Heart sound signal collection method, device and equipment and storage medium

Abstract

The application discloses a heart sound signal collection method and device, equipment and a storage medium, relates to the technical field of heart sound processing, and the method is applied to a heart sound signal collection wearable device. The device comprises a bone voiceprint sensor and an audio collection device. The audio collection device is installed within a target range from the bone voiceprint sensor. The method comprises the following steps: acquiring a to-be-de-noised heart sound signal collected by the bone voiceprint sensor and an environmental noise signal collected by the audio collection device; performing signal comparison according to the environmental noise signal and the to-be-de-noised heart sound signal to obtain a first heart sound signal; processing the first heart sound signal according to a signal amplitude range, and obtaining a target heart sound signal according to a processing result. Through the above method, the external noise problem in the heart sound signal collected by the VPU is solved, the amplitude of the heart sound signal is amplified to the amplitude range that can be processed by the algorithm, the algorithm training amount is effectively reduced, and the algorithm calculation precision is improved.

Description

Technical Field

[0001] This application relates to the field of heart sound processing technology, and in particular to heart sound signal acquisition methods, devices, equipment and storage media. Background Technology

[0002] When the heart contracts, the valves open and close, producing a clicking sound. These sounds vibrate against the chest wall, and the resulting sounds are called heart sounds. A bone conduction voiceprint sensor (VPU) utilizes the principle of sound wave transmission through bone vibration. An internal chip converts the vibrational signals into electrical signals. Theoretically, a VPU should only receive bone vibration signals. However, due to factors such as current VPU technology, manufacturing processes, and testing methods, in practice, VPUs may pick up signals beyond bone vibration and environmental noise, affecting the accuracy and stability of subsequent heart sound-based diagnosis of disease symptoms. Summary of the Invention

[0003] The main purpose of this application is to provide a method, apparatus, device and storage medium for acquiring heart sound signals, which aims to solve the technical problem that external noise signals exist during the acquisition of heart sound signals in the prior art, which makes it impossible to perform accurate feature recognition based on heart sound signals.

[0004] To achieve the above objectives, this application proposes a method for acquiring heart sound signals. The method is applied to a wearable device for acquiring heart sound signals. The wearable device includes a bone conduction sensor and an audio acquisition device, wherein the audio acquisition device is installed within a target range of the bone conduction sensor. The method includes:

[0005] The system acquires the heart sound signal to be denoised collected by the bone voiceprint sensor and the environmental noise signal collected by the audio acquisition device.

[0006] The first heart sound signal is obtained by comparing the environmental noise signal and the heart sound signal to be denoised.

[0007] The first heart sound signal is processed according to the signal amplitude range, and the target heart sound signal is obtained based on the processing result.

[0008] In one embodiment, the step of comparing the environmental noise signal and the heart sound signal to be denoised to obtain the first heart sound signal includes:

[0009] The environmental noise signal and the heart sound signal to be denoised are aligned to obtain a first noise signal and a second heart sound signal.

[0010] The first noise signal is subjected to spectral processing to obtain the second noise signal;

[0011] The second noise signal and the second heart sound signal are subjected to difference processing to obtain the first heart sound signal.

[0012] In one embodiment, the step of aligning the ambient noise signal and the heart sound signal to be denoised to obtain a first noise signal and a second heart sound signal includes:

[0013] The phase adjustment amount is determined by calculating the cross-correlation function based on the environmental noise signal and the heart sound signal to be denoised.

[0014] The environmental noise signal and the heart sound signal to be denoised are phase-calibrated according to the phase adjustment amount to obtain a third noise signal and a third heart sound signal.

[0015] The third noise signal and the third heart sound signal are time-delayed to obtain the first noise signal and the second heart sound signal.

[0016] In one embodiment, the step of performing spectral processing on the first noise signal to obtain the second noise signal includes:

[0017] Determine the target cutoff frequency based on the frequency characteristics of the heart sound signal;

[0018] A low-pass filter is obtained by designing a filter based on the target cutoff frequency.

[0019] The first noise signal is filtered by the low-pass filter to obtain the fourth noise signal;

[0020] The gain of the fourth noise signal is adjusted to obtain the second noise signal.

[0021] In one embodiment, the step of adjusting the gain of the fourth noise signal to obtain the second noise signal includes:

[0022] The fourth noise signal was subjected to spectral analysis to obtain the spectral analysis results;

[0023] Based on the spectrum analysis results, design the gain curve and determine the gain adjustment amount for each frequency range;

[0024] The gain of the fourth noise signal is adjusted according to the gain adjustment amount in each frequency range to obtain the second noise signal.

