Heart sound signal quality evaluation method, device, equipment and medium
By acquiring and processing heart sound signals and determining their quality assessment values, the problem of unstable signal quality in wearable devices is solved, enabling efficient signal assessment and location guidance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-10
- Publication Date
- 2026-04-14
AI Technical Summary
When wearable devices collect heart sound signals, the difficulty in accurately placing the device due to differences in the heart position of each user leads to unstable signal quality, and there is a lack of effective signal quality assessment methods.
By acquiring the heart sound signal to be evaluated, determining the peak times of the first and second heart sound signals, extracting the heart sound signal and noise signal, and calculating the signal power ratio to evaluate the signal quality, including preprocessing steps such as normalization, envelope extraction, and bandpass filtering.
It enables accurate assessment of heart sound signal quality, reduces assessment costs and difficulty, and is suitable for embedded systems and mobile terminals with limited computing power.
Smart Images
Figure CN121845631A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of signal processing technology, and more specifically, to a method, apparatus, device, and medium for quality assessment of heart sound signals. Background Technology
[0002] Heart sounds, the sounds produced by the mechanical activity of the heart, are a key non-invasive indicator for assessing cardiovascular health. Therefore, obtaining high-quality heart sound signals is crucial for daily monitoring of sub-healthy individuals, cardiac function assessment in athletes, and basic health screenings.
[0003] Currently, wearable devices can accurately capture heart sound signals. However, because the position of each user's heart often varies, it is difficult for users to accurately place the wearable device at the precise heart sound signal pickup location, leading to unstable signal quality of the heart sound signals acquired by the wearable device. Therefore, how to evaluate the signal quality of the heart sound signals acquired by wearable devices to guide the pickup location has become an urgent technical problem to be solved. Summary of the Invention
[0004] One objective of this application is to provide a new technical solution for quality assessment of heart sound signals.
[0005] According to a first aspect of this application, a method for assessing the quality of heart sound signals is provided, comprising: Acquire the heart sound signal to be evaluated, which includes a first heart sound signal, a second heart sound signal, and a noise signal; Based on the heart sound signals to be evaluated, determine the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal. Based on each first occurrence time and each second occurrence time, extract the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be evaluated; Based on the first heart sound signal, the second heart sound signal, and the noise signal, determine the quality assessment value of the heart sound signal to be evaluated.
[0006] Optionally, before determining the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal based on the heart sound signals to be evaluated, the method further includes: The heart sound signal to be evaluated is normalized to obtain the first processed heart sound signal; The heart sound signal to be evaluated is updated to the first processed heart sound signal.
[0007] Optionally, before determining the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal based on the heart sound signals to be evaluated, the method further includes: The envelope extraction process is performed on the heart sound signal to be evaluated to obtain the second processed heart sound signal; The second processed heart sound signal is sequentially subjected to bandpass filtering and normalization to obtain the third processed heart sound signal; The heart sound signal to be evaluated is updated to the third processed heart sound signal.
[0008] Optionally, determining the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal based on the heart sound signals to be evaluated includes: Multiple target local maximum amplitude values were determined from the heart sound signals to be evaluated; Based on the multiple target local maximum amplitude values, the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal are determined respectively.
[0009] Optionally, before determining multiple target local maximum amplitude values from the heart sound signal to be evaluated, the method further includes: The amplitude values of the heart sound signals to be evaluated that are less than the preset amplitude value are updated to the preset amplitude value to obtain the fourth processed heart sound signal. The heart sound signal to be evaluated is updated to the fourth processed heart sound signal.
[0010] Optionally, determining multiple target local maximum amplitude values from the heart sound signal to be evaluated includes: Multiple initial local maximum values were determined from the heart sound signal to be evaluated; Based on the preset window length and preset sliding step size, multiple sub-heart sound signals are extracted from the heart sound signal to be evaluated; For any of the sub-heart sound signals, retain the largest local maximum value among the initial local maximum values at the time the sub-heart sound signal occurs; The maximum local value corresponding to each of the sub-heart sounds is determined as multiple target local maximum values in the heart sound signals to be evaluated.
[0011] Optionally, determining the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal based on the plurality of target local maximum amplitude values includes: Based on the plurality of target local maximum values, determine the time interval between adjacent target local maximum values; The time interval with the highest frequency corresponds to the maximum value among the local maximum amplitude values of adjacent targets, and the time interval with the lowest frequency corresponds to the minimum value among the local maximum amplitude values of adjacent targets, and the time interval with the highest frequency corresponds to the second occurrence time.
[0012] Optionally, before extracting the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be evaluated according to each first occurrence time and each second occurrence time, the method further includes: For the first occurrence time, if the signal amplitude at the first occurrence time is less than the average amplitude, the first occurrence time is discarded, and the average amplitude is the average value among the multiple target local maximum amplitudes; For any of the retained first occurrence times, if the interval between the first occurrence time and the next first occurrence time is less than a preset interval, the next first occurrence time is discarded.
[0013] Optionally, the step of extracting the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be evaluated based on each first occurrence time and each second occurrence time includes: For any of the first occurrence times, the heart sound signals within a preset duration centered on the first occurrence time in the heart sound signal to be evaluated are determined as the first heart sound signal; For any second occurrence time, the heart sound signal within the preset duration centered on the second occurrence time in the heart sound signal to be evaluated is determined as the second heart sound signal; For any of the first occurrence times, the heart sound signal within the preset duration centered on the first intermediate time within the heart sound signal to be evaluated is determined as the first noise signal of the ventricular systolic interval, where the first intermediate time is the intermediate time between the first occurrence time and the first second occurrence time located after the first occurrence time; For any second occurrence time, the heart sound signal within the preset duration centered on the second intermediate time within the heart sound signal to be evaluated is determined as the second noise signal of the ventricular diastolic interval. The second intermediate time is the intermediate time between the second occurrence time and the first first occurrence time located after the second occurrence time. The noise signal includes the first noise signal and the second noise signal.
