Heart sound segmentation methods, devices, electronic equipment and readable storage media

Abstract

This application discloses a method, apparatus, electronic device, and readable storage medium for heart sound segmentation. This application relates to the field of medical signal processing technology. The heart sound segmentation method includes: synchronously acquiring physiological signals, wherein the physiological signals include heart sound signals; obtaining a segmentation threshold corresponding to the heart sound signals; segmenting the heart sound signals based on the segmentation threshold to obtain a first heart sound and a second heart sound; and determining the systolic duration and diastolic duration of the heart sound signals based on the first and second heart sounds. This application reduces the resource consumption for heart sound signal segmentation.

Description

Technical Field

[0001] This application relates to the field of medical signal processing technology, and in particular to a method, apparatus, electronic device and readable storage medium for heart sound segmentation. Background Technology

[0002] A key component of computer-aided heart sound analysis is the segmentation of heart sound signals, specifically distinguishing the precise locations of the first heart sound (S1), systolic, second heart sound (S2), and diastolic phase within each cardiac cycle. In each cardiac cycle, the first heart sound (S1) is caused by vibrations generated during ventricular contraction due to the closure of the mitral and tricuspid valves, the opening of the aortic and pulmonary valves, and ventricular systole. The second heart sound (S2) is primarily formed by vibrations caused by the closure of the aortic and pulmonary valves and the reduced blood flow in the aorta and pulmonary arteries. Systole is the interval between S1 and S2, and diastole begins from S2 and extends to the start of the next cardiac cycle at S1. The accuracy of heart sound signal segmentation directly impacts the effectiveness of subsequent heart sound signal analysis.

[0003] In related technologies, network models are commonly used for heart sound segmentation. The segmentation algorithm based on the Logistic Regression Hidden Semi-Markov Model (LR-HSMM) is one of the commonly used heart sound segmentation methods. However, model-based heart sound segmentation requires complex model calculations, resulting in high computational complexity and high consumption of hardware and other resources. Therefore, there is an urgent need for a heart sound segmentation method with low resource consumption for heart sound signals.

[0004] The above background information is provided only to assist in understanding the inventive concept and technical solution of this application. It does not necessarily belong to the prior art of this patent application, nor does it necessarily provide technical teaching. It is intended to provide general background information and does not necessarily constitute prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, electronic device, and readable storage medium for heart sound segmentation, aiming to solve the technical problem of reducing the resource consumption of heart sound signal segmentation on a server.

[0006] To achieve the above objectives, this application provides a heart sound segmentation method, the heart sound segmentation method comprising:

[0007] Synchronous acquisition of physiological signals, including heart sound signals;

[0008] Obtain the segmentation threshold corresponding to the heart sound signal, and segment the heart sound signal based on the segmentation threshold to obtain the first heart sound and the second heart sound;

[0009] The duration of the systolic phase and the duration of the diastolic phase of the heart sound signal are determined based on the first and second heart sounds.

[0010] Optionally, the physiological signal further includes an electrocardiogram signal and a pulse signal, and before the step of obtaining the segmentation threshold corresponding to the heart sound signal, the method further includes:

[0011] Determine the peak value of the QRS wave in the electrocardiogram signal, and take the time corresponding to the peak value of the QRS wave as the first time.

[0012] Determine the trough point of the pulse signal, and use the time corresponding to the trough point as the second time;

[0013] Determine the first and second zero-crossing points of the pulse signal, take the time corresponding to the first zero-crossing point as the third time, and take the time corresponding to the second zero-crossing point as the fourth time;

[0014] A first threshold for the heart sound signals corresponding to the first time and the second time is determined, and a second threshold for the heart sound signals corresponding to the third time and the fourth time is determined;

[0015] Use the first threshold and the second threshold as the segmentation threshold.

[0016] Optionally, the step of determining the first threshold corresponding to the first time and the second time includes:

[0017] Obtain or determine the heart sound envelope signal corresponding to the heart sound signal;

[0018] The peak value of the heart sound envelope signal between the first time and the second time is taken as the first heart sound peak value;

[0019] The first heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a first threshold value, wherein the first threshold value is less than the first heart sound peak value.

[0020] Optionally, the step of determining the second threshold corresponding to the third time and the fourth time includes:

[0021] Obtain or determine the heart sound envelope signal corresponding to the heart sound signal;

[0022] The peak value of the heart sound envelope signal between the third time and the fourth time is taken as the second heart sound peak value;

[0023] The second heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a second threshold value, wherein the second threshold value is less than the second heart sound peak value.

[0024] Optionally, the segmentation threshold includes a first threshold and a second threshold, and the step of segmenting the heart sound signal based on the segmentation threshold includes:

[0025] Obtain or determine the heart sound envelope signal corresponding to the heart sound signal;

[0026] The duration of the heart sound envelope signal value being greater than the first threshold is taken as the first duration window;

[0027] The duration of the heart sound envelope signal value being greater than the second threshold is taken as the second duration window;

[0028] The heart sound signal within the first duration window is taken as the first heart sound, and the heart sound signal within the second duration window is taken as the second heart sound.

[0029] Optionally, the step of determining the systolic duration and diastolic duration of the heart sound signal based on the first and second heart sounds includes:

[0030] Determine the cardiac cycles included in the heart sound signals, and sequentially traverse each of the cardiac cycles;

[0031] The end time of the first heart sound within the traversed cardiac cycle is taken as the first end time. The next cardiac cycle corresponding to the traversed cardiac cycle is determined, and the start time of the first heart sound within the next cardiac cycle is taken as the first start time.

[0032] The start time of the second heart sound within the traversed cardiac cycle is taken as the second start time, and the end time of the second heart sound within the traversed cardiac cycle is taken as the second end time.

[0033] The time difference between the first end time and the second start time is taken as the duration of the contraction period;

[0034] The time difference between the first start time and the second end time is taken as the duration of diastole;

[0035] Until the end of each cardiac cycle, the average systolic duration of all said systolic durations is determined, and the average diastolic duration of all said diastolic durations is determined;

[0036] The average systolic duration is taken as the systolic duration of the heart sound signal, and the average diastolic duration is taken as the diastolic duration of the heart sound signal.

[0037] Furthermore, to achieve the above objectives, this application also provides a heart sound segmentation device, the heart sound segmentation device comprising:

[0038] A signal acquisition module is used to synchronously acquire physiological signals, including heart sound signals.

[0039] The segmentation module is used to obtain the segmentation threshold corresponding to the heart sound signal, and to segment the heart sound signal based on the segmentation threshold to obtain a first heart sound and a second heart sound.

[0040] The determination module is used to determine the duration of systole and diastole based on the first heart sound and the second heart sound.

[0041] This application also provides an electronic device, which is a physical device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the heart sound segmentation method as described above.

[0042] This application also provides a readable storage medium, which is a computer-readable storage medium, on which a program implementing the heart sound segmentation method is stored. The program implementing the heart sound segmentation method is executed by a processor to implement the steps of the heart sound segmentation method as described above.

[0043] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the heart sound segmentation method described above.

