure signal based on the current motion mode to obtain the motion interference signal in the pressure signal includes: If the current exercise mode is cycling mode, then the pressure signal is subjected to fast Fourier transform to obtain the frequency domain representation of the pressure signal, and based on the preset energy ratio and the energy distribution of the frequency interval in the frequency domain representation, the first target frequency interval and the second target frequency interval are determined. The frequency filtering range is determined based on the riding speed collected by the speed sensor, and the signal frequencies in the first target frequency range are filtered based on the frequency filtering range to obtain the first target signal frequency and the second target signal frequency in the first target frequency range. For each target signal frequency in the first target frequency interval, the strength of the second interference signal is determined based on the average difference between the peak value of each signal frequency and the center signal frequency, and the average difference between the peak value of each signal frequency and the two preceding and following valley values ​​of the signal frequency. The signals within the first target frequency range whose second interference signal strength is greater than or equal to the second preset strength threshold, the signals corresponding to the second target frequency range, and the signals corresponding to the second target signal frequency are determined as the motion interference signals; The step of identifying the pressure signal based on the current motion mode to obtain the motion interference signal in the pressure signal includes: If the current motion mode is swimming mode, the motion cycle is determined based on the attitude information collected by the gyroscope, and the pressure signal is split based on the motion cycle to obtain multiple signal subsequences; Based on a preset period threshold and a preset amplitude threshold, combined with the fluctuation period and amplitude changes of the signal in each signal subsequence, the signal subsequences are filtered to obtain the first target signal subsequence and the second target signal subsequence containing water wave interference. For each first target signal subsequence, the intensity of the third interference signal is determined based on the mean of the difference between the signal peak and the amplitude value of each signal, the mean of the difference between the signal trough and the amplitude value of each signal, and the mean of the standard deviation of the amplitude of each signal. The signals corresponding to the first target signal subsequence and the second target signal subsequence, whose third interference signal strength is greater than or equal to the third preset strength threshold, are determined as the motion interference signals.

6. An electronic device, comprising: The memory and processor are characterized in that the memory stores a computer software program, and when the processor reads and executes the computer software program, it implements the blood pressure monitoring method as described in claim 5.

7. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores a computer software program, which, when executed by a processor, implements the blood pressure monitoring method as described in claim 5.

Images