[0014] Optionally, determining the quality assessment value of the heart sound signal to be evaluated based on the first heart sound signal, the second heart sound signal, and the noise signal includes: Based on each of the first heart sound signals and each of the second heart sound signals, determine the heart sound signal power value in the heart sound signals to be evaluated; Based on the noise signal, determine the noise signal power value in the heart sound signal to be evaluated; The quality assessment value of the heart sound signal to be evaluated is determined by the ratio between the power value of the heart sound signal and the power value of the noise signal.
[0015] According to a second aspect of this application, a heart sound signal quality assessment device is provided, comprising: The acquisition module is used to acquire the heart sound signal to be evaluated, which includes a first heart sound signal, a second heart sound signal, and a noise signal; The determining module is used to determine, based on the heart sound signals to be evaluated, the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal; The extraction module is configured to extract the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be evaluated based on each first occurrence time and each second occurrence time. An evaluation module is used to evaluate the quality value of the heart sound signal to be evaluated based on the first heart sound signal, the second heart sound signal, and the noise signal.
[0016] According to a third aspect of this application, an electronic device is provided, the electronic device comprising the means as described in the second aspect; Alternatively, the electronic device includes a memory and a processor, the memory for storing computer instructions and the processor for retrieving the computer instructions from the memory to perform the method as described in any one of the first aspects.
[0017] According to a fourth aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method according to any one of the first aspects.
[0018] This application provides a method for quality assessment of heart sound signals, comprising: acquiring a heart sound signal to be assessed, the heart sound signal to be assessed including a first heart sound signal, a second heart sound signal, and a noise signal; determining, based on the heart sound signal to be assessed, a first occurrence time of the peak value of each first heart sound signal and a second occurrence time of the peak value of each second heart sound signal; extracting the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be assessed based on each first occurrence time and each second occurrence time; and determining a quality assessment value of the heart sound signal to be assessed based on the first heart sound signal, the second heart sound signal, and the noise signal. This method for quality assessment of heart sound signals can achieve quality assessment of heart sound signals. Furthermore, this method is implemented based on the characteristics of the first and second heart sound signals and does not involve complex machine learning models, thus reducing the assessment cost and difficulty of heart sound signal quality assessment.
[0019] Other features and advantages of this application will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description
[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the present application and, together with their description, serve to explain the principles of the present application.
[0021] Figure 1 This is a flowchart illustrating a method for assessing the quality of heart sound signals provided in this application; Figure 2 This is a schematic diagram of the original heart sound signal to be evaluated and the third-processed heart sound signal provided in this application; Figure 3 This is a schematic diagram of the structure of a heart sound signal quality assessment device provided in this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in this application. Detailed Implementation
[0022] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of the present application.
[0023] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this application and its application or use.
[0024] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.
[0025] In all the examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.
[0026] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.
[0027] This application provides a method for assessing the quality of heart sound signals, which is applied to electronic devices. The electronic devices can be wearable devices, such as smartwatches, smart bracelets, and smart rings. Figure 1 As shown, the method includes the following steps S1100 to S1400.
[0028] Step S1100: Obtain the heart sound signal to be evaluated.
[0029] The heart sound signals to be evaluated include the first heart sound signal, the second heart sound signal, and noise signals.
[0030] In this embodiment, the heart sound signals acquired by the electronic device are used as the heart sound signals to be evaluated. The first heart sound signal in the heart sound signal to be evaluated is the main vibrational component generated during the cardiac cycle by the sudden closure of the atrioventricular valves (mitral and / or tricuspid valves) at the beginning of ventricular systole, marking the start of ventricular systole; this first heart sound signal is commonly referred to as s1. The second heart sound signal is the main vibrational component generated during the cardiac cycle by the closure of the aortic valves (aortic and / or pulmonary valves) at the beginning of ventricular diastole, marking the start of the ventricular diastolic interval; this second heart sound signal is commonly referred to as s2. Furthermore, any signals other than the first and second heart sound signals in the heart sound signal to be evaluated are noise signals.
[0031] It is understandable that the heart sound signal to be evaluated typically includes multiple first heart sound signals and multiple second heart sound signals. Furthermore, the heart sound signal to be evaluated is specifically a time-series signal whose amplitude varies over time, and the time sequence corresponds to the sampling time of the sampling point.
[0032] In one example, the heart sound signal to be evaluated is as follows: Figure 2 As shown by the black curve in the image.
[0033] Based on the characteristics of the first and second heart sound signals, the first heart sound signal can be located by identifying the peak occurrence time of the first heart sound signal in the heart sound signal to be evaluated. Similarly, the second heart sound signal can be located by identifying the peak occurrence time of the second heart sound signal in the heart sound signal to be evaluated. After locating the first and second heart sound signals, the noise signal can be located. Therefore, the peak occurrence time of each first heart sound signal and the peak occurrence time of each second heart sound signal in the heart sound signal to be evaluated are determined through the following step S1200.
[0034] Step S1200: Based on the heart sound signals to be evaluated, determine the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal.
[0035] In this embodiment, the time when the peak value of each first heart sound signal in the heart sound signal to be evaluated occurs is recorded as the first occurrence time, and the time when the peak value of each second heart sound signal in the heart sound signal to be evaluated occurs is recorded as the second occurrence time.
[0036] In one embodiment of this application, in order to accurately determine the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal, the heart sound signal quality assessment method provided in this application further includes the following steps S1210 and S1211 before the above step S1200.
