A heart sound based blood pressure monitoring method and system

Abstract

The present application relates to the technical field of blood pressure, in particular to a blood pressure monitoring method and system based on heart sound, comprising: step 1: obtaining heart sound data in the calibration process; step 2: based on the heart sound data, abnormal heart sound data is obtained by analysis; wherein the abnormal heart sound data includes calibration abnormal value ZYJ; step 3: comparing the obtained calibration abnormal value ZYJ with the calibration abnormal threshold value, if the calibration abnormal value ZYJ is greater than or equal to the calibration abnormal threshold value, a calibration data unqualified signal is generated; based on the calibration data unqualified signal, the heart sound data is corrected; the present application analyzes the abnormal condition of the heart sound data, judges the stability and accuracy of the data, so that when the blood pressure is estimated by using the heart sound data, the accuracy of the blood pressure measurement of the user can be effectively ensured; by independently analyzing the external noise data and combining the analysis with the heart sound data, the reason affecting the heart sound data can be found out, and the influence degree of the external noise data can be judged.

Description

Technical Field

[0001] This invention relates to the field of blood pressure technology, and specifically to a blood pressure monitoring method and system based on heart sounds. Background Technology

[0002] Chinese patent CN114642409B discloses a method for sensing human pulse waves, a method for monitoring heart rate, and a device for monitoring blood pressure. The method for sensing human pulse waves includes: obtaining blood volume change information of the target human monitoring point based on the signal intensity of millimeter waves reflected from the target human monitoring point; calculating the second derivative of the blood volume change information with respect to time to obtain an acceleration signal characterizing the change in blood vessel volume at the target human monitoring point; and filtering the acceleration signal to obtain a fine-grained pulse wave signal from the target human body within the current monitoring time from which a diatonic pulse wave can be extracted.

[0003] In the prior art, there are related technologies for estimating blood pressure using heart sound data obtained through calibration. However, due to interference from external environment and other factors at the source of heart sound acquisition, the heart sound data will have large fluctuations and errors. Therefore, using heart sound data with large fluctuations to monitor blood pressure will result in inaccurate blood pressure readings obtained by the user. Summary of the Invention

[0004] The purpose of this invention is to provide a blood pressure monitoring method and system based on heart sounds, and to solve the following technical problem: due to interference from the external environment, the heart sound data will fluctuate greatly and have errors at the source of heart sound acquisition. Therefore, using heart sound data with large fluctuations to monitor blood pressure will result in inaccurate blood pressure readings obtained by the user.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] A blood pressure monitoring method based on heart sounds includes the following steps:

[0007] Step 1: Obtain heart sound data during the calibration process;

[0008] Step 2: Based on the heart sound data, analyze and obtain the calibration anomaly value ZYJ;

[0009] Step 3: Compare the obtained calibration anomaly value ZYJ with the calibration anomaly threshold. If the calibration anomaly value ZYJ is greater than or equal to the calibration anomaly threshold, a calibration data failure signal is generated.

[0010] Step 4: When a non-compliant calibration data signal is obtained, the interference effect ratio BYg is output based on the noise overlap degree DZc and the noise influence degree DZy.

[0011] If the interference effect ratio BYg is less than the interference effect ratio threshold, then a weak interference effect signal is generated.

[0012] Step 5: Based on the weak signal affected by interference, obtain the calibration avoidance coefficient and adjust the blood pressure detection process.

[0013] As a further aspect of the present invention: the method for obtaining the calibration anomaly value ZYJ is as follows:

[0014] Obtain the heart rate value within the calibration time and compare the heart rate value with the heart rate range value;

[0015] If the heart rate value is within the heart rate range, an abnormal heart rate signal is generated; the time data of the abnormal heart rate signal is obtained, including the average duration of the abnormality and the average time interval of the abnormality.

[0016] Based on the average duration of abnormality ZYc and the average time interval of abnormality ZYg, the calibration abnormality value ZYJ is output.

[0017] As a further aspect of the present invention: the method for obtaining the average duration of abnormal time ZYc is as follows:

[0018] Within the calibration time, the time of each occurrence of abnormal heart rate signal is obtained, the total time of occurrence of abnormal heart rate signal and the total number of occurrences of abnormal heart rate signal are obtained, and the average duration of abnormal heart rate signal ZYc is output based on the total time of occurrence of abnormal heart rate signal and the total number of occurrences of abnormal heart rate signal.

