Blood pressure data calculation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a blood pressure data calculation method and device, electronic equipment and a storage medium, and the method comprises the steps: firstly, obtaining pressure curve data measured by a pressure sensor in continuous time, and extracting the pressure curve data to obtain descending curve data; then, performing polynomial curve fitting on the descending branch curve data to generate fitted curve data, and generating pulse wave envelope curve data based on the descending branch curve data and a fluctuation value of each data point corresponding to the fitted curve data; and finally, selecting a target data point based on the slope of the pulse wave envelope curve data, and obtaining blood pressure measurement data based on the corresponding pressure value data of the target data point in the pressure curve data, thereby improving the accuracy and anti-interference capability of blood pressure data calculation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of measurement data processing, in particular to a blood pressure data calculation method and device, an electronic device and a storage medium. BACKGROUND

[0002] Electronic sphygmomanometers are currently widely used health monitoring devices in families and clinics, and the mainstream technical solution thereof is the oscillometric method. In a typical measurement process, the device inflates the cuff to block the arterial blood flow, and then slowly deflates. During this period, the pressure sensor monitors the pressure change in the cuff in real time and captures the weak pressure oscillation wave generated by the arterial blood vessels with the heartbeat. Currently, the blood pressure data processing method commonly used in the industry is to form an envelope line based on these oscillation waves, and to calculate using the fixed ratio method, that is, to determine the systolic pressure and diastolic pressure by finding specific ratio points before and after the maximum amplitude of the envelope line according to the empirical coefficient obtained through large-scale clinical statistics.

[0003] However, the traditional oscillometric method based on the fixed ratio, whose algorithm model mainly comes from universal clinical statistical data, lacks adaptability to individual physiological characteristics and ignores the differences between individuals, so there is a large gap between its measurement accuracy and the "gold standard" of invasive measurement. In particular, for patients with hypertension accompanied by arrhythmia, the shape and amplitude of a single pulse wave may fluctuate dramatically and irregularly, and the traditional fixed ratio method is easily disturbed by a single abnormal pulse point when processing such irregular signals, which cannot accurately reflect the overall true blood pressure level during the measurement period, thereby making the blood pressure data measured and calculated by the traditional oscillometric method based on the fixed ratio less accurate. SUMMARY

[0004] The blood pressure data calculation method, device, electronic device and storage medium provided by the embodiments of the present application can improve the accuracy of blood pressure data measurement and calculation.

[0005] To achieve the above-mentioned purpose, the first aspect of the embodiments of the present application provides a blood pressure data calculation method, which comprises:

[0006] Obtaining pressure curve data measured by a pressure sensor in a continuous time, and extracting the pressure curve data to obtain descending branch curve data;

[0007] Performing polynomial curve fitting on the descending branch curve data to generate fitting curve data, and generating pulse wave envelope curve data based on the fluctuation value of each data point corresponding to the descending branch curve data and the fitting curve data;

[0008] Select a target data point based on a slope of the pulse wave envelope curve data, and obtain blood pressure measurement data based on a corresponding pressure value data of the target data point in the pressure curve data.

[0009] In some embodiments, the extracting the pressure curve data to obtain the descending branch curve data comprises:

[0010] Determining a point with a maximum pressure value from the pressure curve data as a critical pressure value;

[0011] Selecting curve data after the critical pressure value from the pressure curve data to obtain the descending branch curve data.

[0012] In some embodiments, the polynomial curve fitting the descending branch curve data to generate the fitted curve data comprises:

[0013] Determining a fitted polynomial function;

[0014] Polynomial fitting the descending branch curve data based on the fitted polynomial function to obtain the fitted curve data.

[0015] In some embodiments, the generating the pulse wave envelope curve data based on a fluctuation value of each data point corresponding to the descending branch curve data and the fitted curve data comprises:

[0016] Obtaining the fluctuation value based on a difference between each time point in the descending branch curve data and a corresponding data point of the fitted curve data;

[0017] Generating a pulse wave oscillation curve based on fluctuation values corresponding to multiple consecutive time points;

[0018] Generating the pulse wave envelope curve data based on the pulse wave oscillation curve.

[0019] In some embodiments, the generating the pulse wave envelope curve data based on the pulse wave oscillation curve comprises:

[0020] Sequentially connecting all peak values in the pulse wave oscillation curve to obtain an upper envelope line;

[0021] Sequentially connecting all trough values in the pulse wave oscillation curve to obtain a lower envelope line;

[0022] Generating the pulse wave envelope curve data based on a difference between the upper envelope line and the lower envelope line.

[0023] In some embodiments, the pressure sensor measures a plurality of pressure curve data in a continuous time, the envelope curve data is generated based on a fluctuation value of each data point corresponding to the descending branch curve data and the fitting curve data, and the envelope curve data includes:

[0024] The initial pulse wave envelope curve corresponding to each of the pressure curve data is generated based on the descending branch curve data and the fitting curve data corresponding to each of the pressure curve data.

[0025] The plurality of initial pulse wave envelope curves are globally filtered and smoothed to obtain the pulse wave envelope curve data.

[0026] In some embodiments, the target data point includes a first data point and a second data point, the blood pressure measurement data includes systolic pressure data and diastolic pressure data, the target data point is selected based on a slope of the pulse wave envelope curve data, and the blood pressure measurement data is obtained based on a pressure value data corresponding to the target data point in the pressure curve data, and the blood pressure data determination module includes:

[0027] The first data point is selected as a data point with the largest slope from the pulse wave envelope curve data, and the second data point is selected as a data point with the smallest slope from the pulse wave envelope curve data.

[0028] The pressure value data corresponding to the first data point in the pressure curve data is taken as the systolic pressure data, and the pressure value data corresponding to the second data point in the pressure curve data is taken as the diastolic pressure data.

[0029] To achieve the above object, a second aspect of the embodiment of the present application provides a blood pressure data calculation device, which includes:

[0030] The data acquisition module is configured to acquire pressure curve data measured by a pressure sensor in a continuous time, and extract the pressure curve data to obtain descending branch curve data.