[0037] Step S1210: Normalize the heart sound signal to be evaluated to obtain the first processed heart sound signal.
[0038] Specifically, a preset normalization algorithm is used to perform normalization processing on the heart sound signal to be evaluated, and the normalized heart sound signal to be evaluated is recorded as the first processed heart sound signal.
[0039] In one example, the preset normalization algorithm can be the zscore algorithm, but it can also be other algorithms; this application does not limit this. Taking the zscore algorithm as the preset normalization algorithm as an example, the above step S1210 can be implemented using the following formula.
[0040] (Formula 1) in, This indicates the heart sound signal to be evaluated. This represents the heart sound signal after the first processing. This represents the average amplitude of the heart sound signal to be evaluated. This represents the standard deviation of the amplitude of the heart sound signal to be evaluated.
[0041] Step S1211: Update the heart sound signal to be evaluated to the first processed heart sound signal.
[0042] Through the above step S1211, the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal can be determined based on the first processed heart sound signal. In this way, the influence of the dimensions of the heart sound signal to be evaluated can be eliminated, and the accuracy of determining the first and second occurrence times can be improved.
[0043] In one embodiment of this application, the method for assessing the quality of heart sound signals provided in this application further includes steps S1220 to S1222 before step S1200.
[0044] Step S1220: Perform envelope extraction processing on the heart sound signal to be evaluated to obtain the second processed heart sound signal.
[0045] Specifically, a preset envelope extraction algorithm is used to perform envelope extraction processing on the heart sound signal to be evaluated, and the envelope of the heart sound signal to be evaluated is obtained, which is denoted as the second processed heart sound signal. The heart sound signal to be evaluated can be the heart sound signal to be evaluated obtained based on the above step S1100, or it can be the first processed heart sound signal obtained based on the above step S1211.
[0046] In one example, the preset envelope extraction algorithm can be the Hilbert transform algorithm, but it can also be other algorithms, which are not limited in this application. Taking the preset envelope extraction algorithm as the Hilbert transform algorithm, and the heart sound signal to be evaluated as the first processed heart sound signal obtained based on the above step S1211 as an example, the above step S1220 can be specifically implemented by the following formulas 2, 3 and 4.
[0047] (Formula 2) (Formula 3) (Formula 4) in, This represents the time variable of the integral term. yes The Hilbert transform result, yes The analytical signal, It is the envelope of the heart sound signal to be evaluated.
[0048] Step S1221: Bandpass filtering and normalization are performed sequentially on the second-processed heart sound signal to obtain the third-processed heart sound signal.
[0049] Based on the characteristics of the first and second heart sound signals, the passband range corresponding to the bandpass filtering process can be set to 0.5~5Hz. By performing bandpass filtering on the second-processed heart sound signal, high-frequency noise and low-frequency drift in the second-processed heart sound signal can be filtered out.
[0050] After performing bandpass filtering on the second-processed heart sound signal to obtain a second-processed heart sound signal with bandpass filtering, normalization processing is then performed on the second-processed heart sound signal with bandpass filtering to eliminate the influence of the dimensions of the second-processed heart sound signal with bandpass filtering. The signal obtained after normalizing the second-processed heart sound signal with bandpass filtering is denoted as the third-processed heart sound signal. The specific implementation of step S1221 can be, for example, the normalization processing in step S1210, which will not be elaborated further here.
[0051] Step S1222: Update the heart sound signal to be evaluated to the third processed heart sound signal.
[0052] In one example, the original heart sound signal to be evaluated obtained based on step S1100 above is... Figure 2 In the case of the black curve, the heart sound signal to be evaluated, updated to the third-processed heart sound signal obtained based on the above step S1222, is as follows: Figure 2 As shown by the red curve in the image.
[0053] based on Figure 2 It can be seen that the peak values of the first heart sound signal and the second heart sound signal in the heart sound signal to be evaluated can be clarified through the above steps S1220 to S1222, which makes it easier to determine the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal.
[0054] In one embodiment of this application, the peak value of the first heart sound signal is typically within a preset peak value range. Therefore, the occurrence time corresponding to the peak value within the peak value range in the third processed heart sound signal can be determined as the first occurrence time of the peak value of the first heart sound signal. Similarly, the second occurrence time of the peak value of the second heart sound signal can be determined.
[0055] Step S1300: Extract the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be evaluated based on each first occurrence time and each second occurrence time.
[0056] In one embodiment of this application, the above step S1300 is specifically implemented by the following steps S1310 to S1313.
[0057] Step S1310: For any first occurrence time, a portion of the heart sound signal within a preset duration centered on the first occurrence time is determined as the first heart sound signal.
[0058] Step S1311: For any second occurrence time, the heart sound signal within a preset duration centered on the first occurrence time within the heart sound signal to be evaluated is determined as the second heart sound signal.
[0059] Since the duration of the first heart sound signal is usually between 100 and 120 ms, and the duration of the second heart sound signal is usually between 100 and 150 ms, the preset duration is set to 100 ms in order to ensure that the extracted first heart sound signal includes only the first heart sound signal and the extracted second heart sound signal includes only the second heart sound signal.
[0060] In one example, such as Figure 2 As shown, the red dots represent the peak value of the first heart sound signal, and the yellow dots represent the peak value of the second heart sound signal. The heart sound signals within the width of the blue rectangle corresponding to the red dots are identified as the first heart sound signal. Since the yellow dots represent the peak value of the second heart sound signal, the heart sound signals within the width of the green rectangle corresponding to the yellow dots are identified as the second heart sound signal.