[0019] As a further aspect of the present invention: the average abnormal time interval ZYg is obtained as follows:

[0020] During the calibration period, the interval between adjacent abnormal heart rate signals is obtained, the total interval between adjacent abnormal heart rate signals and the total number of intervals between abnormal heart rate signals are obtained, and the average abnormal time interval ZYg is output based on the total interval between adjacent abnormal heart rate signals and the total number of intervals between abnormal heart rate signals.

[0021] As a further aspect of the present invention: in step 4, the noise impact degree DZy is obtained as follows:

[0022] The real-time ambient noise value is obtained within the calibration time; if the ambient noise value is greater than or equal to the ambient noise threshold, a noise impact signal is generated, and the ambient noise value containing the noise impact signal is marked as the impact noise value.

[0023] Obtain all the influence noise values ​​within the calibration time and get the total influence noise value. Based on the total influence noise value and the calibration time, output the mean influence noise value.

[0024] Then, based on the mean of the noise impact and the preset value of the noise impact, the noise impact degree DZy is output.

[0025] As a further aspect of the present invention: in step 4, the noise overlap ratio DZc is obtained as follows:

[0026] The time when the noise value appears within the calibration time is obtained, the noise impact time is marked, the noise impact time is compared with the time when the heart rate abnormal signal appears, and the overlap time length is obtained. Based on all the overlap time lengths, the total overlap time is obtained.

[0027] Based on the total overlap time and calibration time, the noise overlap degree DZc is output.

[0028] As a further aspect of the present invention, the overlap analysis process is as follows: when there is a time overlap between the time of the abnormal heart rate signal and the time of noise influence, the length of the overlap time is extracted.

[0029] As a further aspect of the present invention: in step 5, the process of obtaining the calibration avoidance coefficient is as follows:

[0030] When a weak interference signal is obtained, the proportion of interference is output based on the calibration anomaly value ZYJ and the interference influence ratio BYg.

[0031] The difference between the percentage of interference impact and the threshold for the percentage of interference impact is calculated to obtain the percentage difference of interference impact.

[0032] If the difference in the proportion of interference impact is less than the threshold for the proportion of interference impact, a calibration planning signal is generated.

[0033] When the calibration planning signal is obtained, the calibration avoidance coefficient XGJ is output based on the interval time TL and overlap time length TC between adjacent abnormal heart rate signals, and the interval time TZ between adjacent noise-affected signals.

[0034] As a further aspect of the present invention, the process of adjusting the blood pressure detection process is as follows:

[0035] If the calibration avoidance coefficient XGJ is greater than or equal to the calibration avoidance coefficient threshold, the interval between the adjacent abnormal heart rate signals is marked as the interval detection time.

[0036] Once the interval detection time is obtained, the blood pressure detection process is performed at intervals according to the marked interval detection time.

[0037] A blood pressure monitoring system based on heart sounds, the monitoring system comprising:

[0038] Acquisition module: Acquires heart sound data during the calibration process;

[0039] Analysis module: Based on heart sound data, analyzes to obtain abnormal heart sound data; among which, abnormal heart sound data includes calibration anomaly value ZYJ;

[0040] Calibration module: The obtained calibration anomaly value ZYJ is compared with the calibration anomaly threshold. If the calibration anomaly value ZYJ is greater than or equal to the calibration anomaly threshold, a calibration data failure signal is generated. The heart sound data is corrected based on the calibration data failure signal.

[0041] The beneficial effects of this invention are:

[0042] (1) This invention obtains the user's heart sound data during the calibration process; wherein, the heart sound data includes the heart rate value corresponding to the calibration time; based on the heart sound data, abnormal heart sound data is obtained; the obtained calibration abnormal value ZYJ is compared with the threshold to obtain the heart sound calibration signal; this invention performs abnormal analysis on the heart sound-related data during heart sound calibration, judges the stability and accuracy of the data, so that when using heart sound data to estimate blood pressure, it has good accuracy and can effectively ensure the accuracy of the user's blood pressure measurement;

[0043] (2) Based on the non-compliance signal of calibration data, this invention obtains the calibration environment influence value, performs interference analysis on the environment, and obtains the interference influence signal; by independently analyzing the external noise data and combining it with the heart sound data, this invention can find the cause of the heart sound data (whether it is caused by noise) and also determine the degree of influence of the external noise data.