[0031] The envelope generation module is configured to perform polynomial curve fitting on the descending branch curve data to generate fitting curve data, and generate pulse wave envelope curve data based on a fluctuation value of each data point corresponding to the descending branch curve data and the fitting curve data.

[0032] The blood pressure data determination module is configured to select a target data point based on a slope of the pulse wave envelope curve data, and obtain blood pressure measurement data based on a pressure value data corresponding to the target data point in the pressure curve data.

[0033] To achieve the above object, a third aspect of the embodiments of the present application provides an electronic device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the blood pressure data calculation method according to the first aspect when executing the computer program.

[0034] To achieve the above object, a fourth aspect of the embodiments of the present application provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the blood pressure data calculation method according to the first aspect.

[0035] The blood pressure data calculation method, device, electronic device and storage medium provided by the embodiments of the present application, the method comprises: first, obtaining pressure curve data measured by a pressure sensor in a continuous time, and extracting the pressure curve data to obtain descending branch curve data; then, performing polynomial curve fitting on the descending branch curve data to generate fitting curve data, and generating pulse wave envelope curve data based on the fluctuation value of each data point corresponding to the descending branch curve data and the fitting curve data; finally, selecting a target data point based on the slope of the pulse wave envelope curve data, and obtaining blood pressure measurement data based on the pressure value data corresponding to the target data point in the pressure curve data. The embodiments of the present application can accurately extract the fluctuation signal reflecting the individual true pulse by performing global polynomial fitting on the descending branch data of the pressure curve, and generate the pulse wave envelope curve, which breaks away from the dependence on universal statistical data of the traditional fixed ratio method, and establishes a customized mathematical model that can reflect individual differences for each measurement process. Secondly, instead of using amplitude ratio, the systolic pressure and diastolic pressure are determined by finding the points with the maximum and minimum slopes on the pulse wave envelope curve, which not only is closer to the physiological and physical meaning of blood pressure measurement in principle, but also can effectively resist the interference of single abnormal pulse wave data caused by arrhythmia and other reasons, avoid misjudgment, and thus can more accurately and stably feedback the overall blood pressure during the measurement, significantly improving the accuracy and anti-interference ability of blood pressure data calculation.

[0036] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and achieved by the structure particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 is a flowchart of a blood pressure data calculation method provided by an embodiment of the present application.

[0038] Figure 2is a schematic diagram of pressure curve data provided by another embodiment of the present application.

[0039] Figure 3 is Figure 1 is a flowchart of step 101 in the method.

[0040] Figure 4 is a schematic diagram of falling branch curve data provided by another embodiment of the present application.

[0041] Figure 5 is Figure 1 is a flowchart of step 102 in the method.

[0042] Figure 6 is Figure 1 is another flowchart of step 102 in the method.

[0043] Figure 7 is a schematic diagram of a pulse wave oscillation curve provided by another embodiment of the present application.

[0044] Figure 8 is Figure 6 is a flowchart of step 603 in the method.

[0045] Figure 9 is a schematic diagram of pulse wave envelope curve data provided by another embodiment of the present application.

[0046] Figure 10 is Figure 1 is still another flowchart of step 102 in the method.

[0047] Figure 11 is a schematic diagram of globally filtered and smoothed pulse wave envelope curve data provided by another embodiment of the present application.

[0048] Figure 12 is Figure 1 is a flowchart of step 103 in the method.

[0049] Figure 13 is a performance simulation schematic diagram of a blood pressure data calculation method provided by another embodiment of the present application.

[0050] Figure 14 is a structural schematic diagram of a blood pressure data calculation apparatus provided by another embodiment of the present application.

[0051] Figure 15 is a hardware structural schematic diagram of an electronic device provided by another embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be given below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and not intended to limit the present application.

[0053] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical sequence is shown in the flowchart, in some cases, the steps shown or described can be performed in a manner different from the module division in the device or the sequence in the flowchart.

[0054] Unless otherwise defined, 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 application belongs. The terminology used in the specification herein is for describing the embodiments of the present application only and not intended to limit the present application.

[0055] Electronic sphygmomanometers are widely used health monitoring devices in families and clinics, and the mainstream technical solution is the oscillometric method. In a typical measurement process, the device inflates the cuff to block the arterial blood flow, and then slowly deflates. During this period, the pressure sensor monitors the pressure change in the cuff in real time and captures the weak pressure oscillation wave generated by the arterial blood vessels with the heartbeat. Currently, the commonly used blood pressure data processing method in the industry is to form an envelope based on these oscillation waves, and to calculate using the fixed ratio method, that is, according to the empirical coefficient obtained from large-scale clinical statistics, the systolic and diastolic pressures are determined by finding specific ratio points before and after the maximum amplitude of the envelope.

[0056] However, the traditional oscillometric method based on the fixed ratio, whose algorithm model is mainly derived from universal clinical statistical data, lacks adaptability to individual physiological characteristics and ignores the differences between individuals, so its measurement accuracy is far from the "gold standard" of invasive measurement. Especially for patients with hypertension accompanied by arrhythmia, the shape and amplitude of a single pulse wave may fluctuate dramatically and irregularly. The traditional fixed ratio method is easily disturbed by a single abnormal pulse point when processing irregular signals, and cannot accurately reflect the overall true blood pressure level during the measurement period, so that the blood pressure data measured and calculated by the traditional oscillometric method with fixed ratio has low accuracy.

[0057] To improve the accuracy of blood pressure measurement and calculation, this application embodiment uses global polynomial fitting of the descending limb data of the pressure curve to accurately extract the fluctuation signal reflecting the individual's true pulse and generate a pulse wave envelope curve. This eliminates the reliance on universal statistical data in the traditional fixed ratio method and establishes a customized mathematical model that reflects individual differences for each measurement process. Secondly, instead of using amplitude ratio, it determines systolic and diastolic pressure by finding the points with the maximum and minimum slopes on the pulse wave envelope curve. This is not only closer to the physiological and physical meaning of blood pressure measurement in principle, but also, because it focuses on the overall trend of data change (i.e., slope) rather than the absolute amplitude of a single pulse wave, it can effectively resist interference from individual abnormal pulse wave data caused by arrhythmia and other reasons, avoiding misjudgment. Thus, it can more accurately and stably reflect the overall blood pressure situation during the measurement period, significantly improving the accuracy and anti-interference ability of blood pressure data calculation.

