CN120899211B

CN120899211B - Blood pressure compensation measurement methods, devices, and smartwatches for sports scenarios

Info

Publication number: CN120899211B
Application number: CN202511414771.XA
Authority: CN
Inventors: 徐弘基; 王静; 季俊; 李毓卓; 翟宁宁; 周兰军
Original assignee: Shanghai Lehuoyuan Medical Technology Co ltd
Current assignee: Shanghai Lehuoyuan Medical Technology Co ltd
Priority date: 2025-09-30
Filing date: 2025-09-30
Publication date: 2025-12-02
Anticipated expiration: 2045-09-30
Also published as: CN120899211A

Abstract

This invention relates to a blood pressure compensation measurement method, device, and smartwatch for sports scenarios. The method generates a lactate accumulation marker by fusing motion acceleration and heart rate signals. Based on this marker, specific frequency components of the pressure oscillation wave signal are extracted and a time-domain envelope is generated. The variation in the width of the envelope's main peak and the abnormal frequency-domain energy distribution are quantified to generate a tension anomaly, which is then mapped to a dynamic vascular volume change curve. A biomechanical compensation curve is constructed using a static vascular volume benchmark, and the envelope, free from vascular tension interference, is reconstructed through frequency-domain convolution. Finally, blood pressure feature points are located based on the differential features of the reconstructed envelope, and a compensated blood pressure value is output. This method establishes, for the first time, a compensation model for lactate metabolism and vascular biomechanical characteristics, solving the problem of systematic shift of feature points caused by abnormal vascular tension after exercise, and significantly reducing blood pressure measurement errors.

Description

Blood pressure compensation measurement method and device for sports scene and intelligent watch

Technical Field

The invention relates to the technical field of blood pressure compensation measurement, in particular to a blood pressure compensation measurement method and device for sports scenes and a smart watch.

Background

In the field of health monitoring, blood pressure measurement in sports scenes is of great importance for assessing cardiovascular function and sports safety. The traditional oscillometric blood pressure measurement technology relies on characteristic point identification of cuff pressure shock waves, and systolic pressure and diastolic pressure are determined by analyzing the maximum slope point and curvature change point of an envelope curve. The method has better reliability in the resting state and has been widely used in household sphygmomanometers and medical equipment. Along with the development of wearable equipment, people are increasingly in demand for real-time blood pressure monitoring in the exercise process, and especially in the scenes of body-building training, athlete physiological monitoring and the like, accurate acquisition of blood pressure data after exercise is vital to preventing cardiovascular accidents.

However, existing blood pressure measurement techniques face significant limitations in the post-exercise scenario. When the human body performs anaerobic exercise, lactic acid accumulation generated by muscle tissues can cause abnormal change of vascular tension, so that the envelope line shape of the cuff pressure shock wave is distorted. The physiological interference is characterized by characteristic point offset, envelope curve broadening and abnormal spectral energy distribution, so that the traditional algorithm can not accurately position the characteristic points of blood pressure. While prior solutions have attempted to suppress limb movement disturbances by motion artifact filtering or acceleration compensation, they have failed to address the core problem of changes in vascular biomechanics due to lactate metabolism, resulting in systematic deviations in measurement results. More importantly, the prior art lacks quantitative modeling capability for dynamic change of blood vessel tension, cannot establish a compensation mechanism between lactic acid accumulation and blood pressure measurement distortion, and the blood pressure data obtained by a user after exercise has misleading risks.

Disclosure of Invention

Based on the above, the invention aims to provide a blood pressure compensation measurement method and device capable of precisely eliminating a sports scene of lactic acid accumulation interference and a smart watch.

The invention adopts the following scheme:

in a first aspect, the present invention provides a blood pressure compensation measurement method for a sports scene, including the steps of:

S1, processing a motion acceleration signal acquired by a triaxial acceleration sensor and a heart rate signal acquired by a heart rate sensor, calculating a motion intensity index based on acceleration and a heart rate recovery slope based on heart rate change rate, and generating a lactic acid accumulation mark based on a preset intensity threshold and a preset recovery threshold;

s2, processing cuff pressure shock wave signals acquired by a pressure sensor, extracting an intrinsic mode function of a frequency range of 0.5-5Hz, and carrying out Hilbert transformation to generate a time domain envelope;

S3, processing the time envelope curve, calculating the variation of the width of the main peak of the envelope curve relative to a static reference and the energy ratio of the 8-12Hz frequency band to the 1-4Hz frequency band, and generating Zhang Liyi constant degrees representing abnormal vascular tension;

S4, processing the tension abnormality degree, calculating a blood vessel Shu Zhangliang obtained through a nonlinear mapping function, and constructing a blood vessel volume compensation curve by combining an exponential decay time function;

S5, processing the time domain envelope curve and the blood vessel volume compensation curve, reconstructing the compensated envelope curve through frequency domain convolution operation, positioning a maximum slope point and a second order correction variable point on the reconstructed envelope curve, and outputting a compensated blood pressure value for eliminating motion interference.

In one embodiment, the S1 method for measuring blood pressure compensation of a sports scene provided by the invention specifically includes the following steps:

S11, integrating the cube roots of the motion acceleration signals acquired by the triaxial acceleration sensor, calculating the integral value of the cube roots of the triaxial composite acceleration in a time window, and generating a motion intensity index;

s12, performing linear regression processing on heart rate signals acquired by a heart rate sensor, calculating a slope value of a heart rate descending rate after movement is stopped, and generating a heart rate recovery slope;

and S13, performing double-threshold logic judgment on the exercise intensity index and the heart rate recovery slope, and generating a lactic acid accumulation mark in an activated state when the exercise intensity exceeds a preset intensity threshold and the heart rate recovery rate is lower than the preset recovery threshold.

In one embodiment, the S2 method for measuring blood pressure compensation of a sports scene provided by the invention specifically includes the following steps:

S21, performing empirical mode decomposition processing on cuff pressure shock wave signals acquired by a pressure sensor, decomposing the signals into a plurality of eigenvalue function components, and extracting eigenvalue functions of a frequency band of 0.5-5 Hz;

S22, performing Hilbert transformation on the eigenmode function, calculating the instantaneous amplitude of an analysis signal, and generating an initial envelope curve;

S23, performing smoothing filtering processing on the initial envelope, eliminating high-frequency fluctuation interference through mean value calculation in a time window, and generating an optimized time domain envelope.

In one embodiment, the S3 method for measuring blood pressure compensation of a sports scene provided by the invention specifically includes the following steps:

s31, carrying out main peak detection processing on the time domain envelope, positioning the global maximum point of the envelope, measuring the half-height width of the envelope, and generating the width variation of the main peak;

S32, carrying out frequency domain energy analysis processing on the time envelope curve, calculating the energy distribution ratio of the 8-12Hz frequency band to the 1-4Hz frequency band, and generating a frequency domain characteristic ratio;

and S33, carrying out weighted fusion processing on the main peak width variation and the frequency domain characteristic ratio, and calculating the comprehensive offset by combining a static reference value to generate tension anomaly degree which is used for indicating the abnormal degree of blood vessel tension caused by lactic acid accumulation.

In one embodiment, the calculation formula of the tension anomaly degree of the blood pressure compensation measurement method of the sports scene provided by the invention is as follows:

;

wherein, the For the degree of dystonia, the degree of dystonia of the blood vessel is characterized,As the amount of variation in the width of the main peak,Is the half-height width of the static reference,Is the characteristic ratio of the frequency domain,As the weight factor of the time domain feature,Is a frequency domain characteristic weight factor.

