A heart rate calculation method, device, medium and electronic equipment

Abstract

This application relates to the field of heart sound signal technology, and discloses a heart rate calculation method, device, medium, and electronic device. The method includes: preprocessing an input heart sound signal to obtain an envelope signal; generating a heart sound signal peak sequence containing heart sound components based on a preset adaptive threshold and the envelope signal; obtaining multiple cardiac cycles of the envelope signal based on the heart sound signal peak sequence; selecting a preset number of cardiac cycles as target cardiac cycles from the heart sound signal peak sequence; calculating the heart rate value corresponding to the heart sound signal based on the average cycle duration of the target cardiac cycles; or calculating the heart rate value corresponding to the heart sound signal based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals. The heart rate calculation method provided by this application can solve the problem of inaccurate heart rate values ​​calculated due to false detections and missed detections, which is unavoidable in traditional heart rate calculation schemes.

Description

Technical Field

[0001] This application relates to the field of heart sound signal technology, and in particular, to a heart rate calculation method, apparatus, medium, and electronic device. Background Technology

[0002] Heart rate monitoring is helpful for the early diagnosis of cardiovascular diseases, the assessment of heart condition, and the early warning of sudden cardiac events. Common heart rate monitoring signals include electrocardiogram (ECG), pulse wave (PPG), and cardiac auscultation. Compared to other physiological signals, cardiac auscultation has a longer history. It diagnoses heart diseases by listening to the vibrations (heart sounds) produced when the heart beats. It can detect not only structural abnormalities of heart valves and defects characterized by heart murmurs, but also provides a cheaper and more reliable alternative. Doctors can perform quick and simple auscultatory diagnoses using a stethoscope without imposing prolonged restrictions on the patient's activity or posture, ensuring patient comfort.

[0003] Heart sounds mainly consist of basic heart sounds, additional heart sounds (S3 and S4), and heart murmurs. The basic heart sound components include the first heart sound (S1) and the second heart sound (S2). Under normal circumstances, only the basic heart sound exists in each cardiac cycle. However, when there are certain heart diseases, such as aortic stenosis or mitral regurgitation, additional heart sounds or murmurs may occur.

[0004] Traditional heart rate calculation schemes often use thresholding methods to process heart sound signals and detect heart sound components. However, simply using thresholding to detect heart sound components and then calculating the heart rate based on these components yields low accuracy. This is because actual heart sound signals may contain additional heart sounds, murmurs, and other noise, which can easily be mistakenly detected as basic heart sound components, leading to false positives. Furthermore, the presence of faint first or second heart sounds can result in missed detections, further contributing to inaccurate heart rate calculations. Therefore, traditional heart rate calculation schemes cannot address the problem of inaccurate heart rate values ​​caused by false positives and missed negatives. Summary of the Invention

[0005] This application provides a heart rate calculation method, device, medium, and electronic device to solve the problem that traditional heart rate calculation schemes cannot solve the problem of inaccurate heart rate values ​​calculated due to false detection and false detection.

[0006] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0007] According to one aspect of the embodiments of this application, a heart rate calculation method is provided, the method comprising:

[0008] The input heart sound signal is preprocessed to obtain the envelope signal;

[0009] Based on a preset adaptive threshold and the envelope signal, a heart sound signal peak sequence containing heart sound components is generated, and the heart sound signal peak sequence includes multiple heart sound signal peaks.

[0010] Multiple cardiac cycles of the envelope signal are obtained based on the heart sound signal peak sequence; the cardiac cycle includes a first heart sound signal and a second heart sound signal, and the first heart sound signal and the second heart sound signal each correspond to a heart sound signal peak;

[0011] A preset number of cardiac cycles are selected from the heart sound signal peak sequence as the target cardiac cycles;

[0012] If all heart sound signal peaks in the target cardiac cycle are determined to be either the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal, the heart rate value corresponding to the heart sound signal is calculated based on the average cycle duration of the target cardiac cycle.

[0013] If any heart sound signal peak in the target cardiac cycle is not determined to be the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal, the heart rate value corresponding to the heart sound signal is calculated based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals.

[0014] The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals can be obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak.

[0015] Multiple cardiac cycles of the envelope signal obtained based on the heart sound signal peak sequence can be classified by a dual-verification heart sound recognition method;

[0016] The heart sound signal peaks can be classified by the dual-verification heart sound recognition method into the first heart sound signal, the second heart sound signal, or an uncertain signal.

[0017] The dual-verification heart sound recognition method includes a first verification and a second verification. When the first verification and the second verification classify the two heart sound signal peaks before the heart sound signal peak into the same category, the heart sound signal peak is classified as the first heart sound signal or the second heart sound signal; otherwise, the heart sound signal peak is classified as the uncertain signal.

[0018] The first verification includes determining the two heart sound signal peaks before the current heart sound signal peak as the first heart sound signal or the second heart sound signal by using the time interval between the second and third heart sound signal peaks before the current heart sound signal peak and the time interval between the first and second heart sound signal peaks before the current heart sound signal peak.