[0025] In one embodiment, the step of processing the first heart sound signal according to the signal amplitude range and obtaining the target heart sound signal based on the processing result includes:

[0026] The first heart sound signal is filtered according to the signal amplitude range to determine the fourth heart sound signal whose signal amplitude is not within the signal amplitude range and the fifth heart sound signal whose signal amplitude is within the signal amplitude range;

[0027] The fourth heart sound signal is amplified to obtain the sixth heart sound signal;

[0028] The fifth and sixth heart sound signals are normalized to obtain the target heart sound signal.

[0029] In one embodiment, after processing the first heart sound signal according to the signal amplitude range and obtaining the target heart sound signal based on the processing result, the method further includes:

[0030] Obtain the propagation time of the first pulse wave;

[0031] The target heart sound signal is characterized by feature recognition using a target peak detection algorithm to obtain the heart sound peak points;

[0032] The proximal end of the second pulse wave propagation time is determined based on the heart sound peak point and the target time window;

[0033] Blood pressure is predicted based on the propagation time of the first pulse wave and the proximal end, and the predicted blood pressure value is determined.

[0034] Furthermore, to achieve the above objectives, this application also proposes a heart sound signal acquisition device, which includes:

[0035] The acquisition module is used to acquire the heart sound signal to be denoised collected by the bone voiceprint sensor and the environmental noise signal collected by the audio acquisition device;

[0036] The comparison module is used to compare the environmental noise signal and the heart sound signal to be denoised to obtain the first heart sound signal.

[0037] The processing module is used to process the first heart sound signal according to the signal amplitude range, and obtain the target heart sound signal according to the processing result.

[0038] In addition, to achieve the above objectives, this application also proposes a wearable device for acquiring heart sound signals, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the heart sound signal acquisition method as described above.

[0039] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the heart sound signal acquisition method described above.

[0040] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the heart sound signal acquisition method described above.

[0041] The heart sound signal acquisition method of this application is applied to a wearable heart sound signal acquisition device. The wearable device includes a bone conduction sensor and an audio acquisition device, which is installed within a target range from the bone conduction sensor. The method includes: acquiring a heart sound signal to be denoised from the bone conduction sensor and an ambient noise signal from the audio acquisition device; comparing the ambient noise signal and the heart sound signal to be denoised to obtain a first heart sound signal; processing the first heart sound signal according to the signal amplitude range; and obtaining a target heart sound signal based on the processing result. Through this method, the ambient noise signal acquired by the audio acquisition device is used to denoise the heart sound signal to be denoised, removing external environmental noise from the heart sound signal. The denoised heart sound signal is then processed using the signal amplitude range to obtain a heart sound signal that can be used for subsequent algorithm processing. This solves the problem of external noise in the heart sound signal acquired by the VPU, while also amplifying the amplitude of the heart sound signal to a range that the algorithm can effectively process, effectively reducing the training load of subsequent algorithms and improving the computational accuracy of subsequent algorithms. Attached Figure Description

[0042] 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.

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating an embodiment of the heart sound signal acquisition method of this application.

[0045] Figure 2 This is a schematic diagram of the wearable device structure for the heart sound signal acquisition method provided in Embodiment 1 of this application;

[0046] Figure 3This is a schematic diagram of the signal relationship in the heart sound signal acquisition method provided in Embodiment 1 of this application;

[0047] Figure 4 This is a flowchart illustrating Embodiment 2 of the heart sound signal acquisition method of this application;

[0048] Figure 5 This is a schematic diagram of the module structure of the heart sound signal acquisition device according to an embodiment of this application;

[0049] Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the heart sound signal acquisition method in the embodiments of this application.

[0050] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0052] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0053] The main solution of this application embodiment is: to acquire the heart sound signal to be denoised collected by the bone voiceprint sensor and the ambient noise signal collected by the audio acquisition device; to compare the ambient noise signal and the heart sound signal to be denoised to obtain a first heart sound signal; to process the first heart sound signal according to the signal amplitude range, and to obtain the target heart sound signal according to the processing result.

[0054] In theory, a bone conduction sensor (VPU) can only receive vibration signals from human bones. However, due to a series of factors such as existing VPU technology, manufacturing process, and testing methods, when using a VPU to test human signals, signals other than human bone vibration and environmental noise will be collected, which will affect the accuracy and stability of subsequent diagnosis of disease symptoms through heart sounds.