In one embodiment, the S4 method for measuring blood pressure compensation of a sports scene provided by the invention specifically includes the following steps:

s41, carrying out nonlinear function mapping processing on the tension anomaly degree, and converting the tension anomaly degree into a blood vessel volume change proportion through hyperbolic tangent transformation to generate a blood vessel Shu Zhangliang;

S42, carrying out exponential decay modeling treatment on the blood vessel Shu Zhangliang, simulating a dynamic recovery process of the blood vessel volume in the lactic acid metabolic process by using a time decay function, and constructing a volume change curve which decreases with time;

And S43, carrying out baseline superposition processing on the volume change curve, adding the volume change curve with a preset static blood vessel volume reference value, and generating a blood vessel volume compensation curve which is used for subsequent frequency domain filtering processing to eliminate abnormal interference of blood vessel tension.

In one embodiment, the S5 method for measuring blood pressure compensation of a sports scene provided by the invention specifically includes the following steps:

S51, carrying out frequency domain convolution processing on the time domain envelope curve and the vascular volume compensation curve, multiplying the envelope curve frequency spectrum by a compensation filter transfer function in the frequency domain, and carrying out inverse Fourier transform to the time domain to generate a reconstructed compensation envelope curve;

s52, performing differential feature extraction processing on the reconstructed compensation envelope, searching a maximum value point by calculating a first derivative and detecting a position point of the second derivative from negative to positive for the first time, and generating a systolic pressure feature moment and a diastolic pressure feature moment;

And S53, performing pressure value mapping processing on the characteristic time of the systolic pressure and the characteristic time of the diastolic pressure, inquiring the cuff pressure value at the corresponding time according to the characteristic time, and generating a compensated blood pressure value comprising a compensated systolic pressure value and a compensated diastolic pressure value.

In one embodiment, the step S52 of the method for measuring blood pressure compensation in a sports scene provided by the present invention specifically includes the following steps:

s521, performing first derivative calculation processing on the reconstructed compensation envelope, and calculating the instantaneous slope value of each sampling point on the envelope by a center difference method to generate a first derivative sequence;

S522, carrying out extreme point detection processing on the first derivative sequence, scanning the whole sequence to find the maximum positive value point and recording the corresponding moment of the maximum positive value point, and generating the characteristic moment of systolic pressure;

S523, performing second derivative calculation processing on the reconstructed compensation envelope, calculating curvature change values of sampling points on the envelope through a second-order center difference method, searching a point of which the first curvature changes from negative to positive after the characteristic moment of systolic pressure, and generating the characteristic moment of diastolic pressure.

In a second aspect, the present invention provides a blood pressure compensation measurement device for a sports scene, the device being configured with:

the lactic acid accumulation mark generation module is used for processing the exercise acceleration signal acquired by the triaxial acceleration sensor and the heart rate signal acquired by the heart rate sensor, calculating an exercise intensity index based on acceleration and a heart rate recovery slope based on heart rate change rate, and generating a lactic acid accumulation mark based on a preset intensity threshold and a preset recovery threshold;

the time domain envelope generation module is used for processing the cuff pressure oscillating wave signals acquired by the pressure sensor, extracting the eigenmode function of the frequency band of 0.5-5Hz and carrying out Hilbert transformation to generate a time domain envelope;

The tension anomaly degree calculation module is used for processing the time domain envelope curve, calculating the variation of the width of the main peak of the envelope curve relative to a static reference and the energy ratio of the 8-12Hz frequency band to the 1-4Hz frequency band, and generating Zhang Liyi constant degrees representing the vascular tension anomaly;

The blood vessel volume compensation curve construction module is used for processing the tension abnormality degree, calculating a blood vessel Shu Zhangliang obtained through a nonlinear mapping function and constructing a blood vessel volume compensation curve by combining an exponential decay time function;

And the compensated blood pressure value output module is used for processing the time domain envelope curve and the blood vessel volume compensation curve, reconstructing the compensated envelope curve through frequency domain convolution operation, positioning a maximum slope point and a second-order derivative positive change point on the reconstructed envelope curve, and outputting a compensated blood pressure value for eliminating motion interference.

In a third aspect, the present application provides a smart watch, including a memory and a processor, where the memory stores a computer program, and the processor implements a blood pressure compensation measurement method for any one of the above sports scenes when executing the computer program.

In summary, the blood pressure compensation measurement method of the motion scene is based on a dual-threshold judgment mechanism of acceleration signal cube root integration and heart rate recovery slope, can accurately identify physiological state changes caused by lactic acid accumulation, overcomes the defect that the traditional method only depends on a single motion sensor to cause misjudgment, can effectively separate signal distortion caused by abnormal vascular tension by extracting specific frequency band components of pressure shock waves and combining with Hilbert envelope extraction technology, solves the problem of characteristic waveform flooding under motion interference, creatively fuses main peak broadening features of a time domain envelope with frequency domain energy distribution abnormal features to construct Zhang Liyi degrees, can realize quantitative characterization of vascular biomechanical property changes, and is most critical in that a vascular volume dynamic response model established through nonlinear mapping and exponential decay functions can accurately simulate recovery rules of vascular tension in the lactic acid metabolism process, can thoroughly eliminate systematic deviation of vascular volume changes on blood pressure characteristic points by combining with frequency domain convolution compensation technology, and finally can guarantee stable and true capture of the characteristic points under complex interference environment by adopting differential feature combined detection mechanism in a positioning link. The method establishes a complete technical chain from lactic acid metabolism dynamics to blood pressure measurement compensation for the first time, can maintain millimeter-mercury-level measurement accuracy in a post-exercise blood vessel tension abnormal scene, and solves the core pain point of the blood pressure monitoring misalignment of wearable equipment in the scenes of body building, rehabilitation, exercise training and the like.

For a better understanding and implementation, the present invention is described in detail below with reference to the drawings.

Drawings

Fig. 1 is a schematic flow chart of a blood pressure compensation measurement method for a sports scene according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of generating tension anomalies according to an embodiment of the present application;

FIG. 3 is a flow chart of generating a compensated blood pressure value including a compensated systolic pressure value and a compensated diastolic pressure value according to an embodiment of the present application;

Fig. 4 is a schematic structural diagram of a blood pressure compensation measurement device in a sports scene according to another embodiment of the present application.

Detailed Description

In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

In one embodiment, as shown in fig. 1, a method for measuring blood pressure compensation of a sports scene is provided, and this embodiment is illustrated by applying the method to a terminal, it will be understood that the method may also be applied to a server, and may also be applied to an apparatus including the terminal and the server, and implemented through interaction between the terminal and the server. In the embodiment, the intelligent watch integrated with the blood pressure measurement module is used as a carrier, the hardware comprises a triaxial acceleration sensor, an optical heart rate sensor, a piezoresistive pressure sensor and an embedded processor, and the software is transplanted to the embedded system after algorithm verification is completed. In this embodiment, the method comprises the steps of:

S1, processing a motion acceleration signal acquired by a triaxial acceleration sensor and a heart rate signal acquired by a heart rate sensor, calculating a motion intensity index based on acceleration and a heart rate recovery slope based on heart rate change rate, and generating a lactic acid accumulation mark based on a preset intensity threshold and a preset recovery threshold.

