Cuff blood pressure measurement method, system and device based on pressure sensor device

Abstract

The present invention provides a cuff blood pressure measurement method, system and device based on a pressure sensing device, the method comprising: collecting electrical signals and cuff pressure signals in the inflation stage and the deflation stage based on a time series to obtain a first oscillation pressure signal sequence and a first cuff pressure signal sequence; extracting the first oscillation pressure signal sequence and the first cuff pressure signal sequence in the deflation stage to form a second oscillation pressure signal sequence and a second cuff pressure signal sequence; performing DC signal extraction on the second cuff pressure signal sequence to obtain a cuff DC pressure sequence, performing peak and valley value extraction and difference processing on the second oscillation pressure signal sequence to obtain a sensing pressure amplitude sequence; constructing an amplitude DC model, combining the cuff DC pressure sequence and the sensing pressure amplitude sequence to obtain the systolic and diastolic pressures of the person to be measured. The present invention can obtain personalized blood pressure parameters based on the personal physiological information of the person to be monitored, and realize accurate blood pressure measurement that varies from person to person.

Description

Technical Field

[0001] The present invention relates to the field of blood pressure measurement, and in particular to a cuff blood pressure measurement method, system and device based on a pressure sensor device. Background Art

[0002] At present, the blood pressure monitoring equipment commonly used in people's daily lives is mainly based on the oscillometric method to measure blood pressure, and the systolic and diastolic blood pressures are obtained through empirical proportional values. However, this commonly used value is a statistical result for a large range of regular populations, and there will be a certain degree of error for people who need to measure blood pressure for a long time. Studies have shown that the oscillometric blood pressure measurement based on the fixed proportion method has certain errors in the blood pressure measurement of people with abnormal blood pressure and special physiological conditions. Among them, the diastolic blood pressure of obese people is significantly underestimated, and the systolic and diastolic blood pressure of patients with preeclampsia are underestimated. The oscillometric method has poor personalization in actual clinical practice and cannot achieve accurate measurement that varies from person to person. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a cuff blood pressure measurement method, system and device based on a pressure sensor device.

[0004] In order to solve the above technical problems, the present invention is solved by the following technical solutions: a cuff blood pressure measurement method based on a pressure sensor device, comprising the following steps:

[0005] Based on the time series, the electrical signals in the inflation stage and the deflation stage are collected to obtain a first oscillation pressure signal sequence; based on the time series, the cuff pressure signals in the inflation stage and the deflation stage are collected to form a first cuff pressure signal sequence, wherein the electrical signal is a response value of a pressure sensor device located inside the cuff, the pressure sensor device is a capacitive pressure sensor device, and the cuff pressure signal includes a DC signal and an AC signal;

[0006] Extracting a first oscillation pressure signal sequence in the deflation phase to form a second oscillation pressure signal sequence, and extracting a first cuff pressure signal sequence in the deflation phase to form a second cuff pressure signal sequence;

[0007] Extracting the DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain the cuff DC pressure sequence, extracting the peak value and the valley value of the oscillating pressure signal in the second oscillating pressure signal sequence to obtain the peak value sequence and the valley value sequence, and performing interpolation and difference processing on the peak value sequence and the valley value sequence to obtain the sensing pressure amplitude sequence;

[0008] Based on the cuff DC pressure, sensor pressure amplitude, systolic pressure data and diastolic pressure data, an amplitude DC model is constructed, and the systolic and diastolic pressures of the subject are obtained by combining the cuff DC pressure sequence and the sensor pressure amplitude sequence.

[0009] As an implementable embodiment, the pressure sensing device is a PVDF film pressure sensor.

[0010] As an implementable method, the electrical signals of the inflation phase and the deflation phase are collected based on the time series to obtain the first oscillation pressure signal sequence, including the following steps:

[0011] Based on the time series, the response values ​​of the pressure sensing device in the inflation phase and the deflation phase, i.e., the electrical signals, are collected to obtain an electrical signal sequence, and the electrical signal sequence is preprocessed to obtain a preprocessed electrical signal sequence, wherein the preprocessing includes one or more of filtering, amplification, linearization, and data conversion;

[0012] Based on the preprocessed electrical signal sequence and combined with the pressure value and electrical signal value mapping model, a first oscillation pressure signal sequence is obtained, wherein the pressure value and electrical signal value mapping model is a numerical relationship model between the pressure value acting on the pressure sensing device and the response value of the pressure sensing device.

[0013] As an implementable method, the extracting the first oscillation pressure signal sequence in the deflation stage to form the second oscillation pressure signal sequence, extracting the first cuff pressure signal sequence in the deflation stage to form the second cuff pressure signal sequence, comprises the following steps:

[0014] Obtaining the maximum pressure point of the first cuff pressure signal in the first cuff pressure signal sequence, and then obtaining the first moment corresponding to the maximum pressure point;

[0015] Based on the first cuff pressure signal sequence, the maximum pressure drop change point of the first cuff pressure signal is obtained, and then the second moment corresponding to the maximum pressure drop change point is obtained, and the period between the first moment and the second moment is the deflation stage;

[0016] forming a second oscillating pressure signal sequence based on the first oscillating pressure signal sequence during the deflation phase;

[0017] Based on the first cuff pressure signal sequence in the deflation phase, a second cuff pressure signal sequence is formed.

[0018] As an implementable method, extracting the DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain the cuff DC pressure sequence includes the following steps:

[0019] performing wavelet transform processing with different scale parameters on the cuff pressure signal in the second cuff pressure signal sequence to obtain wavelet coefficients with different scale parameters;

[0020] The wavelet coefficients with scale parameters greater than a preset scale threshold are extracted from the wavelet coefficients with different scale parameters to obtain an initial DC pressure sequence;

[0021] Performing inverse wavelet transform on the DC pressure in the initial DC pressure signal sequence, and obtaining a reconstructed DC pressure sequence, which is the cuff DC pressure sequence;

[0022] Wherein, the wavelet transform is expressed as follows:

[0023]

[0024] The inverse wavelet transform is expressed as follows:

[0025]

[0026] in, represents the wavelet coefficients, represents the scale parameter, represents the translation parameter, represents the cuff pressure signal in the second cuff pressure signal sequence, represents the wavelet basis function, Indicates time, represents the DC pressure in the reconstructed DC pressure sequence, represents the DC pressure in the initial DC pressure sequence, Represents the admissibility constant of the wavelet basis function.

