Signal denoising processing method and device, auscultation device and storage medium

Abstract

The application relates to the technical field of signal processing, in particular to a signal denoising processing method and device, a auscultation device and a storage medium, which are applied to a stethoscope comprising a body sound signal module and an environment signal module. A body sound sound inlet hole of the body sound signal module is attached to a sound collecting cavity shell, the body sound sound inlet hole is communicated with a sound collecting hole arranged on the sound collecting cavity shell, and a noise sound inlet hole of the environment signal module is arranged on the sound collecting cavity shell in a reverse direction. After a sound collecting cavity of the stethoscope is contacted with a human body surface of a target user to form a closed space, a body sound signal collected by the body sound signal module and an environment noise signal collected by the environment signal module are acquired. The body sound signal is subjected to signal filtering processing, a body sound target signal is determined according to the obtained body sound filtered signal and a sound pickup angle of the body sound signal module, and a body sound real signal is determined according to the body sound target signal and the environment noise signal. The application aims to improve the denoising processing capability of the stethoscope to improve the accuracy of auscultation.

Description

Technical Field

[0001] This application relates to the field of signal processing technology, and in particular to a signal noise reduction processing method, apparatus, auscultation device, and storage medium. Background Technology

[0002] With the continuous development of medical technology and signal processing technology, electronic intelligent stethoscopes have become an indispensable tool in modern medical diagnosis.

[0003] Currently available electronic stethoscopes mainly feature heart and lung sound acquisition and simple noise reduction functions, but their auscultation effectiveness is still severely affected by environmental noise. Furthermore, while electronic stethoscopes can amplify weak body sound signals (such as heart and lung sounds), their high sensitivity makes them susceptible to interference from environmental noise, thus reducing diagnostic accuracy.

[0004] Therefore, improving the noise reduction capabilities of stethoscopes to enhance the accuracy of auscultation is a pressing technical problem that needs to be solved. Summary of the Invention

[0005] The main objective of this application is to provide a signal noise reduction processing method, device, auscultation equipment, and storage medium, which aims to improve the noise reduction processing capability of the stethoscope to enhance the accuracy of auscultation.

[0006] To achieve the above objectives, this application provides a signal noise reduction processing method. The signal noise reduction processing method is applied to a stethoscope including a body sound signal module and an environmental signal module. The body sound inlet of the body sound signal module is attached to the sound receiving cavity shell of the stethoscope. The body sound inlet is connected to the sound receiving hole provided on the sound receiving cavity shell. The noise inlet of the environmental signal module is disposed opposite to the sound receiving cavity shell.

[0007] The signal noise reduction processing method includes:

[0008] After the stethoscope's sound-receiving cavity comes into contact with the target user's body surface to form a sealed space, the body sound signal collected by the body sound signal module and the environmental noise signal collected by the environmental signal module are acquired.

[0009] The body sound signal is filtered to obtain a body sound filtered signal, and the body sound target signal is determined based on the body sound filtered signal and the pickup angle of the body sound signal module.

[0010] The actual body sound signal is determined based on the target body sound signal and the environmental noise signal.

[0011] In one embodiment, the body sound signal module includes a first body sound sensor and a second body sound sensor arranged side by side at preset distance intervals, and the step of determining the body sound target signal based on the body sound filter signal and the pickup angle of the body sound signal module includes:

[0012] Based on the first pickup angle region of the first body sound sensor and the second pickup angle region of the second body sound sensor, the pickup angle of the body sound signal module is constructed, and the signal acquisition frequency band of the pickup angle is determined.

[0013] Find the signal frequency band that is the same as the signal acquisition frequency band from the overall signal frequency band of the body sound filtering signal, and take the body sound filtering signal corresponding to the signal frequency band that is the same as the signal acquisition frequency band as the body sound target signal.

[0014] In one embodiment, the step of constructing the pickup angle of the body sound signal module based on the first pickup angle region of the first body sound sensor and the second pickup angle region of the second body sound sensor includes:

[0015] Determine the first pickup angle region of the first body sound sensor and the second pickup angle region of the second body sound sensor, and obtain the pickup intersection region formed by the first pickup angle region and the second pickup angle region;

[0016] The pickup intersection angle value of the pickup intersection region is obtained by subtracting the minimum pickup angle value of the pickup intersection region from the maximum pickup angle value of the pickup intersection region.

[0017] Taking the midpoint between the first body sound sensor and the second body sound sensor as the origin, and the central axis of the sensor passing through the origin as the angle bisector, an angle region with the same angle value as the sound pickup intersection angle is constructed in the sound receiving cavity as the sound pickup angle of the body sound signal module.

[0018] In one embodiment, the step of determining the actual body sound signal based on the target body sound signal and the environmental noise signal includes:

[0019] Determine the noise threshold of the environmental noise signal and the body sound threshold of the body sound target signal;

[0020] The negative of the noise threshold is superimposed onto the body sound threshold according to the preset pickup cavity transfer function to obtain the body sound prediction signal of the body sound signal module;

[0021] The body sound prediction signal is Gaussian transformed into the body sound observation signal of the body sound signal module, and it is detected whether the body sound prediction signal is within the signal observation threshold range corresponding to the body sound observation signal;

[0022] If the predicted body sound signal is within the range of the signal observation threshold, then the predicted body sound signal is taken as the true body sound signal.

[0023] In one embodiment, the step of Gaussian transforming the body sound prediction signal into the body sound observation signal of the body sound signal module includes:

[0024] Determine multiple signal frequency values ​​of the body sound prediction signal within a preset acquisition time;

[0025] The mean value of each signal frequency value is obtained by performing mean processing on each signal frequency value, and the variance value of each signal frequency value is obtained by performing variance processing on the squared difference between each signal frequency value and the mean value.

[0026] Gaussian transformation is performed based on the frequency mean and the frequency variance to obtain the body sound observation signal of the body sound signal module.