[0058] The method for calculating blood pressure data in the embodiments of this application will be described in detail below. (Refer to...) Figure 1 This is an optional flowchart of the blood pressure data calculation method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps 101 to 103. It is also understood that this embodiment... Figure 1 The order of steps 101 to 103 is not specifically limited; the order of steps can be adjusted or certain steps can be added or removed according to actual needs. The blood pressure data calculation method provided in this application embodiment can be applied to any smart terminal, server, computer, etc. connected to the electronic blood pressure monitor, or directly applied to the smart processing chip in the electronic blood pressure monitor, etc.

[0059] Step 101: Obtain the pressure curve data measured by the pressure sensor over a continuous time period, and extract the pressure curve data to obtain the branch curve data.

[0060] Step 101 will be described in detail below.

[0061] In some embodiments, the raw data measured by the pressure sensor over a continuous time period, i.e., pressure curve data, is first acquired by the execution component of this method. This pressure curve data completely records the pressure changes of the blood pressure cuff throughout the entire process from inflating to deflating, and includes weak oscillating signals reflecting arterial pulsation.

[0062] Reference Figure 2 This is a schematic diagram of pressure curve data provided in an embodiment of this application. Figure 2As shown in the figure, the pressure sensor shows the relationship between the pressure curve data and time in a complete blood pressure measurement cycle. The horizontal axis represents time, and the vertical axis represents pressure. The overall curve shows a rising trend followed by a falling trend. The former half of the curve, which shows a rapid rise in pressure, is called the "upstroke", representing the process of tightening the sphygmomanometer cuff and increasing pressure. The latter half of the curve, which shows a gentle decline in pressure, is called the "downstroke", representing the process of deflating the cuff and reducing pressure. The core calculation of the application is based on the downstroke curve data. In addition, as shown in the details pointed by the red arrow in the figure, there are small fluctuations superimposed on the smooth upstroke and downstroke curve. These fluctuations are the core pulse signals that need to be extracted and analyzed by the algorithm, which are caused by the pressure oscillation of the arterial blood vessels with the heartbeat.

[0063] In order to effectively calculate blood pressure, a predetermined part of the pressure curve data needs to be extracted to obtain the downstroke curve data. The downstroke curve data specifically refers to the pressure data sequence collected when the cuff is in the deflation stage. Since the arterial blood vessels gradually recover from the compressed state in this stage, the pulse oscillation signal is the clearest and most typical, and is the core data basis for the calculation of the sphygmomanometer.

[0064] Referring to Figure 3 The pressure curve data is extracted to obtain the downstroke curve data. This includes steps 301 to 302.

[0065] Step 301: Determine the point with the maximum pressure value data in the pressure curve data as the critical pressure value.

[0066] Step 302: Select the curve data after the critical pressure value from the pressure curve data to obtain the downstroke curve data.

[0067] The steps 301 to 302 are described in detail below.

[0068] In some embodiments, in order to accurately separate the key data segment for blood pressure calculation, it is necessary to analyze the complete pressure curve data to determine a clear segmentation point. Specifically, this step searches and identifies a data point with the maximum pressure reading by traversing the entire pressure curve data sequence. This "point with the maximum pressure value data" corresponds to the end of the sphygmomanometer cuff inflation process and the start of the deflation process in a physical sense, so the pressure value corresponding to this point is defined as a key parameter, i.e. the critical pressure value. This critical pressure value serves as a unique and objective reference, providing a reliable basis for subsequent data extraction operations.

[0069] After the critical pressure value is determined, the data extraction operation is performed using the benchmark. Specifically, the time point at which the critical pressure value is located is taken as the dividing line, and all curve data after the critical pressure value in time is selected and separated from the original pressure curve data. This part of the selected "curve data after the critical pressure value" is defined as the descending branch curve data for subsequent core algorithm analysis. In this way, the descending branch curve data is accurately defined as the complete process of smooth decline from the highest point of the cuff pressure, ensuring that the data segment intercepted contains all effective pulse wave information for oscillographic analysis.

[0070] Referring to Figure 4 , a schematic diagram of the descending branch curve data provided by the embodiment of the present application is shown. As shown in Figure 4 , the descending branch curve data obtained after the data extraction step is shown. The curve is formed by taking the data in the latter half (i.e. the cuff deflation stage) after determining the pressure peak from the complete pressure-time image (i.e. the pressure curve data shown in Figure 2 ). The abscissa represents time, and the ordinate represents pressure. The data points clearly depict the overall trend of the cuff pressure declining smoothly and linearly over time in this measurement period. This accurately separated descending branch curve data is the key processing object of the entire algorithm, which eliminates invalid information in the inflation stage, completely retains the core pulse oscillation signal for blood pressure calculation, and will be directly input for the next step of polynomial curve fitting.

[0071] Through the above steps 301 and 302, an automatic, accurate and reliable data preprocessing method is formed. By first determining the critical pressure value as an objective and unique anchor point, and then segmenting the pressure curve data according to the anchor point, the descending branch curve data necessary for blood pressure calculation can be accurately separated from the original measurement signal, effectively eliminating the interference of irrelevant data such as the cuff inflation stage, ensuring that the data source for subsequent core calculation steps such as polynomial fitting, envelope generation and slope analysis is pure, complete and effective, thereby laying a solid foundation for the accuracy and stability of the entire blood pressure data calculation method.

[0072] Step 102: Perform polynomial curve fitting on the descending branch curve data to generate fitted curve data, and generate pulse wave envelope curve data based on the fluctuation value of each data point corresponding to the descending branch curve data and the fitted curve data.