[0027] As an implementation method, the peak values ​​and valley values ​​of the oscillating pressure signal in the second oscillating pressure signal sequence are extracted to obtain a peak value sequence and a valley value sequence, and interpolation and difference processing are performed on the peak value sequence and the valley value sequence to obtain a sensing pressure amplitude sequence, including the following steps:

[0028] Extracting the peak value and the valley value of the oscillation pressure signal in the second oscillation pressure signal sequence respectively to obtain a first peak value sequence and a first valley value sequence;

[0029] Interpolating the moments when the peak values ​​in the first peak value sequence are null values ​​to obtain a second peak value sequence, and interpolating the moments when the valley values ​​in the first valley value sequence are null values ​​to obtain a second valley value sequence;

[0030] The peak value and the valley value at each corresponding moment in the second peak value sequence and the second valley value sequence are subjected to difference processing to obtain the sensing pressure amplitude at each corresponding moment, and further obtain the sensing pressure amplitude sequence.

[0031] As an implementable method, the amplitude DC model is constructed based on the cuff DC pressure, the sensor pressure amplitude, the systolic pressure data and the diastolic pressure data, including the following steps:

[0032] Based on the cuff DC pressure, systolic pressure data and diastolic pressure data, the sensor pressure amplitude is fitted to obtain the amplitude DC model, where the amplitude DC model is expressed as follows:

[0033]

[0034] in, represents the sensing pressure amplitude in the sensing pressure amplitude sequence, represents the cuff DC pressure in the cuff DC pressure sequence, and represents the coefficient, Represents systolic blood pressure data, Indicates diastolic blood pressure data.

[0035] As an implementable method, combining the cuff DC pressure sequence and the sensor pressure amplitude sequence to obtain the systolic and diastolic pressures of the subject includes the following steps:

[0036] Based on the sensed pressure amplitude, the fitness function of the particle is constructed;

[0037] Randomly generate an initialization particle swarm, obtain the position and velocity of each particle in the initialization particle swarm, and then obtain the initial individual optimal position of each particle and the initial global optimal position of the particle swarm, where the position of the particle is the parameter to be solved in the amplitude DC model, including systolic pressure and diastolic pressure;

[0038] Get the fitness of each particle's current position based on the fitness function;

[0039] If the fitness of the current position of the particle is better than the fitness of the individual optimal position, the individual optimal position is updated; if the fitness of the current position of any particle is better than the fitness of the global optimal position, the global optimal position is updated, and the position and speed of the particle are updated to obtain the updated particle speed and updated particle position;

[0040] Until the termination condition is met, the final global optimal position is output, which is the optimal solution of the parameters to be solved of the amplitude DC model, and then the systolic and diastolic blood pressures of the subject are obtained;

[0041] Wherein, the fitness function is expressed as follows:

[0042]

[0043] The updated particle velocity is expressed as follows:

[0044]

[0045] The updated particle position is expressed as follows:

[0046]

[0047] in, represents fitness, represents the sensing pressure amplitude in the sensing pressure amplitude sequence, represents the sensor pressure amplitude based on the current position of the particle, represents the number of predicted sensor pressure amplitudes, represents the updated particle velocity, represents the inertia weight, represents the particle velocity of the last iteration, represents the optimal position of the individual particle in the last iteration, represents the particle position of the last iteration, represents the global optimal position of the last iteration, represents the learning factor, Represents a random number, Indicates the updated particle position.

[0048] A cuff blood pressure measurement system based on a pressure sensor device, comprising a pressure acquisition module, a pressure extraction module, a DC and amplitude extraction module, and a model solving module;

[0049] The pressure acquisition module collects electrical signals in the inflation stage and the deflation stage based on the time series to obtain a first oscillation pressure signal sequence, and collects cuff pressure signals in the inflation stage and the deflation stage based on the time series to form a first cuff pressure signal sequence, wherein the electrical signal is a response value of a pressure sensor device located inside the cuff, the pressure sensor device is a capacitive pressure sensor device, and the cuff pressure signal includes a DC signal and an AC signal;

[0050] The pressure extraction module extracts the first oscillation pressure signal sequence in the deflation phase to form a second oscillation pressure signal sequence, and extracts the first cuff pressure signal sequence in the deflation phase to form a second cuff pressure signal sequence;

[0051] The DC and amplitude extraction module extracts the DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain the cuff DC pressure sequence, extracts the peak value and the valley value of the oscillating pressure signal in the second oscillating pressure signal sequence to obtain the peak value sequence and the valley value sequence, and performs interpolation and difference processing on the peak value sequence and the valley value sequence to obtain the sensing pressure amplitude sequence;

[0052] The model solving module constructs an amplitude DC model based on the cuff DC pressure, the sensor pressure amplitude, the systolic pressure data and the diastolic pressure data, and obtains the systolic pressure and diastolic pressure of the subject by combining the cuff DC pressure sequence and the sensor pressure amplitude sequence;

[0053] Among them, the amplitude DC model is expressed as follows:

[0054]

[0055] in, represents the sensing pressure amplitude in the sensing pressure amplitude sequence, represents the cuff DC pressure in the cuff DC pressure sequence, and represents the coefficient, Represents systolic blood pressure data, Indicates diastolic blood pressure data.

[0056] A computer-readable storage medium stores a computer program, wherein the computer program implements the following method when executed by a processor:

[0057] Based on the time series, the electrical signals in the inflation stage and the deflation stage are collected to obtain a first oscillation pressure signal sequence; based on the time series, the cuff pressure signals in the inflation stage and the deflation stage are collected to form a first cuff pressure signal sequence, wherein the electrical signal is a response value of a pressure sensor device located inside the cuff, the pressure sensor device is a capacitive pressure sensor device, and the cuff pressure signal includes a DC signal and an AC signal;

[0058] Extracting a first oscillation pressure signal sequence in the deflation phase to form a second oscillation pressure signal sequence, and extracting a first cuff pressure signal sequence in the deflation phase to form a second cuff pressure signal sequence;

[0059] Extracting the DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain the cuff DC pressure sequence, extracting the peak value and the valley value of the oscillating pressure signal in the second oscillating pressure signal sequence to obtain the peak value sequence and the valley value sequence, and performing interpolation and difference processing on the peak value sequence and the valley value sequence to obtain the sensing pressure amplitude sequence;

[0060] Based on the cuff DC pressure, sensor pressure amplitude, systolic pressure data and diastolic pressure data, an amplitude DC model is constructed, and the systolic and diastolic pressures of the subject are obtained by combining the cuff DC pressure sequence and the sensor pressure amplitude sequence.