[0027] In one embodiment, after the step of detecting whether the body sound prediction signal is within the signal observation threshold range corresponding to the body sound observation signal, the signal noise reduction processing method includes:

[0028] If the predicted body sound signal is not within the range of the signal observation threshold, determine multiple signal observation frequency values ​​of the body sound observation signal within the acquisition time, and determine the total observation frequency value between each of the signal observation frequency values, as well as the total signal frequency value between each of the signal frequency values.

[0029] Based on the divisor quotient between the total signal frequency and the total observed frequency, a log-likelihood value is calculated to obtain the adjustment function of the body sound signal module;

[0030] The adjustment function is used as the next pickup cavity transfer function, and the step of adding the negative of the noise threshold to the body sound threshold according to the preset pickup cavity transfer function is returned.

[0031] In one embodiment, after the step of determining the true body sound signal based on the target body sound signal and the ambient noise signal, the signal noise reduction processing method further includes:

[0032] The actual body sound signal is input into a preset auscultation record model for model training to obtain the auscultation record report of the target user, and the health results of the auscultation record report are displayed to the target user.

[0033] Furthermore, to achieve the above objectives, this application also provides a signal noise reduction processing device. This device is applied to a stethoscope including a body sound signal module and an environmental signal module. The body sound inlet of the body sound signal module is attached to the outer shell of the stethoscope's sound-receiving cavity, and the body sound inlet is connected to the sound-receiving hole provided on the sound-receiving cavity shell. The noise inlet of the environmental signal module is disposed opposite to the sound-receiving cavity shell. The signal noise reduction processing device includes:

[0034] The acquisition module is used to acquire the body sound signal collected by the body sound signal module and the environmental noise signal collected by the environmental signal module after the sound receiving cavity of the stethoscope comes into contact with the human body surface of the target user to form a closed space.

[0035] The filtering module is used to perform signal filtering processing on the body sound signal to obtain a body sound filtered signal, and to determine the body sound target signal based on the body sound filtered signal and the pickup angle of the body sound signal module.

[0036] The real signal determination module is used to determine the real body sound signal based on the target body sound signal and the environmental noise signal.

[0037] Each functional module of the signal noise reduction processing device of this application implements the steps of the signal noise reduction processing method of this application as described above during operation.

[0038] In addition, to achieve the above objectives, this application also provides an auscultation device, which includes a memory, a processor, and a signal noise reduction processing program stored in the memory and executable on the processor. When the signal noise reduction processing program is executed by the processor, it implements the steps of the above-described signal noise reduction processing method.

[0039] In addition, to achieve the above objectives, this application also provides a storage medium, which is a computer-readable storage medium, and stores a signal noise reduction processing program thereon. When the signal noise reduction processing program is executed by a processor, it implements the steps of the above-described signal noise reduction processing method.

[0040] This application provides a signal noise reduction processing method that optimizes the noise reduction capabilities of existing stethoscopes. Specifically, the body sound signal module of this application has its body sound inlet hole attached to the outer shell of the stethoscope's sound-receiving cavity and connected to the sound-receiving hole on the sound-receiving cavity shell. Next, after the stethoscope's sound-receiving cavity forms a sealed space with the target user's body surface, the hole design connecting the body sound inlet hole and the sound-receiving hole effectively reduces the loss and distortion of the body sound signal during transmission, ensuring that the body sound signal module can accurately collect the body sound signal. Simultaneously, the structure of the environmental signal module's noise inlet hole facing away from the sound-receiving cavity shell allows the environmental signal module to clearly capture surrounding environmental noise signals, thus avoiding interference with the body sound signal. The sound signal is confused; subsequently, the body sound signal is effectively filtered to obtain a clearer and purer filtered body sound signal. Combined with the pickup angle, which reflects the signal receiving and radiation range of the body sound signal module, a more accurate and clear target body sound signal can be determined, effectively eliminating signal interference outside the signal receiving and radiation range. Finally, the environmental noise signal collected by the environmental signal module cancels out the noise part in the target body sound signal, thereby obtaining an accurate true body sound signal, effectively improving the signal-to-noise ratio of the body sound signal, thus significantly improving the stethoscope's noise reduction processing capability, and thus enhancing the accuracy of auscultation. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating the first embodiment of the signal noise reduction processing method of this application;

[0042] Figure 2 This is a schematic diagram of the stethoscope microphone assembly structure involved in the embodiments of this application;

[0043] Figure 3 This is a block diagram of the stethoscope system involved in the embodiments of this application;

[0044] Figure 4 This is a schematic diagram of a dual-microphone pickup array involved in the embodiments of this application;

[0045] Figure 5 This is a block diagram illustrating the active noise reduction principle of the embodiments of this application;

[0046] Figure 6 This is a schematic diagram of the signal noise reduction processing device involved in the embodiments of this application;

[0047] Figure 7 This is a schematic diagram of the auscultation device involved in the embodiments of this application.

[0048] Explanation of icon numbers:

[0049] 10. Body sound signal module; 20. Environmental signal module; 101. First body sound sensor; 102. Second body sound sensor.

[0050] The realization of the purpose, functional 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] This application provides a signal noise reduction processing method, referring to... Figure 1 As shown, Figure 1 This is a flowchart illustrating the first embodiment of the signal noise reduction processing method of this application.

[0052] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0053] Current electronic smart stethoscopes on the market only support simple heart and lung sound acquisition or single noise reduction functions. Adding multiple active noise reduction methods would greatly improve the auscultation effect.

[0054] Traditional electronic stethoscopes amplify weak body sound signals and have functions such as signal storage, display, and playback, greatly facilitating doctors' auscultation. However, due to their high sensitivity, they are also very susceptible to interference from environmental noise. To reduce the stethoscope's sensitivity to environmental noise, piezoelectric film pickups can be used. Piezoelectric film pickups collect displacement signals, thus they are less susceptible to environmental noise interference. However, to ensure sensitivity, the stethoscope head requires a specific structural design, resulting in high costs and making it difficult to promote to home users. Current electronic stethoscopes generally use electret microphones for sound pickup, which have advantages such as simple structural design and low cost. In other words, electret microphones are one of the preferred sensors for existing electronic stethoscopes. However, electret microphones are very sensitive and are easily affected by environmental noise even when encapsulated in a metal cavity.

