Lung sound signal processing method, apparatus, and system

Abstract

Embodiments of the present application relate to the technical field of computer, and particularly relate to a lung sound signal processing method, device and system. First, lung sound data and pressure data of a user are acquired based on a lung sound acquisition process, then the lung sound data is divided into multiple lung sound sub-data in the time dimension according to the pressure data, and lung sound features of the lung sound data are determined according to the multiple lung sound sub-data. The method simultaneously acquires lung sound data and pressure data, accurately segments the lung sound data through the pressure data, improves the signal quality of the lung sound data, and makes the extraction of lung sound features easier and more accurate.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus and system for processing lung sound signals. Background Technology

[0002] The lungs are the main organs of the respiratory system, and monitoring and protecting lung health anytime, anywhere is important for everyone. Lung sounds are produced by the vibration caused by turbulence as airflow passes through the respiratory tract and alveoli, transmitting sound through the lung tissue and chest wall to the body surface. Wearable devices equipped with sensors can collect and process lung sound signals.

[0003] In current lung sound signal processing, the acquired lung sound signals are often of poor quality, significantly impacting subsequent signal processing. For example, during lung sound signal acquisition, heart sounds, ambient noise, and friction rubs are often acquired simultaneously. Even with filtering, noise reduction, or heart-lung sound separation, it is difficult to extract useful information from these lung sound signals. Summary of the Invention

[0004] This application provides a method, apparatus, and system for processing lung sound signals. The method uses pressure data to assist in acquiring lung sound data and segments the lung sound data according to the pressure data, thereby improving the signal quality of the lung sound data and making the extraction of lung sound features easier and more accurate.

[0005] In a first aspect, embodiments of this application provide a method for processing lung sound signals, the method comprising:

[0006] Lung sound data and pressure data of users are acquired based on the lung sound acquisition process;

[0007] Based on the pressure data, the lung sound data is divided into multiple lung sound sub-data in the time dimension;

[0008] The lung sound features of the lung sound data are determined based on the multiple lung sound sub-data.

[0009] In this embodiment of the application, lung sound data is segmented according to pressure data, which enables more accurate extraction of lung sound features and makes lung sound signal processing more accurate.

[0010] In one embodiment, the process of acquiring the user's lung sound data and pressure data based on the lung sound acquisition procedure includes:

[0011] Simultaneously, the user's lung sound data and pressure data were collected during the first time period;

[0012] Determine whether the pressure data meets the preset standard;

[0013] If it is determined that the pressure data does not meet the preset standard, the lung sound data and the pressure data are collected again.

[0014] In this embodiment, the signal quality of lung sound data is determined by pressure data, and re-acquisition is performed when the signal quality does not meet the conditions. Improving the signal quality of lung sound data can effectively improve the accuracy of lung sound signal processing.

[0015] In one embodiment, the method further includes:

[0016] If the pressure data is determined to meet the preset standard, the lung sound acquisition process ends.

[0017] In one embodiment, simultaneously collecting the user's lung sound data and pressure data within a first time period includes:

[0018] After detecting the user's triggered acquisition command, based on the user's periodic breathing, the user's lung sound data and pressure data are acquired simultaneously during the first time period;

[0019] The first signal waveform corresponding to the pressure data is displayed on the screen in real time. The first signal waveform is used to assist the user in performing the periodic breathing.

[0020] In this embodiment, the first signal waveform that displays pressure data in real time can assist the user in performing periodic breathing that meets the conditions, thereby ensuring the signal quality of lung sound data.

[0021] In one embodiment, determining whether the pressure data meets a preset standard includes:

[0022] Determine the second signal waveform corresponding to the pressure data within the first time period;

[0023] Multiple peaks of the second signal waveform are determined, and peaks with values ​​less than a first threshold are identified as non-standard peaks.

[0024] If the number of non-standard peaks is greater than the second threshold, then the pressure data is determined to be inconsistent with the preset standard; otherwise, the pressure data is determined to be consistent with the preset standard.

[0025] In this embodiment, the peak of the second signal waveform of the pressure data reflects the degree of deep breathing by the user. If the peak value is small, it indicates that the user's breathing does not meet the standard, and lung sound data needs to be re-collected. By detecting the number of non-standard peaks, this step can accurately determine whether the pressure data meets the preset standard.