[0061] A cuff blood pressure measuring device based on a pressure sensor device comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the following method when executing the computer program:

[0062] Based on the time series, the electrical signals in the inflation stage and the deflation stage are collected to obtain a first oscillation pressure signal sequence; based on the time series, the cuff pressure signals in the inflation stage and the deflation stage are collected to form a first cuff pressure signal sequence, wherein the electrical signal is a response value of a pressure sensor device located inside the cuff, the pressure sensor device is a capacitive pressure sensor device, and the cuff pressure signal includes a DC signal and an AC signal;

[0063] Extracting a first oscillation pressure signal sequence in the deflation phase to form a second oscillation pressure signal sequence, and extracting a first cuff pressure signal sequence in the deflation phase to form a second cuff pressure signal sequence;

[0064] Extracting the DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain the cuff DC pressure sequence, extracting the peak value and the valley value of the oscillating pressure signal in the second oscillating pressure signal sequence to obtain the peak value sequence and the valley value sequence, and performing interpolation and difference processing on the peak value sequence and the valley value sequence to obtain the sensing pressure amplitude sequence;

[0065] Based on the cuff DC pressure, sensor pressure amplitude, systolic pressure data and diastolic pressure data, an amplitude DC model is constructed, and the systolic and diastolic pressures of the subject are obtained by combining the cuff DC pressure sequence and the sensor pressure amplitude sequence.

[0066] The present invention has significant technical effects due to the adoption of the above technical solution:

[0067] The present invention places a pressure sensor device with direct current isolation and alternating current transmission characteristics on the inflatable airbag of the oscillometric cuff, and uses the direct current isolation and alternating current transmission characteristics of the pressure sensor device to capture the oscillation signal of the brachial blood pressure, and extracts the DC signal part from the cuff pressure signal. Therefore, the cuff pressure signal is only used to measure the external pressure of the cuff, which optimizes the performance of the existing oscillometric cuff in measuring oscillation signals, and constructs an amplitude DC model to obtain diastolic pressure and systolic pressure. Compared with the traditional oscillometric method that directly calculates diastolic pressure and systolic pressure using big data empirical ratio values, the present invention can obtain personalized blood pressure parameters based on the specific physiological information of the individual to be monitored, realize personalized monitoring in actual clinical practice, and realize accurate measurement that varies from person to person. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0069] Figure 1 It is a schematic diagram of the process of the present invention;

[0070] Figure 2 is a schematic diagram of a pressure sensing device and a cuff of the present invention;

[0071] Figure 3 It is an overall schematic diagram of the system of the present invention;

[0072] Figure numerals: 10, pressure sensing device; 20, cuff; 21, inflatable airbag; 100, pressure acquisition module; 200, pressure extraction module; 300, DC and amplitude extraction module; 400, model solving module. DETAILED DESCRIPTION

[0073] The present invention is further described in detail below in conjunction with the embodiments, which are explanations of the present invention but are not limited to the following embodiments. In the absence of conflict, the features in the following embodiments can be combined with each other.

[0074] Embodiment 1:

[0075] A blood pressure measurement method based on a cuff of a pressure sensor device, such as Figure 1 As shown, the following steps are included:

[0076] S100: collecting electrical signals in the inflation stage and the deflation stage based on a time series to obtain a first oscillation pressure signal sequence, collecting cuff pressure signals in the inflation stage and the deflation stage based on the time series to form a first cuff pressure signal sequence, wherein the electrical signal is a response value of a pressure sensor device located inside the cuff, the pressure sensor device is a capacitive pressure sensor device, and the cuff pressure signal includes a DC signal and an AC signal;

[0077] S200: extracting a first oscillation pressure signal sequence in the deflation phase to form a second oscillation pressure signal sequence, and extracting a first cuff pressure signal sequence in the deflation phase to form a second cuff pressure signal sequence;

[0078] S300: extracting a DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain a cuff DC pressure sequence, extracting a peak value and a valley value of the oscillating pressure signal in the second oscillating pressure signal sequence to obtain a peak value sequence and a valley value sequence, and performing interpolation and difference processing on the peak value sequence and the valley value sequence to obtain a sensing pressure amplitude sequence;

[0079] S400: Based on the cuff DC pressure, the sensor pressure amplitude, the systolic pressure data and the diastolic pressure data, an amplitude DC model is constructed, and the systolic pressure and diastolic pressure of the subject are obtained by combining the cuff DC pressure sequence and the sensor pressure amplitude sequence.

[0080] In S100, electrical signals in the inflation phase and the deflation phase are collected based on a time series to obtain a first oscillation pressure signal sequence, and cuff pressure signals in the inflation phase and the deflation phase are collected based on the time series to form a first cuff pressure signal sequence, wherein the electrical signal is a response value of a pressure sensor device located inside the cuff, the pressure sensor device is a capacitive pressure sensor device, and the cuff pressure signal includes a DC signal and an AC signal, and the following steps are included:

[0081] S110: Collecting electrical signals in the inflation phase and the deflation phase based on the time series to obtain a first oscillation pressure signal sequence.

[0082] In this step, since the capacitive pressure sensing device has the characteristics of isolating DC and passing AC, the pressure sensing device of the present application transmits the AC part of the signal, and the DC part of the signal will be isolated. The oscillating electrical signal it transmits is the AC part of the electrical signal, that is, the oscillating electrical signal.

[0083] like Figure 2 As shown, the pressure sensing device 10 is closely attached to the inflatable airbag 21 inside the oscillometric cuff 20, the pressure sensing device 10 is parallel to both sides of the inflatable airbag 21 of the oscillometric cuff 20, and is located in the middle of the airbag. When in use, the oscillometric cuff is worn 1 to 3 cm above the elbow. The output port of the inflatable airbag 21 of the oscillometric cuff 20 is connected to an external air pump, and two output leads of the pressure sensing device 10 are connected to an external signal receiving device. In this embodiment, the pressure sensing device 10 is a PVDF film pressure sensor.

[0084] Obtaining a first oscillation pressure signal sequence based on the electrical signal comprises the following steps:

[0085] (1) Calibration of pressure sensor device. Pressurize the pressure sensor device based on the known pressure value to obtain the corresponding response value of the pressure sensor device, that is, the electrical signal value (voltage or current). Through multiple experiments, a mapping model between pressure value and electrical signal value, that is, a calibration curve or calibration equation, is obtained. If the pressure sensor device is an existing finished product, the calibration curve or calibration equation is known and does not need to be obtained through experiments.