[0055] To reduce the impact of environmental noise, one of the most common noise reduction methods for such applications is dual-microphone adaptive filtering. This method uses a main microphone to collect the noisy signal and a secondary microphone to collect the ambient noise. The ambient noise measured by the secondary microphone is linearly processed and then used to cancel out the noise in the noisy signal, thus achieving noise reduction. Due to its strong noise reduction capabilities, dual-microphone adaptive filtering has been widely used in remote conferencing, mobile phones, and many other applications. However, the widespread adoption of dual-microphone adaptive filtering in electronic stethoscopes faces the following disadvantages:

[0056] (i) Currently, products with dual-microphone adaptive filtering are either too large or too expensive; however, electronic stethoscopes need to be easy to move and handheld, which limits their size; in order to promote and apply them, the cost of electronic stethoscopes should not be too high.

[0057] (ii) When using mobile healthcare to achieve remote auscultation, mobile phones are usually used as signal receiving terminals. Common access methods include audio port and Bluetooth. However, when Bluetooth mobile phones are connected to other Bluetooth headsets or wristbands, manual switching and pairing are required. Furthermore, Bluetooth signal transmission bandwidth and speed are relatively low, making it difficult to meet the needs of high-quality audio signal transmission.

[0058] To address the technical shortcomings of existing electronic stethoscopes, which are susceptible to interference from environmental noise and have difficulty accurately identifying body sound signals, this application provides a signal noise reduction processing method, apparatus, stethoscope device, and storage medium.

[0059] The signal noise reduction processing method of this application is applied to a stethoscope including a body sound signal module 10 and an environmental signal module 20, or is executed by a stethoscope device that performs signal noise reduction processing. Specifically, the signal noise reduction processing method described below is executed by the control center in the stethoscope device. The executing entity of this application will not be described in detail in the following embodiments. Furthermore, the body sound inlet hole of the body sound signal module 10 provided in this application is attached to the sound receiving cavity shell of the stethoscope, and the body sound inlet hole is connected to the sound receiving hole provided in the sound receiving cavity shell. The noise inlet hole of the environmental signal module 20 is disposed opposite to the sound receiving cavity shell.

[0060] The signal noise reduction processing method of this application includes:

[0061] Step S10: After the stethoscope's sound-receiving cavity comes into contact with the target user's body surface to form a sealed space, the body sound signal collected by the body sound signal module 10 and the environmental noise signal collected by the environmental signal module 20 are acquired.

[0062] In this embodiment, the stethoscope provided in this application includes a body sound signal module 10 and an environmental signal module 20. The body sound inlet of the body sound signal module 10 is precisely installed on the outer shell of the stethoscope's sound-receiving cavity, ensuring direct communication with the sound-receiving hole on the sound-receiving cavity shell. For example, when the stethoscope's sound-receiving cavity is in close contact with the target user's body surface to form a closed space, the communication hole between the body sound inlet and the sound-receiving hole can significantly reduce energy loss and distortion of the body sound signal during transmission, thereby ensuring that the body sound signal module 10 can accurately capture the body sound signal. Simultaneously, the noise inlet of the environmental signal module 20 is cleverly located on the back of the sound-receiving cavity shell. This back-to-back placement structure allows the environmental signal module 20 to clearly capture ambient noise signals from the surrounding environment, thus clearly distinguishing between body sound signals and ambient noise signals, avoiding mutual interference, and ensuring that the data collected by the stethoscope is purer and more accurate.

[0063] It should be noted that the body sound signal module 10 provided in this application may include a first body sound sensor 101 and a second body sound sensor 102 arranged side by side at a preset distance interval, and both the first body sound sensor 101 and the second body sound sensor 102 are... Figure 2 The diagram shows a bottom-aperture MEMS (Micro Electromechanical System) microphone. Exemplarily, this bottom-aperture MEMS microphone includes at least a PCB substrate, MEMS devices, diaphragms, a backplate, and an ASIC (Application Specific Integrated Circuit) chip. Exemplarily, the PCB substrate has multiple pads arranged at predetermined intervals and soldered to a predetermined FPC (Flexible Printed Circuit). The flexible printed circuit board is then bonded and fixed to the outer shell of the sound-receiving cavity using double-sided adhesive. In other words, this application places the bottom-aperture MEMS microphone on the outer shell of the stethoscope's sound-receiving cavity instead of its inner wall, effectively facilitating production, assembly, and repair. Furthermore, the PCB substrate also has a body sound inlet hole communicating with the sound-receiving hole on the outer shell of the sound-receiving cavity. MEMS devices are fixedly connected to the PCB substrate at both ends of this body sound inlet hole, and diaphragms of the same size are respectively disposed on both ends of the MEMS devices. That is, the MEMS devices are electrically connected to the backplate via the diaphragms, and the backplate is electrically connected to the PCB substrate via the ASIC. Additionally, refer to... Figure 2 This application attaches sealing foam or sponge around the bottom-opening MEMS microphone and uses double-sided tape to seal the body sound inlet hole, thereby increasing the sound pickup directivity of the bottom-opening MEMS microphone and reducing noise pickup.

[0064] Environmental signal module 20 is Figure 2 The top-aperture MEMS (Micro Electromechanical System) microphone shown includes a PCB substrate, MEMS device, diaphragm, backplate, and ASIC. The PCB substrate has multiple pads arranged at predetermined intervals and is soldered to a predetermined FPC (Flexible Printed Circuit). The two ends of the MEMS device are electrically connected to the enclosed space formed by the PCB substrate, creating the rear cavity of the top-aperture MEMS microphone. Furthermore, diaphragms of the same size are respectively disposed on both ends of the MEMS device. The MEMS device is electrically connected to the backplate via the diaphragms, and the backplate is electrically connected to the PCB substrate via the ASIC, thus forming the microphone acquisition circuit. A noise inlet hole is then provided on the surface of the package cavity containing the microphone acquisition circuit, relative to the PCB substrate. This noise inlet hole can be understood as the front cavity of the top-aperture MEMS microphone, located directly in front of the ASIC.