[0073] Step 102 will be described in detail below.

[0074] After obtaining the descending branch curve data, in order to eliminate the baseline drift and separate the pure pulse signal, the descending branch curve data is subjected to polynomial curve fitting. Polynomial curve fitting is a mathematical modeling technique that can generate a smooth fitting curve data representing the trend of pressure gently declining, which can be regarded as a dynamic pressure baseline.

[0075] Referring to Figure 5 The polynomial curve fitting of the descending branch curve data generates fitting curve data, including the following steps 501 to 502.

[0076] Step 501: Determine the fitting polynomial function.

[0077] Step 502: Based on the fitting polynomial function, perform polynomial fitting on the descending branch curve data to obtain the fitting curve data.

[0078] The steps 501 to 502 are described in detail below.

[0079] In some embodiments, in order to accurately model the descending branch curve data, it is necessary to first determine the fitting polynomial function. The fitting polynomial function here is a pre-set mathematical equation with a specific degree, which will be used as a template to approximate the actual descending branch curve data. For example, a cubic polynomial function. It is crucial to choose the appropriate function degree, which needs to be flexible enough to capture the nonlinear characteristics in the pressure decline process, while avoiding the problem of overfitting caused by too high degree. The essence of this step is to select a mathematical tool that best balances accuracy and stability for subsequent fitting calculations.

[0080] When the fitting polynomial function is determined, the core calculation of polynomial fitting based on this function will be performed on the descending branch curve data. Polynomial fitting is a process of finding the best parameter combination (i.e. polynomial coefficients) in the fitting polynomial function through regression analysis and other algorithms, with the goal of minimizing the overall error between the final curve and the original descending branch curve data points. The output of this process is a new sequence of data, i.e. fitting curve data. This set of fitting curve data is graphically represented as a smooth curve passing through the original data points, which accurately depicts the macro trend of the cuff pressure decline and filters out the high-frequency pulse wave signal superimposed on it.

[0081] In one example, the mathematical method is to perform cubic polynomial curve fitting on the entire descending branch curve, linear regression, and the implementation code example is as follows in the matlab code.

[0082] % Assume there are data X and y

[0083] % X = [...];

[0084] % y = [...];

[0085] % Use polyfit for a cubic polynomial fit

[0086] p = polyfit(X, y, 3); % p contains coefficients from highest to lowest order

[0087] % Use polyval to calculate the fitted values

[0088] xFine = linspace(min(X), max(X), 100);

[0089] yFine = polyval(p, xFine);

[0090] % Plot the original data and the fitted curve

[0091] figure;

[0092] plot(X, y, 'o'); % Original data points

[0093] hold on;

[0094] plot(xFine, yFine, '-'); % Fitted curve

[0095] xlabel('X');

[0096] ylabel('Y');

[0097] title('Cubic Polynomial Fit');

[0098] legend('Data Points', 'Fitted Curve');

[0099] grid on;

[0100] hold off;

[0101] % Display the fitted polynomial equation

[0102] fprintf('Fitted Equation: y = %.4fx^3 + %.4fx^2 + %.4fx + %.4f\n', p(1), p(2), p(3), p(4));

[0103] By the above steps 501 and 502, a highly accurate and dynamically adaptive pressure baseline is generated for each blood pressure measurement. By first determining a suitable fitting polynomial function and then performing polynomial fitting on the actual descending curve data, a fitting curve data that perfectly fits the current measurement situation can be generated, which can accurately separate the low-frequency macro trend representing pressure drop from the high-frequency signal representing pulse oscillation, without causing signal distortion as traditional filters may do, providing a solid foundation for subsequent accurate calculation of pulse fluctuation values, and is a key prerequisite for improving the accuracy and anti-interference ability of the entire blood pressure algorithm.

[0104] Subsequently, based on the descending curve data and the fitting curve data, a series of fluctuation values are obtained by calculating the difference between the two at each corresponding data point. This series of fluctuation values constitutes a pulse wave oscillation curve without the descending baseline, more truly reflecting the blood vessel volume changes caused by heartbeats. Finally, by performing envelope processing on the pulse wave oscillation curve, such as extracting the difference between its upper and lower envelope lines, the pulse wave envelope curve data for subsequent analysis can be generated.

[0105] Referring to Figure 6 Based on the fluctuation value of each data point corresponding to the descending curve data and the fitting curve data, the pulse wave envelope curve data is generated, including the following steps 601 to 603.

[0106] Step 601: Based on the difference between each time point in the descending curve data and the corresponding data point in the fitting curve data, the fluctuation value is obtained.

[0107] Step 602: Based on the fluctuation values corresponding to multiple consecutive time points, a pulse wave oscillation curve is generated.

[0108] Step 603: Based on the pulse wave oscillation curve, the pulse wave envelope curve data is generated.

[0109] The steps 601 to 603 are described in detail below.

[0110] In some embodiments, in order to separate the pure pulse signal from the background pressure, the previously acquired descending curve data and the fitting curve data generated by fitting are used. The system calculates the "difference" between the actual pressure measurement value in the descending curve data and the baseline pressure value in the fitting curve data at each discrete time point, which is the fluctuation value. Each fluctuation value accurately quantifies the pressure oscillation amplitude caused by arterial pulsation at that instant, effectively stripping the weak physiological signal from the macro pressure drop trend.

[0111] In one example, the point (x1, y1) is taken as an example, the corresponding point (x1', y1') on the fitting curve (f(x)) can be calculated approximately, x1' = x1, y1' = f(x1), and the approximate distance is O = y1 - y1'.

[0112] After a series of continuous fluctuation values covering the entire deflation time period are calculated, these data points are used to construct a new function image. This step is based on the fluctuation values corresponding to multiple consecutive time points, which are plotted in a coordinate system with time as the horizontal axis and fluctuation value as the vertical axis, thereby generating a pulse wave oscillation curve. The pulse wave oscillation curve is a curve that fluctuates up and down around the zero baseline, which intuitively and purely presents the original form and rhythm of the pressure oscillation caused by the periodic beating of the heart during the deflation of the cuff, and is the basis for subsequent envelope analysis.