[0086] (2) Based on the time series, the response value of the pressure sensor device during the inflation stage and the deflation stage, i.e., the electrical signal, is collected to obtain an electrical signal sequence, and the electrical signal sequence is preprocessed to obtain a preprocessed electrical signal sequence. The preprocessing includes filtering, amplification, linearization, data conversion, etc. Filtering is used to remove noise and interference in the electrical signal and improve the signal-to-noise ratio of the signal, which can usually be achieved through analog filters or digital filters. If the output signal of the pressure sensor device is weak, it needs to be amplified for subsequent data processing and analysis. If the pressure sensor device is nonlinear, it needs to be linearized so that the output signal and the pressure value have a linear relationship.

[0087] (3) Based on the preprocessed electrical signal sequence and in combination with a pressure value and electrical signal value mapping model, the electrical signal values ​​are converted into corresponding pressure values, thereby obtaining a first oscillation pressure signal sequence.

[0088] S120: Collecting cuff pressure signals in the inflation phase and the deflation phase based on the time series to form a first cuff pressure signal sequence.

[0089] In this step, the first cuff pressure signal sequence includes a DC signal part and an AC signal part. These two parts together reflect the change of pressure in the cuff and the fluctuation information of arterial blood pressure, which is the basis of oscillometric blood pressure measurement. The pressure signal output by the oscillometric cuff includes a DC part and an AC part. When the oscillometric blood pressure is measured, the oscillometric cuff is inflated to block the arterial blood flow, and the gas pressure in the cuff is detected during the deflation process. In this process, the pressure in the cuff changes gradually, and this change is continuous and stable, similar to a DC signal. The DC signal part mainly reflects the change of static pressure in the cuff, which provides a benchmark for measurement, that is, the process in which the pressure in the cuff gradually decreases as the deflation process proceeds. When the pressure in the oscillometric cuff decreases to a certain extent, the arterial blood flow begins to gradually recover, and a series of small pulses will be generated in the cuff at this time. These small pulses are generated by the fluctuation of the arterial wall and the flow of blood. These small pulses are superimposed on the static pressure in the cuff to form the AC part of the pressure signal. The AC signal part contains the fluctuation information of arterial blood pressure.

[0090] The first cuff pressure signal sequence is a sequence of cuff pressure signals in the oscillometric cuff inflation stage and deflation stage. The pressure sensing device 10 is tightly attached to the inflatable airbag 21 inside the oscillometric cuff 20, so the signals in the first oscillation pressure signal sequence and the first cuff pressure signal sequence are synchronized.

[0091] In S200, extracting a first oscillation pressure signal sequence in the pressure relief stage (deflation stage) to form a second oscillation pressure signal sequence, extracting a first cuff pressure signal sequence in the pressure relief stage (deflation stage) to form a second cuff pressure signal sequence, includes the following steps:

[0092] (1) Based on the first cuff pressure signal sequence, obtain the maximum pressure point in the first cuff pressure signal sequence, and then obtain the first moment corresponding to the maximum pressure point ;

[0093] (2) Based on the first cuff pressure signal sequence, the point with the maximum pressure drop change in the first cuff pressure signal sequence is obtained, and then the second moment corresponding to the point with the maximum pressure drop change is obtained. ; First moment and the second moment The time period between is the pressure relief phase (deflation phase). or ,generally and Not equal.

[0094] (3) extracting the first oscillation pressure signal sequence in the pressure relief stage (deflation stage) to obtain the second oscillation pressure signal sequence;

[0095] (4) The first cuff pressure signal sequence in the pressure relief stage (deflation stage) is extracted, and preprocessed by filtering, amplification, linearization and data conversion to obtain the second cuff pressure signal sequence.

[0096] In S300, a DC signal of the cuff pressure signal in the second cuff pressure signal sequence is extracted to obtain a cuff DC pressure sequence, a peak value and a valley value of the oscillating pressure signal in the second oscillating pressure signal sequence are extracted to obtain a peak value sequence and a valley value sequence, and interpolation and difference processing are performed on the peak value sequence and the valley value sequence to obtain a sensing pressure amplitude sequence, including the following steps:

[0097] S310: Extracting a direct current signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain a cuff direct current pressure sequence.

[0098] In this step, in the process of measuring blood pressure by oscillometric method, extracting DC signal from the second cuff pressure signal sequence is one of the key steps. The technologies that can realize this DC signal extraction include mean method, time domain analysis method, digital filtering method, Fourier transform method, wavelet transform method, etc.

[0099] The mean method extracts the DC component by averaging the signal. The cuff pressure signal (that is, the second cuff pressure signal sequence) in the pre-processed decompression stage is accumulated and summed, and then divided by the number of samples to obtain the average value, which is the DC component. The time domain analysis method extracts the DC component by analyzing the time domain characteristics of the second cuff pressure signal sequence. The signal can be moved and averaged using a sliding window, so that the high-frequency component is attenuated during the averaging process, while the low-frequency component (including the DC component) is basically maintained. The signal after moving average is the extracted DC component. When extracting the DC signal, the digital filtering method can use a low-pass digital filter to filter out the high-frequency component in the signal and retain the low-frequency and DC components. The filtered signal is the extracted DC component. Commonly used filters include Butterworth filters and Chebyshev filters. The Fourier transform method decomposes the second cuff pressure signal sequence into sinusoidal components of different frequencies. When extracting the DC signal, the signal is Fourier transformed, and then the high-frequency components are filtered out, retaining only the low-frequency and DC components. Finally, an inverse Fourier transform is performed to obtain the extracted DC component.

[0100] Here, the wavelet transform method decomposes the second cuff pressure signal sequence into time-frequency characteristics of different scales. When extracting the DC signal, the low-frequency and DC components are selectively extracted according to the characteristics of the frequency band. Wavelet transform provides an analysis method in the time-frequency domain, which has good adaptability to non-stationary signals. The corresponding DC signal extraction technology is selected according to actual needs, and this application does not limit it.

[0101] It should be noted that it is well known to those skilled in the art that although pressure data is collected by the cuff, in the scenario of blood pressure measurement, the cuff pressure and the cuff pressure are numerically equal, because pressure is a form of pressure, so the cuff DC pressure and the cuff DC pressure are actually only conceptual conversions, not numerical conversions. Based on the habits of those skilled in the art, the Chinese characters in this application are still expressed as pressure, but the symbols are expressed as (pressure).