[0026] In one embodiment, determining whether the pressure data meets a preset standard includes:

[0027] Determine the second signal waveform corresponding to the pressure data within the first time period;

[0028] Based on multiple adjacent peaks or troughs of the second signal waveform, multiple period values ​​are determined, and period values ​​with values ​​less than a third threshold are determined as non-standard period values.

[0029] If the number of non-standard periodic values ​​is greater than the fourth threshold, then the pressure data is determined to be inconsistent with the preset standard; otherwise, the pressure data is determined to be consistent with the preset standard.

[0030] In this embodiment, the period of the second signal waveform of the pressure data also reflects the degree of deep breathing of the user. If the period value is small, it means that the user's breathing is shallow and does not meet the standard, and lung sound data needs to be collected again.

[0031] In one embodiment, the step of re-collecting the lung sound data and the pressure data if it is determined that the pressure data does not meet the preset standard includes:

[0032] If it is determined that the pressure data does not meet the preset standard, the user is reminded to re-trigger the data collection command according to the preset reminder method.

[0033] In one embodiment, the preset reminder method includes one or more of the following combinations:

[0034] Voice reminder;

[0035] Text reminder;

[0036] Screen flashing reminder;

[0037] Vibration alert.

[0038] In one embodiment, dividing the lung sound data into multiple lung sound sub-data along the time dimension based on the pressure data includes:

[0039] Determine the third signal waveform of the pressure data;

[0040] Multiple time division points are determined based on multiple peaks or troughs of the third signal waveform;

[0041] The lung sound data is divided into multiple lung sound sub-data in the time dimension according to the time segmentation point, wherein each lung sound sub-data is used to indicate the lung sound data corresponding to the user in a breath.

[0042] In this embodiment, lung sound data is precisely segmented using pressure data, making the extraction of lung sound features more accurate.

[0043] In one embodiment, the lung sound features include one or more of the following:

[0044] Mel frequency cepstral coefficients;

[0045] Zero crossing rate;

[0046] Spectral centroid;

[0047] Signal bandwidth.

[0048] In one embodiment, before dividing the lung sound data into multiple lung sound sub-data in the time dimension based on the pressure data, the method further includes:

[0049] The lung sound data is subjected to noise reduction filtering.

[0050] In one embodiment, before dividing the lung sound data into multiple lung sound sub-data in the time dimension based on the pressure data, the method further includes:

[0051] The lung sound data is subjected to cardiopulmonary sound separation processing.

[0052] In this embodiment, lung sound data and pressure data are collected simultaneously. Pressure data assists in the collection of lung sound data, and the lung sound data is accurately segmented after collection, making the extraction of lung sound features more precise.

[0053] Secondly, embodiments of this application provide a lung sound signal processing device, the device comprising:

[0054] The acquisition module is used to acquire the user's lung sound data and pressure data based on the lung sound acquisition process;

[0055] The processing module is used to divide the lung sound data into multiple lung sound sub-data in the time dimension according to the pressure data;

[0056] A determination module is used to determine the lung sound features of the lung sound data based on the plurality of lung sound sub-data.

[0057] Thirdly, embodiments of this application provide a lung sound signal processing system, the system comprising:

[0058] Pressure sensors, audio stethoscopes, and processors;

[0059] The pressure sensor is used to acquire the user's pressure data, the audio stethoscope is used to acquire the user's lung sound data, and the processor is able to implement the method provided in the first aspect based on the pressure data and the lung sound data.

[0060] Fourthly, embodiments of this application provide an electronic device, including:

[0061] At least one processor; and

[0062] At least one memory communicatively connected to the processor, wherein:

[0063] The memory stores program instructions, and the processor can execute the method provided in the first aspect by calling the program instructions.

[0064] Fifthly, embodiments of this application provide a computer-readable storage medium comprising a stored program, wherein the program, when executed by a processor, implements the method provided in the first aspect.