[0065] Additionally, it should be noted that the sensors installed in the body sound signal module 10 and the environmental signal module 20 in this application are all MEMS microphones, which can be subjected to SMT (Surface Mount Technology) operations with the preset flexible printed circuit board. Compared with traditional ECM (Electret Condenser Micphone), MEMS microphones have lower vibration coupling to PCB noise caused by speakers mounted on the same PCB substrate. At the same time, their sensitivity is less affected by temperature, vibration, humidity and time, and their sensitivity and frequency response consistency are better, which is beneficial to subsequent noise reduction processing.

[0066] Step S20: Perform signal filtering processing on the body sound signal to obtain a body sound filtered signal, and determine the body sound target signal based on the body sound filtered signal and the pickup angle of the body sound signal module 10.

[0067] In this embodiment, the body sound signal is amplified according to a preset signal amplification factor to obtain an amplified body sound signal. Next, a signal frequency band with the same preset signal frequency range is found in the amplified body sound signal, thereby effectively filtering out interference sounds from other frequency bands (such as environmental noise, high-frequency noise, etc.). Then, a purer body sound filtered signal can be generated based on the signal frequency band with the same signal frequency range. Combined with the pickup angle that reflects the signal receiving radiation range of the body sound signal module 10, a more accurate and clear body sound target signal can be determined, effectively eliminating signal interference outside the signal receiving radiation range.

[0068] For example, refer to Figure 3 , Figure 3 This is a block diagram of a stethoscope system according to an embodiment of this application. The body sound signal used in this application refers to the heart and lung sounds simultaneously collected by the first body sound sensor 101 and the second body sound sensor 102. Based on the electrical connection between the body sound signal module 10 and the low-noise amplifier, after receiving the body sound signal uploaded by the body sound signal module 10, the low-noise amplifier amplifies the body sound signal according to a preset signal amplification factor, thus accurately obtaining the amplified body sound signal. Furthermore, the low-noise amplifier used in this application ensures that the body sound signal maintains high sound quality while being amplified, reducing the impact of noise and distortion. Next, based on the electrical connection between the low-noise amplifier and the bandpass filter, after receiving the amplified body sound signal sent by the bandpass filter, the bandpass filter filters the amplified body sound signal according to its preset signal frequency range, thereby obtaining a filtered body sound signal after filtering out interference from other frequency bands. Next, based on the electrical connection between the bandpass filter and the active noise cancellation (ADC) frequency processing chip, when the ADC frequency processing chip receives the body sound filtering signal sent by the bandpass filter, it performs preliminary noise reduction processing on the body sound filtering signal according to the pickup angle of the body sound signal module 10. This allows for a clearer body sound target signal to be accurately obtained, effectively eliminating signal interference outside the signal reception and radiation range of that pickup angle. Furthermore, the low-noise amplifier and bandpass filter provided in this application amplify and filter the body sound signal while also amplifying and filtering the environmental noise signal.

[0069] It should be noted that the low-noise amplifier provided in this application can be a preamplifier of model PGA2500, which has an adjustable amplification factor of 10dB to 65dB (i.e., the preset signal amplification factor), and can adjust the amplification of the microphone signal according to actual needs.

[0070] Body sound signals can include heart sound signals and lung sound signals, with heart sound signals mainly concentrated in the frequency range of 30–500 Hz, while lung sound signals are located in the range of 100–1000 Hz. Therefore, the bandpass filter provided in this application can be an active bandpass filter, and the passband frequency of the active bandpass filter can be set to 30–1000 Hz.

[0071] Step S30: Determine the actual body sound signal based on the target body sound signal and the environmental noise signal.

[0072] In this embodiment, refer to Figure 3Based on the electrical connection of the environmental signal module 20, low-noise amplifier, bandpass filter and active noise cancellation frequency processing chip, after receiving the amplified and filtered environmental noise signal, the active noise cancellation frequency processing chip can cancel the noise part in the body sound target signal through the environmental noise signal, thereby obtaining an accurate true body sound signal, effectively improving the signal-to-noise ratio of the body sound signal, thus significantly improving the noise reduction processing capability of the stethoscope, and thus enhancing the accuracy of auscultation.

[0073] In summary, this application provides a signal noise reduction processing method that optimizes the noise reduction capabilities of existing stethoscopes. Specifically, the body sound signal module 10 of this application has its body sound inlet hole attached to the outer shell of the stethoscope's sound-receiving cavity and connected to the sound-receiving hole on the sound-receiving cavity shell. Next, after the stethoscope's sound-receiving cavity forms a sealed space with the target user's body surface, the hole design connecting the body sound inlet hole and the sound-receiving hole effectively reduces the loss and distortion of the body sound signal during transmission, ensuring that the body sound signal module 10 can accurately collect the body sound signal. Simultaneously, the structure of the noise inlet hole of the environmental signal module 20, which is positioned away from the sound-receiving cavity shell, allows the environmental signal module 20 to clearly capture surrounding environmental noise signals, thereby avoiding... The body sound signal is then effectively filtered to obtain a clearer and purer filtered signal. Combined with the pickup angle reflecting the signal receiving radiation range of the body sound signal module 10, the target body sound signal can be further determined more accurately and clearly, effectively eliminating signal interference outside the signal receiving radiation range. Finally, the ambient noise signal collected by the ambient signal module 20 cancels out the noise part in the target body sound signal, thereby obtaining an accurate true body sound signal, effectively improving the signal-to-noise ratio of the body sound signal, thus significantly improving the stethoscope's noise reduction processing capability and enhancing the accuracy of auscultation.

[0074] Furthermore, based on the first embodiment of the signal noise reduction processing method of this application, a second embodiment of the signal noise reduction processing method of this application is proposed.

[0075] Furthermore, in some feasible embodiments, the body sound signal module 10 includes a first body sound sensor 101 and a second body sound sensor 102 arranged side by side at a preset distance interval. The above step S20: determining the body sound target signal based on the body sound filtering signal and the pickup angle of the body sound signal module 10, further includes the following implementation steps:

[0076] Step S201: Based on the first pickup angle region of the first body sound sensor 101 and the second pickup angle region of the second body sound sensor 102, construct the pickup angle of the body sound signal module 10 and determine the signal acquisition frequency band of the pickup angle.