[0102] In this embodiment, wavelet transform is used to extract the DC signal from the second cuff pressure signal sequence, including the following steps:

[0103] (1) The cuff pressure in the second cuff pressure signal sequence is processed by wavelet transform with different scale parameters to obtain wavelet coefficients with different scale parameters, where the wavelet transform is expressed as follows:

[0104]

[0105] in, represents the wavelet coefficients, It represents the scale parameter, which determines the degree of expansion and contraction of the wavelet function, corresponding to the frequency component of the signal. The larger the scale, the lower the frequency of the corresponding signal. represents the translation parameter, which determines the position of the wavelet function in the time domain. represents the cuff pressure signal in the second cuff pressure signal sequence (including DC signal and AC signal), Represents the wavelet basis function, which determines the characteristics and resolution of the wavelet transform. It is selected according to the characteristics of the signal and the processing requirements. Commonly used wavelet basis functions include Haar, Daubechies, Symlet, etc. Indicates time.

[0106] (2) Scale parameters in wavelet coefficients with different scale parameters Greater than the preset scale threshold The wavelet coefficients are extracted to obtain the initial DC pressure signal sequence. After wavelet transformation, a series of wavelet coefficients are obtained. , in order to extract the DC signal, we need to pay attention to the scale parameter Larger coefficients because the DC signal corresponds to lower frequency components. Preset scale threshold , weigh and select according to the frequency characteristics of the signal and the amplitude of the DC signal. Greater than the preset scale threshold Some of the wavelet coefficients are considered to correspond to DC signals.

[0107] (3) The initial DC pressure signal sequence is processed by inverse wavelet transform to obtain a reconstructed DC pressure signal sequence, which is the cuff DC pressure sequence. The inverse wavelet transform is expressed as follows:

[0108]

[0109] in, represents the DC pressure signal in the reconstructed DC pressure signal sequence, represents the admissibility constant of the wavelet basis function, It ensures that the inverse transform of wavelet transform exists and is unique. It represents the DC pressure in the initial DC pressure signal sequence, that is, the wavelet coefficient whose scale parameter is greater than the preset scale threshold. Each reconstructed DC pressure constitutes a cuff DC pressure sequence, which reflects the average level or stable state of the cuff pressure during blood pressure measurement.

[0110] S320: extracting the peak value and the valley value of the oscillating pressure signal in the second oscillating pressure signal sequence to obtain a peak value sequence and a valley value sequence, and performing interpolation and difference processing on the peak value sequence and the valley value sequence to obtain a sensing pressure amplitude sequence, including the following steps:

[0111] (1) Peak and valley values ​​are extracted based on the second oscillation pressure signal sequence to obtain a first peak value sequence and a first valley value sequence.

[0112] The extraction of peaks and valleys can be achieved through signal processing software. Peak detection can use the peak detection function (such as findpeaks function) in signal processing software such as MATLAB to detect the peak in the signal. The peak corresponds to the highest point in the signal, and appropriate parameters (such as minimum peak height, minimum interval between two peaks, etc.) are set to ensure that the detected peak is accurate. Valley detection can use valley detection functions (such as variants of findpeaks function) or by comparing adjacent sample values ​​to determine the minimum value to detect valleys in the signal. Valleys correspond to the lowest point in the signal, and appropriate parameters are set to ensure that the detected valleys are accurate.

[0113] (2) Taking the time period of the deflation phase as a reference, interpolation processing is performed on the moments of the first peak sequence and the first valley sequence that are null values ​​during the deflation period to obtain the second peak sequence and the second valley sequence.

[0114] The interpolation process is to ensure that the second peak sequence and the second valley sequence have corresponding values ​​at each moment. If the moments are not completely aligned due to different interpolation methods, the moments can be aligned by interpolation or resampling. The interpolation methods that can be used include linear interpolation, quadratic curve interpolation, etc.

[0115] (3) Performing difference processing on each corresponding moment of the second peak sequence and the second valley sequence to obtain the sensing pressure amplitude at each corresponding moment. The sensing pressure amplitude at each moment constitutes a sensing pressure amplitude sequence. The sensing pressure amplitude represents the fluctuation range of the oscillating pressure signal in each cycle.

[0116] In S400, based on the cuff DC pressure, the sensor pressure amplitude, the systolic pressure data and the diastolic pressure data, an amplitude DC model is constructed, and the systolic pressure and diastolic pressure of the subject to be measured are obtained by combining the cuff DC pressure sequence and the sensor pressure amplitude sequence, including the following steps:

[0117] S410: Based on the cuff DC pressure, the sensor pressure amplitude, the systolic pressure data, and the diastolic pressure data, an amplitude DC model is constructed. The theoretical basis of the amplitude DC model is as follows:

[0118] (1) The arterial compliance model known to those skilled in the art is expressed as follows:

[0119] (1)

[0120] in, Indicates the diameter and volume of blood vessels. represents the transmural pressure of blood vessels, represents the length of the vascular pressurization segment, All represent personalized parameters, which can be obtained by performing nonlinear least squares fitting on the subject's vascular data.

[0121] Combining the effect of human skin and soft tissue on the change of vessel diameter with the compliance of the blood vessel itself, the transmural pressure of the blood vessel can be reduced. Simplified as the difference between the blood pressure value and the DC cuff pressure, it is expressed as follows:

[0122] (2)

[0123] in, Indicates blood pressure value. Indicates DC cuff pressure.

[0124] (2) The vascular volume and cuff volume are coupled and expressed as follows:

[0125] (3)

[0126] in, Indicates the volume of the inner ring of the cuff. represents the initial cuff inner ring volume, That is, the initial arm volume when the blood vessels are in a collapsed state. When the blood vessels collapse, they are blocked and the blood vessel volume is regarded as 0.

[0127] (3) The relationship between cuff pressure and peripheral volume is expressed as follows:

[0128] (4)

[0129] in, Indicates the maximum elastic modulus of the cuff, Indicates the cuff airbag volume, represents the nonlinear constant, represents the initial volume of the cuff periphery, That is, the initial volume of the cuff periphery when the cuff airbag is not stretched.

[0130] (4) During the cuff inflation and deflation phases, it is expressed as follows:

[0131] (5)

[0132] in, represents the atmospheric pressure, Indicates the volume of gas pumped into the cuff.

[0133] Initial air volume inside the cuff Initial cuff inner ring volume , initial volume of cuff periphery Related, expressed as follows:

[0134] (6)

[0135] Combining the above steps, the oscillometric measurement process can be completely modeled.