[0061] Step S1312: For any first occurrence time, the heart sound signal within a preset duration centered on the first intermediate time within the heart sound signal to be evaluated is determined as the first noise signal of the ventricular systolic interval.
[0062] The first intermediate time is the intermediate time between the first occurrence time and the first second occurrence time that follows the first occurrence time.
[0063] For any given first occurrence time, the interval between that first occurrence time and the first subsequent second occurrence time is the ventricular systolic interval, during which noise signals exist. In this embodiment, the noise signals present during the ventricular systolic interval are denoted as the first noise signal. To align with the granularity of the aforementioned first and second heart sound signals, improve signal comparability and fairness, and ensure that the first noise signal includes as much noise signal as possible, the heart sound signals within a preset duration centered on the first intermediate time are determined as the first noise signal of the ventricular systolic interval.
[0064] Step S1313: For any second occurrence time, the heart sound signal within a preset duration centered on the second intermediate time within the heart sound signal to be evaluated is determined as the second noise signal of the ventricular diastolic interval.
[0065] The second intermediate time is the intermediate time between the second occurrence time and the first occurrence time after the second occurrence time, and the noise signal includes the first noise signal and the second noise signal.
[0066] For any second occurrence time, the interval between this second occurrence time and the first occurrence time thereafter is the ventricular diastolic interval, during which noise signals exist. In this embodiment, the noise signals present during the ventricular diastolic interval are denoted as the second noise signal. To align with the granularity of the aforementioned first heart sound signal, second heart sound signal, and first noise signal, and to improve the comparability and fairness of the signals, while ensuring that the second noise signal includes as much noise signal as possible, the heart sound signals within a preset duration centered on the second intermediate time are determined as the second noise signal of the ventricular diastolic interval.
[0067] In one example, the first noise signal is as follows: Figure 2 The heart sound signal within the width of the orange rectangle, and the second noise signal as follows. Figure 2 Heart sound signals within the width of the purple rectangle.
[0068] Through steps S1310 to S1313 described above, the first heart sound signal, the second heart sound signal, and the noise signal in the heart sound signal to be evaluated can be accurately extracted. This provides a basis for accurately determining the quality assessment value of the heart sound signal to be evaluated in the subsequent process.
[0069] Step S1400: Determine the quality assessment value of the heart sound signal to be evaluated based on the first heart sound signal, the second heart sound signal, and the noise signal.
[0070] In one example of this application, step S1400 is specifically implemented by the following steps S1410 to S1412.
[0071] Step S1410: Determine the power value of the heart sound signal in the heart sound signal to be evaluated based on each first heart sound signal and each second heart sound signal.
[0072] Specifically, for any given first heart sound signal, the average power value of the first heart sound signal is calculated using the following formula (Formula 5). After obtaining the average power value of each first heart sound signal, the average power values of all first heart sound signals are summed to obtain the total power value of the first heart sound signal. Formula 5 is as follows.
[0073] (Formula 5) in, This indicates the number of sampling points in the first heart sound signal. It indicates the first The amplitude corresponding to each sampling point This represents the average power value of the first heart sound signal.
[0074] Using the same calculation method as the calculation method for the total power value of the first heart sound signal, the total power value of the second heart sound signal is calculated. The sum of the total power value of the first heart sound signal and the total power value of the second heart sound signal is determined as the heart sound signal power value in the heart sound signal to be evaluated.
[0075] Step S1412: Determine the noise signal power value in the heart sound signal to be evaluated based on the noise signal.
[0076] When the noise signal includes a first noise signal and a second noise signal, the same calculation method as used for calculating the total power value of the first heart sound signal is employed to calculate the total power value of the first noise signal and the total power value of the second noise signal, respectively. Furthermore, the sum of the total power value of the first noise signal and the total power value of the second noise signal is determined as the noise signal power value in the heart sound signal to be evaluated.
[0077] Step S1413: Determine the quality assessment value of the heart sound signal to be evaluated by the ratio between the power value of the heart sound signal and the power value of the noise signal.
[0078] Specifically, step S1413 above is implemented through the following formula six.
[0079] (Formula 6) in, This represents the quality assessment value of the heart sound signal to be evaluated. This represents the power value of the heart sound signal. This represents the power value of the noise signal.
[0080] After determining the quality assessment value of the heart sound signal to be evaluated, the pickup position of the electronic device can be guided based on this quality assessment value. For example, if the quality assessment value is less than a preset quality assessment value, a prompt message can be output to remind the user to adjust the pickup position of the heart sound signal.
[0081] Based on the above, the heart sound signal quality assessment method provided in this application can achieve quality assessment of heart sound signals. Furthermore, this method is implemented based on the characteristics of the first and second heart sound signals, and does not involve complex machine learning models, thus reducing the assessment cost and difficulty of heart sound signal quality assessment.
[0082] This application provides a method for quality assessment of heart sound signals, comprising: acquiring a heart sound signal to be assessed, the heart sound signal to be assessed including a first heart sound signal, a second heart sound signal, and a noise signal; determining, based on the heart sound signal to be assessed, a first occurrence time of the peak value of each first heart sound signal and a second occurrence time of the peak value of each second heart sound signal; extracting the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be assessed based on each first occurrence time and each second occurrence time; and determining a quality assessment value of the heart sound signal to be assessed based on the first heart sound signal, the second heart sound signal, and the noise signal. This method for quality assessment of heart sound signals can achieve quality assessment of heart sound signals. Furthermore, this method is implemented based on the characteristics of the first and second heart sound signals and does not involve complex machine learning models, thus reducing the assessment cost and difficulty of heart sound signal quality assessment.
[0083] In one embodiment of this application, based on any of the above embodiments, step S1200 is specifically implemented by the following steps S1230 and S1231.