The system is integrated in a triaxial acceleration sensor of the intelligent watch to collect movement acceleration signals, meanwhile, an optical heart rate sensor integrated in the intelligent watch is used for collecting heart rate signals, filtering processing is performed on the movement acceleration signals collected by the intelligent watch to remove limb tremor noise, self-adaptive filtering processing is performed on the heart rate signals collected by the intelligent watch to remove movement artifacts, and a reference signal of the self-adaptive filtering is taken from the output of the triaxial acceleration sensor integrated in the intelligent watch.

Preferably, the system performs vector synthesis operation on the preprocessed triaxial acceleration signals, and then performs average value calculation on the synthesized signals by adopting a sliding window to obtain the motion intensity index based on acceleration. The system determines a preset intensity threshold through a clinical experiment, in the clinical experiment process, the system synchronously acquires blood lactic acid concentration data of a subject through a monitoring unit associated with the intelligent watch, and the preset intensity threshold is determined according to the corresponding relation between the blood lactic acid concentration and the exercise intensity index.

The system identifies the moment of motion stop by the change in the acceleration signal, and determines that motion is stopped when the motion intensity index falls from above a certain level to below a certain level. And the system extracts a heart rate sequence acquired by the intelligent watch within a period of time after the motion stops, and performs linear fitting operation on the heart rate sequence to obtain a heart rate recovery slope. The system determines a preset recovery threshold through clinical data, and determines the preset recovery threshold according to the corresponding relation between the heart rate recovery slope and the lactic acid metabolism state. When the exercise intensity index reaches a preset intensity threshold and the heart rate recovery slope reaches a preset recovery threshold, the system sets the lactic acid accumulation mark to a specific state, otherwise, the system sets the lactic acid accumulation mark to another state.

S2, processing the cuff pressure shock wave signals acquired by the pressure sensor, extracting the eigenmode function of the frequency range of 0.5-5Hz, and carrying out Hilbert transformation to generate a time domain envelope curve.

Specifically, the system controls the piezoresistive pressure sensor of the intelligent watch, acquires pressure shock wave signals in the process of inflation and deflation of the cuff, and the measuring range of the sensor covers the whole range of cuff pressure change. The system carries out Butterworth high-pass filtering on the original pressure shock wave signal, removes baseline drift caused by slow deflation of the cuff, eliminates high-frequency electromagnetic interference through low-pass filtering, and obtains a preprocessed signal. And the system executes empirical mode decomposition on the preprocessed signals, repeatedly calculates upper and lower envelopes of the signals, takes an average value as a trend term, removes the trend term from the original signals until the residual signals meet the judging condition of the eigenmode function, and separates out multi-order eigenmode functions.

The system screens out the frequency band corresponding to the intrinsic component of the blood pressure shock wave to eliminate respiratory interference and muscle tremor interference, wherein the respiratory interference is the frequency band lower than the frequency band of the intrinsic component, and the muscle tremor interference is the frequency band higher than the frequency band of the intrinsic component.

S3, processing the time domain envelope curve, calculating the variation of the width of the main peak of the envelope curve relative to the static reference and the energy ratio of the 8-12Hz frequency band to the 1-4Hz frequency band, and generating Zhang Liyi constant degrees representing abnormal vascular tension.

Specifically, the system repeatedly executes multiple times of blood pressure measurement under the resting state of the user to be detected, extracts a time domain envelope after each measurement, calculates the half-width of the main peak of the envelope, and takes the average value of the multiple times of half-widths as a static reference of the width of the main peak of the envelope. When in a motion scene, the system calculates a first derivative of a real-time domain envelope curve, searches an extreme point of the first derivative from positive to negative to locate a main peak position, calculates the half-width of the real-time main peak, and obtains the variation relative to a static reference through difference and ratio operation. The system performs fast Fourier transform on the preprocessed pressure shock wave signals to obtain frequency domain distribution and then divides two characteristic frequency bands, wherein the first frequency band corresponds to vascular smooth muscle high-frequency vibration, namely energy change during tension abnormality, and the second frequency band corresponds to basic blood flow low-frequency vibration, the system performs integral operation on the two frequency bands to obtain energy values, the energy values are obtained through ratio operation, a weighted sum calculation model is constructed based on the energy values and the energy values, the weight coefficients are calibrated through multiple linear regression of a plurality of groups of blood pressure measurement samples after movement, the change values and the energy values are substituted into the model to obtain Zhang Liyi degrees representing vascular tension abnormality, the tension abnormality value range corresponds to different abnormality grades, and the higher grades are more strongly compensated.

And S4, processing the tension abnormality degree, calculating a blood vessel Shu Zhangliang obtained through a nonlinear mapping function, and constructing a blood vessel volume compensation curve by combining an exponential decay time function.

Specifically, the embodiment establishes the association relation between the blood vessel tension anomaly degree and the blood vessel Shu Zhangliang through experiments, adopts ultrasonic Doppler equipment to measure the change of the arterial inner diameter of a subject after movement, synchronously records the blood vessel tension anomaly degree to form an experimental database, performs fitting operation on data of the database to obtain a nonlinear mapping function, wherein the function comprises parameters corresponding to the maximum blood vessel Shu Zhangliang of the wrist radial artery of a healthy adult, and parameters ensuring that Shu Zhangliang approaches to the maximum diastole tensor when the tension anomaly degree reaches the upper limit, and based on the processing, the system substitutes the real-time tension anomaly degree into the function to obtain the blood vessel inner diameter additionally Shu Zhangliang caused by lactic acid accumulation.

Specifically, the system defines an exponential decay time function based on lactic acid metabolism time dependency, the function comprises an initial decay time constant corresponding to lactic acid metabolism rate at the moment of movement stop and a decay coefficient determined based on lactic acid half-life experimental measurement results, the input is time after movement stop, the output is a decay coefficient reflecting vasomotor tensor recovery trend, frequency parameters corresponding to cuff deflation rate periodic characteristics are introduced, blood vessels Shu Zhangliang and exponential decay time function output values are combined with frequency-related periodic function values through multiplication operation, and a vascular volume compensation curve dynamically adjusted along with time is constructed and used for counteracting the influence of vascular volume abnormality on a time domain envelope curve.

Specifically, the system performs fast fourier transform on the time domain envelope curve and the blood vessel volume compensation curve respectively, and converts the time domain signal into a frequency domain signal to obtain a frequency domain signal corresponding to the time domain envelope curve and a frequency domain signal corresponding to the blood vessel volume compensation curve. The system performs product operation on two frequency domain signals in the frequency domain, the operation is equivalent to convolution operation in the time domain, and edge effect in the time domain convolution process can be avoided. The system executes inverse fast Fourier transform on the frequency domain signal after the product operation, and converts the frequency domain signal back to a time domain signal to obtain a reconstructed compensation envelope.

Further, the system performs first derivative operation on the compensation envelope to obtain a first-order guide signal of the compensation envelope, and then locates a maximum point in the first-order guide signal, wherein the maximum point is a systolic pressure characteristic point, corresponds to a peak value of the amplitude change rate of the shock wave when the cuff pressure and the arterial systolic pressure are balanced, and records the cuff static pressure at the moment as the systolic pressure. The system performs second derivative operation on the compensation envelope line to obtain a second derivative signal of the compensation envelope line, then positions a zero crossing point which is changed from negative to positive in the second derivative signal, wherein the zero crossing point is a characteristic point of diastolic pressure, the corresponding cuff pressure is lower than the oscillation wave amplitude change rate inflection point when arterial diastolic pressure, the system records the cuff static pressure at the moment and is used as diastolic pressure, and finally, the systolic pressure and the diastolic pressure are integrated to generate a compensation blood pressure value, the compensation blood pressure value can effectively eliminate motion interference, a more accurate and reliable blood pressure measurement result is provided for a user, and therefore the purpose of blood pressure compensation measurement under a motion scene is achieved.