[0077] In this embodiment, the angular range in which the first sound sensor 101 can effectively pick up sound is defined as the first sound pickup angle region, and the angular range in which the second sound sensor 102 can effectively pick up sound is defined as the second sound pickup angle region. Subsequently, based on the same angular range in the first and second sound pickup angle regions, the sound pickup angle can be accurately generated. That is, the sound pickup angle refers to the range in which the first sound sensor 101 and the second sensor can jointly pick up sound. Then, the range in which the sound pickup angle can pick up sound is defined as the signal acquisition frequency band of the sound pickup angle.

[0078] Step S202: Find the signal frequency band that is the same as the signal acquisition frequency band from the overall signal frequency band of the body sound filtering signal, and take the body sound filtering signal corresponding to the signal frequency band that is the same as the signal acquisition frequency band as the body sound target signal.

[0079] In this embodiment, within the overall frequency band of the body sound filtering signal, a frequency band portion matching the signal acquisition frequency band corresponding to the pickup angle is selected. Specifically, the frequency band portion in the overall frequency band of the body sound filtering signal that is the same as the signal acquisition frequency band is taken as the frequency band portion matching the signal acquisition frequency band. Subsequently, the frequency band portion matching the signal acquisition frequency band is determined as the body sound target signal, thereby effectively eliminating signal interference outside the signal receiving radiation range of the pickup angle.

[0080] Furthermore, in some other feasible embodiments, the above step S201: constructing the pickup angle of the body sound signal module 10 based on the first pickup angle region of the first body sound sensor 101 and the second pickup angle region of the second body sound sensor 102, may also include the following implementation steps:

[0081] Step S2011: Determine the first pickup angle region of the first body sound sensor 101 and the second pickup angle region of the second body sound sensor 102, and obtain the pickup intersection region formed by the first pickup angle region and the second pickup angle region.

[0082] In this embodiment, the angle range in which the first sound sensor 101 can effectively pick up sound is defined as the first sound pickup angle region, and the angle range in which the second sound sensor 102 can effectively pick up sound is defined as the second sound pickup angle region. Then, the angle range in which the first sound pickup angle region and the second sound pickup angle region are the same is defined as the sound pickup intersection region.

[0083] Step S2012: Subtract the minimum pickup angle value in the pickup intersection region from the maximum pickup angle value in the pickup intersection region to obtain the pickup intersection angle value of the pickup intersection region.

[0084] In this embodiment, by calculating the difference between the maximum and minimum pickup angle values ​​in the pickup intersection region, the angular range in which the two body sound sensors can jointly pick up sound can be accurately determined, i.e., the pickup intersection angle value of the pickup intersection region. This is crucial for applications requiring precise control of the sound source or the elimination of noise from specific directions. Specifically, within the determined pickup intersection angle range, the two body sound sensors can simultaneously receive body sound signals, which helps reduce errors introduced by the position or directional limitations of a single sensor and improves the accuracy of body sound signal acquisition.

[0085] Step S2013: Taking the midpoint between the first body sound sensor 101 and the second body sound sensor 102 as the origin, and the sensor central axis passing through the origin as the angle bisector, construct an angled region in the sound receiving cavity that is the same as the sound pickup intersection angle value as the sound pickup angle of the body sound signal module 10.

[0086] In this embodiment, refer to Figure 4 , Figure 4 This is a schematic diagram of a dual-microphone pickup array involved in the embodiments of this application. In this application, an angled region with the same angle value as the pickup intersection is constructed within the sound receiving cavity as the pickup angle of the body sound signal module 10 (i.e., Figure 4 As shown in α), this significantly improves the accuracy and directionality of body sound signal acquisition. Specifically, this application uses the midpoint between the first body sound sensor 101 and the second body sound sensor 102 as the origin, and the sensor's central axis passing through this origin as the angle bisector. This ensures that the pickup angle can accurately match the common effective pickup range of the first body sound sensor 101 and the second body sound sensor 102, thereby effectively reducing interference from non-body sound target signals, that is, reducing... Figure 4 The noise interference in the two dashed triangular regions shown significantly improves the quality and clarity of the body sound signal, thus making subsequent signal processing more accurate and reliable.

[0087] Furthermore, in some feasible embodiments, step S30 above: determining the actual body sound signal based on the target body sound signal and the environmental noise signal, further includes the following implementation steps:

[0088] Step S301: Determine the noise threshold of the environmental noise signal and the body sound threshold of the body sound target signal.

[0089] In this embodiment, refer to Figure 3 After the active noise cancellation frequency processing chip receives the amplified and filtered environmental noise signal and the body sound target signal respectively, the active noise cancellation frequency processing chip can accurately obtain the noise threshold of the environmental noise signal and the body sound threshold of the body sound target signal, thereby providing accurate and effective data support for the subsequent determination of the body sound prediction signal.

[0090] Step S302: The negative number of the noise threshold is superimposed on the body sound threshold according to the preset sound pickup cavity transfer function to obtain the body sound prediction signal of the body sound signal module 10.

[0091] In this embodiment, refer to Figure 5 , Figure 5 This is a block diagram illustrating the active noise reduction principle of the embodiments of this application. When the ambient noise signal (i.e. Figure 5 The noise shown is transmitted to the target sound signal (i.e., the sound) via a preset pickup cavity transfer function. Figure 5 When using the sound pickup cavity of the Sound (as shown), the negative of the noise threshold of the ambient noise signal is simultaneously superimposed onto the body sound threshold of the body sound target signal, thereby accurately obtaining the body sound prediction signal of the body sound signal module 10. That is, this application can effectively obtain a body sound prediction signal with external noise filtered out through inverse superposition noise reduction processing.