[0055] This application provides a solution that uses environmental noise signals collected by an audio acquisition device to denoise heart sound signals, removes external environmental noise from the heart sound signals, and processes the denoised heart sound signals using the signal amplitude range, thereby obtaining heart sound signals that can be used for subsequent algorithm processing. This solves the problem of external noise in the heart sound signals collected by the VPU, and also amplifies the amplitude of the heart sound signals to a range that the algorithm can effectively process, effectively reducing the training load of subsequent algorithms and improving the computational accuracy of subsequent algorithms.

[0056] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a wearable device for collecting heart sounds that can perform the above functions. The following description uses a wearable device for collecting heart sounds as the executing entity to illustrate this embodiment and the subsequent embodiments.

[0057] Based on this, this application provides a method for acquiring heart sound signals, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the heart sound signal acquisition method of this application.

[0058] In this embodiment, the method is applied to a wearable device for acquiring heart sound signals. The wearable device includes a bone conduction sensor and an audio acquisition device. The audio acquisition device is installed within a target range of the bone conduction sensor. The method includes steps S10 to S30:

[0059] Step S10: Obtain the heart sound signal to be denoised collected by the bone voiceprint sensor and the environmental noise signal collected by the audio acquisition device.

[0060] It should be noted that, in this embodiment, the wearable device for acquiring heart sound signals includes a VPU and an audio acquisition device. In this embodiment, the audio acquisition device can be a noise-canceling microphone or other noise-canceling audio acquisition device. The wearable device for acquiring heart sound signals is as follows: Figure 2 As shown, the VPU is fixed to the skin contact portion of the heart sound signal acquisition wearable device using a flexible material. There is no bottom shell in the area where the VPU is fixed; only the flexible material for fixing the VPU exists there. The audio acquisition device is located inside the bottom shell of the heart sound signal acquisition wearable device, installed within a target range from the VPU, ensuring the audio acquisition device is near the VPU. In this embodiment, the flexible material can be soft rubber or other materials with high flexibility and deformability. The flexibility allows for significant deformation under external force without easily breaking, and it can recover or partially recover its original shape after the external force is removed. In this embodiment, the VPU picks up heart sound vibration signals and external noise signals during signal acquisition. The flexible material helps the VPU acquire heart sound vibration signals; the audio acquisition device is used to pick up environmental noise signals other than heart sound vibration signals.

[0061] It is understood that when a user collects heart sound signals through a wearable heart sound signal acquisition device, the device acquires the heart sound vibration signal containing external noise signals collected by the VPU and the environmental noise signal collected by the audio acquisition device. In this embodiment, the heart sound signal to be denoised refers to the heart sound vibration signal containing external noise signals.

[0062] Step S20: Compare the environmental noise signal and the heart sound signal to be denoised to obtain the first heart sound signal.

[0063] It should be noted that the ambient noise signal and the heart sound signal to be denoised are aligned; the aligned ambient noise signal undergoes spectral processing, including but not limited to low-pass filtering and gain adjustment, to improve the quality of the ambient noise signal, reduce noise, and enhance the useful signal; the processed ambient noise signal and the aligned heart sound signal to be denoised are then subjected to difference processing to eliminate common background noise and interference, thereby extracting the heart sound vibration signal free of external noise. In this embodiment, the heart sound vibration signal free of external noise is the first heart sound signal.

[0064] Step S30: Process the first heart sound signal according to the signal amplitude range, and obtain the target heart sound signal according to the processing result.

[0065] It should be noted that the signal amplitude range is a pre-defined range of signal strength. Within this range, the machine learning algorithm can effectively process the heart sound signal. The first heart sound signal is processed using the signal amplitude range; heart sound signals with amplitudes smaller than the range are amplified, and the amplitude of the amplified first heart sound signal is normalized to obtain the target heart sound signal.

[0066] In one feasible implementation, step S30 may include steps A11 to A13:

[0067] Step A11: Filter the first heart sound signal according to the signal amplitude range to determine the fourth heart sound signal whose signal amplitude is not within the signal amplitude range and the fifth heart sound signal whose signal amplitude is within the signal amplitude range.

[0068] Step A12: Amplify the fourth heart sound signal to obtain the sixth heart sound signal.

[0069] Step A13: Normalize the fifth heart sound signal and the sixth heart sound signal to obtain the target heart sound signal.