[0065] In this embodiment, lung sound data and stress data of the user are first acquired based on the lung sound acquisition process. Then, the lung sound data is divided into multiple lung sound sub-data in the time dimension according to the stress data. Next, the lung sound features of the lung sound sub-data are determined, and the user's health level is determined based on the lung sound features. This method simultaneously acquires lung sound data and stress data, and accurately segments the lung sound data through stress data, improving the signal quality of the lung sound data and making the extraction of lung sound features easier and more accurate. Attached Figure Description

[0066] Figure 1 A flowchart of a lung sound signal processing method provided in an embodiment of this application;

[0067] Figure 2 A schematic diagram of a lung sound signal processing method provided in an embodiment of this application;

[0068] Figure 3 A schematic diagram of another lung sound signal processing method provided in an embodiment of this application;

[0069] Figure 4 A schematic diagram of another lung sound signal processing method provided in an embodiment of this application;

[0070] Figure 5A A schematic diagram of another lung sound signal processing method provided in an embodiment of this application;

[0071] Figure 5B A schematic diagram of another lung sound signal processing method provided in an embodiment of this application;

[0072] Figure 6A A schematic diagram of another lung sound signal processing method provided in an embodiment of this application;

[0073] Figure 6B A schematic diagram of another lung sound signal processing method provided in an embodiment of this application;

[0074] Figure 7This is a schematic diagram of a lung sound signal processing device provided in an embodiment of this application;

[0075] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0076] To better understand the technical solutions in this specification, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0077] It should be understood that the described embodiments are merely some, not all, of the embodiments in this specification. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without inventive effort are within the scope of protection of this specification.

[0078] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0079] To address the problems of excessive interference in current lung sound signal processing and difficulties in extracting lung sound features, this application provides a lung sound signal processing method that makes lung sound feature extraction easier and more accurate.

[0080] Figure 1 This is a flowchart illustrating a lung sound signal processing method provided in an embodiment of this application. This method can be applied to terminal devices such as smartwatches. Figure 1 As shown, the method may include:

[0081] Step 101: Obtain the user's lung sound data and pressure data based on the lung sound acquisition process.

[0082] In this embodiment of the application, the smartwatch can be equipped with both a pressure sensor and an audio stethoscope. The pressure sensor is used to collect pressure data, and the audio stethoscope is used to collect lung sound data.

[0083] In one embodiment, the smartwatch simultaneously collects lung sound data and pressure data from the user within a first time period. It then determines whether the pressure data meets a preset standard. If the pressure data does not meet the preset standard, the lung sound and pressure data are collected again. During the lung sound data collection process, if the user takes steady, deep breaths, the signal quality of the collected lung sound data is relatively good. Simultaneously, there is a correlation between the user's breathing state and the pressure data detected by the smartwatch. For example, the deeper the user's breathing, the higher the detected pressure value. Therefore, if the pressure data does not meet the preset standard, it can be determined that the signal quality of the lung sound data is likely problematic and needs to be recollected. If the smartwatch determines that the pressure data meets the preset standard, the lung sound collection process ends.

[0084] Step 102: Divide the lung sound data into multiple lung sound sub-data in the time dimension based on the pressure data.

[0085] In this embodiment, the smartwatch segments the lung sound data, enabling more accurate subsequent processing. As audio data, lung sound data is susceptible to interference from noise, heart sounds, and other factors during acquisition, making it difficult to distinguish the user's breathing intervals. Pressure data, however, is correlated with the user's breathing, allowing for precise segmentation of the lung sound data.

[0086] Step 103: Determine the lung sound characteristics of the lung sound data based on multiple lung sound sub-data.

[0087] Compared to whole-segment lung sound data, segmenting the lung sound data according to the user's breathing interval and then extracting lung sound features from each segment makes lung sound feature extraction easier and more accurate. Each lung sound sub-data segment corresponds to the lung sound data of one breath of the user. The lung sound features that the smartwatch can determine from each lung sound sub-data segment may include: Mel frequency cepstral coefficients, zero-crossing rate, spectral centroid, and signal bandwidth, etc. The lung sound features exemplified in this application embodiment are some of the more common lung sound features. Depending on actual needs, the smartwatch can also determine other lung sound features, which are not limited in this application embodiment.