[0044] (3) Based on the interference effect signal, the present invention obtains the calibration avoidance coefficient and adjusts the heart sound calibration process. The present invention obtains the calibration avoidance coefficient by analyzing the interval time and the length of the overlap time. The calibration avoidance coefficient can be used to adjust the next blood pressure detection cycle based on heart sound, so as to realize the interval detection of the user, thereby making the detected heart sound data more accurate and less affected by external interference, thus effectively improving the accuracy of blood pressure estimation based on the detected heart sound data. Attached Figure Description

[0045] The invention will now be further described with reference to the accompanying drawings.

[0046] Figure 1 This is a flowchart of a blood pressure monitoring method based on heart sounds provided in Embodiment 1 of the present invention;

[0047] Figure 2 This is a flowchart of the first alternative blood pressure monitoring method based on heart sounds provided in Embodiment 1 of the present invention;

[0048] Figure 3This is a flowchart of the second alternative blood pressure monitoring method based on heart sounds provided in Embodiment 1 of the present invention;

[0049] Figure 4 This is a schematic diagram of a blood pressure monitoring system based on heart sounds provided in Embodiment 2 of the present invention. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Example 1

[0052] Please see Figure 1 As shown, the present invention is a blood pressure monitoring method based on heart sounds, comprising the following steps:

[0053] Step 1: Obtain the user's heart sound data during the calibration process.

[0054] The heart sound data includes the heart rate value corresponding to the calibration time.

[0055] In some embodiments, a heart sound calibrator is used to calibrate the user's heart sound, and a calibration time is set, thereby obtaining the user's heart rate value within the calibration time.

[0056] Step 2: Based on the heart sound data, analyze and obtain abnormal heart sound data; among which, the abnormal heart sound data includes the calibration abnormal value ZYJ.

[0057] In this embodiment, the heart sound data can be matched with preset standard heart sound data for similarity. The reciprocal of the similarity is minus one and set as the calibration anomaly value ZYJ. The larger the similarity, the smaller ZYJ. When the similarity is 100%, ZYJ is 0.

[0058] In some embodiments, the user's heart rate value during the calibration period is obtained and compared with the heart rate range value;

[0059] If the heart rate value is within the heart rate range, an abnormal heart rate signal is generated; if the heart rate value is outside the heart rate range, a normal heart rate signal is generated.

[0060] The time data of abnormal heart rate signals is obtained, including the average duration of abnormality and the average time interval of abnormality.

[0061] The obtained mean duration of abnormal time and mean time interval of abnormality are labeled as ZYc and ZYg, respectively; using the formula The calibration anomaly value ZYJ is calculated; where a1 and a2 are both proportional coefficients. For example, a1 is 1.48 and a2 is 1.52.

[0062] For example, the average duration of abnormal time, ZYc, is obtained as follows:

[0063] During the calibration period, the time of each occurrence of abnormal heart rate signal is obtained, the total time of occurrence of abnormal heart rate signal and the total number of occurrences of abnormal heart rate signal are calculated, and the total time of abnormal heart rate signal is divided by the total number of occurrences of abnormal heart rate signal to obtain the average duration of abnormality ZYc.

[0064] For example, the mean of the abnormal time interval ZYg is obtained as follows:

[0065] During the calibration period, the interval between adjacent abnormal heart rate signals is obtained, and the total interval between adjacent abnormal heart rate signals and the total number of intervals between abnormal heart rate signals are counted. The average abnormal time interval ZYg is obtained by dividing the total interval between adjacent abnormal heart rate signals by the total number of intervals between abnormal heart rate signals.

[0066] It needs to be explained that the calculation formula for the calibration anomaly value ZYJ integrates the time data of abnormal heart rate signals to reflect the overall degree of calibration anomalies.