[0070] It should be noted that due to individual user differences, the quality of heart sound signals varies for each person, and the signal processing range of machine learning algorithms is limited; there are cases where the algorithm cannot effectively identify signals with excessively small amplitudes. Therefore, in this embodiment, the first heart sound signal is filtered based on its amplitude range to obtain heart sound signals whose amplitude is less than the lower limit of the amplitude range. In this embodiment, the fourth heart sound signal refers to a heart sound signal whose amplitude is less than the lower limit of the amplitude range; the fourth heart sound signal is not within the amplitude range.

[0071] It is understood that heart sound signals with amplitudes greater than the upper limit of the signal amplitude range and fifth heart sound signals with amplitudes within the signal amplitude range are not processed; the fourth heart sound signal is amplified, and the amplification process can be performed using any of the following methods: proportional method, adaptive filtering algorithm, and others. In this embodiment, the sixth heart sound signal refers to the amplified fourth heart sound signal.

[0072] In the specific implementation, the fifth heart sound signal, the sixth heart sound signal, and the heart sound signal whose amplitude is greater than the upper limit of the signal amplitude range are normalized to unify the amplitude of the heart sound signals to the same scale, thereby obtaining the target heart sound signal that can be used for subsequent algorithm processing.

[0073] In one feasible implementation, steps B11 to B14 may be included after step S30:

[0074] Step B11: Obtain the propagation time of the first pulse wave.

[0075] Step B12: The target heart sound signal is characterized by feature recognition using a target peak detection algorithm to obtain the heart sound peak point.

[0076] Step B13: Determine the proximal end of the second pulse wave propagation time based on the heart sound peak point and the target time window.

[0077] Step B14: Based on the propagation time of the first pulse wave and the proximal end, predict the blood pressure and determine the predicted blood pressure value.

[0078] It should be noted that current blood pressure testing algorithms based on heart sound signals all employ machine learning, feeding a large amount of raw signals into the training model and obtaining results through extensive training and validation. Currently, these algorithms cannot accurately calculate heart sound blood pressure. This is partly because some heart sound signals are weak or of poor quality, often submerged in noise, making them difficult for the algorithm to identify. It is also because the waveforms of heart sound signals vary considerably, and the algorithm's data volume cannot fully cover all of them, hindering training with large datasets. The algorithm requires extensive data training, and its signal processing range is limited; it cannot effectively identify signals with excessively small amplitudes. However, by inputting the target heart sound signal from this embodiment into the algorithm, a stable calculation result can be obtained.

[0079] It is understandable that the first pulse wave propagation time refers to PWTT1, a measured value of pulse wave propagation time. PWTT1 refers to the time from the start of cardiac contraction to the pulse wave reaching a certain distal position, and its source can be either an electrocardiogram signal or a pulse wave signal. Using a target peak detection algorithm, the first heart sound peak point of the target heart sound signal is accurately identified. Within the target time window near the first heart sound peak point, the proximal end of the second pulse wave propagation time PWTT2 is determined. Using a regression model combining the proximal end and PWTT1, blood pressure prediction can be performed, yielding the corresponding predicted blood pressure value. For example... Figure 3 As shown, the first heart sound peak point S1 Peak 214 can be identified by the target heart sound signal PCG. S1 is the sound emitted at the beginning of heart contraction, and S2 is the sound emitted during heart diastole. The peak value PPG Peak 213 of the pulse wave signal can be obtained by the pulse wave signal PPG, thereby obtaining the pulse wave propagation time PWTT1. By combining the proximal end of PWTT2 and PWTT1 through a regression model, the blood pressure value can be calculated.

[0080] In this embodiment, by combining a VPU and an audio acquisition device with the processing method described herein, the target heart sound signal can be effectively extracted, no longer affected by external factors such as the gender, weight, or body structure of the test population. As long as the human body has a normal heartbeat, the heart sound signal can be extracted, eliminating the need for frequent adjustments to the device's testing position to find the optimal heart sound test point. By normalizing the heart sound signal amplitude, even if the extracted heart sound signal is weak, it can be amplified to an amplitude range that the algorithm can effectively process, improving the algorithm's feature point recognition accuracy and processing capability, and simplifying the computational load of the algorithm's original data. This also simplifies the algorithm's training workload, eliminating the need to train the algorithm model by finding different populations with different heart sound signals.