[0044] This application synchronously acquires physiological signals, including heart sound signals; obtains a segmentation threshold corresponding to the heart sound signals; segments the heart sound signals based on the segmentation threshold to obtain a first heart sound and a second heart sound; and determines the duration of systole and diastole based on the first and second heart sounds. Thus, compared with existing model-based heart sound segmentation methods, this application's embodiment segments the heart sound signals based on a segmentation threshold to obtain a first and second heart sound, and calculates the diastolic and systolic phases based on the first and second heart sounds, completing the complete heart sound segmentation. This requires only simple value comparison operations to complete the segmentation, eliminating the need for complex model calculations, thus reducing computational complexity and resource consumption for heart sound signal segmentation. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a flowchart illustrating the first embodiment of the heart sound segmentation method of this application;

[0048] Figure 2 This is a schematic diagram of the overall architecture of the wearable device system in this application;

[0049] Figure 3 This is a schematic diagram of the wearable device structure of this application;

[0050] Figure 4 This is a schematic diagram of the physiological signals of the heart sound segmentation method in this application;

[0051] Figure 5 This is a schematic diagram of the prediction process for the heart sound segmentation method of this application;

[0052] Figure 6 This is another prediction flowchart of the heart sound segmentation method in this application;

[0053] Figure 7 This is a schematic diagram of the device modules of the heart sound segmentation device of this application;

[0054] Figure 8 This is a schematic diagram of the hardware operating environment of the heart sound segmentation device in the embodiments of this application.

[0055] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0056] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, 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.

[0057] Example 1

[0058] This application presents a heart sound segmentation method according to a first embodiment. Please refer to [link / reference]. Figure 1 The heart sound segmentation method includes:

[0059] Step S10: Synchronously acquire physiological signals, wherein the physiological signals include heart sound signals;

[0060] This physiological signal includes, but is not limited to, heart sound signals. It may also include electrocardiogram (ECG) signals and pulse signals, which are used to assist in heart sound segmentation, improving segmentation accuracy. This physiological signal can be collected by relevant devices. For example, if a user uses a wearable device, the user's physiological signals can be collected based on the wearable device. Specifically, this wearable device can be a smartwatch, smart bracelet, etc.

[0061] Furthermore, physiological signals are simultaneously acquired at the same time to determine the relationship between electrocardiogram (ECG), pulse, and heart sound signals and time, ensuring strict synchronization of physiological signals. The system can also record the data from the start of acquisition using calibrated real-time data.

[0062] Step S20: Obtain the segmentation threshold corresponding to the heart sound signal, and segment the heart sound signal based on the segmentation threshold to obtain the first heart sound and the second heart sound;

[0063] Heart sound segmentation specifically involves distinguishing the precise locations of the first heart sound (S1), systolic, second heart sound (S2), and diastolic phase within each cardiac cycle. The first heart sound (S1) is caused by vibrations generated during ventricular contraction due to the closure of the mitral and tricuspid valves, the opening of the aortic and pulmonary valves, and ventricular systole. The second heart sound (S2) is primarily formed by the closure of the aortic and pulmonary valves, along with vibrations caused by reduced blood flow in the aorta and pulmonary arteries. Systole is the interval between S1 and S2, and diastole begins from S2 and extends to the start of the next cardiac cycle (S1). The accuracy of heart sound signal segmentation directly affects the analysis of subsequent heart sound signals. Therefore, the duration of systole is the duration between S1 and S2, and the duration of diastole is the duration from S2 to the start of the next cardiac cycle (S1).

[0064] In one feasible implementation, the segmentation threshold includes a first threshold and a second threshold, and the step of segmenting the heart sound signal based on the segmentation threshold includes:

[0065] Step S201: Obtain or determine the heart sound envelope signal corresponding to the heart sound signal;

[0066] Specifically, the upper envelope of the heart sound signal can be determined, and the upper envelope can be filtered to obtain the heart sound envelope signal corresponding to the heart sound signal.

[0067] Step S202: The duration window during which the signal value of the heart sound envelope signal is greater than the first threshold is taken as the first duration window;

[0068] Step S203: The duration window during which the signal value of the heart sound envelope signal is greater than the second threshold is taken as the second duration window;

[0069] Step S204: The heart sound signal within the first duration window is taken as the first heart sound, and the heart sound signal within the second duration window is taken as the second heart sound.

[0070] It should be noted that the filtering of heart sound signals can specifically be baseline removal and moving average filtering to reduce interference signals.

[0071] Understandably, for each cardiac cycle, there is a corresponding first duration window and a second duration window. The first heart sound within the first duration window is denoted as S1(t), where t is the t-th cardiac cycle. The second heart sound within the second duration window is denoted as S2(t). (Refer to...) Figure 4 As shown, the physiological signals include electrocardiogram (ECG) signals, phonocardiogram (PCG) signals, and pulse signals. For example, the phonocardiogram signal is segmented, and within each cardiac cycle, a first heart sound (S1) and a second heart sound (S2) are obtained.

[0072] Step S30: Determine the duration of the systolic phase and the duration of the diastolic phase of the heart sound signal based on the first heart sound and the second heart sound.

[0073] Let the first heart sound be S1 and the second heart sound be S2. The systolic phase is the interval between S1 and S2, and the diastolic phase is from S2 to the start of the next cardiac cycle S1. In other words, the duration of the systolic phase is the interval between S1 and S2, and the duration of the diastolic phase is the duration from S2 to the start of the next cardiac cycle S1.

[0074] In one feasible implementation, the step of determining the systolic duration and diastolic duration of the heart sound signal based on the first heart sound and the second heart sound includes:

[0075] Step S301: Determine the cardiac cycle included in the heart sound signal, and sequentially traverse each cardiac cycle;

[0076] Step S302: Take the end time of the first heart sound within the traversed cardiac cycle as the first end time, determine the next cardiac cycle corresponding to the traversed cardiac cycle, and take the start time of the first heart sound within the next cardiac cycle as the first start time.

[0077] Step S303: Take the start time of the second heart sound within the traversed cardiac cycle as the second start time, and take the end time of the second heart sound within the traversed cardiac cycle as the second end time.

[0078] Step S304: The time difference between the first end time and the second start time is taken as the duration of the contraction period;

[0079] Step S305: The time difference between the first start time and the second end time is taken as the duration of the diastolic phase;

[0080] Step S306: Until the end of each cardiac cycle traversal, determine the average systolic duration of all said systolic durations and the average diastolic duration of all said diastolic durations.

[0081] Step S307: The average systolic duration is taken as the systolic duration of the heart sound signal, and the average diastolic duration is taken as the diastolic duration of the heart sound signal.

[0082] Let S1(t) be the first heart sound of the t-th cardiac cycle, and S2(t) be the second heart sound of the t-th cardiac cycle. Let S1(t) be the start time of S1(t). start The end time of S1(t) is denoted as S1(t). end The starting time of S2(t) is denoted as S2(t). start The end time of S2(t) is denoted as S2(t). end (t), then the duration of the systolic phase corresponding to the t-th cardiac cycle is S1. end (t) and S2 start The time difference between (t) and the duration of diastole is S1. start (t+1) and S2 end Based on the time difference between (t), if the heart sound signal includes heart sound signals of multiple cardiac cycles, then for each cardiac cycle there is a systolic duration and a diastolic duration. The average duration of the systolic duration corresponding to all cardiac cycles can be used as the final systolic duration. Similarly, the average duration of the diastolic duration corresponding to all cardiac cycles can be used as the final diastolic duration.