[0113] Referring to Figure 7 , a schematic diagram of a pulse wave oscillation curve provided by an embodiment of the present application is shown. As Figure 7 indicated, the generated pulse wave oscillation curve is shown. The curve is plotted with time as the horizontal coordinate and the fluctuation value (i.e., "O (amplitude)" in the title of the figure) as the vertical coordinate. As Figure 7 can be seen, the curve is a fluctuation signal that oscillates up and down around the zero baseline, and the amplitude shows a characteristic trend of first increasing and then decreasing over time, forming a typical spindle shape. This curve represents the pure arterial pulse signal successfully separated from the deflation curve data, which intuitively reflects the pressure oscillation caused by each heartbeat during the deflation of the cuff. The pulse wave oscillation curve is the direct data basis for generating the pulse wave envelope curve data in the subsequent step.

[0114] In order to extract the intensity change trend of the pulse oscillation, the generated pulse wave oscillation curve needs to be processed. This step is based on the pulse wave oscillation curve, and through a specific envelope extraction algorithm, the pulse wave envelope curve data used for blood pressure value calculation is generated. For example, one possible implementation is to first identify and connect all the peak points and trough points in the pulse wave oscillation curve respectively to form the upper envelope line and the lower envelope line, and then calculate the difference between the upper and lower envelope lines to obtain a pulse wave envelope curve data that can smoothly reflect the overall amplitude change of the pulse oscillation.

[0115] Referring to Figure 8 , based on the pulse wave oscillation curve, the pulse wave envelope curve data is generated, including the following steps 801 to 803.

[0116] Step 801: sequentially connecting all the peak values in the pulse wave oscillation curve to obtain the upper envelope line.

[0117] Step 802: Connect all the trough values in the pulse wave oscillation curve in sequence to obtain the lower envelope curve.

[0118] Step 803: Based on the difference between the upper envelope curve and the lower envelope curve, generate the pulse wave envelope curve data.

[0119] The steps 801 to 803 are described in detail below.

[0120] In some embodiments, in order to outline the upper limit of the intensity of the pulse wave oscillation. First, based on the previously generated pulse wave oscillation curve, all the local maximum points on the curve are identified and located by algorithm, that is, the peak values. Each peak value corresponds to the maximum positive amplitude reached by a single pulse oscillation. After identifying all the peak values, the system will use methods such as linear interpolation or spline interpolation to connect these peak value points in time sequence, thereby forming a continuous trajectory that can reflect the change of the upper limit of the oscillation intensity with time, which is defined as the upper envelope curve.

[0121] In a similar manner to the previous step, the purpose is to outline the lower limit of the intensity of the pulse wave oscillation. This step also acts on the pulse wave oscillation curve, but its goal is to identify and locate all the local minimum points on the curve, that is, the trough values. Each trough value corresponds to the maximum negative amplitude reached by a single pulse oscillation. After identifying all the trough values, the system will also connect these trough value points in time sequence to form a continuous trajectory that reflects the change of the lower limit of the oscillation intensity with time, which is defined as the lower envelope curve.

[0122] In order to obtain a single curve that represents the net amplitude of pulse oscillation, the upper envelope curve and the lower envelope curve generated in the previous two steps will be integrated. This is achieved by calculating the "difference" between the value of the upper envelope curve and the value of the lower envelope curve at each time point. Since the value of the lower envelope curve is usually negative or zero, this "difference" actually represents the peak-to-peak value amplitude of the pulse wave oscillation curve at this time. Combining all the calculated differences at all time points generates the final and unique pulse wave envelope curve data, which is a smooth, non-negative curve that fully reflects the overall trend of the pulse oscillation intensity.

[0123] Reference Figure 9 is a schematic diagram of pulse wave envelope curve data provided by an embodiment of the present application. As shown in Figure 9As shown in the middle, the pulse wave envelope curve data generated in the present application and used for blood pressure calculation is shown. The curve is obtained by envelope extraction (for example, calculating the difference between the upper and lower envelope lines, and using linear interpolation approximation) of the pulse wave oscillation curve of the previous step, which represents the overall trend of the pulse oscillation net amplitude. To further eliminate noise interference, the Savitzky-Golay filter, moving average and other smoothing algorithms can also be used to process the curve in the technical solution, so that the trend is clearer, as shown by the smooth curve shape in the figure. The horizontal coordinate is time, and the vertical coordinate is oscillation value. The fluctuation of the curve directly reflects the complete physiological process that the pulse wave intensity becomes weak, strong and weak again during the deflation of the cuff. This final pulse wave envelope curve data is the key difference between the present application and traditional methods. The subsequent steps will no longer be based on the proportion of the amplitude, but by analyzing the slope of each point on the curve to determine the systolic and diastolic pressures, thereby achieving more accurate blood pressure measurement.

[0124] Through the above steps 801 to 803, a robust and complete pulse amplitude information extraction scheme is formed. By constructing the upper envelope line and the lower envelope line respectively to define the complete dynamic range of oscillation, and then calculating the difference between the two to generate the final pulse wave envelope curve data, it is ensured that the quantification of pulse amplitude is based on the peak-to-peak value. This method can more accurately reflect the true oscillation intensity compared to the single envelope method which only considers the peak value, and has better anti-baseline drift and noise interference ability. Finally, a high-quality feature curve is obtained which can be directly used for subsequent slope analysis, providing a decisive guarantee for the high precision and high reliability of the entire blood pressure calculation method.

[0125] Through the above steps 601 to 603, a complete process of accurately extracting and quantifying core physiological features from mixed signals is achieved. By first calculating the fluctuation value to accurately separate the signal, then generating the pulse wave oscillation curve for visual presentation, and finally extracting its envelope to generate the pulse wave envelope curve data, the original complex pressure signal is systematically transformed into a smooth, clean and rich physiological information feature curve. This provides a high-quality, high signal-to-noise ratio analysis object for the subsequent slope-based blood pressure determination step, greatly eliminating noise and baseline interference, and is a key link to ensure the accuracy and reliability of the final blood pressure measurement result.