[0084] Step S1230: Determine multiple target local maximum amplitude values from the heart sound signals to be evaluated.
[0085] The heart sound signal to be evaluated in step S1230 can be the heart sound signal to be evaluated that has been updated to the first processed heart sound signal in step S1211, or the heart sound signal to be evaluated that has been updated to the third processed heart sound signal in step S1222.
[0086] In order to quickly find the target local maximum amplitude, in one embodiment of this application, the heart sound signal quality assessment method provided by this application further includes the following steps S1230-1 and S1230-2 before the above step S1230.
[0087] Step S1230-1: Update the amplitude values of the heart sound signals to be evaluated that are less than the preset amplitude value to the preset amplitude value to obtain the fourth processed heart sound signal.
[0088] In this embodiment, the preset amplitude is a value smaller than the maximum local amplitude in the heart sound signal. This value can be set empirically and pre-stored in the electronic device. In one example, the preset amplitude is 0.
[0089] Step S1230-2: Update the heart sound signal to be evaluated to the fourth processed heart sound signal.
[0090] By using the above steps S1230-1, some non-local maximum amplitude components in the heart sound signal to be evaluated can be suppressed, thereby reducing interference with the determination of the target local maximum amplitude and increasing the speed of determining the target local maximum amplitude. Based on this, updating the heart sound signal to be evaluated to the fourth-processed heart sound signal allows for a faster determination of the target local maximum amplitude from the fourth-processed heart sound signal.
[0091] Through the above steps S1230, the target local maximum value is first found from the heart sound signal to be evaluated. Then, through the following steps S1231, the peak value of each first heart sound signal and the peak value of each second heart sound signal are found from the multiple target local maximum values, thereby determining the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal.
[0092] In one embodiment of this application, the above step S1230 is specifically implemented by the following steps S1230-3 to S1230-6.
[0093] Step S1230-3: Determine multiple initial local maximum amplitude values from the heart sound signals to be evaluated.
[0094] Specifically, the heart sound signal to be evaluated can be the fourth processed heart sound signal obtained in step S1230-1 above. Based on this, the specific implementation of step S1230-3 is as follows: each local maximum amplitude value in the fourth processed heart sound signal that serves as the heart sound signal to be evaluated is determined as the initial local maximum amplitude value.
[0095] Step S1230-4: Extract multiple sub-heart sound signals from the heart sound signal to be evaluated according to the preset window length and preset sliding step size.
[0096] The preset window length is less than the normal duration between the peak value of the first heart sound signal and the peak value of its adjacent second heart sound signal.
[0097] In one example, the preset window length is typically 50ms, and the preset sliding step is 1ms.
[0098] In this embodiment, the portion of the heart sound signal to be evaluated that lies within a window is denoted as a sub-heart sound signal. Through the above steps S1230-4, multiple sub-heart sound signals can be extracted from the heart sound signal to be evaluated.
[0099] Step S1230-5: For any sub-heart sound signal, retain the largest local maximum value among the initial local maximum values within the time of occurrence of the sub-heart sound signal.
[0100] Since the peak values of the first heart sound signal and the second heart sound signal are usually far apart, the above steps S1230-5 can avoid the existence of initial local maximum values that are too close among multiple initial local maximum values.
[0101] Step S1230-6: The maximum local maximum value corresponding to each sub-heart sound signal is determined as multiple target local maximum values in the heart sound signal to be evaluated.
[0102] Step S1231: Based on the multiple target local maximum amplitude values, determine the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal.
[0103] Since the amplitude of the first heart sound signal is greater than that of the second heart sound signal, and the first and second heart sound signals alternate, in one embodiment of this application, for each pair of temporally adjacent target local maximum amplitudes among multiple target local maximum amplitudes, the relatively larger target local maximum amplitude is determined as the peak value of the first heart sound signal, and the relatively smaller target local maximum amplitude is determined as the peak value of the second heart sound signal. Having determined the peak value of each first heart sound signal and the peak value of each second heart sound signal, the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal can be determined.
[0104] In one embodiment of this application, in order to more accurately determine the peak value of each first heart sound signal and the peak value of each second heart sound signal, the above step S1231 is specifically implemented through the following steps S1231-1 and S1231-2.
[0105] Step S1231-1: Determine the time interval between adjacent target local maximum values based on multiple target local maximum values.
[0106] Specifically, for multiple target local maximum values, the time interval between two adjacent target local maximum values is calculated.
[0107] Step S1231-2: The time of occurrence corresponding to the maximum value among the local maximum amplitude values of the adjacent target corresponding to the time interval with the highest frequency is determined as the first occurrence time, and the time of occurrence corresponding to the minimum value among the local maximum amplitude values of the adjacent target corresponding to the time interval with the highest frequency is determined as the second occurrence time.
[0108] In one example, considering tolerable errors, the specific implementation of step S1231-2 is as follows: based on the time interval between the local maximum values of adjacent targets determined in step S1231-1, multiple time interval intervals are divided according to the time interval, and the number of time intervals falling into each time interval interval is counted; the time interval that belongs to the same time interval interval and has the largest number is determined as the time interval with the highest frequency.
[0109] Since the time interval between the first heart sound signal and the first second heart sound signal thereafter is the most stable, and the peak value of the first heart sound signal is greater than the peak value of the second heart sound signal, the time of occurrence corresponding to the maximum value among the local maximum amplitude values of the adjacent target corresponding to the time interval with the highest frequency is determined as the first occurrence time, and the time of occurrence corresponding to the minimum value among the local maximum amplitude values of the adjacent target corresponding to the time interval with the highest frequency is determined as the second occurrence time.