[0083] Example 2

[0084] Based on the first embodiment of this application, in another embodiment of this application, the same or similar content as in Embodiment 1 can be referred to the above description and will not be repeated hereafter. Furthermore, in a feasible implementation, the physiological signal further includes an electrocardiogram signal and a pulse signal. Before the step of obtaining the segmentation threshold corresponding to the heart sound signal, the method further includes:

[0085] Step A10: Determine the peak value of the QRS wave in the electrocardiogram signal, and take the time corresponding to the peak value of the QRS wave as the first time.

[0086] Step A20: Determine the trough point of the pulse signal and use the time corresponding to the trough point as the second time.

[0087] Step A30: Determine the first and second zero-crossing points of the pulse signal, take the time corresponding to the first zero-crossing point as the third time, and take the time corresponding to the second zero-crossing point as the fourth time;

[0088] Step A40: Determine a first threshold corresponding to the first time and the second time, and determine a second threshold corresponding to the third time and the fourth time;

[0089] Step A50: Use the first threshold and the second threshold as the segmentation threshold.

[0090] Understandably, for each cardiac cycle, the ECG and pulse signals are used to determine the first time corresponding to the peak value of the QRS wave in the ECG signal, the second time corresponding to the trough value of the pulse signal, and the third and fourth times of the first and second zero-crossing points of the pulse signal. Then, the first and second thresholds for that cardiac cycle are determined. Using these thresholds, the heart sound signals of that cardiac cycle are segmented to obtain the second systolic duration and the second diastolic duration. This process improves the accuracy of heart sound segmentation by segmenting the heart sound signals based on each cardiac cycle.

[0091] In one feasible implementation, the step of determining the first threshold corresponding to the first time and the second time includes:

[0092] Step B10: Obtain or determine the heart sound envelope signal corresponding to the heart sound signal;

[0093] Step B20: The peak value of the heart sound envelope signal between the first time and the second time is taken as the first heart sound peak value;

[0094] Step B30: Adjust the first heart sound peak value based on a preset adjustment coefficient to obtain a first threshold value, wherein the first threshold value is less than the first heart sound peak value.

[0095] The preset adjustment coefficient can be any pre-set coefficient, such as 0.1, 0.15, 0.2, etc. The first heart sound peak value is adjusted based on the preset adjustment coefficient. Specifically, the first threshold value can be obtained by multiplying the preset adjustment coefficient by the first heart sound peak value.

[0096] In this embodiment, a first threshold is determined based on the peak value of the first heart sound between the first time and the second time. This first threshold is related to the peak value of the first heart sound, and different peak values ​​correspond to different thresholds. This enables intelligent adjustment of the threshold, rather than using a fixed threshold for heart sound segmentation, thereby improving the segmentation accuracy of heart sound segmentation.

[0097] In one possible implementation, the step of determining the second threshold corresponding to the third time and the fourth time includes:

[0098] Step C10: Obtain or determine the heart sound envelope signal corresponding to the heart sound signal;

[0099] Step C20: The peak value of the heart sound envelope signal between the third time and the fourth time is taken as the second heart sound peak value;

[0100] Step C30: Adjust the second heart sound peak value based on a preset adjustment coefficient to obtain a second threshold value, wherein the second threshold value is less than the second heart sound peak value.

[0101] The preset adjustment coefficient can be the same as or different from the aforementioned adjustment coefficient. The second heart sound peak value is adjusted based on the preset adjustment coefficient, or the preset adjustment coefficient can be multiplied by the second heart sound peak value to obtain a second threshold. This second threshold is related to the second peak value; different peak values ​​correspond to different thresholds, thereby enabling intelligent adjustment of the threshold, rather than using a fixed threshold for heart sound segmentation, thus improving the segmentation accuracy of heart sound segmentation.

[0102] To aid in understanding the technical concept or principle of this application, a specific embodiment is provided:

[0103] In this specific embodiment, the heart sound segmentation process is as follows:

[0104] S1, identify the peak point of the QRS wave in the electrocardiogram signal and obtain the peak point position sequence R(t);

[0105] S2, identify the trough point and two zero-crossing points of the pulse signal, and obtain the trough point position sequence V(t), the first zero-crossing point position sequence Cross_zero1(t), and the second zero-crossing point position sequence Cross_zero2(t);

[0106] S3, calculate the upper envelope of the heart sound signal, and perform baseline removal and moving average filtering on the upper envelope.

[0107] Eliminate baseline drift and noise interference;

[0108] S4, calculate the peak value of the heart sound envelope signal between the R(t) and V(t) sequences, setting the threshold to 10% of the peak value, and then select the envelope start point sequence S1 that exceeds the threshold.start (t) and the ending point sequence S1 end The time difference (t) is used as the duration sequence S1(t);

[0109] S5, calculate the peak value of the heart sound envelope signal between the Cross_zero1(t) and Cross_zero2(t) sequences, with a threshold value of 10% of the peak value. Sequence S2 containing envelope starting points exceeding the threshold is then used. start (t) and the ending point sequence S2 end The time difference (t) is used as the duration sequence S2(t);

[0110] S6, using S1 end (t) and S2 start The duration sequence of the contraction period, Sys(t), is obtained by calculating the time difference (t). Then, using S1... star t(t+1) and S2 end Dia(t) is the duration sequence of diastolic phase.

[0111] It should be noted that the above specific embodiments are only used to understand this application and do not constitute a limitation on the heart sound segmentation process of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0112] Example 3

[0113] Blood pressure is an important physiological parameter reflecting human health. With the accelerating aging of the population and changes in modern lifestyles, the incidence of hypertension is constantly rising. Hypertension is one of the major risk factors for cardiovascular disease, which is the leading cause of death worldwide. Therefore, monitoring blood pressure with a precise and convenient device can greatly help in the prevention of hypertension.

[0114] Traditional blood pressure measurement methods mostly rely on oscillometric cuff-type electronic blood pressure monitors. However, this method causes significant discomfort to users during the inflation and deflation of the cuff, and the devices are bulky and not portable. In recent years, the emergence of cuffless blood pressure monitors has solved the discomfort of cuffs and greatly reduced their size. With the increasing number of wearable device users, the demand for wearable devices to measure blood pressure has also grown, especially with some cuffless monitors integrated into smartwatches, increasing user appeal and real-time measurement capabilities. However, the accuracy of cuffless blood pressure monitors still needs improvement.

[0115] Cuffless blood pressure measurement devices primarily estimate blood pressure through pulse transit time. Pulse transit time (PWTT) is defined as the time required for blood ejected from the proximal end of the heart to reach the distal end at the same moment. A common method to obtain PWTT is to simultaneously acquire electrocardiogram (ECG) signals and pulse wave signals, using the R-wave peak of the ECG signal as the starting point and the characteristic point of the pulse wave as the ending point; this time difference is the pulse transit time.

[0116] However, the R-wave peak is not actually the time when the heart begins to contract. There is a preparation period before the heart begins to contract, called the preejection period (PEP). Due to the existence of the preejection period, blood pressure estimates based on pulse transit time are unreliable.