[0067] Step 3: Compare the obtained calibration anomaly value ZYJ with the calibration anomaly threshold. If the calibration anomaly value ZYJ is greater than or equal to the calibration anomaly threshold, a calibration data failure signal is generated. The heart sound data is then corrected based on the calibration data failure signal.

[0068] In some embodiments, the obtained calibration anomaly value ZYJ is compared with the calibration anomaly threshold;

[0069] If the calibration anomaly value ZYJ is greater than or equal to the calibration anomaly threshold, a calibration data failure signal is generated. The heart sound data is then corrected based on the calibration data failure signal. Specifically, the heart sound data corresponding to the calibration data failure signal is removed, and the user's blood pressure is measured and estimated based on the corrected heart sound data.

[0070] It should be noted that if the calibration anomaly value ZYJ is less than the calibration anomaly threshold, a calibration data pass signal is generated; when a calibration data pass signal is generated, the user's blood pressure is measured and estimated based on the heart sound data.

[0071] It should be noted that: a calibration data failure signal indicates that the calibrated data has significant abnormal fluctuations, and the abnormal stability of the calibration data source needs to be analyzed; a calibration data acceptance signal indicates that the calibrated data has minor abnormal fluctuations, meaning that blood pressure can be estimated using the calibrated heart sound data.

[0072] The technical solution of this invention is as follows: Heart sound data of the user during the calibration process is acquired; wherein, the heart sound data includes the heart rate value corresponding to the calibration time; based on the heart sound data, abnormal heart sound data is obtained; the obtained calibration abnormal value ZYJ is compared with a threshold to obtain a heart sound calibration signal; this invention performs abnormality analysis on heart sound-related data during heart sound calibration, judges the stability and accuracy of the data, so that when using heart sound data for blood pressure estimation, it has good accuracy and can effectively ensure the accuracy of user blood pressure measurement.

[0073] Example 2

[0074] Please see Figure 2 As shown, the present invention is a blood pressure monitoring method based on heart sounds, which further includes the following steps:

[0075] Step 4: When a calibration data failure signal is generated, the interference effect ratio BYg is output based on the noise overlap degree DZc and the noise influence degree DZy.

[0076] An interference effect signal is generated based on the interference effect ratio BYg and the interference effect ratio threshold; the validity of the heart sound data is determined based on the interference effect signal.

[0077] Among them, the interference signals include strong interference signals and weak interference signals;

[0078] In some embodiments, when a non-compliant calibration data signal is obtained, the ambient noise value within the calibration time is acquired, and the noise overlap and noise impact are analyzed and labeled as DZc and DZy, respectively.

[0079] The noise overlap ratio DZc and noise impact ratio DZy are obtained and substituted into the formula BYg=ln(b1×DZc+b2×DZy) to calculate the interference impact ratio BYg; where b1 and b2 are both proportionality coefficients, b1 is 0.62 and b2 is 0.38.

[0080] The obtained interference effect ratio BYg is compared with the interference effect ratio threshold.

[0081] If the interference ratio BYg is greater than or equal to the interference ratio threshold, a strong interference signal is generated. This strong interference signal indicates that the heart sound data is too affected by noise and cannot be used as a basis for estimating the user's blood pressure; its validity is invalid.

[0082] If the interference effect ratio BYg is less than the interference effect ratio threshold, a weak interference effect signal is generated. This weak interference effect signal indicates that the heart sound data is not significantly affected by noise and can still be used as a basis for estimating the user's blood pressure measurement. Its validity is valid.

[0083] For example, the noise impact factor DZy is obtained as follows:

[0084] The real-time ambient noise value within the calibration time is obtained, and the obtained ambient noise value is compared with the ambient noise threshold.

[0085] If the ambient noise value is greater than or equal to the ambient noise threshold, a noise impact signal is generated, and the ambient noise value containing the noise impact signal is marked as the impact noise value.

[0086] If the ambient noise level is less than the ambient noise threshold, the generated noise will not affect the signal.

[0087] Obtain all the impact noise values ​​within the calibration time, sum them up to get the total impact noise value, and divide the total impact noise value by the calibration time to get the average impact noise value.

[0088] The noise impact factor DZy is obtained by dividing the mean impact noise by the preset impact noise value. Note that the preset impact noise value is obtained by those skilled in the art based on historical data.