[0081] The heart sound signal acquisition method of this embodiment is applied to a wearable heart sound signal acquisition device. The wearable heart sound signal acquisition device includes a bone conduction sensor and an audio acquisition device. The bone conduction sensor is fixed to the skin contact portion of the wearable heart sound signal acquisition device using a flexible material. The audio acquisition device is installed within a target range from the bone conduction sensor. The method includes: acquiring a heart sound signal to be denoised acquired by the bone conduction sensor and an environmental noise signal acquired by the audio acquisition device; comparing the environmental noise signal and the heart sound signal to be denoised to obtain a first heart sound signal; processing the first heart sound signal according to the signal amplitude range; and obtaining a target heart sound signal based on the processing result. Through the above method, the heart sound signal to be denoised is denoised based on the environmental noise signal acquired by the audio acquisition device, removing external environmental noise from the heart sound signal. The denoised heart sound signal is then processed using the signal amplitude range to obtain a heart sound signal that can be used for subsequent algorithm processing. This solves the problem of external noise in the heart sound signal acquired by the VPU, while also amplifying the amplitude of the heart sound signal to a range that the algorithm can effectively process, effectively reducing the training load of subsequent algorithms and improving the computational accuracy of subsequent algorithms.

[0082] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 The heart sound signal acquisition method further includes steps S21 to S23 in step S20:

[0083] Step S21: Align the environmental noise signal and the heart sound signal to be denoised to obtain a first noise signal and a second heart sound signal.

[0084] It should be noted that signal alignment includes, but is not limited to, alignment operations such as signal phase adjustment and signal delay adjustment, to ensure that the ambient noise signal and the heart sound signal to be denoised are synchronized in time. In this embodiment, the first noise signal refers to the aligned ambient noise signal, and the second heart sound signal refers to the aligned heart sound signal to be denoised.

[0085] In one feasible implementation, step S21 may include steps C11 to C13:

[0086] Step C11: Calculate the phase adjustment amount by performing a cross-correlation function based on the environmental noise signal and the heart sound signal to be denoised.

[0087] Step C12: Perform phase calibration processing on the environmental noise signal and the heart sound signal to be denoised according to the phase adjustment amount to obtain the third noise signal and the third heart sound signal.

[0088] Step C13: Adjust the time delay of the third noise signal and the third heart sound signal to obtain the first noise signal and the second heart sound signal.

[0089] It should be noted that the cross-correlation function of the ambient noise signal and the heart sound signal to be denoised is calculated to determine the time delay corresponding to the maximum correlation value, thereby determining the phase adjustment amount. A Fourier transform is then used to convert either the ambient noise signal or the heart sound signal to be denoised to the frequency domain, and the phase adjustment amount is applied to the frequency-domain adjusted signal to align it with the other signal. Then, the adjusted heart sound signal to be denoised or the adjusted ambient noise signal is inversely transformed to the time domain to obtain the phase-adjusted ambient noise signal and the heart sound signal to be denoised. In this embodiment, the third noise signal refers to the phase-adjusted ambient noise signal, and the third heart sound signal refers to the phase-adjusted heart sound signal to be denoised.

[0090] Understandably, to ensure that the heart sounds corresponding to the third heart sound signal and the third noise signal are synchronized at the same time point and to reduce signal distortion caused by time difference, the third noise signal and the third heart sound signal can be time-delayed by any of the following methods: time-domain shifting, interpolation, or other methods, thereby obtaining the time-delayed third noise signal and the time-delayed third heart sound signal. In this embodiment, the first noise signal refers to the time-delayed third noise signal, and the second heart sound signal refers to the time-delayed third heart sound signal.

[0091] Step S22: Perform spectrum processing on the first noise signal to obtain the second noise signal.

[0092] It should be noted that spectrum processing includes, but is not limited to, low-pass filtering and gain adjustment, to improve the quality of ambient noise signals and enhance useful signals. In this embodiment, the second noise signal refers to the first noise signal after spectrum processing.

[0093] In one feasible implementation, step S22 may include steps D11 to D14:

[0094] Step D11: Determine the target cutoff frequency based on the frequency characteristics of the heart sound signal.

[0095] Step D12: Design a filter based on the target cutoff frequency to obtain a low-pass filter.

[0096] Step D13: The first noise signal is filtered by the low-pass filter to obtain the fourth noise signal.