[0117] Based on the above problems, and the first and second embodiments of this application, in another embodiment of this application, the content that is the same as or similar to the first, second, or third embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, in a feasible implementation, after the step of determining the duration of the systolic phase and the duration of the diastolic phase of the heart sound signal based on the first and second heart sounds, the method further includes:

[0118] Step D10: Extract features from the physiological signal to obtain signal features, wherein the signal features include the duration of the pre-ejaculation phase and the pulse transit time;

[0119] In this embodiment, the heart sound segmentation method is applied to wearable devices, such as smartwatches, smart bracelets, etc.

[0120] For example, see Figure 2-3 As shown, the wearable device includes a housing 1 and sensors disposed on the housing for synchronously acquiring physiological signals. The sensors include a first sensor for acquiring heart sound signals, a second sensor for acquiring pulse signals, and a third sensor for acquiring electrocardiogram (ECG) signals. The first sensor may be a VPU (VoicePick Up, bone conduction) sensor 250, the second sensor may be a photoelectric pulse sensor 240, and the third sensor may be an electrode sensor. Specifically, the electrode sensor may include three electrodes: a first electrode 210 and a third electrode 230 form a circuit for ECG signal acquisition; a second electrode 220 provides a reference point to eliminate the potential difference between the body and the wearable device, improving the signal-to-noise ratio of the ECG signal acquisition.

[0121] Furthermore, referring to Figure 2-3As shown, the wearable device may further include a device switch 110 for turning the wearable device on and off; a device processor 120 for executing program code in the memory to perform various functions of the wearable device; a time calibration module 130 for displaying real-time time and data synchronization and acquisition calibration; an interaction module 140 for collecting the user's personalized information, responding to signals generated by the user's blood pressure measurement operation, and providing simple blood pressure measurement usage instructions, including a blood pressure measurement activation signal and usage prompts including the blood pressure measurement signal acquisition location and the user's acquisition posture; a physiological signal acquisition module 150 for collecting physiological signals related to blood pressure measurement and accelerometer signals. The physiological signals related to blood pressure measurement include electrocardiogram signals, pulse signals, and heart sound signals. A data processing module 160 is used to process the physiological signal segments collected by the physiological signal measurement module in real time, and the data processing steps mainly include signal noise reduction, signal quality assessment, and feature extraction. A wireless communication module 180 is used to transmit the collected physiological signal data, the actual user blood pressure value, and the user's personalized information to a server or terminal via a wireless module for the construction of a blood pressure measurement database. The blood pressure measurement module 170 is used to analyze the user's physiological signal data and / or personalized information, ultimately predict blood pressure, return the blood pressure prediction result, and determine the current blood pressure level.

[0122] In addition, refer to Figure 3 As shown, the physiological signal acquisition module also includes a 6-axis signal acquisition module. Accelerometer and gyroscope signals are mainly acquired through the 6-axis signal acquisition module, which is primarily composed of a 6-axis sensor 260 integrated within the device. Before blood pressure measurement, the 6-axis signal acquisition module can calculate the current Euler angles to assist the user in positioning the acquisition location and posture. During blood pressure measurement, the 6-axis signal acquisition module can monitor the user's arm movement and combine it with ECG, heart sound, and pulse signals to perform physiological signal denoising, thereby improving the signal-to-noise ratio of these signals during acquisition.

[0123] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on wearable devices. They may have more or fewer of the aforementioned components, or combine some components, or separate some components, or have different component arrangements. The various components described above can be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing or application-specific integrated circuits.

[0124] The target of this detection can be the user of the wearable device. Furthermore, physiological signals are simultaneously and synchronously acquired at the same time to determine the relationship between electrocardiogram (ECG), pulse, and heart sound signals and time, ensuring strict synchronicity of the physiological signals. The system can also record the data from the moment acquisition begins using calibrated real-time data.

[0125] Furthermore, to improve the accuracy of the extracted signal features before extracting the signal features of the physiological signal, signal processing can be performed on the physiological signal, such as filtering, noise reduction, and segmentation. Based on the processed physiological signal, feature extraction is then performed to obtain the signal features.

[0126] In one feasible implementation, the step of feature extraction of the physiological signal includes:

[0127] Step D101: Perform signal preprocessing on the physiological signal to obtain a preprocessed physiological signal, wherein the signal preprocessing includes one or more of filtering, normalization, and noise reduction;

[0128] In this embodiment, preferably, signal preprocessing includes normalization, filtering, and noise reduction. Optionally, the acquired physiological signals are normalized, and then further bandpass filtered using a pre-designed FIR bandpass filter to apply bandpass filtering to the electrocardiogram, pulse, and heart sound signals. The filtered data and acceleration signal are then subjected to adaptive filtering for secondary processing to remove noise caused by motion artifacts, resulting in clean, high-quality physiological signals.

[0129] Step D102: Determine the duration of the preprocessed physiological signal;

[0130] Step D103: If the duration of the signal is longer than a preset duration, the preprocessed physiological signal is segmented to obtain multiple sub-physiological signals.

[0131] It should be noted that the preprocessed physiological signal is segmented to obtain multiple sub-physiological signals. This segmentation can be done without temporal overlap. For example, if the signal duration is 12 seconds, segmenting it in 3-second intervals results in four sub-physiological signals: 0-3 seconds, 3-6 seconds, 6-9 seconds, and 9-12 seconds. Alternatively, the physiological signal can be segmented with temporal overlap, dividing each signal into segments of fixed duration (Sig_t), with an overlap length of any value within the range (0 to Sig_t-1). For example, if the signal duration is 9 seconds, segmenting it in 3-second intervals with a 1-second overlap results in four sub-physiological signals: 0-3 seconds, 2-5 seconds, 4-7 seconds, and 6-9 seconds.

[0132] Furthermore, the preprocessed physiological signals are segmented to obtain multiple sub-physiological signals. The signal quality of each sub-physiological signal can be evaluated, sub-physiological signals with poor signal quality can be deleted, and signal features can be extracted based on sub-physiological signals with better signal quality to ensure the effectiveness of the extracted signal features.

[0133] One implementation method for evaluating the signal quality of each sub-physiological signal segment can be achieved by calculating features such as the RR interval and KSQI index of the electrocardiogram signal, the peak interval and number of zero-crossings of the pulse signal, and the SSQI coefficient and mean of the heart sound signal within each sub-physiological signal segment. These features are then combined with the change time of the acceleration signal amplitude (e.g., excluding sub-physiological signals whose amplitude time overlaps with the acceleration signal amplitude) to eliminate signal segments affected by noise. These features are then input into a classification model, such as an SVM (Support Vector Machine) model, to perform a coarse classification of each signal segment, such as dividing it into usable and unusable sub-physiological signals. Signal features are then extracted based on these sub-physiological signals.

[0134] Step D204: For each segment of the sub-physiological signal, extract the sub-signal features of the sub-physiological signal;

[0135] Step D205: Determine the mean signal feature of all the sub-signal features, and use the mean signal feature as the signal feature of the psychological signal.

[0136] If the duration of the preprocessed physiological signal is longer than a preset duration, such as 5 seconds, 6 seconds, or 7 seconds, the preprocessed physiological signal can be segmented to extract the sub-signal features of each segment of the physiological signal.