[0126] Referring to Figure 10 , based on the fluctuation value of each data point corresponding to the descending branch curve data and the fitting curve data, the pulse wave envelope curve data is generated, including the following steps 1001 to 1002.

[0127] Step 1001: Based on the descending branch curve data and the fitting curve data corresponding to each pressure curve data, an initial pulse wave envelope curve corresponding to each pressure curve data is generated.

[0128] Step 1002: Perform global filter smoothing on the plurality of initial pulse wave envelope curves to obtain pulse wave envelope curve data.

[0129] The steps 1001 to 1002 are described in detail below.

[0130] In general, the pressure sensor will measure multiple pressure curve data in a continuous time. Therefore, in order to improve the stability of the results, the aforementioned signal processing procedures are performed separately and completely for each independent pressure curve data. This means that for each measurement result, the system will independently complete the extraction of its descending branch curve data, perform polynomial fitting to obtain fitting curve data, and finally generate a corresponding envelope curve. The envelope curve generated from single measurement data is defined as the initial pulse wave envelope curve, so after completing this step, the system will obtain the same number of initial pulse wave envelope curves as the number of measurements.

[0131] After obtaining a plurality of initial pulse wave envelope curves, the information from different measurement periods will be fused to obtain a more representative single result. That is, global filter smoothing is performed on the plurality of initial pulse wave envelope curves. The global filter smoothing here is a data fusion technique, for example, the amplitude values of all initial pulse wave envelope curves at each corresponding time point can be weighted averaged or arithmetically averaged, thereby effectively integrating all information of multiple measurements. Finally, the processing will generate a unique, smooth, and average trend reflecting pulse wave envelope curve data.

[0132] Reference Figure 11 is a schematic diagram of the pulse wave envelope curve data after global filter smoothing provided by an embodiment of the present application. As shown in Figure 11 , the final pulse wave envelope curve data generated after fusing multiple measurement results is shown. The curve (i.e. the "oscillating waveform after global noise reduction" in the figure title) is a single result obtained by performing global filter smoothing on the plurality of initial pulse wave envelope curves. Compared with the envelope curve generated by single measurement, the shape of the curve in the figure is abnormally smooth, which directly indicates that the global filter smoothing can effectively filter out random noise and transient physiological fluctuations that may exist in each independent measurement. This highly smooth and stable curve more accurately reflects the overall and true pulse amplitude change trend of the user during the measurement period, and it will be used as the basis for final slope analysis to determine systolic and diastolic blood pressure. Its high signal-to-noise ratio and high stability provide the final guarantee for the accuracy and reliability of the entire algorithm.

[0133] Through the above steps 1001 and step 1002, by collecting multiple pressure curve data and generating initial pulse wave envelope curve respectively, and then performing global filtering and smoothing processing on these curves, the principle of "multiple measurements and averaging" in clinical practice is simulated at the algorithm level. This approach can effectively suppress random noise, transient physiological fluctuations or accidental errors caused by arrhythmia and other factors that may occur in a single measurement. The final single pulse wave envelope curve data, which integrates all the information from multiple measurements, can more accurately and stably reflect the user's true overall blood pressure level in that time period, thereby significantly enhancing the anti-interference ability and credibility of the blood pressure measurement results.

[0134] Step 103: Select target data points based on the slope of the pulse wave envelope curve data, and obtain blood pressure measurement data based on the pressure value data corresponding to the target data points in the pressure curve data.

[0135] Step 103 will be described in detail below.

[0136] In some embodiments, after generating the pulse wave envelope curve data, the present application adopts an innovative feature point selection strategy. Specifically, target data points will be selected based on the slope of the pulse wave envelope curve data. The slope here refers to the tangent slope of each point on the envelope curve, which represents the rate of change in pulse oscillation amplitude. Then by traversing the entire envelope curve, the specific point of the slope is identified as the target data point. After selection, based on the time information of the target data point, the corresponding pressure value data in the original pressure curve data is searched back and output as the final blood pressure measurement data, which corresponds to the systolic and diastolic blood pressure in physiological terms.

[0137] Referring to Figure 12 , based on the slope of the pulse wave envelope curve data, target data points are selected, and blood pressure measurement data is obtained based on the pressure value data corresponding to the target data points in the pressure curve data, including the following steps 1201 to step 1202.

[0138] Step 1201: Select the data point with the largest slope from the pulse wave envelope curve data as the first data point, and select the data point with the smallest slope from the pulse wave envelope curve data as the second data point.

[0139] Step 1202: The pressure value data corresponding to the first data point in the pressure curve data is taken as the systolic pressure data, and the pressure value data corresponding to the second data point in the pressure curve data is taken as the diastolic pressure data.

[0140] Steps 1201 to 1202 will be described in detail below.

[0141] In some embodiments, the present application adopts an innovative feature point recognition technique to replace the traditional fixed ratio method. In the present application, the final generated pulse wave envelope curve data is subjected to a differential operation to obtain the slope of each point on the curve. The slope here represents the rate of change of the pulse oscillation amplitude over time. Subsequently, the algorithm will traverse the entire curve, find and select the point where the slope reaches the maximum positive value, and define it as the first data point; at the same time, find and select the point where the slope reaches the maximum negative value (i.e. the minimum value), and define it as the second data point. These two data points correspond to the key moments of the fastest growth and decay of the pulse oscillation amplitude in physical terms.

[0142] After determining the positions of the first data point and the second data point on the time axis, the present application maps these time points back to the original pressure measurement values to complete the final blood pressure calculation. Specifically, the system will find the pressure value data corresponding to the same time point in the initial pressure curve data according to the time coordinate of the first data point, and take this pressure value as the final systolic pressure data. Similarly, the system will also find the corresponding pressure value data in the pressure curve data according to the time coordinate of the second data point, and take it as the final diastolic pressure data. At this point, a complete blood pressure measurement calculation is completed.