[0092] It should be noted that the algorithm for inverse superposition noise reduction can be expressed by the following formula (1):

[0093] D O =D Sound -G(w)*D Noise …………Formula (1)

[0094] Among them, D O This can be understood as the body sound prediction signal of body sound signal module 10; D Sound This can be understood as the body sound threshold of the target signal; G(w) can be understood as the preset pickup cavity transfer function, which can be customized according to actual application requirements, and this application does not impose any restrictions here; D Noise This can be understood as the noise threshold of the environmental noise signal.

[0095] Step S303: Transform the body sound prediction signal into a body sound observation signal of the body sound signal module 10, and detect whether the body sound prediction signal is within the signal observation threshold range corresponding to the body sound observation signal;

[0096] Step S304: If the predicted body sound signal is within the range of the signal observation threshold, then the predicted body sound signal is taken as the actual body sound signal.

[0097] In this embodiment, Figure 3The active noise reduction frequency processing chip shown transforms the body sound prediction signal into a Gaussian-transformed body sound observation signal of the body sound signal module 10. It then detects whether the body sound prediction signal is within the signal observation threshold range corresponding to the body sound observation signal. If the body sound prediction signal is within the signal observation threshold range, it treats the body sound prediction signal as the actual body sound signal and passes it through the feedforward processing module (i.e., ...). Figure 5 The output of Dff (as shown) ensures time synchronization between body sound signals from different body sound sensors, effectively improving the output quality of the true body sound signal.

[0098] The signal observation threshold range can be customized according to actual application requirements. For example, the signal observation threshold range can be understood as fluctuating around the signal threshold of the body sound observation signal by increasing or decreasing by ±0.1. The above embodiment is only one implementation method of this application, and this application does not make any limitation.

[0099] Furthermore, in some other feasible embodiments, step S303 above: transforming the body sound prediction signal into a Gaussian signal of the body sound signal module 10, may also include the following implementation steps:

[0100] Step S3031: Determine multiple signal frequency values ​​of the body sound prediction signal within a preset acquisition time;

[0101] Step S3032: Perform mean processing on each of the signal frequency values ​​to obtain the frequency mean among the signal frequency values, and perform variance processing on the squared difference between each signal frequency value and the frequency mean to obtain the frequency variance among the signal frequency values.

[0102] In this embodiment, after determining multiple signal frequency values ​​of the body sound prediction signal within a preset acquisition time, the total frequency value among each signal frequency value can be accurately calculated. Then, based on the total frequency value and the total number of all signal frequency values, the mean frequency value used to characterize the central trend of all signal frequencies can be accurately calculated. Next, the squared difference between each signal frequency value and the mean frequency value is calculated, thereby effectively quantifying the dispersion and fluctuation of all signal frequencies. Finally, the total squared difference between all squared differences is divided by the total number of all signal frequency values, thereby accurately calculating the frequency variance value among each signal frequency value, so as to provide strong data support for subsequently determining the body sound observation signal under ideal conditions.

[0103] Step S3033: Perform Gaussian transformation based on the mean frequency and the variance frequency to obtain the body sound observation signal of the body sound signal module 10.

[0104] In this embodiment, by performing a Gaussian transformation on the frequency mean and frequency variance according to a preset Gaussian transformation function, the body sound observation signal that is close to the ideal state (i.e., the state without noise interference) can be accurately obtained, thus providing an accurate and reliable judgment standard for determining the true body sound signal.

[0105] It should be noted that the preset Gaussian transform function can be as shown in the following formula (2):

[0106]

[0107] Among them, D O ′ represents the body sound observation signal; z represents the random variable corresponding to the Gaussian distribution function, which can be customized according to application requirements; μ represents the frequency mean; σ 2 represents the frequency variance; exp represents the exponential function with a base e.

[0108] Furthermore, in some feasible embodiments, after step S303 above: detecting whether the body sound prediction signal is within the signal observation threshold range corresponding to the body sound observation signal, the subsequent signal noise reduction processing method may also include the following implementation steps:

[0109] Step A10: If the body sound prediction signal is not within the signal observation threshold range, determine multiple signal observation frequency values ​​of the body sound observation signal within the acquisition time, and determine the total observation frequency value between each of the signal observation frequency values, and the total signal frequency value between each of the signal frequency values;

[0110] Step A20: Based on the divisor quotient between the total signal frequency and the total observed frequency, calculate the log-likelihood value to obtain the adjustment function of the body sound signal module 10.

[0111] In this embodiment, if the body sound prediction signal is not within the signal observation threshold range corresponding to the body sound observation signal, then multiple signal observation frequency values ​​of the body sound observation signal within a preset acquisition time are determined, and the total observation frequency value among all signal observation frequency values ​​and the total signal frequency value among all signal frequency values ​​are further calculated; next, the total signal frequency value is divided by the total observation frequency value, so that the divisor quotient between the total signal frequency value and the total observation frequency value can be accurately obtained; then, the log-likelihood value of the divisor quotient is calculated according to the preset transfer function algorithm, so that the adjustment function of the body sound signal module 10 can be accurately obtained.

[0112] It should be noted that the preset transfer function algorithm can be as shown in the following formula (3):

[0113] G(w)′=-log l(Z|θ*h)…………Formula (3)

[0114] Wherein, G(w)′ is the adjustment function of the body sound signal module 10; θ is a fixed value, which is the random variable for adjusting the pickup cavity transfer function, and can be customized according to application requirements; h represents the total signal frequency; Z represents the total observed frequency; log l represents the mathematical operation formula for calculating the log-likelihood; Z|θ*h represents the divisor quotient obtained by dividing the product of the total signal frequency and the random variable by the total observed frequency.

[0115] Step A30: Use the adjustment function as the next pickup cavity transfer function, and return to the step of superimposing the negative number of the noise threshold onto the body sound threshold according to the preset pickup cavity transfer function.

[0116] In this embodiment, the adjustment function is used as the next pickup cavity transfer function, and the step of superimposing the negative number of the noise threshold onto the body sound threshold according to the preset pickup cavity transfer function is returned to be executed. This makes the signal noise reduction processing method more robust and widely applicable in practical applications.