[0137] Understandably, this involves segmenting the preprocessed physiological signals, specifically the preprocessed ECG, pulse, and heart sound signals. Sub-signal features are extracted from each sub-physiological signal, forming an n-dimensional feature sequence X(t), where n is the number of features. The mean of each dimension of all X(t) is calculated to obtain the mean signal feature, which is the final signal feature. For example, suppose a physiological signal including ECG, pulse, and heart sound signals is segmented to obtain three sub-physiological signals: sub-physiological signal 1, sub-physiological signal 2, and sub-physiological signal 3. Sub-physiological signal 1 includes sub-ECG signal 1, sub-heart sound signal 1, and sub-pulse signal 1; sub-physiological signal 2 includes sub-ECG signal 2, sub-heart sound signal 2, and sub-pulse signal 2; and sub-physiological signal 3 includes sub-ECG signal 3, sub-heart sound signal 3, and sub-pulse signal 3. Extract the signal features of sub-physiological signal 1, denoted as sub-signal feature 1 [1_1, 1_2, 1_3], extract the signal features of sub-physiological signal 1, denoted as sub-signal feature 2 [2_1, 2_2, 2_3], extract the signal features of sub-physiological signal 3, denoted as sub-signal feature 3 [3_1, 3_2, 3_3], and the final signal features obtained are [(1_1+2_1+3_1) / 3, (1_2+2_2+3_2) / 3, (1_3+2_3+3_3) / 3].

[0138] Furthermore, after extracting the sub-signal features of each sub-physiological signal, outlier processing can be performed on all sub-signal features to remove abnormal features. Optionally, for the signal features of each sub-physiological signal segment, outlier feature sequence processing is performed according to the box plot principle. An exemplary processing flow is as follows: S1, the feature values ​​of each sub-physiological signal segment constitute an n-dimensional feature sequence X(t), where n is the number of features; S2, set the upper and lower edges of each dimension feature, such as calculating the upper quartile Q1 of each dimension feature. i Lower quartile Q3 i Interquartile Range (IQR) i Take the top edge Q1 i -1.5IQR i Q3 at the bottom edge i +1.5IQR i S3, filter out outlier data outside the upper and lower edges of each feature dimension; S4, obtain the feature sequence S(t) after removing outliers; S5, calculate the mean of the filtered feature sequence to obtain the mean signal feature S-.

[0139] The signal characteristics include, but are not limited to, the duration of the pre-ejaculation phase and the pulse transit time. They may also include pulse arrival time (PAT), the ratio of the systolic duration of the pulse signal to the diastolic duration of the heart sound signal, the ratio of the diastolic duration of the pulse signal to the heart sound signal, time-domain characteristics, frequency-domain characteristics, time-frequency characteristics, statistical characteristics, etc.

[0140] The time-domain features include, but are not limited to, the following: RR interval (RR), RR standard deviation (SDNN), and root mean square deviation (RMSSD) of the electrocardiogram (ECG) signal; PP interval (PP), half-amplitude pulse width (PW50), systolic duration, diastolic duration, rise time, area of ​​fastest rise, peak height, and rise slope of the pulse signal; first zero-crossing time, last inflection point time, peak value and first zero-crossing slope, peak slope, and peak area of ​​the VPG signal (obtained by first-order difference processing of the pulse signal); descent time, peak value and descent slope, and first zero-crossing and descent slope of the APG signal (obtained by second-order difference processing of the pulse signal); and duration of the first heart sound, second heart sound, systolic duration, and diastolic duration of the heart sound signal.

[0141] Frequency domain characteristics include, but are not limited to, the following: power spectral density of electrocardiogram signal; first component frequency and amplitude of pulse signal, second component frequency and amplitude, third component frequency and amplitude; main component frequencies of heart sound signal S1, main component frequencies of heart sound signal S2, etc.

[0142] Time-frequency features mainly include, but are not limited to, the following features: wavelet coefficients, Hilbert-Huang transform coefficients, Mel cepstral coefficients, linear prediction coefficient features, etc.

[0143] Statistical characteristics mainly include, but are not limited to, the following: kurtosis factor, skewness factor, and standard deviation of the characteristic sequence.

[0144] Step D20: Obtain the duration of the systolic phase and the duration of the diastolic phase of the pulse signal;

[0145] The pulse signal has different signal characteristics during systole and diastole. Based on this, the duration of systole and diastole can be extracted from the pulse signal. The specific extraction method can be adopted using existing technology, which will not be described in detail in this embodiment.

[0146] Step D30: The ratio of the duration of the systolic phase of the pulse signal to the duration of the systolic phase of the heart sound signal is taken as the systolic duration ratio.

[0147] Step D40: The ratio of the diastolic duration of the pulse signal to the diastolic duration of the heart sound signal is taken as the diastolic duration ratio.

[0148] Step D50: The systolic duration ratio, the diastolic duration ratio, and the signal feature are used as target signal features;

[0149] Step D60: Input the signal features into a preset blood pressure prediction model for training, so that the blood pressure prediction model can output a blood pressure prediction result.

[0150] The trained blood pressure model can be a blood pressure prediction model trained on a database, which includes at least real blood pressure data and signal feature data corresponding to each real blood pressure data point. This database can be obtained by pre-collecting real blood pressure data and signal feature data.

[0151] Furthermore, in order to improve the prediction accuracy of the blood pressure prediction model and achieve personalized blood pressure prediction, the real blood pressure values ​​and physiological signals of the test subjects can be collected multiple times in advance to establish an individual dataset. This individual dataset can then be used as a database to train the prediction model and complete the training of the blood pressure prediction model.

[0152] As one implementation method, the pre-training process of the blood pressure prediction model can be as follows: S1, feature selection is performed from a multi-class feature library using an existing database; S2, mutual information between features is calculated pairwise, where p(x) is the probability of x occurring, p(y) is the probability of y occurring, and p(x,y) is the probability of x and y occurring simultaneously, i.e., the joint probability. Higher mutual information indicates a higher degree of dependence between the two features. Features below the mutual information threshold are removed to obtain a new feature subset; S3, the correlation coefficient between the new feature subset and blood pressure is calculated. The higher the correlation coefficient, the stronger the linear correlation between the feature and blood pressure; S4, the feature subsets are sorted from high to low according to the correlation coefficient to obtain the sorted feature subsets; S5, the sorted feature subsets are divided into training and testing sets with a ratio of 8:2; S6, for the training set, 10-fold cross-validation and backward feature selection are used to select the number of features to obtain the feature subset S with the lowest RMSE (Root Mean Squared Error); S7, the final feature subset is used to train a multiple linear regression model. Where BP is the specific blood pressure value, S is the optimal feature subset, Ki is the fitting coefficient of the multiple linear regression model, and n is the dimension of the optimal feature subset.

[0153] In addition, personalized characteristics such as age, gender, height, weight, and BMI (Body Mass Index) of the test subject can be collected and used to train the model with signal feature data to obtain a pre-trained personalized blood pressure prediction model. After extracting signal features based on physiological signals, the personalized characteristics of the test subject, such as age, gender, height, weight, and BMI, are further collected. The signal features and personalized features are then input into the pre-trained personalized blood pressure prediction model to output the blood pressure prediction result. Considering the influence of factors such as age, gender, height, weight, and BMI on blood pressure, the accuracy of blood pressure prediction can be further improved.