[0110] In one embodiment of this application, in order to further improve the accuracy of the first time and the second time used when extracting the first heart sound signal, the second heart sound signal and the noise signal from the heart sound signal to be evaluated, the quality assessment method provided in this application further includes the following steps 1320 and S1321 before the above step S1300.
[0111] Step 1320: For the first occurrence time, if the signal amplitude at the first occurrence time is less than the average amplitude, the first occurrence time is discarded. The average amplitude is the average of the local maximum amplitudes of multiple targets.
[0112] Since the peak values of different first heart sound signals are basically the same, and the peak value of the first heart sound signal is greater than the peak value of the second heart sound signal, the peak value of the first heart sound signal is greater than the average value among multiple target local maximum amplitude values, i.e., the average peak value. Based on this, for the first occurrence time, if the signal amplitude at the first occurrence time is less than the average amplitude, it indicates that the first occurrence time is a false detection. In this case, the first occurrence time is discarded; otherwise, the first occurrence time is retained.
[0113] Step S1321: For any retained first occurrence time, if the interval between the first occurrence time and the next first occurrence time is less than a preset interval, the next first occurrence time of the first occurrence time is discarded.
[0114] The preset interval is the minimum interval between adjacent first heart sound signals. In one example, the preset interval is 0.5s.
[0115] If the interval between the first occurrence time and the next first occurrence time is less than a preset interval, then the aforementioned next first occurrence time is determined to be a falsely detected first occurrence time and is discarded.
[0116] The first occurrence time and the second occurrence time can be accurately selected through the above steps S1320 and S1321.
[0117] As can be seen from the above embodiments, the heart sound signal quality assessment method provided in this application, based on the characteristics of the first and second heart sound signals, can accurately determine the first and second occurrence times, and this determination method requires low computational power. Therefore, the heart sound signal quality assessment method provided in this application is suitable for deployment in embedded systems or mobile terminals with limited computing power.
[0118] Based on the above embodiments, the present application provides a method for quality assessment of heart sound signals, including the following steps S2001 to S2020.
[0119] Step S2001: Obtain the heart sound signal to be evaluated, which includes a first heart sound signal, a second heart sound signal, and a noise signal; Step S2002: Perform normalization processing on the heart sound signal to be evaluated to obtain the first processed heart sound signal; Step S2003: Perform envelope extraction processing on the first processed heart sound signal to obtain the second processed heart sound signal; Step S2004: Bandpass filtering and normalization are performed sequentially on the second processed heart sound signal to obtain the third processed heart sound signal; Step S2005: Update the amplitude values of the heart sound signal after the third processing that are less than the preset amplitude value to the preset amplitude value to obtain the heart sound signal after the fourth processing. Step S2006: Determine multiple initial local maximum amplitude values from the heart sound signals after the fourth processing; Step S2007: Extract multiple sub-heart sound signals from the heart sound signal to be evaluated according to the preset window length and preset sliding step size; Step S2008: For any sub-heart sound signal, retain the largest local maximum value among the initial local maximum values within the time of occurrence of the sub-heart sound signal; Step S2009: Determine the maximum local maximum value corresponding to each sub-heart sound signal as multiple target local maximum values in the heart sound signal after the fourth processing; Step S2010: Determine the time interval between adjacent local maximum values of targets based on multiple target local maximum values; Step S2011: The time of occurrence corresponding to the maximum value among the local maximum amplitude values of adjacent targets corresponding to the time interval with the highest frequency is determined as the first occurrence time, and the time of occurrence corresponding to the minimum value among the local maximum amplitude values of adjacent targets corresponding to the time interval with the highest frequency is determined as the second occurrence time. Step S2012: For the first occurrence time, if the signal amplitude at the first occurrence time is less than the average amplitude, the first occurrence time is discarded. The average amplitude is the average of the local maximum amplitudes of multiple targets. Step S2013: For any retained first occurrence time, if the interval between the first occurrence time and the next first occurrence time is less than a preset interval, the next first occurrence time of the first occurrence time is discarded. Step S2014: For any first occurrence time, the heart sound signal within a preset duration centered on the first occurrence time within the heart sound signal to be evaluated is determined as the first heart sound signal; Step S2015: For any second occurrence time, the heart sound signal within a preset duration centered on the second occurrence time in the heart sound signal to be evaluated is determined as the second heart sound signal; Step S2016: For any first occurrence time, the heart sound signal within a preset duration centered on the first intermediate time in the heart sound signal to be evaluated is determined as the first noise signal of the ventricular systolic interval. The first intermediate time is the intermediate time between the first occurrence time and the first second occurrence time after the first occurrence time. Step S2017: For any second occurrence time, the heart sound signal within a preset duration centered on the second intermediate time in the heart sound signal to be evaluated is determined as the second noise signal of the ventricular diastolic interval. The second intermediate time is the intermediate time between the second occurrence time and the first first occurrence time after the second occurrence time. The noise signal includes the first noise signal and the second noise signal. Step S2018: Determine the power value of the heart sound signal in the heart sound signal to be evaluated based on each first heart sound signal and each second heart sound signal; Step S2019: Determine the power value of the noise signal in the heart sound signal to be evaluated based on the noise signal; Step S2020: Determine the quality assessment value of the heart sound signal to be evaluated by the ratio between the power value of the heart sound signal and the power value of the noise signal.