[0088] In this embodiment, the smartwatch simultaneously collects the user's lung sound data and pressure data. The pressure data can detect the signal quality of the lung sound data and accurately segment the lung sound data, making the extraction of lung sound features easier and more accurate.

[0089] In one embodiment, the smartwatch can determine whether the pressure data meets a preset standard based on the following steps: After collecting pressure data and lung sound data, the smartwatch first determines the second signal waveform corresponding to the pressure data in a first time period, then determines multiple peaks of the second signal waveform, and identifies peaks with values ​​less than a first threshold as non-standard peaks. If the number of non-standard peaks detected is greater than the second threshold, the pressure data is determined to not meet the preset standard; otherwise, the pressure data is determined to meet the preset standard. Alternatively, the smartwatch can also determine multiple period values ​​based on multiple adjacent peaks or troughs of the second signal waveform, and identify period values ​​with values ​​less than a third threshold as non-standard period values. If the number of non-standard period values ​​detected is greater than a fourth threshold, the pressure data is determined to not meet the preset standard; otherwise, the pressure data is determined to meet the preset standard. It is understood that if a user takes a standard deep breath, both the peak and period values ​​of the second signal waveform will be greater than a certain value. If the peaks are small, it indicates that the user's breathing is shallow; if the period values ​​are small, it indicates that the user's breathing is rapid. In this breathing state, the interference in the collected lung sound data is relatively severe.

[0090] In one embodiment, if the smartphone detects that the pressure data does not meet a preset standard, it will remind the user to re-collect lung sound data and pressure data. The reminder methods include: voice reminder, text reminder, screen flashing reminder, and vibration reminder. One of several reminder methods can be used, multiple reminder methods can be used simultaneously, or other reminder methods can be employed.

[0091] In one embodiment, the smartwatch can input the acquired lung sound features into a trained classification model to obtain corresponding results. This step can be used to detect the user's lung condition, and the detection results can include: lung health, lung infection, or abnormal results. Specifically, lung infection can include low risk of lung infection, high risk of lung infection, low risk of COPD, and high risk of COPD. Abnormal results include results other than common diseases.

[0092] In a specific embodiment, a user can use a smartwatch to complete the lung sound signal processing method provided in this application embodiment. Figure 2 As shown, the smartwatch 200 has an audio stethoscope 210 and a display screen 220 on the front, and a pressure sensor 230 on the back. The process of the smartwatch 200 performing lung sound signal processing can be as follows: Figure 3As shown, after the smartwatch 200 receives the user-triggered data acquisition command, the audio stethoscope 210 and pressure sensor 230 simultaneously acquire data. The audio stethoscope 210 acquires raw audio data, and the pressure sensor 230 acquires pressure data. During acquisition, the audio stethoscope 210 collects not only lung sound data but also heart sound data, environmental noise, and interference data such as friction rubs. Therefore, the raw audio data needs to be processed to extract lung sound data, such as through filtering and heart-lung sound separation. The smartwatch 200 can determine the user's respiratory interval and respiratory depth based on the pressure data acquired by the pressure sensor 230. The respiratory interval is used to segment lung sound data and determine respiratory rate, while the respiratory depth assists in completing the acquisition process. During the acquisition process, the smartwatch 200 displays the signal waveform corresponding to the pressure data on the display screen 220 in real time. The peak or trough values ​​of the signal waveform represent the user's respiratory depth. If the user's breathing is shallow, the user can immediately see this on the display screen 220 and increase their respiratory depth during the next breath. The Smartwatch 200 combines respiratory rate and depth to determine the signal quality of lung sound data. If the respiratory depth is too shallow or the respiratory rate is too high, it indicates that the user is not performing periodic deep breathing, and the signal quality of the lung sound data is likely poor, requiring re-collection. In addition to determining the signal quality of lung sound data, the Smartwatch 200 can also segment the lung sound data according to the breathing interval. This means that pressure data and lung sound data have the same period, with each period corresponding to one of the user's breaths. The Smartwatch 200 can extract precise lung sound features from the segmented lung sound data and input these features into a classification model to determine the user's health assessment results.