[0089] For example, the noise overlap ratio DZc is obtained as follows:

[0090] The time when the noise value appears within the calibration time is obtained, the noise impact time is marked, the noise impact time is compared with the time when the heart rate abnormal signal appears, and the overlap time length is obtained. All the overlap time lengths are added together to obtain the total overlap time.

[0091] For example, the overlap analysis process is as follows: there is a time overlap between the time of the abnormal heart rate signal and the time of noise influence, and the length of the overlap time is extracted;

[0092] Divide the total overlap time by the calibration time to obtain the noise overlap ratio DZc.

[0093] It should be noted that: a strong interference signal indicates that when calibrating a user's heart sound, noise in the external environment has a significant impact on the stability of the heart sound calibration data, which will affect the estimation of blood pressure based on the heart sound data; a weak interference signal indicates that when calibrating a user's heart sound, noise in the external environment has a smaller impact on the stability of the heart sound calibration data.

[0094] The technical solution of this invention is as follows: Based on the non-compliance signal of calibration data, the influence value of the calibration environment is obtained, and interference analysis is performed on the calibration environment to obtain the interference influence signal; This invention can find the cause of the influence on the heart sound calibration data (whether it is caused by noise) by independently analyzing the external noise data and combining it with the heart sound calibration data, and can also determine the degree of influence of the external noise data.

[0095] Example 3

[0096] Please see Figure 3 As shown, the present invention is a blood pressure monitoring method based on heart sounds, which, compared with Example 2, further includes the following steps:

[0097] Step 5: Based on the interference signal, obtain the calibration avoidance coefficient and adjust the blood pressure detection process.

[0098] In some embodiments, when a strong interference signal is received, if it is convenient to change the environment, the user's environment can be selected, or the blood pressure monitoring time can be rescheduled.

[0099] Furthermore, when a weak interference signal is obtained, the calibration anomaly value ZYJ and the interference impact ratio BYg are acquired. The calibration anomaly value ZYJ is divided by the interference impact ratio BYg to obtain the interference impact ratio.

[0100] The difference between the percentage of interference impact and the threshold for the percentage of interference impact is calculated to obtain the percentage difference of interference impact.

[0101] Compare the difference in the proportion of interference impact with the threshold for the difference in the proportion of interference impact.

[0102] If the difference in the proportion of interference is greater than or equal to the threshold of the proportion of interference, a calibration check signal is generated. When the calibration check signal is obtained, other reasons that affect the accuracy of heart sound data calibration during the heart sound calibration process are investigated, including checking the heart sound stethoscope.

[0103] If the difference in the proportion of interference impact is less than the threshold for the proportion of interference impact, a calibration planning signal is generated.

[0104] When the calibration planning signal is obtained, the interval time and overlap time length between adjacent abnormal heart rate signals, as well as the interval time between adjacent noise-affected signals, are acquired and labeled as TL, TC, and TZ, respectively. The calibration avoidance coefficient XGJ is calculated using the formula XGJ = c1*TL - c2*TC + c3*TZ. Here, c1, c2, and c3 are coefficients, with c1 set to 0.16, c2 to 0.48, and c3 to 0.36. The values ​​of c1, c2, and c3 represent the proportions of the influence of the interval time and overlap time length between adjacent abnormal heart rate signals, and the interval time between adjacent noise-affected signals, on the calibration avoidance coefficient XGJ, respectively. The interval time between adjacent abnormal heart rate signals is positively correlated with the interval time between adjacent noise-affected signals, while the overlap time length is negatively correlated with the interval time between adjacent noise-affected signals.

[0105] Extract the calibration avoidance coefficient XGJ between all adjacent abnormal heart rate signals, and compare the calibration avoidance coefficient XGJ with the calibration avoidance coefficient threshold.

[0106] If the calibration avoidance coefficient XGJ is greater than or equal to the calibration avoidance coefficient threshold, the interval between adjacent abnormal heart rate signals is marked as the interval detection time.

[0107] If the calibration avoidance coefficient XGJ is less than the calibration avoidance coefficient threshold, the interval between adjacent abnormal heart rate signals is marked as the non-interval detection time.