[0019] The second verification includes determining the two heart sound signal peaks before the current heart sound signal peak as either the first heart sound signal or the second heart sound signal by using the time interval between the current heart sound signal peak and the first heart sound signal peak before the current heart sound signal peak and the time interval between the first heart sound signal peak before the current heart sound signal peak and the second heart sound signal peak.

[0020] In one embodiment of this application, based on the foregoing scheme, the preprocessing of the input heart sound signal to obtain the envelope signal includes:

[0021] The heart sound signal is downsampled and filtered to remove noise, resulting in filtered data, which is a bipolar signal.

[0022] The filtered data is converted into a unipolar signal Shannon energy signal by calculating the Shannon energy of the heart sound signal;

[0023] The envelope signal is generated based on the Shannon energy signal.

[0024] In one embodiment of this application, based on the foregoing scheme, generating a heart sound signal peak sequence containing heart sound components based on a preset adaptive threshold and the envelope signal includes:

[0025] Obtain all envelope values ​​in the envelope signal;

[0026] Select the envelope segments above the adaptive threshold from all the envelope values ​​as the envelope peaks of the heart sound signal;

[0027] The heart sound signal peak sequence is generated based on the envelope peak of the heart sound signal.

[0028] In one embodiment of this application, based on the foregoing scheme, generating the heart sound signal peak sequence based on the heart sound signal envelope peak includes:

[0029] A target number of envelope peaks are selected from the envelope peaks of the heart sound signal as target envelope peaks;

[0030] Extreme points are selected from the target envelope peaks as target envelope peak extreme points, and the interval between any two adjacent target envelope peak extreme points is greater than a preset interval threshold.

[0031] The heart sound signal peak sequence is generated based on the target envelope peak; wherein, a single target envelope peak corresponds to a single heart sound signal peak.

[0032] In one embodiment of this application, based on the foregoing scheme, calculating the heart rate value corresponding to the heart sound signal according to the average cycle duration of the target cardiac cycle includes:

[0033] Obtain the average cycle duration of the target cardiac cycle;

[0034] Divide 60 by the average cycle duration to obtain the heart rate value corresponding to the heart sound signal.

[0035] In one embodiment of this application, based on the foregoing scheme, calculating the heart rate value corresponding to the heart sound signal according to the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals includes:

[0036] Calculate multiple instantaneous heart rate values ​​within the target cardiac cycle based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals;

[0037] The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals can be obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak.

[0038] The instantaneous heart rate values ​​within the target cardiac cycle are clustered using the K-means clustering algorithm to obtain a preset number of clusters;

[0039] The cluster with the most instantaneous heart rate values ​​is selected from the preset number of clusters as the target cluster;

[0040] The heart rate value corresponding to the heart sound signal is calculated based on the target cluster.

[0041] In one embodiment of this application, based on the foregoing scheme, calculating the heart rate value corresponding to the heart sound signal based on the target cluster includes:

[0042] Obtain the number and value of the instantaneous heart rate values ​​in the target cluster;

[0043] The average value of the instantaneous heart rate of the target cluster is calculated based on the number of instantaneous heart rate values ​​and the numerical value of the instantaneous heart rate values;

[0044] If the average value is greater than a preset heart rate threshold, the average value will be used as the heart rate value corresponding to the heart sound signal;

[0045] If the average value is less than the heart rate threshold, the heart rate value corresponding to the heart sound signal is calculated based on the time interval between two adjacent heart sound signal peaks.

[0046] According to one aspect of the embodiments of this application, a heart rate calculation device is provided. The device includes: a preprocessing unit, configured to preprocess an input heart sound signal to obtain an envelope signal; a generation unit, configured to generate a heart sound signal peak sequence containing heart sound components based on a preset adaptive threshold and the envelope signal, the heart sound signal peak sequence including multiple heart sound signal peaks; an acquisition unit, configured to acquire multiple cardiac cycles of the envelope signal based on the heart sound signal peak sequence; the cardiac cycle including a first heart sound signal and a second heart sound signal, the first heart sound signal and the second heart sound signal each corresponding to one of the heart sound signal peaks; and a selection unit, configured to select a preset number of cardiac cycles from the heart sound signal peak sequence. The target cardiac cycle is defined as follows: a first calculation unit is used to calculate the heart rate value corresponding to the heart sound signal based on the average cycle duration of the target cardiac cycle if all heart sound signal peaks in the target cardiac cycle are determined to be either the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal; a second calculation unit is used to calculate the heart rate value corresponding to the heart sound signal based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals if any heart sound signal peak in the target cardiac cycle is not determined to be either the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal.

[0047] The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals can be obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak.

[0048] Multiple cardiac cycles of the envelope signal obtained based on the heart sound signal peak sequence can be classified by a dual-verification heart sound recognition method;

[0049] The heart sound signal peaks can be classified by the dual-verification heart sound recognition method into the first heart sound signal, the second heart sound signal, or an uncertain signal.