[0143] Through the above steps 1201 and 1202, by selecting the first data point and the second data point based on the slope of the pulse wave envelope curve data, the determination of the blood pressure value is directly related to the dynamic change rate of the pulse amplitude, which is more physically meaningful than the fixed ratio method that relies on universal statistical rules, and is closer to the principle of determining the "first sound" and "fading sound" by Korotkoff method. This method is more sensitive to the overall waveform trend and not sensitive to the absolute amplitude of individual abnormal pulse waves, so it has stronger anti-interference ability when processing data of complex conditions such as arrhythmia. Finally, the systolic pressure data and diastolic pressure data obtained by mapping these two dynamic feature points can more accurately and reliably reflect the real blood pressure condition of the user.

[0144] Reference Figure 13 is a performance simulation schematic diagram of a blood pressure data calculation method provided by an embodiment of the present application. As shown in Figure 13 is a performance simulation comparison diagram of the blood pressure data calculation method provided by the present application when processing measurement data of a user with arrhythmia (atrial premature beat). Figure 13The middle blue curve represents the dramatic fluctuation of the original pulse wave envelope of the arrhythmia user, reflecting the challenge of such data to traditional algorithms; while the smooth orange curve represents the pulse wave envelope curve data finally generated after global filtering and smoothing processing, clearly showing the strong ability of the algorithm provided by the present application to extract the core trend under strong interference. The text above the graph provides key performance comparison data: taking the reading (144 / 64) of the professional Fluke NIBP calibrator as the reference standard, the calculation result (141 / 61) of the algorithm of the present application is highly consistent with it, while the calculation results of other products (155 / 74 and 143 / 80) are significantly deviated from the standard value. Therefore, the graph powerfully proves from the two aspects of vision and data that the blood pressure data calculation method provided by the present application can effectively resist the interference of arrhythmia and other abnormal situations through global data modeling and filtering processing, and its calculation result has higher accuracy and reliability compared with existing products.

[0145] The embodiments of the present application also provide a blood pressure data calculation device, which can implement the blood pressure data calculation method described above, and refer to Figure 14 The device 1400 comprises:

[0146] The data acquisition module 1410 is configured to acquire pressure curve data measured by the pressure sensor in continuous time, and extract the pressure curve data to obtain the descending branch curve data.

[0147] The envelope generation module 1420 is configured to perform polynomial curve fitting on the descending branch curve data to generate fitting curve data, and generate pulse wave envelope curve data based on the fluctuation value of each data point corresponding to the descending branch curve data and the fitting curve data.

[0148] The blood pressure data determination module 1430 is configured to select a target data point based on the slope of the pulse wave envelope curve data, and obtain blood pressure measurement data based on the pressure value data corresponding to the target data point in the pressure curve data.

[0149] In some embodiments, the data acquisition module 1410 is further configured to:

[0150] determine the point with the maximum pressure value data in the pressure curve data as the critical pressure value;

[0151] select the curve data after the critical pressure value from the pressure curve data to obtain the descending branch curve data.

[0152] In some embodiments, the envelope generation module 1420 is further configured to:

[0153] determine the fitting polynomial function;

[0154] Based on the fitting polynomial function, the polynomial fitting is performed on the descending branch curve data to obtain fitting curve data.

[0155] In some embodiments, the envelope generation module 1420 is further configured to:

[0156] Based on the difference between each time point in the descending branch curve data and the corresponding data point in the fitting curve data, the fluctuation value is obtained.

[0157] Based on the fluctuation values corresponding to multiple consecutive time points, the pulse wave oscillation curve is generated.

[0158] Based on the pulse wave oscillation curve, the pulse wave envelope curve data is generated.

[0159] In some embodiments, the envelope generation module 1420 is further configured to:

[0160] The upper envelope line is obtained by sequentially connecting all the peak values in the pulse wave oscillation curve.

[0161] The lower envelope line is obtained by sequentially connecting all the trough values in the pulse wave oscillation curve.

[0162] Based on the difference between the upper envelope line and the lower envelope line, the pulse wave envelope curve data is generated.

[0163] In some embodiments, the envelope generation module 1420 is further configured to:

[0164] Based on the descending branch curve data and the fitting curve data corresponding to each pressure curve data, the initial pulse wave envelope curve corresponding to each pressure curve data is generated.

[0165] The global filtering and smoothing processing is performed on the multiple initial pulse wave envelope curves to obtain the pulse wave envelope curve data.

[0166] In some embodiments, the blood pressure data determination module 1430 is further configured to:

[0167] The data point with the largest slope in the pulse wave envelope curve data is selected as the first data point, and the data point with the smallest slope in the pulse wave envelope curve data is selected as the second data point.

[0168] The pressure value data corresponding to the first data point in the pressure curve data is taken as the systolic pressure data, and the pressure value data corresponding to the second data point in the pressure curve data is taken as the diastolic pressure data.

[0169] In the above embodiments, the description of each embodiment has its own focus, and the specific embodiments of the blood pressure data calculation device are basically the same as the specific embodiments of the above blood pressure data calculation method, which will not be repeated here.

[0170] The embodiment of the present application further provides an electronic device, comprising:

[0171] at least one memory;

[0172] at least one processor;

[0173] at least one program;

[0174] The program is stored in the memory, and the processor executes the at least one program to realize the blood pressure data calculation method provided in the embodiment of the present application. The electronic device can be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a vehicle-mounted computer, etc.

[0175] Please refer to Figure 15 , Figure 15 The hardware structure of the electronic device of another embodiment is illustrated, and the electronic device comprises:

[0176] The processor 1501 can be implemented in the form of a general CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, etc., and is used to execute related programs to realize the technical solutions provided in the embodiments of the present application.