[0117] Furthermore, in some other feasible embodiments, after step S30 above: determining the actual body sound signal based on the target body sound signal and the environmental noise signal, the subsequent signal noise reduction processing method may also include the following implementation steps:

[0118] Step B10: Input the actual body sound signal into a preset auscultation record model for model training to obtain the auscultation record report of the target user, and display the health results of the auscultation record report to the target user.

[0119] In this embodiment, based on the electrical connection between the active noise cancellation (ADC) audio processing chip and the SOC (System on Chip) main control chip, after the SOC main control chip receives the actual body sound signal, the SOC main control chip can... Figure 3 The WIFI and Bluetooth chips shown communicate wirelessly with smart terminals (such as mobile phones, computers, and cloud servers of professional medical institutions) that are equipped with a preset auscultation recording model. This allows for the accurate and reliable transmission of real body sound signals to the preset auscultation recording model for model training, thereby generating an auscultation record report for the target user. The auscultation record report is then uploaded to the SOC main control chip via the smart terminal. Finally, based on the electrical connection between the SOC main control chip and the LED display screen, the health results of the auscultation record report are displayed to the target user on the LED display screen.

[0120] In another implementation, refer to Figure 3Doctors can also connect to in-ear Bluetooth headphones via Wi-Fi and Bluetooth chips, or through the headphone jack, enabling efficient and comfortable on-site auscultation; furthermore, Figure 3 The memory shown can be used to store the target user's actual body sound signals and auscultation record reports. Based on the electrical connection between the SOC main control chip and the memory and the "button / switch / volume / pairing" button, the target user's actual body sound signals can be played back or the health results of the auscultation record report (i.e., whether there are health problems in the actual body sound signals) can be displayed to the target user on the LED display screen through the "button / switch / volume / pairing" button control. This effectively solves the technical problems of traditional medical stethoscopes, such as weak sound, discomfort when worn, susceptibility to environmental noise interference, limited auscultation results, and inability to record and play back in real time.

[0121] It should be noted that, referring to Figure 3 This application can also power the lithium battery in the electronic stethoscope provided in this application via a USB charging and data interface, the lithium battery being used to drive... Figure 3 The voltage management chip shown provides power to the SOC main control chip. In addition, the lithium battery capacity of this application can be customized according to actual application requirements. For example, the lithium battery capacity can be 500mAh to achieve a working time of more than 10 hours.

[0122] In summary, this application has the following settings: Figure 2 The microphone array shown collects body sound signals and ambient noise signals respectively. Then, the body sound signals and ambient noise signals are processed by a low-noise amplifier and a bandpass filter, and finally processed by the microphone array configured in this application. Figure 3 The active noise cancellation (ADC) frequency processing chip shown utilizes ambient noise signals to cancel out the noise component in the body sound signal, thus accurately obtaining the true body sound signal; then, based on the SOC main control chip, it is respectively connected with... Figure 3 The electrical connections shown to the WIFI and Bluetooth chip, LED display, memory, etc. enable intelligent hearing function, thereby effectively solving the technical problems of traditional medical stethoscopes, such as weak sound, discomfort when worn, susceptibility to environmental noise interference, limited auscultation results, and inability to record and play back in real time.

[0123] Furthermore, this application also provides a signal noise reduction processing device applied to a stethoscope including a body sound signal module 10 and an environmental signal module 20. The body sound inlet of the body sound signal module 10 is attached to the outer shell of the stethoscope's sound-receiving cavity, and the body sound inlet is connected to the sound-receiving hole provided on the outer shell of the sound-receiving cavity. The noise inlet of the environmental signal module 20 is disposed opposite to the outer shell of the sound-receiving cavity. Please refer to [reference needed]. Figure 6 , Figure 6 This is a schematic diagram of the signal noise reduction processing device involved in the embodiments of this application.

[0124] The signal noise reduction processing device of this application includes:

[0125] The acquisition module H01 is used to acquire the body sound signal collected by the body sound signal module 10 and the environmental noise signal collected by the environmental signal module 20 after the sound receiving cavity of the stethoscope comes into contact with the human body surface of the target user to form a closed space.

[0126] The filtering module H02 is used to perform signal filtering processing on the body sound signal to obtain a body sound filtered signal, and to determine the body sound target signal based on the body sound filtered signal and the pickup angle of the body sound signal module 10.

[0127] The real signal determination module H03 is used to determine the real body sound signal based on the target body sound signal and the environmental noise signal.

[0128] Each functional module of the signal noise reduction processing device of this application implements the steps of the signal noise reduction processing method of this application as described above during operation.

[0129] In addition, this application also provides a stethoscope device. Please refer to... Figure 7 , Figure 7 This is a schematic diagram of the auscultation device involved in the embodiments of this application. Specifically, the auscultation device in the embodiments of this application can be a device that performs a local signal noise reduction processing method.

[0130] like Figure 7 As shown, the auscultation device according to this application embodiment may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0131] The memory 1005 is disposed on the main body of the stethoscope device. The memory 1005 stores a program that, when executed by the processor 1001, performs corresponding operations. The memory 1005 is also used to store parameters used by the stethoscope device. The memory 1005 can be a high-speed RAM or a stable, non-volatile memory, such as a disk drive. Optionally, the memory 1005 can also be a storage device independent of the aforementioned processor 1001.

[0132] Those skilled in the art will understand that Figure 7The structure of the auscultation device shown does not constitute a limitation on the auscultation device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0133] like Figure 7 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a signal noise reduction processing program for a stethoscope.

[0134] exist Figure 7 In the stethoscope device shown, the processor 1001 can be used to call the signal noise reduction processing program of the stethoscope device stored in the memory 1005 and execute the steps of any of the above signal noise reduction processing methods.

[0135] Furthermore, this application provides a storage medium, which is a computer-readable storage medium. This computer-readable storage medium stores a signal noise reduction processing program, which, when executed by a processor, implements the steps of the above-described signal noise reduction processing method.