[0050] The dual-verification heart sound recognition method includes a first verification and a second verification. When the first verification and the second verification classify the two heart sound signal peaks before the heart sound signal peak into the same category, the heart sound signal peak is classified as the first heart sound signal or the second heart sound signal; otherwise, the heart sound signal peak is classified as the uncertain signal.

[0051] The first verification includes determining the two heart sound signal peaks before the current heart sound signal peak as the first heart sound signal or the second heart sound signal by using the time interval between the second and third heart sound signal peaks before the current heart sound signal peak and the time interval between the first and second heart sound signal peaks before the current heart sound signal peak.

[0052] The second verification includes determining the two heart sound signal peaks before the current heart sound signal peak as either the first heart sound signal or the second heart sound signal by using the time interval between the current heart sound signal peak and the first heart sound signal peak before the current heart sound signal peak and the time interval between the first heart sound signal peak before the current heart sound signal peak and the second heart sound signal peak.

[0053] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, on which a computer program is stored, the computer program including executable instructions that, when executed by a processor, implement the heart rate calculation method as described in the above embodiments.

[0054] According to one aspect of the embodiments of this application, an electronic device is provided, including: one or more processors; and a memory for storing executable instructions of the processors, which, when executed by the one or more processors, cause the one or more processors to implement the heart rate calculation method as described in the above embodiments.

[0055] In the technical solution of this application embodiment, a denoised envelope signal is obtained by preprocessing the heart sound signal, and then a heart sound signal peak sequence containing heart sound components is generated by using a preset adaptive threshold and the envelope signal. Multiple cardiac cycles of the envelope signal are obtained through the heart sound signal peak sequence, and selecting a preset number of cardiac cycles as the target cardiac cycle can reduce the computational load of heart rate values, resulting in higher computational efficiency.

[0056] When all heart sound signal peaks in the target cardiac cycle have been identified, the heart sound signal type is either the first heart sound signal or the second heart sound signal. At this point, it indicates that heart rate can be calculated, and the heart rate value corresponding to the heart sound signal is calculated using the average cycle duration of the target cardiac cycle.

[0057] When any heart sound signal peak in the target cardiac cycle is not identified as the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal, that is, when any heart sound signal peak in the target cardiac cycle cannot be identified as the heart sound signal peak corresponding to a certain heart sound signal type, false detection or missed detection may occur. The heart rate value corresponding to the heart sound signal is calculated by the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals.

[0058] The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals can be obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak.

[0059] The heart rate calculation method provided in this application can solve the problem that traditional heart rate calculation schemes cannot solve the problem of inaccurate heart rate values ​​due to false detection and false negative detection.

[0060] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0061] 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. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0062] Figure 1 This is a flowchart illustrating a heart rate calculation method according to an embodiment of this application;

[0063] Figure 2 This is a schematic diagram illustrating the process of generating a heart sound signal peak sequence containing heart sound components based on a preset adaptive threshold and the envelope signal, according to an embodiment of this application.

[0064] Figure 3 This is a schematic diagram of a cardiac cycle without murmur components according to an embodiment of this application;

[0065] Figure 4 This is a schematic diagram of a cardiac cycle including murmur components, according to an embodiment of this application;

[0066] Figure 5 This is a schematic diagram illustrating the change in signal waveform during preprocessing of heart sound signals according to an embodiment of this application;

[0067] Figure 6 This is a schematic diagram illustrating a dual-verification heart sound recognition method according to an embodiment of this application;

[0068] Figure 7 This is a structural block diagram of a heart rate calculation device according to an embodiment of this application;

[0069] Figure 8 This is a schematic diagram of a computer-readable storage medium according to an embodiment of this application;

[0070] Figure 9 This is a schematic diagram of the system structure of an electronic device according to an embodiment of this application;

[0071] Figure 10 This is a schematic diagram illustrating the results of K-means clustering according to an embodiment of this application;

[0072] Figure 11 This is a schematic diagram illustrating the missed detection of heart sound signals according to an embodiment of this application. Detailed Implementation

[0073] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0074] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0075] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller node devices.

[0076] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0077] It should be noted that "multiple" in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0078] The implementation details of the technical solutions in the embodiments of this application are described in detail below:

[0079] First, it should be noted that the heart rate calculation scheme proposed in this application can be applied to the technical field of heart sound signals. It should be clarified that the accurate heart rate value is calculated based on the premise that both the first and second heart sounds are determined, and a single cardiac cycle includes both the first and second heart sounds. Therefore, if there are false detections or false negatives—that is, abnormal heart sounds or noise components are mistakenly detected as heart sounds, or some or all of the first or second heart sounds are missed—the calculated heart rate value will be inaccurate. The heart rate calculation scheme proposed in this application can accurately determine the heart rate value.

[0080] According to one aspect of this application, a method for calculating heart rate is provided. Figure 1 The flowchart below illustrates a heart rate calculation method according to an embodiment of this application. This heart rate calculation method includes at least steps 110 to 160, detailed below:

[0081] In step 110, the input heart sound signal is preprocessed to obtain the envelope signal.