[0093] In another specific embodiment, the user can also use a breathing belt to assist in detection, establishing a connection between the smartwatch and the breathing belt, such as a Bluetooth connection. The breathing belt is equipped with a pressure sensor to collect pressure data and send the pressure data to the smartwatch. Figure 4 As shown, arrow 410 points to a smartwatch that is equipped with both an audio stethoscope and a pressure sensor. Users only need to place it on the collection point on the lungs to complete lung sound signal processing. Arrow 420 points to the smartwatch and arrow 430 points to the breathing belt. The connection between the two can also realize the lung sound signal processing method of this application embodiment.

[0094] If the user chooses to use only the smartwatch for lung sound signal processing, the smartwatch's display screen can be as follows: Figure 5A As shown, it can specifically include:

[0095] Step 1: Please select the data collection point.

[0096] Users need to select one collection point from multiple collection points. The circle indicated by arrow 501 is a collection point.

[0097] Step 2: Place the watch close to the back of the watch, with the front of the watch facing the collection point, and prepare to take a deep breath. Click "Start" to prepare for collecting lung sound data.

[0098] Place the front of the smartwatch close to the corresponding data collection point, and press the back of the smartwatch against your palm or wrist. The front of the watch has an audio stethoscope to collect lung sound data, while the back has a pressure sensor to collect pressure data. After holding your breath and preparing, tap "Start" to trigger the data collection command, while simultaneously taking deep breaths. The smartwatch will then receive the command and begin data collection.

[0099] Step 3: Observe the waveform and adjust your breathing depth. Take a deep breath until the peak of the wave exceeds the pressure threshold, and then exhale slowly.

[0100] The smartwatch displays the first signal waveform corresponding to the pressure data in real time; the waveform indicated by arrow 502 is the first signal waveform. During data collection, the user observes the respiratory waveform to adjust their breathing depth, taking a deep breath until the peak exceeds the pressure threshold and then exhaling slowly. If the peak of the first signal waveform exceeds the pressure threshold, it can be preliminarily determined that the user's breathing depth meets the standard.

[0101] Step 4: Your breathing depth is insufficient. Please take a deep breath to collect lung sound data.

[0102] If the peak of the first signal waveform does not exceed the pressure threshold, the user is reminded to increase their breathing force next time.

[0103] Step 5, data acquisition for 30 seconds.

[0104] The first time period can be preset according to the actual situation, such as 30 seconds or 1 minute. If the smartwatch detects that the pressure data does not meet the preset standard, the data will be collected again. The smartwatch can make a judgment after the pressure data is collected, or it can make a judgment in real time. For example, the total data collection time is 30 seconds, and it is expected to take 6 breaths, with 5 seconds for each breath. The smartphone can set the second threshold to 3. If more than 3 pressure data do not meet the preset standard, the data will be collected again. If the pressure data corresponding to the first 3 breaths does not meet the preset standard, the smartwatch can directly re-collect the data after 15 seconds, or it can make a judgment on whether to re-collect lung sound data after the 30-second collection is completed.

[0105] Step 6: Lung sound data acquisition completed.

[0106] After data collection and processing, the smartwatch will display the final health prediction results. In real-world scenarios, the smartwatch can also connect to a smartphone, displaying the text and waveforms on the smartphone, thus enhancing the overall monitoring experience.

[0107] In this embodiment of the application, the waveforms of lung sound signal processing using a smartwatch can be... Figure 5B As shown, arrow 503 points to the first signal waveform of the pressure data, arrow 504 points to the second signal waveform and the preset first threshold, and arrow 505 points to the third signal waveform. Arrow 506 points to the original audio data, arrow 507 points to the lung sound data after filtering and heart-lung sound separation, and arrow 508 points to the lung sound data segmentation.

[0108] If the user chooses to use both a smartwatch and a breathing belt for lung sound signal processing, the smartwatch display can be as follows: Figure 6A As shown. The displayed images are basically the same, but the waveforms in step 3 differ. Using a breathing strap to collect pressure data yields better quality data than using a pressure sensor on the back of the watch. The waveform from the breathing strap is similar to a sine wave, while the waveform from the pressure sensor only fluctuates during inhalation and becomes stable during exhalation. Users can wear the watch on their wrist and the breathing strap on their abdomen to achieve lung sound signal processing as described in this embodiment. The corresponding waveform images can be shown as follows. Figure 6B As shown, the waveforms corresponding to the pressure data are different. Arrow 601 points to the first signal waveform, arrow 602 points to the second signal waveform, and arrow 603 points to the third signal waveform.