[0154] Furthermore, after obtaining the blood pressure prediction result, it can be output on the wearable device. Simultaneously, the prediction result can be uploaded to a terminal or server connected to the wearable device for user viewing. The terminal and server can access the user's historical blood pressure data, aiding in diagnosis. Personalized blood pressure measurement plans can be customized based on historical data, providing a more comprehensive understanding of the user's health status and enabling more scientific medical advice.

[0155] In this embodiment, physiological signals of the subject are collected, including electrocardiogram (ECG), pulse, and heart sound signals. Feature extraction is performed on these physiological signals to obtain signal features, including the pre-ejection duration and pulse transit time. These signal features are then input into a pre-trained blood pressure prediction model, which outputs a blood pressure prediction result. Thus, compared to existing methods that estimate blood pressure based on pulse transit time, this embodiment predicts the subject's blood pressure by fusing signal features such as the pre-ejection duration and pulse transit time, taking into account the impact of the pre-ejection duration on blood pressure, thereby improving the accuracy of blood pressure prediction.

[0156] In this embodiment, after heart sound signal segmentation, the second systolic duration and the second diastolic duration based on the heart sound signal are obtained, and the first systolic duration and the second diastolic duration of the pulse signal are obtained. The ratio between the two is also used as a signal feature, thereby comprehensively measuring the diastolic and systolic durations of the heart sound signal and the pulse signal, which can further improve the accuracy of blood pressure prediction.

[0157] In one possible implementation, the step of feature extraction from the physiological signal includes:

[0158] Step E10: Determine the QRS peak value of the electrocardiogram signal, determine the heart sound peak value of the heart sound signal, determine the time difference between the two peak values, and use the time difference as the duration of the pre-ejection phase.

[0159] It should be noted that if the physiological signal is segmented, then the feature extraction of the physiological signal in this embodiment can actually be the feature extraction of each sub-physiological signal. The electrocardiogram signal, heart sound signal and pulse signal are also the electrocardiogram signal, heart sound signal and pulse signal included in the sub-physiological signal.

[0160] Understandably, referring to Figure 4 As shown, physiological signals include electrocardiogram (ECG) signals, phonocardiogram (PCG) signals, and pulse signals. The peak values ​​of the ECG and PCG signals are determined. Specifically, this involves identifying the QRS peak value of the ECG signal belonging to the same cardiac cycle and the peak value of the PCG signal. The time corresponding to these two peak values ​​is obtained, and the time difference between them is taken as the pre-ejaculation duration. If the physiological signals include multiple cardiac cycles, the pre-ejaculation duration corresponding to each cardiac cycle can be determined, and the average of all pre-ejaculation durations is taken as the final pre-ejaculation duration.

[0161] Step E20: Obtain the pulse transit time based on the pulse signal and the heart sound signal.

[0162] Starting from the S1 peak point of the heart sound signal and ending at the pulse wave feature point, the time difference is the pulse transmission time. One or more pulse wave feature points can be selected to obtain one or more corresponding pulse transmission times. That is, the pulse transmission time includes one or more. Users can set the selection rules of pulse wave feature points according to the actual situation. This embodiment does not impose a specific limit on the number of features of pulse transmission time.

[0163] Similarly, based on the synchronous acquisition of electrocardiogram (ECG) and pulse signals, starting from the R-wave peak of the ECG signal, one or more pulse arrival times (PATs) are determined, and these one or more pulse arrival times can also be used as the extracted signal features.

[0164] In this embodiment, fusion signal features such as the duration of pre-ejaculation and pulse transit time are extracted, providing an effective data foundation for predicting blood pressure values.

[0165] To aid in understanding the technical concept or principle of this application, a specific embodiment is provided:

[0166] See Figure 5-6As shown, the blood pressure prediction process in this specific embodiment is as follows:

[0167] The wristwatch device is activated via a power switch and connects to a server and a mobile app. After time calibration, the user can input personalized information such as height and weight. The system then prompts the user with configuration instructions. Once the user wears the wristwatch as instructed, it begins blood pressure measurement and simultaneously collects physiological signals, including electrocardiogram (ECG), heart sounds, and pulse. It also collects the user's acceleration and angular velocity to calculate the user's current Euler angles, assisting in locating the measurement position and posture. During blood pressure measurement, the collected acceleration and angular velocity information monitors arm movement and, combined with ECG, heart sounds, and pulse signals, performs noise reduction. Signal processing is applied to the collected physiological signals, including filtering (specifically bandpass filtering and adaptive filtering) and signal quality assessment. High-quality physiological signals are then feature-extracted and input into a blood pressure prediction model for prediction. The prediction results are displayed and uploaded simultaneously.

[0168] It should be noted that the above specific embodiments are only used to understand this application and do not constitute a limitation on the blood pressure prediction process of this application or a limitation on the application device. Any simple modifications based on this technical concept are within the protection scope of this application.

[0169] Example 4

[0170] This invention also provides a heart sound segmentation device, please refer to... Figure 7 The heart sound segmentation device includes:

[0171] A signal acquisition module is used to synchronously acquire physiological signals, including heart sound signals.

[0172] The segmentation module is used to obtain the segmentation threshold corresponding to the heart sound signal, and to segment the heart sound signal based on the segmentation threshold to obtain a first heart sound and a second heart sound.

[0173] The determination module is used to determine the duration of systole and diastole based on the first heart sound and the second heart sound.

[0174] The physiological signals also include electrocardiogram signals and pulse signals, and the segmentation module is further used for:

[0175] Determine the peak value of the QRS wave in the electrocardiogram signal, and take the time corresponding to the peak value of the QRS wave as the first time.

[0176] Determine the trough point of the pulse signal, and use the time corresponding to the trough point as the second time;

[0177] Determine the first and second zero-crossing points of the pulse signal, take the time corresponding to the first zero-crossing point as the third time, and take the time corresponding to the second zero-crossing point as the fourth time;

[0178] A first threshold for the heart sound signals corresponding to the first time and the second time is determined, and a second threshold for the heart sound signals corresponding to the third time and the fourth time is determined;

[0179] Use the first threshold and the second threshold as the segmentation threshold.

[0180] The segmentation module is further configured to:

[0181] Obtain or determine the heart sound envelope signal corresponding to the heart sound signal;

[0182] The peak value of the heart sound envelope signal between the first time and the second time is taken as the first heart sound peak value;

[0183] The first heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a first threshold value, wherein the first threshold value is less than the first heart sound peak value.

[0184] The segmentation module is further configured to:

[0185] Obtain or determine the heart sound envelope signal corresponding to the heart sound signal;

[0186] The peak value of the heart sound envelope signal between the third time and the fourth time is taken as the second heart sound peak value;

[0187] The second heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a second threshold value, wherein the second threshold value is less than the second heart sound peak value.

[0188] The segmentation threshold includes a first threshold and a second threshold, and the segmentation module is further configured to:

[0189] Obtain or determine the heart sound envelope signal corresponding to the heart sound signal;

[0190] The duration of the heart sound envelope signal value being greater than the first threshold is taken as the first duration window;

[0191] The duration of the heart sound envelope signal value being greater than the second threshold is taken as the second duration window;

[0192] The heart sound signal within the first duration window is taken as the first heart sound, and the heart sound signal within the second duration window is taken as the second heart sound.