[0097] It should be noted that heart sound signals are mainly concentrated in the frequency band below 200Hz. A corresponding target cutoff frequency can be designed based on the frequency characteristics of the heart sound signals. Using digital signal processing software, a low-pass filter can be designed in conjunction with the target cutoff frequency. The type of low-pass filter includes, but is not limited to, finite impulse response (FIR) filters and infinite impulse response (IR) filters. By applying the designed low-pass filter to the first noise signal, high-frequency noise is effectively removed, and interference is reduced, thus obtaining the low-pass filtered first noise signal. In this embodiment, the fourth noise signal refers to the low-pass filtered first noise signal.

[0098] Step D14: Adjust the gain of the fourth noise signal to obtain the second noise signal.

[0099] It should be noted that, in order to balance the energy distribution of the signal, the gain of different frequency components of the fourth noise signal is adjusted to obtain the adjusted fourth noise signal. In this embodiment, the fourth noise signal after gain adjustment is the second noise signal.

[0100] In one feasible implementation, step D14 may include steps E11 to E13:

[0101] Step E11: Perform spectrum analysis on the fourth noise signal to obtain the spectrum analysis results.

[0102] Step E12: Design a gain curve based on the spectrum analysis results and determine the gain adjustment amount in each frequency range.

[0103] Step E13: Adjust the gain of the fourth noise signal according to the gain adjustment amount in each frequency range to obtain the second noise signal.

[0104] It should be noted that a spectral analysis was performed on the fourth noise signal to determine its energy distribution across different frequency ranges, thus obtaining the corresponding spectral analysis results. Based on these results, a gain curve was designed to enhance the low-frequency range containing the heart sound signal and suppress high-frequency noise, thereby determining the gain adjustment amounts for different frequency ranges. The gain of the fourth noise signal was then adjusted according to the gain adjustment amounts for each frequency range to obtain the second noise signal.

[0105] Step S23: Perform difference processing on the second noise signal and the second heart sound signal to obtain the first heart sound signal.

[0106] It should be noted that the difference between the second noise signal and the second heart sound signal is calculated to eliminate common background noise and interference, and the heart sound vibration signal that does not contain external noise signals is extracted from the second heart sound signal to obtain the first heart sound signal.

[0107] This embodiment obtains a first noise signal and a second heart sound signal by aligning the ambient noise signal and the heart sound signal to be denoised; performs spectral processing on the first noise signal to obtain a second noise signal; and performs difference processing on the second noise signal and the second heart sound signal to obtain the first heart sound signal. The first heart sound signal can be accurately obtained through this method.

[0108] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the heart sound signal acquisition method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0109] This application also provides a heart sound signal acquisition device, please refer to... Figure 5 The heart sound signal acquisition device includes:

[0110] The acquisition module 10 is used to acquire the heart sound signal to be denoised collected by the bone voiceprint sensor and the environmental noise signal collected by the audio acquisition device.

[0111] The comparison module 20 is used to compare the environmental noise signal and the heart sound signal to be denoised to obtain the first heart sound signal.

[0112] The processing module 30 is used to process the first heart sound signal according to the signal amplitude range, and obtain the target heart sound signal according to the processing result.

[0113] Optionally, the comparison module 20 is further configured to:

[0114] The environmental noise signal and the heart sound signal to be denoised are aligned to obtain a first noise signal and a second heart sound signal; the first noise signal is subjected to spectral processing to obtain a second noise signal; the second noise signal and the second heart sound signal are subjected to difference processing to obtain a first heart sound signal.

[0115] Optionally, the comparison module 20 is further configured to:

[0116] The phase adjustment amount is determined by calculating the cross-correlation function of the ambient noise signal and the heart sound signal to be denoised; the phase adjustment amount is then used to perform phase calibration processing on the ambient noise signal and the heart sound signal to be denoised to obtain a third noise signal and a third heart sound signal; the third noise signal and the third heart sound signal are then subjected to time delay adjustment to obtain a first noise signal and a second heart sound signal.

[0117] Optionally, the comparison module 20 is further configured to:

[0118] The target cutoff frequency is determined based on the frequency characteristics of the heart sound signal; a filter is designed based on the target cutoff frequency to obtain a low-pass filter; the first noise signal is filtered by the low-pass filter to obtain a fourth noise signal; the gain of the fourth noise signal is adjusted to obtain a second noise signal.

[0119] Optionally, the comparison module 20 is further configured to:

[0120] The fourth noise signal is subjected to spectral analysis to obtain the spectral analysis results; a gain curve is designed based on the spectral analysis results to determine the gain adjustment amount in each frequency range; the fourth noise signal is adjusted according to the gain adjustment amount in each frequency range to obtain the second noise signal.