[0109] Figure 7 This is a schematic diagram of a lung sound signal processing device provided in an embodiment of this application. This device can be deployed in a smartwatch to implement the lung sound signal processing method provided in this embodiment, such as... Figure 7 As shown, the device may include: an acquisition module 710, a processing module 720, and a determination module 730.

[0110] The acquisition module 710 is used to acquire the user's lung sound data and pressure data based on the lung sound acquisition process.

[0111] The processing module 720 is used to divide the lung sound data into multiple lung sound sub-data in the time dimension based on the pressure data.

[0112] The determination module 730 is used to determine the lung sound features of the lung sound data based on the plurality of lung sound sub-data.

[0113] The specific execution steps of each of the above modules can be found in the description of the method flowchart.

[0114] This application also provides a lung sound signal processing system, which includes a pressure sensor, an audio stethoscope, and a processor. The pressure sensor is used to acquire the user's pressure data, the audio stethoscope is used to acquire the user's lung sound data, and the processor can implement the lung sound signal processing method provided in this application based on the pressure data and lung sound data.

[0115] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0116] Electronic device 800 is deployed in terminal devices such as smartphones. Electronic device 800 may include processor 810, internal memory 821, sensor module 830, power management module 831, battery 832, and display screen 840, etc. Sensor module 830 may include: pressure sensor 830A and audio stethoscope 830B.

[0117] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 800. In other embodiments of this application, the electronic device 800 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0118] The processor 810 may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0119] The controller can generate operation control signals based on the instruction opcode and timing signals to complete the control of instruction fetching and execution.

[0120] The processor 810 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 810 is a cache memory. This memory can store instructions or data that the processor 810 has just used or that are used repeatedly. If the processor 810 needs to use the instruction or data again, it can retrieve it directly from the memory. This avoids repeated accesses, reduces the waiting time of the processor 810, and thus improves the efficiency of the system.

[0121] In some embodiments, the processor 810 may include one or more interfaces. An interface may include an inter-integrated circuit (I2C) interface, which is a bidirectional synchronous serial bus including a serial data line (SDA) and a serial clock line (SCL).

[0122] It is understood that the interface connection relationships between the modules illustrated in the embodiments of this application are merely illustrative and do not constitute a structural limitation on the electronic device 800. In other embodiments of this application, the electronic device 800 may also employ different interface connection methods or combinations of multiple interface connection methods as described in the above embodiments.

[0123] The power management module 831 is used to connect the battery 832 and the processor 810. The power management module 831 receives input from the battery 832 and supplies power to the processor 810 and internal memory 821, etc.

[0124] Display screen 840 is used to display images, videos, etc. Display screen 840 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a Mini LED, a MicroLED, a Micro-OLED, a quantum dot light-emitting diode (QLED), etc.

[0125] The 830B audio stethoscope is used to detect sound signals and can convert sound signals into electrical signals.

[0126] The 830A pressure sensor is used to sense pressure signals and can convert them into electrical signals.

[0127] Internal memory 821 can be used to store computer executable program code, which includes instructions. Internal memory 821 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback, image playback, etc.), etc. The data storage area may store data created during the use of electronic device 800 (such as audio data, phonebook, etc.). Furthermore, internal memory 821 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc. Processor 810 executes various functional applications and data processing of electronic device 800 by running instructions stored in internal memory 821 and / or instructions stored in memory located in the processor.

[0128] The processor 810 can execute various functional applications and data processing by running programs stored in the internal memory 821, such as implementing the lung sound signal processing method provided in the embodiments of this application.

[0129] This application also provides a non-transitory computer-readable storage medium that stores computer instructions that cause the computer to execute the lung sound signal processing method provided in this application.