[0193] The determining module is further configured to:

[0194] Determine the cardiac cycles included in the heart sound signals, and sequentially traverse each of the cardiac cycles;

[0195] The end time of the first heart sound within the traversed cardiac cycle is taken as the first end time. The next cardiac cycle corresponding to the traversed cardiac cycle is determined, and the start time of the first heart sound within the next cardiac cycle is taken as the first start time.

[0196] The start time of the second heart sound within the traversed cardiac cycle is taken as the second start time, and the end time of the second heart sound within the traversed cardiac cycle is taken as the second end time.

[0197] The time difference between the first end time and the second start time is taken as the duration of the contraction period;

[0198] The time difference between the first start time and the second end time is taken as the duration of diastole;

[0199] Until the end of each cardiac cycle, the average systolic duration of all said systolic durations is determined, and the average diastolic duration of all said diastolic durations is determined;

[0200] The average systolic duration is taken as the systolic duration of the heart sound signal, and the average diastolic duration is taken as the diastolic duration of the heart sound signal.

[0201] The heart sound segmentation device further includes a blood pressure prediction module, wherein the blood pressure prediction mode is used for:

[0202] Feature extraction is performed on the physiological signal to obtain signal features, wherein the signal features include the duration of the pre-ejaculation phase and the pulse transit time;

[0203] The duration of the systolic phase and the duration of the diastolic phase of the pulse signal are obtained.

[0204] The ratio of the duration of the systolic phase of the pulse signal to the duration of the systolic phase of the heart sound signal is taken as the systolic duration ratio.

[0205] The ratio of the diastolic duration of the pulse signal to the diastolic duration of the heart sound signal is taken as the diastolic duration ratio.

[0206] The systolic duration ratio, the diastolic duration ratio, and the signal characteristics are used as target signal characteristics;

[0207] The signal features are input into a preset blood pressure prediction model for training, so that the blood pressure prediction model can output blood pressure prediction results.

[0208] The blood pressure prediction mode is also used for:

[0209] Determine the QRS peak value of the electrocardiogram signal, determine the heart sound peak value of the heart sound signal, determine the time difference between the two peak values, and use the time difference as the duration of the pre-ejection phase;

[0210] The pulse delivery time is obtained based on the pulse signal and the heart sound signal.

[0211] In addition, the signal acquisition module is also used for:

[0212] Acceleration and gyroscope signals during user measurement process.

[0213] The signal acquisition module includes: an electrocardiogram measurement module, a pulse measurement module, a heart sound signal measurement module, and a 6-axis signal acquisition module.

[0214] The electrocardiogram (ECG) signal is primarily acquired through an ECG measurement module, which mainly consists of a high-impedance chip and three dry electrodes with good conductivity. The pulse signal is primarily acquired through a pulse measurement module, which mainly consists of multi-wavelength LEDs (light-emitting diodes), a photoelectric sensor, and a filtering and amplification circuit. The final pulse signal is obtained by fusing the multi-wavelength LEDs. To ensure the compact size of the cuffless blood pressure monitoring watch, the high-impedance characteristics of the simulated ECG signal acquisition, the fusion of the pulse signal, the filtering and amplification circuit, and the synchronization of the two physiological signals are all implemented using an integrated AFE chip.

[0215] Heart sound signals are mainly acquired through a heart sound signal measurement module, which is mainly composed of a digital VPU sensor. The VPU sensor is rigidly attached to the inside of the watch case. The amplification factor of the VPU sensor is adjusted to prevent signal overflow during the test, so as to obtain a complete heart sound signal.

[0216] Accelerometer and gyroscope signals are primarily acquired through a 6-axis signal acquisition module, which mainly consists of a 6-axis sensor integrated within the watch. Before blood pressure measurement, the 6-axis signal acquisition module calculates the current Euler angles to assist the user in positioning the acquisition location and posture. During blood pressure measurement, the 6-axis signal acquisition module monitors the user's arm movement and combines it with ECG, heart sound, and pulse signals to denoise the physiological signals, thereby improving the signal-to-noise ratio of these signals during acquisition.

[0217] In addition, the heart sound segmentation device also includes:

[0218] The watch case houses the sensors used for collecting physiological signals and the watch's control system.

[0219] The time calibration module is used to display real-time time and perform data synchronization and calibration.

[0220] The interaction module collects personalized user information, responds to signals generated during blood pressure measurement, and provides simple usage instructions for the blood pressure monitoring watch. The signals generated during blood pressure measurement include an activation signal. The watch usage instructions include the blood pressure monitoring watch's signal acquisition location and the user's acquisition posture.

[0221] The data processing module is used to process physiological signal segments collected by the physiological signal measurement module in real time. The data processing steps mainly include signal noise reduction, signal quality assessment, and feature extraction.

[0222] The wireless communication module is used to transmit the collected physiological signal data, the actual user's blood pressure value, and the user's personalized information to the server or mobile terminal via wireless means, for the construction of the blood pressure measurement watch database.

[0223] The watch case includes a power switch and three dry electrodes for ECG monitoring. The power switch primarily controls the watch's on / off function and access to the internal menu. The first and third electrodes form a circuit for ECG signal acquisition, while the second electrode provides a reference point to eliminate the potential difference between the body and the watch, improving the signal-to-noise ratio of the ECG signal. The watch case also includes a rigidly connected VPU sensor and a photoelectric pulse sensor for measuring heart sound signals and photoplethysmography (PPG) pulse signals.

[0224] The time calibration module generates a real-time clock, controlling the sensors to simultaneously begin synchronously acquiring physiological signals at the same time. It determines the relationship between ECG, pulse, and heart sound signals and time to ensure strict synchronization of the physiological signals. The calibrated real-time time is then used to record the moment data acquisition begins.

[0225] The interaction module includes an input module, a display module, and a prompt module, all of which are implemented by the watch's internal MCU (Microcontroller Unit) and the watch screen. The input module 141 within the interaction module is used to input personalized information into the watch before blood pressure measurement via the watch screen. This includes not only personal information such as gender, height, age, and weight, but also information such as whether antihypertensive medication is being taken and the name of the medication.

[0226] The display module within the interactive module shows how to use the watch and the measurement steps. After completing the personalized information input steps, the user can click on the blood pressure measurement function on the screen to see how to wear the watch and the posture the user should maintain during measurement. After completing the user tutorial, the testing phase begins, and the watch can prompt adjustments to the arm position via a prompt module to ensure the quality of physiological signal acquisition.

[0227] The prompting module in the interaction module includes a voice chip and a linear vibration motor, which is used to prompt the user about the operation process, arm placement, and measurement posture to ensure the accuracy of blood pressure measurement.

[0228] The data processing module includes a signal noise reduction module and a signal quality assessment module.

[0229] The signal denoising module normalizes the acquired physiological signals and then applies them to a pre-designed FIR (Finite Impulse Response) bandpass filter for ECG, pulse, and heart sound signals. The filtered data, along with the acceleration signal, undergoes further adaptive filtering to remove noise caused by motion artifacts, resulting in clean, high-quality physiological signals.

[0230] The signal quality assessment module is used to divide each signal into signal segments of fixed duration (Sig_t), typically >5s, with an overlap length of any value within the range (0 to Sig_t-1). Within each signal segment, features such as the RR interval and KSQI index of the ECG signal, the peak interval, standard deviation of the peak interval, and number of zero-crossings of the pulse signal, and the SSQI coefficient and mean of the heart sound signal are calculated. These features are then combined with the change time of the acceleration signal amplitude, and an SVM model is used to perform coarse classification of each signal segment, eliminating signal segments affected by noise interference.