[0108] When the interval testing time is obtained, users can be scheduled to have their blood pressure tested again based on heart sound data. In the next testing cycle, users will be tested at intervals according to the marked interval testing time, so that the heart sound data obtained is more accurate and less affected by external interference, thereby effectively improving the accuracy of blood pressure estimation based on the adjusted heart sound data.

[0109] The technical solution of this invention is as follows: Based on the interference signal, a calibration avoidance coefficient is obtained, and the heart sound calibration process is adjusted. This invention obtains the calibration avoidance coefficient by analyzing the interval time and the length of the overlap time. The calibration avoidance coefficient can be used to avoid the next detection cycle, so as to realize the interval detection of the user, thereby making the detected heart sound data more accurate and less affected by external interference, thus effectively improving the accuracy of blood pressure estimation based on the heart sound data obtained after calibration.

[0110] Example 4

[0111] Please see Figure 4 As shown, the present invention is a blood pressure monitoring system based on heart sounds, comprising:

[0112] Acquisition module: Obtains the user's heart sound data during the calibration process;

[0113] Analysis module: Based on heart sound data, analyzes to obtain abnormal heart sound data; among which, abnormal heart sound data includes calibration anomaly value ZYJ;

[0114] Calibration module: Compares the obtained calibration anomaly value ZYJ with the threshold. If the calibration anomaly value ZYJ is greater than or equal to the calibration anomaly threshold, a calibration data failure signal is generated.

[0115] Interference judgment module: When a non-compliant calibration data signal is generated, the noise overlap degree DZc and noise influence degree DZy are obtained. The interference influence ratio BYg is calculated by using the formula BYg=ln(b1×DZc+b2×DZy).

[0116] If the interference effect ratio BYg is greater than or equal to the interference effect ratio threshold, a strong interference effect signal is generated.

[0117] If the interference effect ratio BYg is less than the interference effect ratio threshold, then a weak interference effect signal is generated.

[0118] Avoidance adjustment module: Based on weak interference signals, it obtains the calibration avoidance coefficient and adjusts the blood pressure detection process;

[0119] When a weak interference signal is obtained, the calibration anomaly value ZYJ and the interference impact ratio BYg are acquired. The calibration anomaly value ZYJ is divided by the interference impact ratio BYg to obtain the interference impact ratio.

[0120] The difference between the percentage of interference impact and the threshold for the percentage of interference impact is calculated to obtain the percentage difference of interference impact.

[0121] If the difference in the proportion of interference impact is less than the threshold for the proportion of interference impact, a calibration planning signal is generated.

[0122] When the calibration planning signal is obtained, the interval time TL and overlap time length TC between adjacent abnormal heart rate signals, as well as the interval time TZ between adjacent noise-affected signals are obtained; the calibration avoidance coefficient XGJ is calculated using the formula XGJ=c1*TL-c2*TC+c3*TZ; where c1, c2, and c3 are all coefficients.

[0123] If the calibration avoidance coefficient XGJ is greater than or equal to the calibration avoidance coefficient threshold, the interval between adjacent abnormal heart rate signals is marked as the interval detection time.

[0124] If the calibration avoidance coefficient XGJ is less than the calibration avoidance coefficient threshold, the interval between adjacent abnormal heart rate signals is marked as the non-interval detection time.