[0082] In one embodiment of this application, step 110 may be performed according to steps S1-S3:

[0083] Step S1: Downsample and filter the heart sound signal to obtain filtered data, which is a bipolar signal.

[0084] Step S2: Convert the filtered data into a unipolar signal Shannon energy signal by calculating the Shannon energy of the heart sound signal.

[0085] Step S3: Generate the envelope signal based on the Shannon energy signal.

[0086] Heart sound signals are mainly concentrated in the range of 20Hz to 1000Hz, while the stethoscope can collect signals at frequencies such as 4000Hz, 8000Hz, and 44100Hz. In order to reduce the amount of computation required for subsequent processing of heart sound signals, the signal is downsampled to a sampling rate of 2000Hz.

[0087] like Figure 5 As shown, Figure 5 A graph showing the changes in the signal waveform during the preprocessing of heart sound signals; Figure 5 The last waveform in the diagram is the waveform of the envelope signal.

[0088] To calculate the heart rate value of the heart sound signals, it is necessary to detect the first heart sound signal (S1) and the second heart sound signal (S2), which are mainly concentrated within 200Hz. In the embodiments of this application, a bandpass digital filter of 20Hz to 200Hz is used to filter the heart sound signals to remove noise outside the frequency band that interferes with the detection of S1 and S2.

[0089] The signal filtered by the bandpass filter is a bipolar signal, so it needs to be converted into a unipolar signal. The unipolar signal is obtained using the Shannon energy formula, as follows:

[0090] y[n]=-(x[n])^2In((x[n])^2) (1)

[0091] x[n] is the filtered signal, and y[n] is the transformed signal value. The obtained unipolar signal is then passed through a moving average filter to obtain the envelope signal, using the following formula:

[0092]

[0093]

[0094] Where y[n] is the Shannon energy signal, and e[n] is the envelope signal after moving average calculation. Formula (2) calculates the average value within a signal window of length N. Formula (3) is the iterative calculation form of formula (2), which can reduce the amount of calculation. The value of N is determined according to the duration of S1 and S2. For example, N can be set to 50ms, that is, N = 0.05 × FS, where FS is the signal sampling frequency, which is 2000Hz in this embodiment.

[0095] Continue to refer to Figure 1 In step 120, a heart sound signal peak sequence containing heart sound components is generated based on a preset adaptive threshold and the envelope signal.

[0096] In one embodiment of this application, such as Figure 2As shown, step 120 can be performed according to steps S4-S6:

[0097] Step S4: Obtain all envelope values ​​in the envelope signal.

[0098] Step S5: Select envelope segments from all the envelope values ​​that are higher than the adaptive threshold as the envelope peaks of the heart sound signal.

[0099] Step S6: Generate the heart sound signal peak sequence based on the envelope peak of the heart sound signal.

[0100] In this application, peak detection of the envelope signal is performed through steps S4 and S5, and the preset adaptive threshold is determined according to the following formula:

[0101]

[0102]

[0103]

[0104]

[0105] Among them Th n This represents the adaptive threshold size determined at time n. The threshold value representing the heart sound components at time n is determined by the mean heart sound. Subtract its standard deviation It is found that, due to the possibility of a large difference in the amplitudes of S1 and S2, their standard deviation may be too large. Too small, at this time combine with By comparison, the larger one is selected using formula (7) as the standard. The value of this threshold determines the lower threshold size required for the detection of heart sound components. The threshold representing the background noise at time n is determined by formula (6) from the mean of the background noise. Plus its 3 times standard deviation It is determined that this threshold defines the upper threshold for noise component detection. Half the difference between the lower threshold defined by heart sound components and the upper threshold defined by noise components is selected as the floating threshold. The global average value of the heart sound signal is used as the baseline threshold. The floating threshold is added to the baseline threshold to obtain the final adaptive threshold. All statistical parameters are obtained through iterative calculation to reduce computational load. The iterative calculation formula is shown below:

[0106]

[0107]

[0108]

[0109]

[0110] Where e[n] is the formula for calculating the envelope signal.

[0111] In one embodiment of this application, step S6 can be performed according to steps S61-S63:

[0112] Step S61: Select a target number of envelope peaks from the envelope peaks of the heart sound signal as target envelope peaks.

[0113] Step S62: Select extreme points from the target envelope peak as extreme points of the target envelope peak, wherein the interval between any two adjacent extreme points of the target envelope peak is greater than a preset interval threshold.

[0114] Step S63: Generate the heart sound signal peak sequence based on the target envelope peak; wherein, a single target envelope peak corresponds to a single heart sound signal peak.

[0115] In this application, the interval threshold can be specifically 0.16s. Peak detection is performed on the signal using a calculated adaptive threshold. Heart sound signal peaks exceeding the adaptive threshold may be heart sound components; otherwise, they may be noise components. The following conditions are used to further constrain heart sound signal peak detection:

[0116] Condition 1: The peak width of the heart sound signal corresponds to the duration of the heart sound signal. The peak width should be greater than 0.02s and less than 0.15s. The duration of the first and second heart sound signals is usually 0.06s-0.15s. Therefore, if the detected peak width is less than 0.02s, the heart sound signal corresponding to the peak is considered to be sharp noise or background noise and is removed. If the detected peak width is greater than 0.15s, the signal peak is considered to contain a complete heart sound component.