And S11, performing cube root integration on the motion acceleration signals acquired by the triaxial acceleration sensor, calculating the integral value of the cube root of the triaxial composite acceleration in a time window, and generating a motion intensity index.

Specifically, the motion acceleration signal collection of the system is realized through the intelligent watch, a real-time data link is established between the three-axis acceleration sensor integrated with the intelligent watch and the embedded processor, and the sensor collects the motion acceleration signals of the X axis, the Y axis and the Z axis of the corresponding wearing position and then directly transmits the motion acceleration signals to the processor. The system performs preprocessing on the triaxial acceleration signals collected by the intelligent watch, and removes limb tremor noise by adopting a filtering algorithm, wherein the noise is generated by wrist unintentional tremor and can interfere the effectiveness of the acceleration signals, and only signal components related to the movement intensity are reserved after filtering. After preprocessing is completed, the system performs vector synthesis operation on the triaxial acceleration signals, integrates the three axial signals into a single synthesized acceleration signal through vector synthesis, avoids misjudgment of the strength of the single axial signal caused by change of the motion direction, and ensures that the synthesized signal can reflect the whole motion amplitude.

The system executes cube root operation on the synthesized acceleration signals, the operation can compress the numerical range of the synthesized acceleration signals, meanwhile, the signal difference under different motion intensities is reserved, the signals are prevented from being excessively amplified at high acceleration values and are covered at low acceleration values, and a stable signal basis is provided for subsequent integration operation. The system sets a fixed time window, the window duration is determined according to the change period of the signal in the motion state, and enough samples can be collected in the window to reflect the current motion intensity. And the system performs integral operation on the synthesized acceleration signal subjected to cube root operation in a set time window, and the integral result is a motion intensity index which is positively correlated with the motion intensity.

And S12, performing linear regression processing on the heart rate signals acquired by the heart rate sensor, calculating a slope value of the heart rate descending rate after the exercise is stopped, and generating a heart rate recovery slope.

Specifically, the integrated optical heart rate sensor of the intelligent watch transmits a light signal with a specific wavelength, and after the light signal penetrates through the skin of the wrist, the sensor receives a light reflection signal generated by blood flow, converts the light reflection signal into a heart rate electric signal, and transmits the electric signal to the embedded processor of the intelligent watch in real time. Preferably, the system preprocesses the heart rate electric signal collected by the intelligent watch, and can eliminate motion artifacts by adopting a self-adaptive filtering algorithm, wherein the motion artifacts are generated by light reflection interference caused by relative displacement between wrist skin and a sensor and muscle contraction, so that false fluctuation occurs in the heart rate signal, the motion signal collected by the three-axis acceleration sensor of the intelligent watch is used as a reference during filtering, filtering parameters are adjusted in real time, and signals reflecting the real heart rate are obtained after the artifacts are removed.

Illustratively, the system identifies a motion stop time based on the motion intensity index, and when the motion intensity index falls from above a certain dynamic threshold to below another dynamic threshold and the state is maintained for a certain period of time, the system determines that the motion is stopped, records and marks the time node of the stop time. After the exercise is stopped, the system extracts heart rate signals in a specific time period from the local storage unit of the intelligent watch after the stopping time to form a continuous heart rate sequence, and the time period needs to cover an initial stage of the heart rate falling from a peak value after the exercise, so that the sequence can reflect the initial trend of heart rate recovery. The system uses time as independent variable and heart rate value as dependent variable, executes linear regression processing on the heart rate sequence, establishes a linear regression model, calculates the model slope value to obtain heart rate recovery slope, and indicates heart rate drop when the slope value is negative, and the absolute value reflects recovery rate.

The system collects exercise intensity indexes under different exercise intensities through the intelligent watch, simultaneously monitors blood lactic acid concentration changes of a subject in a correlated mode, records blood lactic acid concentration values corresponding to the exercise intensity indexes, when the exercise intensity indexes reach a certain value, the blood lactic acid concentration exceeds a resting state basic concentration and continuously rises, the value is determined to be a preset intensity threshold, and on the other hand, the system collects heart rate recovery slopes of different subjects after exercise is stopped through the intelligent watch, simultaneously monitors corresponding blood lactic acid metabolism states, when the heart rate recovery slopes are lower than a certain value, the blood lactic acid metabolism rate is obviously reduced, the accumulation state is difficult to quickly relieve, and the value is determined to be the preset recovery threshold.

The system acquires the generated real-time exercise intensity index, compares the real-time exercise intensity index with a preset intensity threshold value, and judges whether the threshold value is exceeded, and simultaneously acquires the generated heart rate recovery slope, compares the generated heart rate recovery slope with the preset recovery threshold value, and judges whether the heart rate recovery slope is lower than the threshold value. When the exercise intensity index exceeds a preset intensity threshold and the heart rate recovery slope is lower than the preset recovery threshold, the system judges that lactic acid accumulation exists to generate a lactic acid accumulation mark in an activated state, and if any condition is not met, the system judges that no significant lactic acid accumulation exists to generate a lactic acid accumulation mark in an inactivated state.

S21, carrying out empirical mode decomposition processing on cuff pressure shock wave signals acquired by the pressure sensor, decomposing the signals into a plurality of eigenvalue function components, and extracting eigenvalue functions of a frequency band of 0.5-5 Hz.

Specifically, the piezoresistive pressure sensor on the inner side of the system control cuff collects pressure shock wave signals in the inflation and deflation processes of the cuff, the measuring range of the sensor covers the whole range of cuff pressure change, and the signals are output by the sensor and then transmitted to the system main control unit. Further, the system preprocesses the original pressure shock wave signal, eliminates baseline drift and high-frequency electromagnetic interference caused by slow deflation of the cuff through filtering operation, and obtains the preprocessed signal. And simultaneously, the system carries out empirical mode decomposition on the preprocessed signals, calculates upper and lower envelopes of the signals, fits extreme points by adopting an interpolation algorithm to generate the upper and lower envelopes, takes the mean value of the upper and lower envelopes as a trend item, and removes the trend item from the original signals. The system repeats the screening process until the residual signals meet the judging condition of the eigenmode function, namely the number of extreme points is equal to or different from the number of zero crossing points by one, and finally the preprocessing signals are decomposed into a plurality of eigenmode function components. According to the frequency band characteristics of the intrinsic components of the blood pressure oscillation wave, the system screens out components corresponding to the frequency band of 0.5-5Hz from a plurality of eigenvalue function components obtained by decomposition, wherein the frequency band is a main energy distribution interval of the blood pressure oscillation wave, and can exclude respiratory interference and muscle tremor interference and serve as target signals for subsequent processing.

S22, performing Hilbert transformation processing on the eigenmode function, calculating the instantaneous amplitude of the analysis signal, and generating an initial envelope curve.