[0136] (5) Substitute the transmural pressure in formula (1) Substitute into formula (2) and choose As an independent variable, it is expressed as follows:

[0137] (7)

[0138] Among them, blood pressure value Taking different values ​​will result in The curve oscillates, and the upper and lower envelopes of the vascular volume oscillation wave are the blood pressure values Take systolic blood pressure Diastolic blood pressure of The curve is shown below:

[0139] (8)

[0140] (9)

[0141] (6) Combining formula (3) and formula (6), another form of expression of vascular volume can be obtained as follows:

[0142] (10)

[0143] In the prior art: (a) the relationship between the pressure and volume (peripheral volume) of the cuff is a linear relationship in a large range, so according to formula (4), can be regarded as 1; (b) According to the prior art, there is formula (11); (c) In the normal human blood pressure range, the difference caused by the nonlinear expansion of the cuff is small and the cuff pressure in the oscillometric measurement is much lower than the atmospheric pressure, then ; (d) Initial state of the cuff can be regarded as 0. According to the above conditions, formula 10 is simplified to formula (12), and formula (11) and formula (12) are respectively expressed as follows:

[0144] (11)

[0145] (12)

[0146] Since, in the oscillometric method, The maximum is 0.1, and formula (12) is further simplified to formula (13), which is expressed as follows:

[0147] (13)

[0148] In the formula, and They represent the linear parameters between cuff pressure and volume, Is a positive number.

[0149] (7) From formula (13), we can know , indicating changes in vascular volume Changes with cuff pressure The change in vascular volume can also be expressed by the difference between the upper envelope (second peak sequence) and the lower envelope (second valley sequence) at the same time, that is, The cuff pressure change can also be measured by the sensor pressure amplitude sequence at the corresponding moment. indicates that, therefore and Inversely proportional, that is , is the unknown coefficient and is a positive number. After sorting, we get formula (14), which is expressed as follows:

[0150] (14)

[0151] According to formula (8) and formula (9), and Can be passed It means that, therefore, You can also The formula is as follows:

[0152] (15)

[0153] (9) Combining formulas (8), (9), and (15), we get the amplitude DC model, which is expressed as follows:

[0154]

[0155] in, and represents the coefficient, , , represents systolic blood pressure, represents diastolic blood pressure, , , and These are parameters to be solved.

[0156] S420: Based on the cuff DC pressure sequence and the sensor pressure amplitude sequence, the amplitude DC model is solved to obtain the systolic pressure and diastolic pressure of the subject.

[0157] Since the amplitude in the DC model , , systolic blood pressure and diastolic blood pressure are all parameters to be solved, and the sensor pressure amplitude and cuff DC pressure are all known numbers, so the systolic pressure can be obtained by solving the sensor pressure amplitude sequence and the cuff DC pressure sequence and diastolic blood pressure .

[0158] This embodiment implements the solution process through artificial intelligence algorithms. The artificial intelligence that can be used to solve the amplitude DC model includes: machine learning algorithms such as nonlinear regression, support vector machine (SVM), decision tree and random forest; deep learning algorithms such as feedforward neural network, convolutional neural network (CNN), recurrent neural network (RNN) and deep learning framework; integrated learning algorithms such as bagging and boosting; and reinforcement learning algorithms, etc.

[0159] The relationship between pressure amplitude and cuff DC pressure is relatively complex and cannot be described by a simple linear model. Nonlinear regression algorithms, such as polynomial regression and exponential regression, can be used to solve the amplitude DC model. Decision trees and random forests can handle nonlinear relationships and automatically select and combine features to obtain a more accurate prediction model. Random forests further improve the stability and accuracy of the model by constructing multiple decision trees and combining their prediction results. Support vector machines can handle high-dimensional data and complex nonlinear relationships, find an optimal hyperplane to distinguish data points of different categories, and thus solve the amplitude DC model.

[0160] Feedforward neural networks, convolutional neural networks, and recurrent neural networks can automatically learn complex features in data and approximate complex functional relationships through multi-layer nonlinear transformations. Neural network models can be constructed to fit the complex relationship between pressure amplitude and cuff DC pressure. Deep learning frameworks such as TensorFlow and PyTorch provide a wealth of neural network construction and training tools to facilitate the implementation of deep learning algorithms.

[0161] Bagging can build multiple different machine learning models and combine them using the bagging method to improve prediction performance. Boosting can build a series of machine learning models and gradually adjust their weights to obtain better prediction results.

[0162] Reinforcement learning algorithms can be used to optimize certain parameters or strategies in the blood pressure measurement process to improve the accuracy and comfort of blood pressure measurement. Appropriate artificial intelligence algorithms can be selected according to actual conditions, and optimized and adjusted in combination with specific application scenarios and requirements, which are not limited in this application.

[0163] In this embodiment, a particle swarm algorithm is used to solve the amplitude DC model through the cuff DC pressure sequence and the sensor pressure amplitude sequence, and then the systolic pressure and the diastolic pressure are obtained, including the following steps:

[0164] (1) Construct the fitness function of the particle, which is expressed as follows:

[0165]

[0166] in, represents fitness, represents the sensing pressure amplitude in the sensing pressure amplitude sequence, Indicates that based on the current position of the particle (predicted ) is the sensor pressure amplitude calculated by the particle swarm algorithm, which is the sensor pressure amplitude predicted by the particle swarm algorithm. Represents the number of sensor pressure amplitudes predicted by the particle swarm algorithm.

[0167] (2) Randomly generate an initial particle swarm, including the initial position and velocity of the particle swarm, and then obtain the initial individual optimal position of the particle and the initial global optimal position of the particle swarm. Each particle position represents a set of parameters to be solved in the amplitude DC model. Solution: The particle velocity represents the direction and rate of particle position update. The initial individual optimal position of a particle is its initial position. The initial global optimal position of a particle swarm is the position of a random particle in the initial particle swarm.

[0168] (3) Calculate the fitness of each particle’s current position based on the fitness function;

[0169] (4) According to the fitness, if the fitness of the particle's current position is better than the fitness of its individual optimal position, the individual optimal position is updated. (The position of each particle with the minimum fitness in its history). If the fitness of any particle's current position is better than the fitness of the global optimal position, the global optimal position is updated. (the position of the particle with the lowest fitness among all particles so far);

[0170] (5) According to the current position, speed, individual optimal position and global optimal position of the particle, the speed and position of the particle are updated to obtain the updated particle speed and updated particle position, which are expressed as follows:

[0171]

[0172]

[0173] in, represents the latest position of the particle, represents the position of the particle in the previous iteration, represents the current velocity of the particle, represents the inertia weight, represents the velocity of the particle in the last iteration, represents the individual optimal position of the particle, represents the current position of the particle, represents the global optimal position of the entire particle swarm, represents the learning factor, Represents a random number.