[0117] Condition 2: The interval between adjacent heart sound peaks is greater than 0.02s, and the interval between their poles is greater than 0.16s. The heart rate range is 40-180 BPM, therefore the duration of one cardiac cycle should be greater than 0.33s. In this case, the systolic and diastolic phases are approximately the same length, so the interval between the first and second heart sound signals should be greater than 0.16s. Therefore, when the distance between the poles of two heart sound peaks is less than 0.16s or the distance between their adjacent boundaries is less than 0.02s, they are considered to belong to the same heart sound peak.

[0118] By using conditions 1 and 2 above, non-heart sound signal peaks are removed, thereby more accurately determining the cardiac cycle in the heart sound signal peak sequence that includes only the first and second heart sound signals as much as possible.

[0119] Continue to refer to Figure 1 In step 130, multiple cardiac cycles of the envelope signal are obtained based on the cardiac sound signal peak sequence; the cardiac cycle includes a first cardiac sound signal and a second cardiac sound signal, and the first cardiac sound signal and the second cardiac sound signal each correspond to a cardiac sound signal peak.

[0120] The cardiac cycle includes a first heart sound signal and a second heart sound signal. The first heart sound signal and the second heart sound signal each correspond to a heart sound signal peak. That is, a single cardiac cycle includes both the first heart sound signal and the second heart sound signal.

[0121] In step 140, a preset number of cardiac cycles are selected from the heart sound signal peak sequence as target cardiac cycles.

[0122] In this application, the preset number can be set according to actual needs. The preset number in the following embodiments of this application is further explained using 4 as an example. By selecting a preset number of cardiac cycles as the target cardiac cycles, the amount of calculation of heart rate values ​​can be reduced, and the efficiency of obtaining heart rate values ​​can be improved.

[0123] Continue to refer to Figure 1 In step 150, if all heart sound signal peaks in the target cardiac cycle are determined to be either the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal, the heart rate value corresponding to the heart sound signal is calculated based on the average cycle duration of the target cardiac cycle.

[0124] In one embodiment of this application, calculating the heart rate value corresponding to the heart sound signal based on the average cycle duration of the target cardiac cycle includes:

[0125] Obtain the average cycle duration of the target cardiac cycle;

[0126] Divide 60 by the average cycle duration to obtain the heart rate value corresponding to the heart sound signal.

[0127] In this application, it is necessary to determine whether the signal peak belongs to the first heart sound signal or the second heart sound signal. Based on the characteristic that the systolic phase of a normal heart sound is shorter than its diastolic phase, such as... Figure 3 As shown, a complete cardiac cycle consists of the first heart sound signal S1, the systolic phase, the second heart sound signal S2, and the diastolic phase. This application uses a dual-verification heart sound classification method to identify S1 and S2. Figure 4This is a schematic diagram showing a cardiac cycle containing murmur components.

[0128] like Figure 6 As shown, the dual-verification heart sound classification method includes a first verification and a second verification. The first verification includes determining whether the first two signal peaks P2 and P1 belong to S1 or S2 based on the duration of the second peak interval ΔT2 and the third peak interval ΔT3 before the current heart sound signal peak P. The second verification includes determining whether the current peak P and the first two peaks P2 and P1 belong to S1 or S2 based on the duration of the first peak interval ΔT1 and the second peak interval ΔT2 before the current heart sound signal peak P.

[0129] When the first and second verifications determine that the two preceding heart sound signal peaks P2 and P1 are the same, it indicates that the two verifications match each other. Therefore, the category of the current heart sound signal peak P determined by the second verification is reliable and is marked as S1 or S2. Otherwise, the current heart sound signal peak classification result is considered unreliable and is marked as uncertain (U).

[0130] If the peaks of the heart sound signal in four consecutive heartbeat cycles can be accurately classified without any uncertain peaks, then it is considered that the signal can be directly used to calculate the heart rate. The heart rate value can be calculated using the following formula:

[0131]

[0132]

[0133] in, and ΔT represents the time corresponding to the i-th peak extreme point of S1 and S2, respectively. cycle This represents the average number of heartbeat cycles during that period, and HR is the calculated average heart rate value for that time period. If the heart sound signal peaks of four consecutive cardiac cycles cannot be accurately classified and there are uncertain peaks, then proceed to the next step.

[0134] Continue to refer to Figure 1 In step 160, if any heart sound signal peak in the target cardiac cycle is not determined to be the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal, the heart rate value corresponding to the heart sound signal is calculated based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals.

[0135] The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals can be obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak.

[0136] In one embodiment of this application, step 160 may be performed according to the following steps S7-S10:

[0137] Step S7: Calculate multiple instantaneous heart rate values ​​within the target cardiac cycle based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals.