[0120] This application also provides a heart sound signal quality assessment device 300, such as... Figure 3 As shown, it includes: The acquisition module 310 is used to acquire the heart sound signal to be evaluated, which includes a first heart sound signal, a second heart sound signal, and a noise signal; The determining module 320 is used to determine, based on the heart sound signals to be evaluated, the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal; Extraction module 330 is used to extract the first heart sound signal, the second heart sound signal and the noise signal from the heart sound signal to be evaluated based on each first occurrence time and each second occurrence time; The evaluation module 340 is used to determine the quality evaluation value of the heart sound signal to be evaluated based on the first heart sound signal, the second heart sound signal and the noise signal.
[0121] In one embodiment of this application, the heart sound signal quality assessment device 300 provided in this application further includes: The first update module is used to perform normalization processing on the heart sound signal to be evaluated to obtain the first processed heart sound signal. The heart sound signal to be evaluated is updated to the first processed heart sound signal.
[0122] In one embodiment of this application, the heart sound signal quality assessment device 300 provided in this application further includes: The second update module is used to perform envelope extraction processing on the heart sound signal to be evaluated to obtain the second processed heart sound signal. The second processed heart sound signal is sequentially subjected to bandpass filtering and normalization to obtain the third processed heart sound signal; The heart sound signal to be evaluated is updated to the third processed heart sound signal.
[0123] In one embodiment of this application, the determining module 320 is specifically used to determine multiple target local maximum amplitude values from the heart sound signal to be evaluated; Based on the multiple target local maximum amplitude values, the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal are determined respectively.
[0124] In one embodiment of this application, the heart sound signal quality assessment device 300 provided in this application further includes: The third update module is used to update the amplitude of the heart sound signal to be evaluated that is less than the preset amplitude to the preset amplitude, so as to obtain the fourth processed heart sound signal. The heart sound signal to be evaluated is updated to the fourth processed heart sound signal.
[0125] In one embodiment of this application, the determining module 320 is specifically used to determine a plurality of initial local maximum amplitude values from the heart sound signal to be evaluated; Based on the preset window length and preset sliding step size, multiple sub-heart sound signals are extracted from the heart sound signal to be evaluated; For any of the sub-heart sound signals, retain the largest local maximum value among the initial local maximum values at the time the sub-heart sound signal occurs; The maximum local value corresponding to each of the sub-heart sounds is determined as multiple target local maximum values in the heart sound signals to be evaluated.
[0126] In one embodiment of this application, the determining module 320 is specifically used to determine the time interval between adjacent target local maximum values based on the plurality of target local maximum values; The time interval with the highest frequency corresponds to the maximum value among the local maximum amplitude values of adjacent targets, and the time interval with the lowest frequency corresponds to the minimum value among the local maximum amplitude values of adjacent targets, and the time interval with the highest frequency corresponds to the second occurrence time.
[0127] In one embodiment of this application, the heart sound signal quality assessment device 300 provided in this application further includes: The elimination module is used to eliminate the first occurrence time if the signal amplitude at the first occurrence time is less than the average amplitude, wherein the average amplitude is the average value among the plurality of target local maximum amplitude values. For any of the retained first occurrence times, if the interval between the first occurrence time and the next first occurrence time is less than a preset interval, the next first occurrence time is discarded.
[0128] In one embodiment of this application, the extraction module 330 is specifically used to determine, for any first occurrence time, the heart sound signal within a preset duration centered on the first occurrence time in the heart sound signal to be evaluated as the first heart sound signal; For any second occurrence time, the heart sound signal within the preset duration centered on the second occurrence time in the heart sound signal to be evaluated is determined as the second heart sound signal; For any of the first occurrence times, the heart sound signal within the preset duration centered on the first intermediate time within the heart sound signal to be evaluated is determined as the first noise signal of the ventricular systolic interval, where the first intermediate time is the intermediate time between the first occurrence time and the first second occurrence time located after the first occurrence time; For any second occurrence time, the heart sound signal within the preset duration centered on the second intermediate time within the heart sound signal to be evaluated is determined as the second noise signal of the ventricular diastolic interval. The second intermediate time is the intermediate time between the second occurrence time and the first first occurrence time located after the second occurrence time. The noise signal includes the first noise signal and the second noise signal.
[0129] In one embodiment of this application, the evaluation module 340 is specifically used to determine the heart sound signal power value in the heart sound signal to be evaluated based on each of the first heart sound signal and each of the second heart sound signal; Based on the noise signal, determine the noise signal power value in the heart sound signal to be evaluated; The quality assessment value of the heart sound signal to be evaluated is determined by the ratio between the power value of the heart sound signal and the power value of the noise signal.
[0130] This application also provides an electronic device, which includes a heart sound signal quality assessment device 300 as provided in any of the above-described device embodiments.
[0131] This application also provides another electronic device 400, such as Figure 4 As shown, the electronic device 400 includes a memory 410 and a processor 420. The memory 410 is used to store computer instructions, and the processor 420 is used to call the computer instructions from the memory 410 to execute any of the heart sound signal quality assessment methods provided in the above method embodiments.
[0132] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the heart sound signal quality assessment methods provided in the above-described method embodiments.
[0133] This application may be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this application.
[0134] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.
[0135] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.
[0136] The computer program instructions used to perform the operations of this application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer-readable program instructions may 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 a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing the status information of the computer-readable program instructions. These electronic circuits can execute the computer-readable program instructions to implement various aspects of this application.
[0137] Various aspects of this application are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.
[0138] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.
[0139] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.
[0140] 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 this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive 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 action, or using a combination of dedicated hardware and computer instructions. It will be well known to those skilled in the art that implementation in hardware, implementation in software, and implementation using a combination of software and hardware are equivalent.
[0141] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of this application is defined by the appended claims.