[0121] Optionally, the comparison module 30 is further configured to:

[0122] The first heart sound signal is filtered according to the signal amplitude range to determine the fourth heart sound signal whose signal amplitude is not within the signal amplitude range and the fifth heart sound signal whose signal amplitude is within the signal amplitude range; the fourth heart sound signal is amplified to obtain the sixth heart sound signal; the fifth heart sound signal and the sixth heart sound signal are normalized to obtain the target heart sound signal.

[0123] Optionally, the comparison module 30 is further configured to:

[0124] The first pulse wave propagation time is obtained; the target heart sound signal is characterized by a target peak detection algorithm to obtain the heart sound peak point; the proximal end of the second pulse wave propagation time is determined based on the heart sound peak point and the target time window; blood pressure is predicted based on the first pulse wave propagation time and the proximal end to determine the predicted blood pressure value.

[0125] The heart sound signal acquisition device provided in this application, employing the heart sound signal acquisition method described in the above embodiments, can solve the technical problem in the prior art where external noise signals exist during heart sound signal acquisition, leading to the inability to perform accurate feature recognition based on the heart sound signals. Compared with the prior art, the beneficial effects of the heart sound signal acquisition device provided in this application are the same as those of the heart sound signal acquisition method provided in the above embodiments, and other technical features in the heart sound signal acquisition device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0126] This application provides a wearable device for acquiring heart sound signals, wherein a bone conduction sensor is fixed to the skin contact portion of the heart sound signal acquisition device by a flexible material. The wearable device for acquiring heart sound signals includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the heart sound signal acquisition method in the above embodiment 1.

[0127] The following is for reference. Figure 6 The diagram illustrates a structural schematic suitable for implementing the wearable heart sound signal acquisition device in the embodiments of this application. The wearable heart sound signal acquisition device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The wearable device for collecting heart sounds shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0128] like Figure 6As shown, the wearable heart sound signal acquisition device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the wearable heart sound signal acquisition device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the heart sound signal acquisition wearable device to wirelessly or wiredly communicate with other devices to exchange data. Although the figure shows a heart sound signal acquisition wearable device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0129] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0130] The wearable heart sound signal acquisition device provided in this application, employing the heart sound signal acquisition method described in the above embodiments, can solve the technical problem in the prior art where external noise signals exist during heart sound signal acquisition, leading to the inability to perform accurate feature recognition based on the heart sound signals. Compared with the prior art, the beneficial effects of the wearable heart sound signal acquisition device provided in this application are the same as those of the heart sound signal acquisition method provided in the above embodiments, and other technical features in this wearable heart sound signal acquisition device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0131] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0132] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0133] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the heart sound signal acquisition method in the above embodiments.

[0134] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0135] The aforementioned computer-readable storage medium may be included in the wearable device for acquiring heart sound signals; or it may exist independently and not assembled into the wearable device for acquiring heart sound signals.

[0136] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the heart sound signal acquisition wearable device, the heart sound signal acquisition wearable device causes the following to occur: acquire the heart sound signal to be denoised acquired by the bone conduction sensor and the ambient noise signal acquired by the audio acquisition device; perform signal comparison based on the ambient noise signal and the heart sound signal to be denoised to obtain a first heart sound signal; process the first heart sound signal according to the signal amplitude range, and obtain a target heart sound signal based on the processing result.

[0137] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0138] 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 code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0139] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0140] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described heart sound signal acquisition method. This solves the technical problem in the prior art where external noise signals exist during heart sound signal acquisition, preventing accurate feature recognition based on the heart sound signals. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the heart sound signal acquisition method provided in the above embodiments, and will not be repeated here.

[0141] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the heart sound signal acquisition method described above.

[0142] The computer program product provided in this application can solve the technical problem that external noise signals exist during the acquisition of heart sound signals in the prior art, which makes it impossible to perform accurate feature recognition based on the heart sound signals. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the heart sound signal acquisition method provided in the above embodiments, and will not be repeated here.