[0138] Step S8: Based on the K-means clustering algorithm, the instantaneous heart rate values ​​within the target cardiac cycle are clustered to obtain a preset number of clusters.

[0139] Step S9: Select the cluster with the most instantaneous heart rate values ​​from the preset number of clusters as the target cluster.

[0140] Step S10: Calculate the heart rate value corresponding to the heart sound signal based on the target cluster.

[0141] In one embodiment of this application, step S10 may be performed according to the following steps S101-S104:

[0142] Step S101: Obtain the number and value of the instantaneous heart rate values ​​in the target cluster;

[0143] Step S102: Calculate the average value of the instantaneous heart rate of the target cluster based on the number of instantaneous heart rate values ​​and the numerical value of the instantaneous heart rate values;

[0144] Step S103: If the average value is greater than a preset heart rate threshold, the average value is used as the heart rate value corresponding to the heart sound signal;

[0145] Step S104: If the average value is less than the heart rate threshold, calculate the heart rate value corresponding to the heart sound signal based on the time interval between two adjacent heart sound signal peaks.

[0146] In this application, the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals is the duration of a single cardiac cycle.

[0147] The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals can be obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak. That is, in three consecutive heart sound signal peaks, the time interval between the first heart sound signal peak and the third heart sound signal peak is taken as the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals.

[0148] When the heart sound signal peaks of four consecutive cardiac cycles cannot be completely and accurately classified, the instantaneous heart rate values ​​within the target cardiac cycle are clustered using the K-means clustering algorithm to obtain a preset number of clusters, which can specifically be 3 clusters.

[0149] Abnormal heart rate values ​​are removed using the K-means clustering algorithm. Assuming that most of the currently detected peaks belong to heart sound signal peaks S1 or S2, and that the order of appearance of the heart sound signal peaks is S1 followed by S2, the peak-to-peak time interval ΔT between each heart sound signal peak is calculated. This ΔT represents the time interval between the previous S1 or the previous S2, which is the duration of one cardiac cycle, and is calculated using the following formula:

[0150]

[0151] To calculate the instantaneous heart rate value.

[0152] Since the number of erroneous signal peaks detected in most cases is small, the instantaneous heart rate values ​​determined are mostly correct and close in size over a short period of time. Therefore, the K-means clustering algorithm is used to divide the instantaneous heart rate values ​​within the target cardiac cycle into 3 clusters, and the average instantaneous heart rate of the cluster with the largest number of clusters is selected as the calculated heart rate value.

[0153] like Figure 10 As shown, the instantaneous heart rate is divided into 3 clusters using the K-means clustering algorithm. The bottom cluster has the most values, while the other two clusters contain abnormal heart rate values ​​due to noise, which are therefore discarded. If the calculated heart rate value is greater than 60 BPM, the final real-time heart rate calculation result is obtained directly; otherwise, it indicates that there may be missed detections in S1 or S2.

[0154] Missed detection of the first heart sound signal S1 or the second heart sound signal S2, such as... Figure 11 As shown, the calculated heart rate is less than 60 BPM at this time, which may be due to the weakness of S1 or S2 or the presence of a heart murmur, causing a certain heart sound component to be missed. Figure 11As shown, S1 is missed because its amplitude is too weak. In this case, the instantaneous heart rate can be calculated using the following formula, where ΔT in the formula refers to the interval between two adjacent heart sound signal peaks.

[0155] Similarly, the K-means clustering algorithm is used to determine the final real-time heart rate value.

[0156]

[0157] Figure 7 This is a block diagram illustrating a heart rate calculation device according to an embodiment of this application.

[0158] Reference Figure 7 As shown, a heart rate calculation device 700 according to one embodiment of this application includes:

[0159] The preprocessing unit 701 is used to preprocess the input heart sound signal to obtain the envelope signal;

[0160] The generation unit 702 is used to generate a heart sound signal peak sequence containing heart sound components based on a preset adaptive threshold and the envelope signal, wherein the heart sound signal peak sequence includes multiple heart sound signal peaks.

[0161] The acquisition unit 703 is used to acquire multiple cardiac cycles of the envelope signal based on the cardiac sound signal peak sequence; the cardiac cycle includes a first cardiac sound signal and a second cardiac sound signal, and the first cardiac sound signal and the second cardiac sound signal each correspond to a cardiac sound signal peak;

[0162] The selection unit 704 is used to select a preset number of cardiac cycles as target cardiac cycles from the heart sound signal peak sequence.

[0163] The first calculation unit 705 is used to calculate the heart rate value corresponding to the heart sound signal based on the average cycle duration of the target cardiac cycle if all heart sound signal peaks in the target cardiac cycle are determined to be either the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal.

[0164] The second calculation unit 706 is used to calculate the heart rate value corresponding to the heart sound signal based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals if any heart sound signal peak in the target cardiac cycle is not determined to be the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal.

[0165] The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals can be obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak.