[0231] The wireless communication module is used to send the collected physiological signals, input personalized information, and actual measured blood pressure values ​​to the terminal and upload them to the cloud server for data collection.

[0232] The heart sound segmentation device provided by this invention, employing the heart sound segmentation method described in Embodiment 1, Embodiment 2, or Embodiment 3 above, can solve the technical problem of how to reduce the resource consumption of heart sound signal segmentation. Compared with the prior art, the beneficial effects of the heart sound segmentation device provided by this invention are the same as those of the heart sound segmentation method provided in the above embodiments, and other technical features in the heart sound segmentation device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0233] Example 5

[0234] This invention provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the heart sound segmentation method in Embodiment 1 above.

[0235] The following is for reference. Figure 8 The diagram illustrates a structural schematic suitable for implementing embodiments of the present disclosure. The electronic device in these embodiments may be a wearable device, etc. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0236] like Figure 8 As shown, the electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM 1002) or a program loaded from a storage device into a random access memory (RAM 1004). The RAM 1004 also stores various programs and data required for the operation of the electronic device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. Input / output (I / O) interfaces are also connected to the bus 1005.

[0237] Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although electronic devices with various systems are shown in the figures, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0238] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of embodiments of this disclosure.

[0239] The electronic device provided by this invention, employing the heart sound segmentation method described in the above embodiments, can solve the technical problem of how to reduce the resource consumption of heart sound signal segmentation. Compared with the prior art, the beneficial effects of the electronic device provided by this invention are the same as those of the heart sound segmentation method described in the above embodiments, and other technical features of this electronic device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0240] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0241] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0242] Example 6

[0243] This invention provides a computer-readable storage medium having computer-readable program instructions stored thereon, which are used to execute the heart sound segmentation method in the first embodiment described above.

[0244] The computer-readable storage medium provided in this embodiment of the invention may be, for example, a USB flash drive, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0245] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0246] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to: synchronously acquire physiological signals, wherein the physiological signals include heart sound signals; obtain a segmentation threshold corresponding to the heart sound signals, segment the heart sound signals based on the segmentation threshold to obtain a first heart sound and a second heart sound; and determine the duration of systole and the duration of diastole based on the first heart sound and the second heart sound.

[0247] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0248] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0249] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0250] The readable storage medium provided by this invention is a computer-readable storage medium that stores computer-readable program instructions for executing the above-described heart sound segmentation method, thereby solving the technical problem of how to reduce the resource consumption of heart sound signal segmentation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this embodiment are the same as the beneficial effects of the heart sound segmentation method provided in Embodiment 1, Embodiment 2, or Embodiment 3, and will not be repeated here.

[0251] Example 7

[0252] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the heart sound segmentation method described above.

[0253] The computer program product provided in this application can solve the technical problem of how to reduce the resource consumption of heart sound segmentation. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiments of the present invention are the same as the beneficial effects of the heart sound segmentation method provided in Embodiment 1, Embodiment 2 or Embodiment 3 above, and will not be repeated here.

[0254] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A method for heart sound segmentation, characterized in that, The heart sound segmentation method includes: Physiological signals are acquired synchronously, including heart sound signals, electrocardiogram signals, and pulse signals; Determine the peak value of the QRS wave in the electrocardiogram signal, and take the time corresponding to the peak value of the QRS wave as the first time. Determine the trough point of the pulse signal, and use the time corresponding to the trough point as the second time; Determine the first and second zero-crossing points of the pulse signal, take the time corresponding to the first zero-crossing point as the third time, and take the time corresponding to the second zero-crossing point as the fourth time; Obtain or determine the heart sound envelope signal corresponding to the heart sound signal; The peak value of the heart sound envelope signal between the first time and the second time is taken as the first heart sound peak value; The first heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a first threshold value, wherein the first threshold value is less than the first heart sound peak value. Determine the second threshold corresponding to the third time and the fourth time; The first threshold and the second threshold are used as segmentation thresholds, and the heart sound signal is segmented based on the segmentation thresholds to obtain the first heart sound and the second heart sound. The duration of the systolic phase and the duration of the diastolic phase of the heart sound signal are determined based on the first and second heart sounds.

2. The heart sound segmentation method as described in claim 1, characterized in that, The step of determining the second threshold corresponding to the third time and the fourth time includes: Obtain or determine the heart sound envelope signal corresponding to the heart sound signal; The peak value of the heart sound envelope signal between the third time and the fourth time is taken as the second heart sound peak value; The second heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a second threshold value, wherein the second threshold value is less than the second heart sound peak value.

3. The heart sound segmentation method as described in claim 1, characterized in that, The segmentation threshold includes a first threshold and a second threshold, and the step of segmenting the heart sound signal based on the segmentation threshold includes: Obtain or determine the heart sound envelope signal corresponding to the heart sound signal; The duration of the heart sound envelope signal value being greater than the first threshold is taken as the first duration window; The duration of the heart sound envelope signal value being greater than the second threshold is taken as the second duration window; The heart sound signal within the first duration window is taken as the first heart sound, and the heart sound signal within the second duration window is taken as the second heart sound.

4. The heart sound segmentation method as described in claim 1, characterized in that, The step of determining the systolic duration and diastolic duration of the heart sound signal based on the first and second heart sounds includes: Determine the cardiac cycles included in the heart sound signals, and sequentially traverse each of the cardiac cycles; The end time of the first heart sound within the traversed cardiac cycle is taken as the first end time. The next cardiac cycle corresponding to the traversed cardiac cycle is determined, and the start time of the first heart sound within the next cardiac cycle is taken as the first start time. The start time of the second heart sound within the traversed cardiac cycle is taken as the second start time, and the end time of the second heart sound within the traversed cardiac cycle is taken as the second end time. The time difference between the first end time and the second start time is taken as the duration of the contraction period; The time difference between the first start time and the second end time is taken as the duration of diastole; Until the end of each cardiac cycle, the average systolic duration of all said systolic durations is determined, and the average diastolic duration of all said diastolic durations is determined; The average systolic duration is taken as the systolic duration of the heart sound signal, and the average diastolic duration is taken as the diastolic duration of the heart sound signal.

5. A heart sound segmentation device, characterized in that, For implementing the heart sound segmentation method as described in any one of claims 1 to 4, the heart sound segmentation device comprises: A signal acquisition module is used to acquire physiological signals, including heart sound signals. The segmentation module is used to obtain the segmentation threshold corresponding to the heart sound signal, and to segment the heart sound signal based on the segmentation threshold to obtain a first heart sound and a second heart sound. The determination module is used to determine the duration of the systolic phase and the duration of the diastolic phase of the heart sound signal based on the first heart sound and the second heart sound.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the steps of the heart sound segmentation method as described in any one of claims 1 to 4.

7. A readable storage medium, characterized in that, The readable storage medium is a computer-readable storage medium, on which a program implementing the heart sound segmentation method is stored, and the program implementing the heart sound segmentation method is executed by a processor to implement the steps of the heart sound segmentation method as described in any one of claims 1 to 4.

Images