Claims
1. A method for quality assessment of heart sound signals, characterized in that, include: Acquire the heart sound signal to be evaluated, which includes a first heart sound signal, a second heart sound signal, and a noise signal; Based on the heart sound signals to be evaluated, determine the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal. Based on each first occurrence time and each second occurrence time, extract the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be evaluated; Based on the first heart sound signal, the second heart sound signal, and the noise signal, determine the quality assessment value of the heart sound signal to be evaluated.
2. The method according to claim 1, characterized in that, Before determining the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal based on the heart sound signals to be evaluated, the method further includes: The heart sound signal to be evaluated is normalized to obtain the first processed heart sound signal; The heart sound signal to be evaluated is updated to the first processed heart sound signal.
3. The method according to claim 1 or 2, characterized in that, Before determining the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal based on the heart sound signals to be evaluated, the method further includes: The envelope extraction process is performed on the heart sound signal to be evaluated to obtain the second processed heart sound signal; The second processed heart sound signal is sequentially subjected to bandpass filtering and normalization to obtain the third processed heart sound signal; The heart sound signal to be evaluated is updated to the third processed heart sound signal.
4. The method according to claim 1, characterized in that, The step of determining the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal based on the heart sound signals to be evaluated includes: Multiple target local maximum amplitude values were determined from the heart sound signals to be evaluated; Based on the multiple target local maximum amplitude values, the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal are determined respectively.
5. The method according to claim 4, characterized in that, Before determining multiple target local maximum amplitude values from the heart sound signal to be evaluated, the method further includes: The amplitude values of the heart sound signals to be evaluated that are less than the preset amplitude value are updated to the preset amplitude value to obtain the fourth processed heart sound signal. The heart sound signal to be evaluated is updated to the fourth processed heart sound signal.
6. The method according to claim 4 or 5, characterized in that, The determination of multiple target local maximum amplitude values from the heart sound signal to be evaluated includes: Multiple initial local maximum values were determined from the heart sound signal to be evaluated; Based on the preset window length and preset sliding step size, multiple sub-heart sound signals are extracted from the heart sound signal to be evaluated; For any of the sub-heart sound signals, retain the largest local maximum value among the initial local maximum values at the time the sub-heart sound signal occurs; The maximum local value corresponding to each of the sub-heart sounds is determined as multiple target local maximum values in the heart sound signals to be evaluated.
7. The method according to claim 4, characterized in that, The step of determining the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal based on the plurality of target local maximum amplitude values includes: Based on the plurality of target local maximum values, determine the time interval between adjacent target local maximum values; The time interval with the highest frequency corresponds to the maximum value among the local maximum amplitude values of adjacent targets, and the time interval with the lowest frequency corresponds to the minimum value among the local maximum amplitude values of adjacent targets, and the time interval with the highest frequency corresponds to the second occurrence time.
8. The method according to claim 4, characterized in that, Before extracting the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be evaluated based on each first occurrence time and each second occurrence time, the method further includes: For the first occurrence time, if the signal amplitude at the first occurrence time is less than the average amplitude, the first occurrence time is discarded, and the average amplitude is the average value among the multiple target local maximum amplitudes; For any of the retained first occurrence times, if the interval between the first occurrence time and the next first occurrence time is less than a preset interval, the next first occurrence time is discarded.
9. The method according to claim 1, characterized in that, The step of extracting the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be evaluated based on each first occurrence time and each second occurrence time includes: For any of the first occurrence times, the heart sound signals within a preset duration centered on the first occurrence time in the heart sound signal to be evaluated are determined as the first heart sound signal; For any second occurrence time, the heart sound signal within the preset duration centered on the second occurrence time in the heart sound signal to be evaluated is determined as the second heart sound signal; For any of the first occurrence times, the heart sound signal within the preset duration centered on the first intermediate time within the heart sound signal to be evaluated is determined as the first noise signal of the ventricular systolic interval, where the first intermediate time is the intermediate time between the first occurrence time and the first second occurrence time located after the first occurrence time; For any second occurrence time, the heart sound signal within the preset duration centered on the second intermediate time within the heart sound signal to be evaluated is determined as the second noise signal of the ventricular diastolic interval. The second intermediate time is the intermediate time between the second occurrence time and the first first occurrence time located after the second occurrence time. The noise signal includes the first noise signal and the second noise signal.
10. The method according to claim 1, characterized in that, The step of determining the quality assessment value of the heart sound signal to be evaluated based on the first heart sound signal, the second heart sound signal, and the noise signal includes: Based on each of the first heart sound signals and each of the second heart sound signals, determine the heart sound signal power value in the heart sound signals to be evaluated; Based on the noise signal, determine the noise signal power value in the heart sound signal to be evaluated; The quality assessment value of the heart sound signal to be evaluated is determined by the ratio between the power value of the heart sound signal and the power value of the noise signal.
11. A device for assessing the quality of heart sound signals, characterized in that, include: The acquisition module is used to acquire the heart sound signal to be evaluated, which includes a first heart sound signal, a second heart sound signal, and a noise signal; The determining module is used to determine, based on the heart sound signals to be evaluated, the first occurrence time of the peak value of each first heart sound signal and the second occurrence time of the peak value of each second heart sound signal; The extraction module is configured to extract the first heart sound signal, the second heart sound signal, and the noise signal from the heart sound signal to be evaluated based on each first occurrence time and each second occurrence time. An evaluation module is used to evaluate the quality value of the heart sound signal to be evaluated based on the first heart sound signal, the second heart sound signal, and the noise signal.
12. An electronic device, characterized in that, The electronic device includes the apparatus as described in claim 11; Alternatively, the electronic device includes a memory and a processor, the memory for storing computer instructions, and the processor for retrieving the computer instructions from the memory to perform the method as described in any one of claims 1-10.
13. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method according to any one of claims 1-10.