[0166] Multiple cardiac cycles of the envelope signal obtained based on the heart sound signal peak sequence can be classified by a dual-verification heart sound recognition method;

[0167] The heart sound signal peaks can be classified by the dual-verification heart sound recognition method into the first heart sound signal, the second heart sound signal, or an uncertain signal.

[0168] The dual-verification heart sound recognition method includes a first verification and a second verification. When the first verification and the second verification classify the two heart sound signal peaks before the heart sound signal peak into the same category, the heart sound signal peak is classified as the first heart sound signal or the second heart sound signal; otherwise, the heart sound signal peak is classified as the uncertain signal.

[0169] The first verification includes determining the two heart sound signal peaks before the current heart sound signal peak as the first heart sound signal or the second heart sound signal by using the time interval between the second and third heart sound signal peaks before the current heart sound signal peak and the time interval between the first and second heart sound signal peaks before the current heart sound signal peak.

[0170] The second verification includes determining the two heart sound signal peaks before the current heart sound signal peak as either the first heart sound signal or the second heart sound signal by using the time interval between the current heart sound signal peak and the first heart sound signal peak before the current heart sound signal peak and the time interval between the first heart sound signal peak before the current heart sound signal peak and the second heart sound signal peak.

[0171] refer to Figure 8 As shown, a program product 800 for implementing the above-described method according to an embodiment of this application is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the program product of this application is not limited thereto. In this document, a 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, apparatus, or device.

[0172] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable 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 devices, magnetic storage devices, or any suitable combination thereof.

[0173] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0174] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0175] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0176] In another respect, this application also provides an electronic device capable of implementing the above-described method.

[0177] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0178] The following reference Figure 9 To describe an electronic device 900 according to this embodiment of the present application. Figure 9 The electronic device 900 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0179] like Figure 9 As shown, the electronic device 900 is manifested in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one processing unit 910, at least one storage unit 920, and a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910).

[0180] The storage unit stores program code that can be executed by the processing unit 910, causing the processing unit 910 to perform the steps described in the "Embodiment Method" section above according to various exemplary embodiments of this application.

[0181] Storage unit 920 may include readable media in the form of volatile storage units, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923.

[0182] The storage unit 920 may also include a program / utility 924 having a set (at least one) of program modules 925, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0183] Bus 930 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0184] Electronic device 900 can also communicate with one or more external devices 1200 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 900, and / or with any device that enables electronic device 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 950. Furthermore, electronic device 900 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 960. As shown, network adapter 960 communicates with other modules of electronic device 900 via bus 930. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0185] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the method according to the embodiments of this application.

[0186] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this application, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0187] It should be understood that this application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for calculating heart rate, characterized in that, The method includes: The input heart sound signal is preprocessed to obtain the envelope signal; A sequence of heart sound signal peaks containing heart sound components is generated based on a preset adaptive threshold and the envelope signal. The heart sound signal peaks are classified using a dual-verification heart sound recognition method, and multiple cardiac cycles of the envelope signal are obtained based on the heart sound signal peak sequence; each cardiac cycle includes a first heart sound signal and a second heart sound signal, and the first heart sound signal and the second heart sound signal each correspond to one heart sound signal peak. A preset number of cardiac cycles are selected from the heart sound signal peak sequence as the target cardiac cycles; If all heart sound signal peaks in the target cardiac cycle are identified as the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal; calculate the heart rate value corresponding to the heart sound signal based on the average cycle duration of the target cardiac cycle. If any heart sound signal peak in the target cardiac cycle is not determined to be the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal, the heart rate value corresponding to the heart sound signal is calculated based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals. The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals is obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak. The heart sound signal peaks are classified by the dual-verification heart sound recognition method as the first heart sound signal, the second heart sound signal, or an uncertain signal. The dual-verification heart sound recognition method includes a first verification and a second verification. When the first verification and the second verification classify the two heart sound signal peaks before the heart sound signal peak into the same category, the heart sound signal peak is classified as the first heart sound signal or the second heart sound signal; otherwise, the heart sound signal peak is classified as the uncertain signal. The first verification includes determining the two heart sound signal peaks before the current heart sound signal peak as the first heart sound signal or the second heart sound signal by using the time interval between the second and third heart sound signal peaks before the current heart sound signal peak and the time interval between the first and second heart sound signal peaks before the current heart sound signal peak. The second verification includes determining the two heart sound signal peaks before the current heart sound signal peak as either the first heart sound signal or the second heart sound signal by using the time interval between the current heart sound signal peak and the first heart sound signal peak before the current heart sound signal peak and the time interval between the first heart sound signal peak before the current heart sound signal peak and the second heart sound signal peak.

2. The heart rate calculation method according to claim 1, characterized in that, The preprocessing of the input heart sound signal to obtain the envelope signal includes: The heart sound signal is downsampled and filtered to remove noise, resulting in filtered data, which is a bipolar signal. The filtered data is converted into a unipolar signal Shannon energy signal by calculating the Shannon energy of the heart sound signal; The envelope signal is generated based on the Shannon energy signal.