Specifically, the system calls and screens the obtained 0.5-5Hz Intrinsic Mode Function (IMF) data, performs Hilbert transform processing on the IMF component, performs Fast Fourier Transform (FFT) on time sequence data of the IMF component, converts a time domain signal into a frequency domain signal, supplements zero value according to the data length of the IMF component in the conversion process, ensures that the frequency domain resolution can cover all frequency points in the 0.5-5Hz frequency band to avoid losing frequency information, multiplies the converted frequency domain signal with a symbol function, determines a value according to positive and negative of the frequency value, wherein the value of the symbol function is 1 when the frequency value is larger than zero, and the value of the symbol function is-1 when the frequency value is smaller than zero.

Further, the system uses the time sequence data of the original IMF component as a real part and the corresponding Hilbert transformation result as an imaginary part, and the time sequence data are combined to form an analytic signal, wherein each time point of the analytic signal comprises two numerical values of the real part and the imaginary part. The system performs instantaneous amplitude calculation on the analytic signal, namely, firstly calculating the square value of the real part and the square value of the imaginary part of the analytic signal at each time point, then adding the two square values to obtain a square sum, and then performing the square operation on the square sum, wherein the operation result is the instantaneous amplitude of the time point. The instantaneous amplitude reflects the amplitude of the cuff pressure shock wave at the corresponding time point and is directly related to the intensity of the arterial pulse. The system sequentially arranges the instantaneous amplitude of each time point according to the time sequence of the signal collected by the intelligent watch to form continuous time sequence data, wherein the time sequence data is an initial envelope curve.

Specifically, the system acquires time sequence data of an initial envelope line, and finds that the initial envelope line has high-frequency fluctuation interference through time sequence change analysis of the data, wherein the interference sources comprise two aspects, namely, the tiny fluctuation of the cuff pressure caused by the tiny control error of a deflation valve in the cuff deflation process is transmitted to a pressure sensor to form pressure fluctuation interference, and the electronic noise of the pressure sensor is generated by current change of an internal circuit of the sensor and is expressed as high-frequency random signal fluctuation. These disturbances cause irregular jitter in the form of the initial envelope, and if they are directly used in the subsequent feature calculation, they will cause deviation in the calculation result, so that the system performs smoothing filtering processing on the initial envelope, and the filtering mode adopts average calculation in a time window.

The system analyzes the time sequence change period of the initial envelope, determines the change period of the envelope by counting the duration of the main peak of the initial envelope, and sets the duration of a fixed time window according to the change period, wherein the duration is required to meet two conditions, namely, the duration is smaller than the half period of the main peak of the initial envelope, the situation that the main peak form is excessively smoothed and key features are lost due to overlong windows is avoided, and the duration is larger than the period of high-frequency fluctuation interference, so that the fluctuation interference can be counteracted by mean value calculation. The system divides the time sequence data of the initial envelope into a plurality of continuous windows according to the time sequence by sliding time windows with fixed step length, each window comprises a fixed number of time sequence data points, and for the window of the edge position, if the number of the data points is less than the set number of the window, the system adopts a mode of repeatedly filling the edge data points to enable the number of the data points of the edge window to reach a set value.

The system calculates the average value of all the data points in each time window, adds the values of the data points in the window to obtain the sum, divides the sum by the number of the data points in the window to obtain the average value of the window, and replaces the values of all the original data points in the window by the average value to finish the smoothing treatment of one window. The system repeats the operations of sliding window, average value calculation and data replacement until all time sequence data points of the initial envelope are subjected to smoothing treatment, an optimized time domain envelope is obtained, main morphological characteristics such as a main peak, a secondary peak and the like related to arterial pulsation in the initial envelope are reserved in the optimized time domain envelope, high-frequency fluctuation interference is eliminated, and the change of the time sequence data is more attached to the real amplitude change of the arterial pulsation.

In one embodiment, as shown in fig. 2, the S3 method for measuring blood pressure compensation of a sports scene provided by the present invention specifically includes the following steps:

and S31, carrying out main peak detection processing on the time domain envelope, positioning the global maximum point of the envelope, measuring the half-height width of the envelope, and generating the main peak width variation.

Specifically, the system firstly executes baseline drift correction on the time envelope curve, and builds a baseline model by adopting a linear fitting algorithm, wherein the formula is as follows:

;

Where B (t) is a baseline value at time t, k is a baseline slope (determined by a linear decrease characteristic of cuff deflation pressure), B is a baseline initial value at time t=0, and t is a time variable. The system calculates the baseline value at each moment through the formula, subtracts the baseline value at the corresponding moment from the original envelope data, and completes drift correction, thereby ensuring that the envelope only reflects the arterial pulse characteristics. After correction, the system performs main peak detection by traversing the envelope time sequence data points and positioning the global maximum point with the maximum amplitude ,Is the time coordinate of the maximum point,Corresponding to the amplitude. Calculating the half height valueDirection ofTraversing back and forth, locating amplitude equal toCalculating the half-height width between the left end point t1 and the right end point t 2:

;

Wherein W is the current main peak half-height width, Is the half-height left endpoint time,Is the half-height right endpoint time. Static reference half-height width for system call pre-store(When the lactic acid accumulation mark is not activated, the intelligent watch collects a resting signal and obtains the resting signal through the same flow), and the main peak width variation is calculated:

;

Wherein DeltaW is the width variation of the main peak, W is the current half-height width, Is the static reference half height width. The variable quantity and the blood vessel tension change are in a correlation relationship, and the data are acquired and calculated by the intelligent watch.

S32, carrying out frequency domain energy analysis processing on the time domain envelope curve, calculating the energy distribution ratio of the 8-12Hz frequency band to the 1-4Hz frequency band, and generating a frequency domain characteristic ratio.

Specifically, the system performs discrete fourier transform on the time envelope, converts the time envelope into a frequency domain signal, and has the formula:

;

wherein X (k) is the frequency domain amplitude of the kth frequency point, For the nth time domain envelope data point, N is the total number of data points, N is the time domain index (0≤n < N), k is the frequency domain index (0≤k < N), and j is the imaginary unit. The system completes the conversion from time domain to frequency domain through the formula, and obtains the amplitude of each frequency point. Subsequently, the system calculates the power spectral density:

;

wherein, the Is the kth frequency pointIs the power spectral density of |X (k) | is the modulus of X (k), N is the total number of data points,Is the frequency value of the kth frequency point. The system respectively performs energy integration on 8-12Hz and 1-4Hz frequency bands according to a preset frequency band:

;

wherein E is the total energy of the target frequency band, For the starting frequency of the frequency band,For the frequency band termination frequency,As a function of power spectral density. Calculating 8-12Hz frequency band energyAnd 1-4Hz frequency band energyGenerating a frequency domain feature ratio:

;

wherein R is the characteristic ratio of the frequency domain, Is the total energy in the frequency range of 8-12Hz,The ratio change reflects the energy shift caused by abnormal blood vessel tension for the total energy of the frequency band of 1-4 Hz.

Specifically, the static reference value stored in the early stage of system call comprises a static reference half-height widthRatio to resting frequency domain characteristicsAnd when the lactic acid accumulation marks are not activated, the intelligent watch collects the rest signals and obtains the rest signals through the same flow, and the rest signals are used as a reference. The system performs weighted fusion on the delta W and the R, and firstly determines a time domain characteristic weight factorAnd frequency domain characteristic weighting factorsThe tension anomaly degree is calculated by substituting a system into a preferred formula through fitting clinical data:

;

And S41, carrying out nonlinear function mapping processing on the tension anomaly degree, and converting the tension anomaly degree into a blood vessel volume change proportion through hyperbolic tangent transformation to generate a blood vessel Shu Zhangliang.