[0174] (6) Iteration. If the termination condition is met, the iteration ends and the final global optimal position is output. The final global optimal position is the optimal solution of the amplitude DC model. , if the termination condition is not met, repeat the above steps (3) to (5) until the termination condition is met. The termination condition can be reaching the maximum number of iterations, or the fitness change is less than a certain threshold, or other forms.

[0175] Embodiment 2:

[0176] A blood pressure measurement system based on a cuff of a pressure sensor device, such as Figure 3 As shown, it includes a pressure acquisition module 100, a pressure extraction module 200, a DC and amplitude extraction module 300, and a model solving module 400;

[0177] The pressure acquisition module 100 collects electrical signals in the inflation stage and the deflation stage based on the time series to obtain a first oscillation pressure signal sequence, and collects cuff pressure signals in the inflation stage and the deflation stage based on the time series to form a first cuff pressure signal sequence, wherein the electrical signal is a response value of a pressure sensor device located inside the cuff, the pressure sensor device is a capacitive pressure sensor device, and the cuff pressure signal includes a DC signal and an AC signal;

[0178] The pressure extraction module 200 extracts the first oscillation pressure signal sequence in the deflation phase to form a second oscillation pressure signal sequence, and extracts the first cuff pressure signal sequence in the deflation phase to form a second cuff pressure signal sequence;

[0179] The DC and amplitude extraction module 300 extracts the DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain the cuff DC pressure sequence, extracts the peak value and the valley value of the oscillation pressure signal in the second oscillation pressure signal sequence to obtain the peak value sequence and the valley value sequence, and performs interpolation and difference processing on the peak value sequence and the valley value sequence to obtain the sensing pressure amplitude sequence;

[0180] The model solving module 400 constructs an amplitude DC model based on the cuff DC pressure, the sensor pressure amplitude, the systolic pressure data and the diastolic pressure data, and obtains the systolic pressure and diastolic pressure of the subject by combining the cuff DC pressure sequence and the sensor pressure amplitude sequence;

[0181] The amplitude DC model is expressed as follows:

[0182]

[0183] in, represents the sensing pressure amplitude in the sensing pressure amplitude sequence, represents the cuff DC pressure in the cuff DC pressure sequence, and represents the coefficient, represents systolic blood pressure, Indicates diastolic blood pressure.

[0184] Various changes and modifications can be made without departing from the spirit and scope of the present invention, and all equivalent technical solutions also belong to the scope of the present invention.

[0185] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0186] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0187] The present invention is described with reference to the flowcharts and / or block diagrams of the method, terminal device (system), and computer program product according to the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0188] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0189] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0190] It should be noted that:

[0191] The "one embodiment" or "embodiment" mentioned in the specification means that the specific features, structures or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. Therefore, the phrases "one embodiment" or "embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment.

[0192] In addition, it should be noted that the shapes and names of the parts and components of the specific embodiments described in this specification may be different. Any equivalent or simple changes made based on the structure, features and principles described in the patent concept of the present invention are included in the protection scope of the patent of the present invention. The technicians in the technical field of the present invention can make various modifications or supplements to the specific embodiments described or replace them in a similar manner, as long as they do not deviate from the structure of the present invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A cuff blood pressure measurement method based on a pressure sensor device, characterized in that: The following steps are involved: Based on the time series, the electrical signals in the inflation stage and the deflation stage are collected to obtain a first oscillation pressure signal sequence; based on the time series, the cuff pressure signals in the inflation stage and the deflation stage are collected to form a first cuff pressure signal sequence, wherein the electrical signal is a response value of a pressure sensor device located inside the cuff, the pressure sensor device is a capacitive pressure sensor device, and the cuff pressure signal includes a DC signal and an AC signal; Extracting a first oscillation pressure signal sequence in the deflation phase to form a second oscillation pressure signal sequence, and extracting a first cuff pressure signal sequence in the deflation phase to form a second cuff pressure signal sequence; Extracting the DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain the cuff DC pressure sequence, extracting the peak value and the valley value of the oscillating pressure signal in the second oscillating pressure signal sequence to obtain the peak value sequence and the valley value sequence, and performing interpolation and difference processing on the peak value sequence and the valley value sequence to obtain the sensing pressure amplitude sequence; Based on the cuff DC pressure, sensor pressure amplitude, systolic pressure data and diastolic pressure data, an amplitude DC model is constructed, and the systolic and diastolic pressures of the subject are obtained by combining the cuff DC pressure sequence and the sensor pressure amplitude sequence.

2. The cuff blood pressure measurement method based on the pressure sensor device according to claim 1 is characterized in that: The pressure sensing device is a PVDF film pressure sensor.

3. The cuff blood pressure measurement method based on the pressure sensor device according to claim 1 is characterized in that: The method of collecting electrical signals in the inflation phase and the deflation phase based on the time series to obtain a first oscillation pressure signal sequence includes the following steps: Based on the time series, the response values ​​of the pressure sensing device in the inflation phase and the deflation phase, i.e., the electrical signals, are collected to obtain an electrical signal sequence, and the electrical signal sequence is preprocessed to obtain a preprocessed electrical signal sequence, wherein the preprocessing includes one or more of filtering, amplification, linearization, and data conversion; Based on the preprocessed electrical signal sequence and combined with the pressure value and electrical signal value mapping model, a first oscillation pressure signal sequence is obtained, wherein the pressure value and electrical signal value mapping model is a numerical relationship model between the pressure value acting on the pressure sensing device and the response value of the pressure sensing device.

4. The cuff blood pressure measurement method based on the pressure sensor device according to claim 1 is characterized in that: The step of extracting the first oscillation pressure signal sequence in the deflation phase to form the second oscillation pressure signal sequence, and extracting the first cuff pressure signal sequence in the deflation phase to form the second cuff pressure signal sequence comprises the following steps: Obtaining the maximum pressure point of the first cuff pressure signal in the first cuff pressure signal sequence, and then obtaining the first moment corresponding to the maximum pressure point; Based on the first cuff pressure signal sequence, the maximum pressure drop change point of the first cuff pressure signal is obtained, and then the second moment corresponding to the maximum pressure drop change point is obtained, and the period between the first moment and the second moment is the deflation stage; forming a second oscillating pressure signal sequence based on the first oscillating pressure signal sequence during the deflation phase; Based on the first cuff pressure signal sequence in the deflation phase, a second cuff pressure signal sequence is formed.