[0125] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0126] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A method for monitoring blood pressure based on heart sounds, characterized in that, Includes the following steps: Step 1: Obtain heart sound data during the calibration process; Step 2: Based on the heart sound data, analyze to obtain abnormal heart sound data; among which, abnormal heart sound data includes calibration abnormal value ZYJ; obtain the heart rate value within the calibration time and compare the heart rate value with the heart rate range value; if the heart rate value is within the heart rate range value, then generate a heart rate abnormality signal; Step 3: Compare the obtained calibration anomaly value ZYJ with the calibration anomaly threshold. If the calibration anomaly value ZYJ is greater than or equal to the calibration anomaly threshold, generate a calibration data failure signal; correct the heart sound data based on the calibration data failure signal. Step 4: When a calibration data failure signal is generated, the interference effect ratio BYg is output based on the noise overlap degree DZc and the noise influence degree DZy. An interference effect signal is generated based on the interference effect ratio BYg and the interference effect ratio threshold; the validity of the heart sound data is determined based on the interference effect signal. The system acquires the real-time ambient noise value within the calibration time; if the ambient noise value is greater than or equal to the ambient noise threshold, a noise impact signal is generated. The time when the noise value appears within the calibration time is obtained, the noise impact time is marked, and the noise impact time is compared with the time when each abnormal heart rate signal appears to obtain the overlap time length. Step 5: Based on the interference signal, obtain the calibration avoidance coefficient and adjust the blood pressure detection process accordingly; Interference signals include weak interference signals; in step 5, the process of obtaining the calibration avoidance coefficient is as follows: When a weak interference signal is obtained, the proportion of interference is output based on the calibration anomaly value ZYJ and the interference influence ratio BYg. The difference between the percentage of interference impact and the threshold for the percentage of interference impact is calculated to obtain the percentage difference of interference impact. If the difference in the proportion of interference impact is less than the threshold for the proportion of interference impact, a calibration planning signal is generated. When the calibration planning signal is obtained, the calibration avoidance coefficient XGJ is output based on the interval time TL and overlap time length TC between adjacent abnormal heart rate signals, and the interval time TZ between adjacent noise-affected signals. The process of adjusting the blood pressure monitoring procedure is as follows: If the calibration avoidance coefficient XGJ is greater than or equal to the calibration avoidance coefficient threshold, the interval between the adjacent abnormal heart rate signals is marked as the interval detection time. Once the interval detection time is obtained, the blood pressure detection process is performed at intervals according to the marked interval detection time.

2. The blood pressure monitoring method based on heart sounds according to claim 1, characterized in that, The calibration anomaly value ZYJ is obtained as follows: The time data of abnormal heart rate signals were acquired, including the average duration of abnormality ZYc and the average time interval of abnormality ZYg. Based on the average duration of the abnormality ZYc and the average time interval of the abnormality ZYg, the calibration abnormality value ZYJ is output.

3. The blood pressure monitoring method based on heart sounds according to claim 2, characterized in that, The method for obtaining the average duration of abnormal periods, ZYc, is as follows: Within the calibration time, the time of each occurrence of abnormal heart rate signal is obtained, the total time of occurrence of abnormal heart rate signal and the total number of occurrences of abnormal heart rate signal are obtained, and the average duration of abnormal heart rate signal ZYc is output based on the total time of occurrence of abnormal heart rate signal and the total number of occurrences of abnormal heart rate signal.

4. The blood pressure monitoring method based on heart sounds according to claim 2, characterized in that, The mean of the abnormal time interval ZYg is obtained as follows: During the calibration period, the interval between adjacent abnormal heart rate signals is obtained, the total interval between adjacent abnormal heart rate signals and the total number of intervals between abnormal heart rate signals are obtained, and the average abnormal time interval ZYg is output based on the total interval between adjacent abnormal heart rate signals and the total number of intervals between abnormal heart rate signals.

5. The blood pressure monitoring method based on heart sounds according to claim 1, characterized in that, In step 4, the noise impact factor DZy is obtained as follows: The environmental noise value that contains noise affecting the signal is marked as the affecting noise value; Obtain all the influence noise values ​​within the calibration time and get the total influence noise value. Based on the total influence noise value and the calibration time, output the mean influence noise value. Then, based on the mean noise level and the preset noise level, the noise impact degree DZy is output. In step 4, the noise overlap ratio DZc is obtained as follows: Based on the lengths of all overlapping times, the total overlap time is obtained; Based on the total overlap time and calibration time, the noise overlap degree DZc is output.

6. A blood pressure monitoring system based on heart sounds, characterized in that, The monitoring system is used to perform the method according to any one of claims 1-5, and the monitoring system includes: Acquisition module: Acquires heart sound data during the calibration process; Analysis module: Based on heart sound data, analyzes and obtains abnormal heart sound data; among which, abnormal heart sound data includes calibration anomaly value ZYJ; Calibration module: The obtained calibration anomaly value ZYJ is compared with the calibration anomaly threshold. If the calibration anomaly value ZYJ is greater than or equal to the calibration anomaly threshold, a calibration data failure signal is generated. The heart sound data is corrected based on the calibration data failure signal.

Images