[0143] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for acquiring heart sound signals, characterized in that, The heart sound signal acquisition method is applied to a wearable heart sound signal acquisition device, which includes a bone conduction sensor and an audio acquisition device. The audio acquisition device is installed within a target range of the bone conduction sensor. The method includes: The system acquires the heart sound signal to be denoised collected by the bone voiceprint sensor and the environmental noise signal collected by the audio acquisition device. The first heart sound signal is obtained by comparing the environmental noise signal and the heart sound signal to be denoised. The first heart sound signal is processed according to the signal amplitude range, and the target heart sound signal is obtained based on the processing result; The step of processing the first heart sound signal according to the signal amplitude range and obtaining the target heart sound signal according to the processing result includes: The first heart sound signal is filtered according to the signal amplitude range to determine the fourth heart sound signal whose signal amplitude is not within the signal amplitude range and the fifth heart sound signal whose signal amplitude is within the signal amplitude range. The signal amplitude range represents the effective processing range of the machine learning algorithm for the heart sound signal. The fourth heart sound signal is amplified to obtain the sixth heart sound signal; The fifth and sixth heart sound signals are normalized to obtain the target heart sound signal.

2. The method as described in claim 1, characterized in that, The step of comparing the environmental noise signal and the heart sound signal to be denoised to obtain the first heart sound signal includes: The environmental noise signal and the heart sound signal to be denoised are aligned to obtain a first noise signal and a second heart sound signal. The first noise signal is subjected to spectral processing to obtain the second noise signal; The second noise signal and the second heart sound signal are subjected to difference processing to obtain the first heart sound signal.

3. The method as described in claim 2, characterized in that, The step of aligning the environmental noise signal and the heart sound signal to be denoised to obtain a first noise signal and a second heart sound signal includes: The phase adjustment amount is determined by calculating the cross-correlation function based on the environmental noise signal and the heart sound signal to be denoised. The environmental noise signal and the heart sound signal to be denoised are phase-calibrated according to the phase adjustment amount to obtain a third noise signal and a third heart sound signal. The third noise signal and the third heart sound signal are time-delayed to obtain the first noise signal and the second heart sound signal.

4. The method as described in claim 2, characterized in that, The step of performing spectral processing on the first noise signal to obtain the second noise signal includes: Determine the target cutoff frequency based on the frequency characteristics of the heart sound signal; A low-pass filter is obtained by designing a filter based on the target cutoff frequency. The first noise signal is filtered by the low-pass filter to obtain the fourth noise signal; The gain of the fourth noise signal is adjusted to obtain the second noise signal.

5. The method as described in claim 4, characterized in that, The step of adjusting the gain of the fourth noise signal to obtain the second noise signal includes: The fourth noise signal was subjected to spectral analysis to obtain the spectral analysis results; Based on the spectrum analysis results, design the gain curve and determine the gain adjustment amount for each frequency range; The gain of the fourth noise signal is adjusted according to the gain adjustment amount in each frequency range to obtain the second noise signal.

6. The method according to any one of claims 1 to 5, characterized in that, After the step of processing the first heart sound signal according to the signal amplitude range and obtaining the target heart sound signal according to the processing result, the method further includes: Obtain the propagation time of the first pulse wave; The target heart sound signal is characterized by feature recognition using a target peak detection algorithm to obtain the heart sound peak points; The proximal end of the second pulse wave propagation time is determined based on the heart sound peak point and the target time window; Blood pressure is predicted based on the propagation time of the first pulse wave and the proximal end, and the predicted blood pressure value is determined.

7. A heart sound signal acquisition device, characterized in that, The heart sound signal acquisition device includes: The acquisition module is used to acquire the heart sound signal to be denoised collected by the bone voiceprint sensor and the environmental noise signal collected by the audio acquisition device; The comparison module is used to compare the environmental noise signal and the heart sound signal to be denoised to obtain the first heart sound signal. The processing module is used to process the first heart sound signal according to the signal amplitude range, and obtain the target heart sound signal according to the processing result; The processing module is further configured to: The first heart sound signal is filtered according to the signal amplitude range to determine the fourth heart sound signal whose signal amplitude is not within the signal amplitude range and the fifth heart sound signal whose signal amplitude is within the signal amplitude range. The signal amplitude range represents the effective processing range of the machine learning algorithm for the heart sound signal. The fourth heart sound signal is amplified to obtain the sixth heart sound signal; The fifth and sixth heart sound signals are normalized to obtain the target heart sound signal.

8. A wearable device for acquiring heart sound signals, characterized in that, The wearable device for acquiring heart sounds includes a bone conduction sensor, which is fixed to the skin contact portion of the wearable device by a flexible material. The wearable device for acquiring heart sounds also includes a memory, a processor, and a heart sound acquisition program stored in the memory and executable on the processor. The heart sound acquisition program is configured to implement the heart sound acquisition method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a heart sound signal acquisition program, which, when executed by a processor, implements the heart sound signal acquisition method as described in any one of claims 1 to 6.

Images