In particular, the system will map through non-linearityConversion to quantifiable ratio of vessel volume change, selection of hyperbolic tangent transformation as mapping functionIs compressed to the range of [0,1] to avoid extreme endsValue-induced volumetric change ratio overflow while retainingPositive correlation characteristics with volume change. The mapping process may employ the following formula:

;

wherein, the For a blood vessel Shu Zhangliang (i.e., a ratio of vessel volume changes, dimensionless),For the maximum vascular volume change proportion (determined based on the actually measured vascular volume value in the resting state and reflecting the upper limit of vasodilation, the data come from the blood vessel related signal in the resting state collected by the intelligent watch), k is the mapping adjustment coefficient (obtained by fitting clinical data and ensuringTake the intermediate valueCan reflect the change of the blood vessel tension linearly),Tension anomalies generated for the step.

System call smart watch storageAnd k parameter are substituted into the obtainedDelta V is calculated by the above formula. When (when)In the event of an increase in the volume,Is close to 1 of the total number of the components,Approach toWhen the Dt is reduced, the first time period is reduced,Is close to the point of 0 and the like,Approaching to 0, the accurate mapping from the tension anomaly degree to the blood vessel Shu Zhangliang is realized, and all operation data come from the early acquisition and processing results of the intelligent watch.

And S42, carrying out exponential decay modeling treatment on the blood vessel Shu Zhangliang, and simulating a dynamic recovery process of the blood vessel volume in the lactic acid metabolic process by using a time decay function to construct a volume change curve which decreases with time.

Specifically, the system is based on the generated vasomotor tensor, simulates the dynamic recovery of the blood vessel volume in the lactic acid metabolism process, the lactic acid metabolism gradually weakens along with the time, the blood vessel tension gradually returns to normal, and the corresponding blood vessel volume change proportion needs to be decreased along with the time. Preferably, the system can be modeled using an exponential decay function, the modeling process using the formula:

;

wherein, the And the dynamic volume change quantity at the time t is the attenuation coefficient, lambda is determined based on the lactic acid metabolism rate, the lactic acid concentration and blood vessel volume change relation fitting of different time points is monitored, the movement stopping time recorded by the data-associated intelligent watch is obtained, and t is the time variable after movement stopping. The system acquires the t value in real time through the intelligent watch, and substitutes the t value into the formula to calculate the corresponding t valuesThe volume change curves are obtained by arranging the volume change curves in time series. The curve has an exponentially decreasing trend with increasing t,The size of the particles is smaller and the particles,Is close to 1 of the total number of the components,Proximity toAs the t is increased,The number of the cells to be processed is increased,Approaching 0, vdecay (t) approaches 0, accurately simulating the vascular volume dynamic recovery process caused by lactic acid metabolism.

In particular, the system needs to introduce a static blood vessel volume reference value to ensure that the compensation curve reflects the absolute change in blood vessel volume, the reference valueAnd when the lactic acid accumulation mark is not activated, the blood vessel volume reference value in the resting state is obtained by collecting the pressure shock wave signal of the cuff in the resting state and combining a blood vessel volume estimation algorithm by the intelligent watch, and is stored in a local storage unit of the intelligent watch. Preferably, the compensation curve construction may employ the following formula:

wherein, the A vessel volume compensation curve (dimensionless) at time t,Is a static blood vessel volume reference value,To the amount of dynamic volume change generated. The formula combines the dynamic volume change quantity with the static reference through baseline superposition, so thatNot only can reflect the vascular volume foundation in the resting state, but also can reflect the dynamic change in the lactic acid metabolic process after exercise.

System call smart watch storageIn combination with real-time calculationsSubstituting the above formula to obtain. Trend of generated vascular volume compensation curve with timeConsistent, initial timeGradually approach with increasing t. The curve is used for subsequent frequency domain filtering processing, and a quantitative compensation basis is provided for eliminating interference of abnormal vascular tension on blood pressure measurement.

In one embodiment, as shown in fig. 3, the step S5 of the method for measuring blood pressure compensation in a sports scene provided by the present invention specifically includes the following steps:

And S51, carrying out frequency domain convolution processing on the time domain envelope curve and the vascular volume compensation curve, multiplying the envelope curve frequency spectrum by a compensation filter transfer function in the frequency domain, and carrying out inverse Fourier transform to the time domain to generate a reconstructed compensation envelope curve.

Specifically, the system calls the optimized time domain envelope curve and the vessel volume compensation curve, and ensures the time axis synchronization of the two curves. The system performs discrete Fourier transform on the optimized time domain envelope curve, converts the time domain signal into frequency domain spectrum to obtain the frequency component distribution of the envelope curve, performs frequency domain analysis on the blood vessel volume compensation curve, and extracts a corresponding compensation filter transfer function, wherein the function is determined by the association relation between the blood vessel volume change and the blood pressure shock wave frequency domain response and is used for pertinently adjusting the frequency spectrum of the envelope curve.

The system performs element-wise multiplication operation on the envelope spectrum and the transfer function of the compensation filter in the frequency domain, adjusts the amplitude of each frequency component of the envelope through the operation, and counteracts the frequency domain distortion caused by abnormal vascular tension. The system executes inverse discrete Fourier transform on the frequency domain signal after operation, converts the signal from the frequency domain back to the time domain, obtains a continuous curve which eliminates lactic acid accumulation interference and has a form close to a resting state, and defines the curve as a reconstructed compensation envelope.

And S52, performing differential feature extraction processing on the reconstructed compensation envelope, searching a maximum value point by calculating a first derivative, detecting a position point where a second derivative is first changed from negative to positive, and generating systolic pressure feature time and diastolic pressure feature time.

Specifically, the system performs differential feature extraction processing on the reconstructed compensation envelope, and calculates the first derivative of the envelope using a sliding window algorithm. The system traverses all data points of the first derivative, locates the data point with the largest amplitude, and the data point corresponds to the moment when the amplitude of the reconstruction compensation envelope changes most rapidly, and the moment is defined as the characteristic moment of the systolic pressure. The system continues to calculate the second derivative for the first derivative, and also adopts a sliding window algorithm to ensure the calculation accuracy, traverses the data points of the second derivative, detects the position point of which the first value is converted into the positive value from the negative value, and defines the time corresponding to the position point as the characteristic time of the diastolic blood pressure. Preferably, the systolic and diastolic characteristic instants are obtained by:

S521, performing first derivative calculation processing on the reconstructed compensation envelope, and calculating the instantaneous slope value of each sampling point on the envelope by a center difference method to generate a first derivative sequence.

Specifically, the system firstly calls the reconstruction compensation envelope data in the buffer unit to determine the sampling interval of the data, wherein the interval is consistent with the sampling frequency of the intelligent watch pressure sensor, and the accuracy of the time dimension of the subsequent differential calculation is ensured. Preferably, the system can execute first derivative calculation on the reconstruction compensation envelope by adopting a central difference method, and for each sampling point on the envelope, two sampling points adjacent to the point are selected, and the instantaneous slope value of the point is obtained by dividing the difference value of the amplitude of the envelope of the front sampling point and the rear sampling point by twice the sampling interval. In the calculation process, for sampling points at the head end and the tail end of the envelope, the system adopts a single-side difference method to supplement calculation, selects one sampling point which is subsequent to the head point and one sampling point which is preceding to the tail point, calculates amplitude difference values with the head point and the tail point respectively, divides the amplitude difference values by sampling intervals, and ensures that each sampling point on the whole envelope time sequence corresponds to one instantaneous slope value. The instantaneous slope values of all the sampling points are arranged in time order to form a first derivative sequence.