[0177] The memory 1502 can be implemented in the form of a ROM (ReadOnly Memory), a static storage device, a dynamic storage device or a RAM (Random Access Memory), etc. The memory 1502 can store an operating system and other application programs, and when the technical solutions provided in the embodiments of the present application are implemented by software or firmware, the related program codes are saved in the memory 1502 and are called and executed by the processor 1501 to realize the blood pressure data calculation method in the embodiments of the present application.

[0178] The input / output interface 1503 is used to realize information input and output.

[0179] The communication interface 1504 is used to realize the communication interaction between the device and other devices, and can realize communication through a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.).

[0180] The bus 1505 transmits information between various components (for example, the processor 1501, the memory 1502, the input / output interface 1503 and the communication interface 1504) of the device.

[0181] The processor 1501, the memory 1502, the input / output interface 1503, and the communication interface 1504 are connected to each other through a bus 1505 to realize communication connection between devices inside.

[0182] The embodiment of the present application further provides a storage medium, which is a computer readable storage medium, and stores a computer program. The computer program is executed by a processor to realize the blood pressure data calculation method.

[0183] The memory is a non-transitory computer readable storage medium, and can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, for example, at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and the remote memory can be connected to the processor through a network. Examples of the network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0184] The embodiments described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0185] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than the figures, or combine certain steps, or different steps.

[0186] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, that is, can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0187] Those skilled in the art can understand that all or some steps in the above disclosed method, the functions of the modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0188] The terms "first", "second", "third", "fourth", and the like in the description of this application and in the claims hereof, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so termed herein is solely for the convenience of the reader and does not limit the scope of the application. It is also to be understood that the description and examples in this application are intended to cover all possible combinations where any of the several elements can represent one or more elements.

[0189] It should be understood that, in this application, "at least one" means one or more, "multiple" means two or more. "And / or" is used to describe the relationship between associated objects, which means that there can be three relationships, for example, "A and / or B" can mean: only A, only B, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c, can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0190] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the above-mentioned units is only a logical function division, and actual implementation can have another division mode, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. The coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0191] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment of the present application.

[0192] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0193] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in part, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions used to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various other media that can store programs.

[0194] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A blood pressure data calculation method, characterized by, The method comprises: obtaining pressure curve data measured by a pressure sensor in continuous time, and extracting the pressure curve data to obtain descending branch curve data; performing polynomial curve fitting on the descending branch curve data to generate fitting curve data, and generating pulse wave envelope curve data based on fluctuation values of each data point corresponding to the descending branch curve data and the fitting curve data; selecting a target data point based on a slope of the pulse wave envelope curve data, and obtaining blood pressure measurement data based on pressure value data corresponding to the target data point in the pressure curve data.

2. The blood pressure data calculation method according to claim 1, wherein, The extracting of the pressure curve data to obtain the descending branch curve data comprises: determining a point with the maximum pressure value data in the pressure curve data as a critical pressure value; selecting curve data after the critical pressure value from the pressure curve data to obtain the descending branch curve data.

3. The blood pressure data calculation method of claim 1, wherein, The polynomial curve fitting on the descending branch curve data to generate fitting curve data comprises: determining a fitting polynomial function; performing polynomial fitting on the descending branch curve data based on the fitting polynomial function to obtain the fitting curve data.

4. The blood pressure data calculation method of claim 1, wherein, The generating of pulse wave envelope curve data based on fluctuation values of each data point corresponding to the descending branch curve data and the fitting curve data comprises: obtaining the fluctuation values based on differences between each time point in the descending branch curve data and the corresponding data point in the fitting curve data; generating a pulse wave oscillation curve based on fluctuation values corresponding to multiple continuous time points; generating the pulse wave envelope curve data based on the pulse wave oscillation curve.

5. The blood pressure data calculation method according to claim 4, wherein, The generating of the pulse wave envelope curve data based on the pulse wave oscillation curve comprises: connecting all peak values in the pulse wave oscillation curve in sequence to obtain an upper envelope line; connecting all trough values in the pulse wave oscillation curve in sequence to obtain a lower envelope line; generating the pulse wave envelope curve data based on differences between the upper envelope line and the lower envelope line.

6. The blood pressure data calculation method of claim 1, wherein, The pressure curve data measured by the pressure sensor in continuous time is multiple, and the generating of pulse wave envelope curve data based on fluctuation values of each data point corresponding to the descending branch curve data and the fitting curve data comprises: generating initial pulse wave envelope curves corresponding to each of the pressure curve data based on the descending branch curve data and the fitting curve data corresponding to each of the pressure curve data; performing global filtering and smoothing processing on the multiple initial pulse wave envelope curves to obtain the pulse wave envelope curve data.

7. The blood pressure data calculation method of claim 1, wherein, The target data point comprises a first data point and a second data point, the blood pressure measurement data comprises systolic pressure data and diastolic pressure data, and the selecting of the target data point based on the slope of the pulse wave envelope curve data and the obtaining of the blood pressure measurement data based on pressure value data corresponding to the target data point in the pressure curve data comprise: selecting a data point with the maximum slope in the pulse wave envelope curve data as the first data point, and selecting a data point with the minimum slope in the pulse wave envelope curve data as the second data point; corresponding to the first data point in the pressure curve data as the systolic pressure data, and corresponding to the second data point in the pressure curve data as the diastolic pressure data.

8. A blood pressure data calculation apparatus characterized by comprising: The device comprises: a data acquisition module, configured to acquire pressure curve data measured by a pressure sensor in continuous time, and extract the pressure curve data to obtain a descending branch curve data; an envelope generation module, configured to perform polynomial curve fitting on the descending branch curve data to generate fitting curve data, and generate pulse wave envelope curve data based on fluctuation values of each data point corresponding to the descending branch curve data and the fitting curve data; a blood pressure data determination module, configured to select a target data point based on a slope of the pulse wave envelope curve data, and obtain blood pressure measurement data based on pressure value data corresponding to the target data point in the pressure curve data.

9. An electronic device, comprising: A device comprises a memory and a processor, and the memory stores a computer program, and the processor implements the blood pressure data calculation method in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the blood pressure data calculation method in any one of claims 1 to 7.

Images