3. The heart rate calculation method according to claim 1, characterized in that, The generation of a heart sound signal peak sequence containing heart sound components based on a preset adaptive threshold and the envelope signal includes: Obtain all envelope values ​​in the envelope signal; Select the envelope segments above the adaptive threshold from all the envelope values ​​as the envelope peaks of the heart sound signal; The heart sound signal peak sequence is generated based on the envelope peak of the heart sound signal.

4. The heart rate calculation method according to claim 3, characterized in that, The step of generating the heart sound signal peak sequence based on the heart sound signal envelope peak includes: A target number of envelope peaks are selected from the envelope peaks of the heart sound signal as target envelope peaks; Extreme points are selected from the target envelope peaks as target envelope peak extreme points, and the interval between any two adjacent target envelope peak extreme points is greater than a preset interval threshold. The heart sound signal peak sequence is generated based on the target envelope peak; wherein, a single target envelope peak corresponds to a single heart sound signal peak.

5. The heart rate calculation method according to claim 1, characterized in that, The step of calculating the heart rate value corresponding to the heart sound signal based on the average cycle duration of the target cardiac cycle includes: Obtain the average cycle duration of the target cardiac cycle; Divide 60 by the average cycle duration to obtain the heart rate value corresponding to the heart sound signal.

6. The heart rate calculation method according to claim 1, characterized in that, The step of calculating the heart rate value corresponding to the heart sound signal based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals includes: Calculate multiple instantaneous heart rate values ​​within the target cardiac cycle based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals; The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals is obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak. The instantaneous heart rate values ​​within the target cardiac cycle are clustered using the K-means clustering algorithm to obtain a preset number of clusters; The cluster with the most instantaneous heart rate values ​​is selected from the preset number of clusters as the target cluster; The heart rate value corresponding to the heart sound signal is calculated based on the target cluster.

7. The heart rate calculation method according to claim 6, characterized in that, The calculation of the heart rate value corresponding to the heart sound signal based on the target cluster includes: Obtain the number and value of the instantaneous heart rate values ​​in the target cluster; The average value of the instantaneous heart rate of the target cluster is calculated based on the number of instantaneous heart rate values ​​and the numerical value of the instantaneous heart rate values; If the average value is greater than a preset heart rate threshold, the average value will be used as the heart rate value corresponding to the heart sound signal; If the average value is less than the heart rate threshold, the heart rate value corresponding to the heart sound signal is calculated based on the time interval between two adjacent heart sound signal peaks.

8. A heart rate calculation device, characterized in that, The device includes: The preprocessing unit is used to preprocess the input heart sound signal to obtain the envelope signal; The generation unit is used to generate a sequence of heart sound signal peaks containing heart sound components based on a preset adaptive threshold and the envelope signal. The acquisition unit is used to classify the heart sound signal peaks using a dual-verification heart sound recognition method, and to acquire multiple cardiac cycles of the envelope signal based on the heart sound signal peak sequence; each cardiac cycle includes a first heart sound signal and a second heart sound signal, and each of the first heart sound signal and the second heart sound signal corresponds to a heart sound signal peak. The selection unit is used to select a preset number of cardiac cycles as target cardiac cycles from the heart sound signal peak sequence. The first calculation unit is used to calculate the heart rate value corresponding to the heart sound signal based on the average cycle duration of the target cardiac cycle if all heart sound signal peaks in the target cardiac cycle are determined to be the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal. The second calculation unit is used to calculate the heart rate value corresponding to the heart sound signal based on the time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals if any heart sound signal peak in the target cardiac cycle is not determined to be the heart sound signal peak corresponding to the first heart sound signal or the heart sound signal peak corresponding to the second heart sound signal. The time interval between two adjacent first heart sound signals or the time interval between two adjacent second heart sound signals is obtained by calculating the time interval between two heart sound signal peaks that are separated by one heart sound signal peak. The heart sound signal peaks are classified by the dual-verification heart sound recognition method as the first heart sound signal, the second heart sound signal, or an uncertain signal. The dual-verification heart sound recognition method includes a first verification and a second verification. When the first verification and the second verification classify the two heart sound signal peaks before the heart sound signal peak into the same category, the heart sound signal peak is classified as the first heart sound signal or the second heart sound signal; otherwise, the heart sound signal peak is classified as the uncertain signal. The first verification includes determining the two heart sound signal peaks before the current heart sound signal peak as the first heart sound signal or the second heart sound signal by using the time interval between the second and third heart sound signal peaks before the current heart sound signal peak and the time interval between the first and second heart sound signal peaks before the current heart sound signal peak. The second verification includes determining the two heart sound signal peaks before the current heart sound signal peak as either the first heart sound signal or the second heart sound signal by using the time interval between the current heart sound signal peak and the first heart sound signal peak before the current heart sound signal peak and the time interval between the first heart sound signal peak before the current heart sound signal peak and the second heart sound signal peak.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to perform the operations performed by the method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to perform the operation performed by the method as described in any one of claims 1 to 7.

Images