S522, carrying out extreme point detection processing on the first derivative sequence, scanning the whole sequence to find the maximum positive value point, recording the corresponding moment, and generating the characteristic moment of systolic pressure.

Specifically, the system traverses each sampling point in the first derivative sequence in time sequence, sequentially extracts the instantaneous slope value of each sampling point from the initial sampling point of the sequence, compares the instantaneous slope value with the instantaneous slope value of the adjacent sampling point, and records the maximum value and the corresponding timestamp in the current traversal process. The traversal continues to the last sampling point of the first derivative sequence, the system finally determines the maximum positive value point in the whole sequence, the instantaneous slope value of the point is the maximum value of all sampling points in the sequence, the value is positive, and the rising rate of the envelope curve at the moment is reflected to be the fastest. The system extracts a time stamp corresponding to the maximum positive value point, wherein the time stamp is the characteristic moment of systolic pressure, and represents a time node when cuff pressure and arterial systolic pressure are balanced.

Specifically, the system calls the generated reconstruction compensation envelope again, calculates the curvature change value of each sampling point by adopting a second-order center difference method, and divides the curvature change value of the nth sampling point on the envelope by the difference value between the first derivative of the (n+1) th sampling point and the first derivative of the (n-1) th sampling point by twice the sampling interval. The system determines the search range as all sampling points after the characteristic time of the systolic pressure, excludes critical changes of an envelope curve rising stage and a focusing amplitude falling stage before the characteristic time of the systolic pressure, and traverses curvature change values in the range. The system detects a sampling point of which the first value is converted from negative to positive, extracts a time stamp corresponding to the sampling point, and defines the time stamp as characteristic time of diastolic pressure, wherein the negative value corresponds to the accelerated decrease of the amplitude of the envelope curve, the positive value corresponds to the decelerated decrease of the amplitude, and the conversion point is a critical time of slowing down the decrease rate and is matched with the physiological process that the cuff pressure is lower than the diastolic pressure.

Specifically, the system synchronously acquires cuff static pressure signals acquired by the piezoresistive pressure sensors, and the signals record static pressure values at different moments in the inflation and deflation processes of the cuffs. And inquiring a static pressure value corresponding to the time in the cuff static pressure signal according to the characteristic time of the systolic pressure by the system, wherein the pressure value is a compensated systolic pressure value after the motion interference is eliminated. And the system is similar to the system, and the static pressure value corresponding to the time is inquired in the cuff static pressure signal according to the characteristic time of the diastolic pressure, and the pressure value is the compensated diastolic pressure value after the motion interference is eliminated. The system integrates the compensated systolic pressure value and the compensated diastolic pressure value into a data set to form a compensated blood pressure value containing two parameters, and the blood pressure value can be directly used for output display to provide accurate data for blood pressure monitoring in a sports scene.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a blood pressure compensation measuring device for realizing the above-mentioned sports scene blood pressure compensation measuring method. The implementation scheme of the device for solving the problem is similar to that described in the above method, so the specific limitation in the embodiments of the blood pressure compensation measurement device for one or more sports scenes provided below can be referred to the limitation of the blood pressure compensation measurement method for sports scenes hereinabove, and will not be repeated here.

Preferably, as shown in fig. 4, the present invention provides a blood pressure compensation measurement device 600 for sports scenes, which is configured with the following modules:

the lactic acid accumulation mark generation module 610 is configured to process a motion acceleration signal acquired by a triaxial acceleration sensor and a heart rate signal acquired by a heart rate sensor, calculate a motion intensity index based on acceleration and a heart rate recovery slope based on a heart rate change rate, and generate a lactic acid accumulation mark based on a preset intensity threshold and a preset recovery threshold;

the time domain envelope generating module 620 is configured to process the cuff pressure oscillation wave signal collected by the pressure sensor, extract an eigenmode function of a frequency band of 0.5-5Hz, and perform hilbert transform to generate a time domain envelope;

The tension abnormality degree calculation module 630 is configured to process the time domain envelope, calculate a variation of a main peak width of the envelope relative to a static reference and an energy ratio of an 8-12Hz frequency band to a 1-4Hz frequency band, and generate Zhang Liyi constants representing a blood vessel tension abnormality;

the blood vessel volume compensation curve construction module 640 is used for processing the tension abnormality degree, calculating a blood vessel Shu Zhangliang obtained through a nonlinear mapping function, and constructing a blood vessel volume compensation curve by combining an exponential decay time function;

The compensated blood pressure value output module 650 is configured to process the time domain envelope curve and the blood vessel volume compensation curve, reconstruct the compensated envelope curve through a frequency domain convolution operation, and locate a maximum slope point and a second derivative positive change point on the reconstructed envelope curve, and output a compensated blood pressure value for eliminating motion interference.

Preferably, the lactic acid accumulation mark producing module 610 provided by the present application is configured with the following units:

the motion intensity index calculation unit is used for integrating the cube roots of the motion acceleration signals acquired by the triaxial acceleration sensor, calculating the integral value of the cube roots of the triaxial composite acceleration in a time window and generating a motion intensity index;

the heart rate recovery slope calculation unit is used for carrying out linear regression processing on the heart rate signals acquired by the heart rate sensor, calculating the slope value of the heart rate descending rate after the exercise is stopped, and generating a heart rate recovery slope;

and the lactic acid accumulation mark judging unit is used for carrying out double-threshold logic judgment on the exercise intensity index and the heart rate recovery slope, and generating the lactic acid accumulation mark in an activated state when the exercise intensity exceeds a preset intensity threshold and the heart rate recovery rate is lower than a preset recovery threshold.

Preferably, the time domain envelope generating module 620 provided by the present application is configured with the following units:

the system comprises an intrinsic mode function extraction unit, a pressure sensor and a pressure sensor, wherein the intrinsic mode function extraction unit is used for carrying out empirical mode decomposition treatment on cuff pressure shock wave signals acquired by the pressure sensor, decomposing the signals into a plurality of intrinsic mode function components and extracting an intrinsic mode function in a frequency range of 0.5-5 Hz;

The initial envelope generating unit is used for performing Hilbert transformation on the eigenmode function of the 0.5-5Hz frequency band, calculating the instantaneous amplitude of the analytic signal and generating an initial envelope;

And the envelope curve smoothing and optimizing unit is used for carrying out smoothing and filtering processing on the initial envelope curve, eliminating high-frequency fluctuation interference through mean value calculation in a time window and generating an optimized time domain envelope curve.

Preferably, the tension anomaly calculation module 630 provided by the present application is configured with the following units:

The main peak width detection unit is used for carrying out main peak detection processing on the time envelope, positioning the global maximum point of the envelope and measuring the half-height width of the envelope, and generating the main peak width variation;

the frequency domain energy ratio calculation unit is used for carrying out frequency domain energy analysis processing on the time domain envelope curve, calculating the energy distribution ratio of the 8-12Hz frequency band to the 1-4Hz frequency band and generating a frequency domain characteristic ratio;

The tension anomaly degree fusion calculation unit is used for carrying out weighted fusion processing on the main peak width variation and the frequency domain characteristic ratio, calculating the comprehensive offset by combining the static reference value, and generating tension anomaly degree, wherein the tension anomaly degree is used for indicating the abnormal degree of blood vessel tension caused by lactic acid accumulation.