[0136] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0137] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0138] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a stethoscope device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0139] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A signal noise reduction processing method, characterized in that, The signal noise reduction processing method is applied to a stethoscope including a body sound signal module and an environmental signal module. The body sound inlet of the body sound signal module is attached to the outer shell of the sound receiving cavity of the stethoscope. The body sound inlet is connected to the sound receiving hole provided on the outer shell of the sound receiving cavity. The noise inlet of the environmental signal module is disposed opposite to the outer shell of the sound receiving cavity. The signal noise reduction processing method includes: After the stethoscope's sound-receiving cavity comes into contact with the target user's body surface to form a sealed space, the body sound signal collected by the body sound signal module and the environmental noise signal collected by the environmental signal module are acquired. The body sound signal is filtered to obtain a body sound filtered signal, and the body sound target signal is determined based on the body sound filtered signal and the pickup angle of the body sound signal module. The actual body sound signal is determined based on the target body sound signal and the environmental noise signal.

2. The signal noise reduction processing method as described in claim 1, characterized in that, The body sound signal module includes a first body sound sensor and a second body sound sensor arranged side by side at preset distance intervals. The step of determining the body sound target signal based on the body sound filter signal and the pickup angle of the body sound signal module includes: Based on the first pickup angle region of the first body sound sensor and the second pickup angle region of the second body sound sensor, the pickup angle of the body sound signal module is constructed, and the signal acquisition frequency band of the pickup angle is determined. Find the signal frequency band that is the same as the signal acquisition frequency band from the overall signal frequency band of the body sound filtering signal, and take the body sound filtering signal corresponding to the signal frequency band that is the same as the signal acquisition frequency band as the body sound target signal.

3. The signal noise reduction processing method as described in claim 2, characterized in that, The step of constructing the pickup angle of the body sound signal module based on the first pickup angle region of the first body sound sensor and the second pickup angle region of the second body sound sensor includes: Determine the first pickup angle region of the first body sound sensor and the second pickup angle region of the second body sound sensor, and obtain the pickup intersection region formed by the first pickup angle region and the second pickup angle region; The pickup intersection angle value of the pickup intersection region is obtained by subtracting the minimum pickup angle value of the pickup intersection region from the maximum pickup angle value of the pickup intersection region. Taking the midpoint between the first body sound sensor and the second body sound sensor as the origin, and the central axis of the sensor passing through the origin as the angle bisector, an angle region with the same angle value as the sound pickup intersection angle is constructed in the sound receiving cavity as the sound pickup angle of the body sound signal module.

4. The signal noise reduction processing method as described in claim 1, characterized in that, The step of determining the actual body sound signal based on the target body sound signal and the environmental noise signal includes: Determine the noise threshold of the environmental noise signal and the body sound threshold of the body sound target signal; The negative of the noise threshold is superimposed onto the body sound threshold according to the preset pickup cavity transfer function to obtain the body sound prediction signal of the body sound signal module; The body sound prediction signal is Gaussian transformed into the body sound observation signal of the body sound signal module, and it is detected whether the body sound prediction signal is within the signal observation threshold range corresponding to the body sound observation signal; If the predicted body sound signal is within the range of the signal observation threshold, then the predicted body sound signal is taken as the true body sound signal.

5. The signal noise reduction processing method as described in claim 4, characterized in that, The step of transforming the body sound prediction signal into the body sound observation signal of the body sound signal module includes: Determine multiple signal frequency values ​​of the body sound prediction signal within a preset acquisition time; The mean value of each signal frequency value is obtained by performing mean processing on each signal frequency value, and the variance value of each signal frequency value is obtained by performing variance processing on the squared difference between each signal frequency value and the mean value. Gaussian transformation is performed based on the frequency mean and the frequency variance to obtain the body sound observation signal of the body sound signal module.

6. The signal noise reduction processing method as described in claim 5, characterized in that, After the step of detecting whether the body sound prediction signal is within the signal observation threshold range corresponding to the body sound observation signal, the signal noise reduction processing method includes: If the predicted body sound signal is not within the range of the signal observation threshold, determine multiple signal observation frequency values ​​of the body sound observation signal within the acquisition time, and determine the total observation frequency value between each of the signal observation frequency values, as well as the total signal frequency value between each of the signal frequency values. Based on the divisor quotient between the total signal frequency and the total observed frequency, a log-likelihood value is calculated to obtain the adjustment function of the body sound signal module; The adjustment function is used as the next pickup cavity transfer function, and the step of adding the negative of the noise threshold to the body sound threshold according to the preset pickup cavity transfer function is returned.

7. The signal noise reduction processing method as described in claim 1, characterized in that, After the step of determining the true body sound signal based on the target body sound signal and the environmental noise signal, the signal noise reduction processing method further includes: The actual body sound signal is input into a preset auscultation record model for model training to obtain the auscultation record report of the target user, and the health results of the auscultation record report are displayed to the target user.

8. A signal noise reduction processing device, characterized in that, The signal noise reduction processing device is applied to a stethoscope including a body sound signal module and an environmental signal module. The body sound inlet of the body sound signal module is attached to the outer shell of the stethoscope's sound-receiving cavity, and the body sound inlet is connected to the sound-receiving hole provided on the outer shell of the sound-receiving cavity. The noise inlet of the environmental signal module is disposed opposite to the outer shell of the sound-receiving cavity. The signal noise reduction processing device includes: The acquisition module is used to acquire the body sound signal collected by the body sound signal module and the environmental noise signal collected by the environmental signal module after the sound receiving cavity of the stethoscope comes into contact with the human body surface of the target user to form a closed space. The filtering module is used to perform signal filtering processing on the body sound signal to obtain a body sound filtered signal, and to determine the body sound target signal based on the body sound filtered signal and the pickup angle of the body sound signal module. The real signal determination module is used to determine the real body sound signal based on the target body sound signal and the environmental noise signal.

9. A stethoscope device, characterized in that, The auscultation device includes a memory, a processor, and a signal noise reduction processing program stored in the memory and executable on the processor. When the processor executes the signal noise reduction processing program, it implements the steps of the signal noise reduction processing method as described in any one of claims 1 to 7.

10. A storage medium, said storage medium being a computer-readable storage medium, characterized in that, The computer-readable storage medium stores a signal noise reduction processing program, which, when executed by a processor, implements the steps of the signal noise reduction processing method as described in any one of claims 1 to 7.

Images