5. The cuff blood pressure measurement method based on the pressure sensor device according to claim 1 is characterized in that: The step of extracting the DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain the cuff DC pressure sequence comprises the following steps: performing wavelet transform processing with different scale parameters on the cuff pressure signal in the second cuff pressure signal sequence to obtain wavelet coefficients with different scale parameters; The wavelet coefficients with scale parameters greater than a preset scale threshold are extracted from the wavelet coefficients with different scale parameters to obtain an initial DC pressure sequence; Performing inverse wavelet transform on the DC pressure in the initial DC pressure signal sequence, and obtaining a reconstructed DC pressure sequence, which is the cuff DC pressure sequence; Wherein, the wavelet transform is expressed as follows: The inverse wavelet transform is expressed as follows: in, represents the wavelet coefficients, represents the scale parameter, represents the translation parameter, represents the cuff pressure signal in the second cuff pressure signal sequence, represents the wavelet basis function, Indicates time, represents the DC pressure in the reconstructed DC pressure sequence, represents the DC pressure in the initial DC pressure sequence, Represents the admissibility constant of the wavelet basis function.

6. The cuff blood pressure measurement method based on the pressure sensor device according to claim 1 is characterized in that: The step of extracting the peak values ​​and valley values ​​of the oscillating pressure signal in the second oscillating pressure signal sequence to obtain a peak value sequence and a valley value sequence, and performing interpolation and difference processing on the peak value sequence and the valley value sequence to obtain a sensing pressure amplitude sequence includes the following steps: Extracting the peak value and the valley value of the oscillation pressure signal in the second oscillation pressure signal sequence respectively to obtain a first peak value sequence and a first valley value sequence; Interpolating the moments when the peak values ​​in the first peak value sequence are null values ​​to obtain a second peak value sequence, and interpolating the moments when the valley values ​​in the first valley value sequence are null values ​​to obtain a second valley value sequence; The peak value and the valley value at each corresponding moment in the second peak value sequence and the second valley value sequence are subjected to difference processing to obtain the sensing pressure amplitude at each corresponding moment, and further obtain the sensing pressure amplitude sequence.

7. The cuff blood pressure measurement method based on the pressure sensor device according to claim 1, characterized in that: The construction of an amplitude DC model based on the cuff DC pressure, the sensor pressure amplitude, the systolic pressure data and the diastolic pressure data comprises the following steps: Based on the cuff DC pressure, systolic pressure data and diastolic pressure data, the sensor pressure amplitude is fitted to obtain the amplitude DC model, where the amplitude DC model is expressed as follows: in, represents the sensing pressure amplitude in the sensing pressure amplitude sequence, represents the cuff DC pressure in the cuff DC pressure sequence, and represents the coefficient, Represents systolic blood pressure data, Indicates diastolic blood pressure data.

8. The cuff blood pressure measurement method based on the pressure sensor device according to claim 1, characterized in that: The method of combining the cuff DC pressure sequence and the sensor pressure amplitude sequence to obtain the systolic and diastolic pressures of the subject includes the following steps: Based on the sensed pressure amplitude, the fitness function of the particle is constructed; Randomly generate an initialization particle swarm, obtain the position and velocity of each particle in the initialization particle swarm, and then obtain the initial individual optimal position of each particle and the initial global optimal position of the particle swarm, where the position of the particle is the parameter to be solved in the amplitude DC model, including systolic pressure and diastolic pressure; Get the fitness of each particle's current position based on the fitness function; If the fitness of the current position of the particle is better than the fitness of the individual optimal position, the individual optimal position is updated; if the fitness of the current position of any particle is better than the fitness of the global optimal position, the global optimal position is updated, and the position and speed of the particle are updated to obtain the updated particle speed and updated particle position; Until the termination condition is met, the final global optimal position is output, which is the optimal solution of the parameters to be solved of the amplitude DC model, and then the systolic and diastolic blood pressures of the subject are obtained; Wherein, the fitness function is expressed as follows: The updated particle velocity is expressed as follows: The updated particle position is expressed as follows: in, represents fitness, represents the sensing pressure amplitude in the sensing pressure amplitude sequence, represents the sensor pressure amplitude based on the current position of the particle, represents the number of predicted sensor pressure amplitudes, represents the updated particle velocity, represents the inertia weight, represents the particle velocity of the last iteration, represents the optimal position of the individual particle in the last iteration, represents the particle position of the last iteration, represents the global optimal position of the last iteration, represents the learning factor, Represents a random number, Indicates the updated particle position.

9. A cuff blood pressure measurement system based on a pressure sensor device, characterized in that: It includes pressure acquisition module, pressure extraction module, DC and amplitude extraction module, and model solution module; The pressure acquisition module collects electrical signals in the inflation stage and the deflation stage based on the time series to obtain a first oscillation pressure signal sequence, and collects cuff pressure signals in the inflation stage and the deflation stage based on the time series to form a first cuff pressure signal sequence, wherein the electrical signal is a response value of a pressure sensor device located inside the cuff, the pressure sensor device is a capacitive pressure sensor device, and the cuff pressure signal includes a DC signal and an AC signal; The pressure extraction module extracts the first oscillation pressure signal sequence in the deflation phase to form a second oscillation pressure signal sequence, and extracts the first cuff pressure signal sequence in the deflation phase to form a second cuff pressure signal sequence; The DC and amplitude extraction module extracts the DC signal of the cuff pressure signal in the second cuff pressure signal sequence to obtain the cuff DC pressure sequence, extracts the peak value and the valley value of the oscillating pressure signal in the second oscillating pressure signal sequence to obtain the peak value sequence and the valley value sequence, and performs interpolation and difference processing on the peak value sequence and the valley value sequence to obtain the sensing pressure amplitude sequence; The model solving module constructs an amplitude DC model based on the cuff DC pressure, the sensor pressure amplitude, the systolic pressure data and the diastolic pressure data, and obtains the systolic pressure and diastolic pressure of the subject by combining the cuff DC pressure sequence and the sensor pressure amplitude sequence; Among them, the amplitude DC model is expressed as follows: in, represents the sensing pressure amplitude in the sensing pressure amplitude sequence, represents the cuff DC pressure in the cuff DC pressure sequence, and represents the coefficient, Represents systolic blood pressure data, Indicates diastolic blood pressure data.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

11. A cuff blood pressure measuring device based on a pressure sensor device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images