Preferably, the vessel volume compensation curve construction module 640 provided by the present application is configured with the following units:

The blood vessel Shu Zhangliang mapping unit is used for carrying out nonlinear function mapping processing on the tension abnormality degree, converting the tension abnormality degree into a blood vessel volume change proportion through hyperbolic tangent transformation, and generating a blood vessel Shu Zhangliang;

The volume change curve modeling unit is used for carrying out exponential decay modeling processing on the vasodilation, simulating the dynamic recovery process of the blood vessel volume in the lactic acid metabolic process by using a time decay function, and constructing a volume change curve which decreases with time;

the blood vessel volume compensation curve generation unit is used for carrying out baseline superposition processing on the volume change curve, adding the volume change curve with a preset static blood vessel volume reference value, and generating a blood vessel volume compensation curve, wherein the blood vessel volume compensation curve is used for subsequent frequency domain filtering processing to eliminate abnormal interference of blood vessel tension.

Preferably, the compensated blood pressure value output module 650 provided by the present application is configured with the following units:

the frequency domain convolution reconstruction unit is used for carrying out frequency domain convolution processing on the time domain envelope curve and the blood vessel volume compensation curve, and generating a reconstructed compensation envelope curve by multiplying the envelope curve frequency spectrum with a compensation filter transfer function in a frequency domain and carrying out inverse Fourier transform to a time domain;

The differential feature extraction unit is used for carrying out differential feature extraction processing on the reconstructed compensation envelope line, searching a maximum value point by calculating a first derivative and detecting a position point of a second derivative which is first changed from negative to positive, so as to generate a systolic pressure feature moment and a diastolic pressure feature moment;

And the compensated blood pressure value mapping unit is used for carrying out pressure value mapping processing on the characteristic time of the systolic pressure and the characteristic time of the diastolic pressure, inquiring the cuff pressure value at the corresponding time according to the characteristic time, and generating a compensated blood pressure value containing the compensated systolic pressure value and the compensated diastolic pressure value.

Preferably, the differential feature extraction unit comprises a first derivative sequence generation subunit, a systolic pressure feature moment detection subunit and a diastolic pressure feature moment detection subunit. The first derivative sequence generation subunit is used for carrying out first derivative calculation processing on the reconstructed compensation envelope, calculating the instantaneous slope value of each sampling point on the envelope through a central difference method to generate a first derivative sequence, the systolic pressure characteristic moment detection subunit is used for carrying out extreme point detection processing on the first derivative sequence, scanning the whole sequence to find the maximum positive value point and recording the corresponding moment to generate the systolic pressure characteristic moment, and the diastolic pressure characteristic moment detection subunit is used for carrying out second derivative calculation processing on the reconstructed compensation envelope, calculating the curvature change value of each sampling point on the envelope through a second central difference method, and searching the point of which the first curvature is changed from negative to positive after the systolic pressure characteristic moment to generate the diastolic pressure characteristic moment.

In an embodiment, the application further provides a smart watch, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the blood pressure compensation measurement method of the sports scene when executing the computer program.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The above-described apparatus embodiments are merely illustrative, wherein the components illustrated as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the disclosed solution. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that various changes and substitutions are possible within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims

1. The blood pressure compensation measurement method of the sports scene is characterized by comprising the following steps of:

S3, processing the time domain envelope curve, calculating the variation of the width of the main peak of the envelope curve relative to a static reference and the energy ratio of 8-12Hz frequency band to 1-4Hz frequency band, and generating Zhang Liyi constant degrees representing abnormal vascular tension;

S4, processing the tension anomaly degree, calculating a blood vessel Shu Zhangliang obtained through a nonlinear mapping function, and constructing a blood vessel volume compensation curve by combining an exponential decay time function;

S5, processing the time domain envelope curve and the blood vessel volume compensation curve, reconstructing the compensated envelope curve through frequency domain convolution operation, positioning a maximum slope point and a second-order derivative positive change point on the reconstructed envelope curve, and outputting a compensated blood pressure value for eliminating motion interference.

2. The method according to claim 1, wherein S1 comprises:

And S13, performing double-threshold logic judgment on the exercise intensity index and the heart rate recovery slope, and generating a lactic acid accumulation mark in an activated state when the exercise intensity exceeds a preset intensity threshold and the heart rate recovery rate is lower than a preset recovery threshold.

3. The method according to claim 1, wherein S2 comprises:

S23, carrying out smoothing filtering treatment on the initial envelope curve, eliminating high-frequency fluctuation interference through mean value calculation in a time window, and generating an optimized time domain envelope curve.

4. The method according to claim 1, wherein S3 comprises:

s31, carrying out main peak detection processing on the time domain envelope, positioning the global maximum point of the envelope, measuring the half-height width of the global maximum point, and generating a main peak width variation;

S32, carrying out frequency domain energy analysis processing on the time domain envelope curve, calculating the energy distribution ratio of the 8-12Hz frequency band to the 1-4Hz frequency band, and generating a frequency domain characteristic ratio;

And S33, carrying out weighted fusion processing on the main peak width variation and the frequency domain characteristic ratio, and calculating the comprehensive offset by combining a static reference value to generate tension anomaly degree, wherein the tension anomaly degree is used for indicating the degree of abnormal vascular tension caused by lactic acid accumulation.

5. The method of claim 4, wherein the tension anomaly is calculated as:

;

6. The method according to claim 1, wherein S4 comprises:

And S43, carrying out baseline superposition processing on the volume change curve, adding the volume change curve with a preset static blood vessel volume reference value, and generating a blood vessel volume compensation curve, wherein the blood vessel volume compensation curve is used for subsequent frequency domain filtering processing to eliminate abnormal interference of blood vessel tension.

7. The method according to any one of claims 1-6, wherein S5 comprises:

S51, carrying out frequency domain convolution processing on the time domain envelope curve and the vascular volume compensation curve, multiplying the envelope curve frequency spectrum with a compensation filter transfer function in a frequency domain, and carrying out inverse Fourier transform to the time domain to generate a reconstructed compensation envelope curve;

s52, performing differential feature extraction processing on the reconstructed compensation envelope, searching a maximum value point by calculating a first derivative, detecting a position point of a second derivative which is first changed from negative to positive, and generating a systolic pressure feature moment and a diastolic pressure feature moment;

and S53, performing pressure value mapping processing on the characteristic time of systolic pressure and the characteristic time of diastolic pressure, inquiring the cuff pressure value at the corresponding time according to the characteristic time, and generating a compensated blood pressure value comprising a compensated systolic pressure value and a compensated diastolic pressure value.

8. The method of claim 7, wherein S52 comprises:

9. A blood pressure compensation measurement device for a sports scene, the device comprising:

The blood vessel volume compensation curve construction module is used for processing the tension anomaly degree, calculating a blood vessel Shu Zhangliang obtained through a nonlinear mapping function, and constructing a blood vessel volume compensation curve by combining an exponential decay time function;

And the compensated blood pressure value output module is used for processing the time domain envelope curve and the blood vessel volume compensation curve, reconstructing the compensated envelope curve through frequency domain convolution operation, positioning a maximum slope point and a second order pilot change point on the reconstructed envelope curve, and outputting a compensated blood pressure value for eliminating motion interference.

10. A smart watch comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the method of any one of claims 1 to 8 when executing the computer program.