[0130] The aforementioned non-transitory computer-readable storage medium may be any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0131] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0132] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0133] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0134] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0135] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

Claims

1. A method for processing lung sound signals, characterized in that, The method includes: Lung sound data and pressure data of users are acquired based on the lung sound acquisition process; Based on the pressure data, the lung sound data is divided into multiple lung sound sub-data in the time dimension; The lung sound features of the lung sound data are determined based on the multiple lung sound sub-data; The process of acquiring lung sound data and pressure data based on lung sound acquisition includes: Upon detecting the user-triggered acquisition command, based on the user's periodic breathing, the user's lung sound data and pressure data are acquired simultaneously during the first time period; The first signal waveform corresponding to the pressure data is displayed on the screen in real time. The first signal waveform is used to assist the user in performing the periodic breathing. Determine whether the pressure data meets the preset standard. If it is determined that the pressure data does not meet the preset standard, then re-collect the lung sound data and the pressure data. Determining whether the pressure data meets a preset standard includes: Determine the second signal waveform corresponding to the pressure data within the first time period; Multiple peaks of the second signal waveform are determined, and peaks with values ​​less than a first threshold are identified as non-standard peaks. If the number of non-standard peaks is greater than the second threshold, it is determined that the pressure data does not meet the preset standard, and the lung sound data and the pressure data are re-acquired; otherwise, it is determined that the pressure data meets the preset standard. Alternatively, determine the second signal waveform corresponding to the pressure data within the first time period; Based on multiple adjacent peaks or troughs of the second signal waveform, multiple period values ​​are determined, and period values ​​with values ​​less than a third threshold are determined as non-standard period values. If the number of non-standard periodic values ​​is greater than the fourth threshold, then the pressure data is determined to be inconsistent with the preset standard; otherwise, the pressure data is determined to be consistent with the preset standard. The step of dividing the lung sound data into multiple lung sound sub-data along the time dimension based on the pressure data includes: Determine the third signal waveform of the pressure data; Multiple time division points are determined based on multiple peaks or troughs of the third signal waveform; The lung sound data is divided into multiple lung sound sub-data in the time dimension according to the time segmentation point, wherein each lung sound sub-data is used to indicate the lung sound data corresponding to the user in a breath.

2. The method according to claim 1, characterized in that, The method further includes: If the pressure data is determined to meet the preset standard, the lung sound acquisition process ends.

3. The method according to claim 1, characterized in that, If it is determined that the pressure data does not meet the preset standard, then re-collecting the lung sound data and the pressure data includes: If it is determined that the pressure data does not meet the preset standard, the user is reminded to re-trigger the data collection command according to the preset reminder method.

4. The method according to claim 3, characterized in that, The preset reminder method includes one or more of the following combinations: Voice reminder; Text reminder; Screen flashing reminder; Vibration alert.

5. The method according to claim 1, characterized in that, The lung sound features include one or more of the following: Mel frequency cepstral coefficients; Zero crossing rate; Spectral centroid; Signal bandwidth.

6. The method according to claim 1, characterized in that, Before dividing the lung sound data into multiple lung sound sub-data in the time dimension based on the pressure data, the method further includes: The lung sound data is subjected to noise reduction filtering.

7. The method according to claim 1, characterized in that, Before dividing the lung sound data into multiple lung sound sub-data in the time dimension based on the pressure data, the method further includes: The lung sound data is subjected to cardiopulmonary sound separation processing.

8. A lung sound signal processing device, characterized in that, The device includes: The acquisition module is used to acquire the user's lung sound data and pressure data based on the lung sound acquisition process; The processing module is used to divide the lung sound data into multiple lung sound sub-data in the time dimension according to the pressure data; The determining module is used to determine the lung sound features of the lung sound data based on the plurality of lung sound sub-data; The acquisition module is specifically used to detect the acquisition command triggered by the user, and simultaneously acquire the user's lung sound data and pressure data in a first time period based on the user's periodic breathing; and display the first signal waveform corresponding to the pressure data on the display screen in real time, the first signal waveform being used to assist the user in performing the periodic breathing; Determine whether the pressure data meets the preset standard. If it is determined that the pressure data does not meet the preset standard, then re-collect the lung sound data and the pressure data. Determining whether the pressure data meets a preset standard includes: Determine the second signal waveform corresponding to the pressure data within the first time period; determine multiple peaks of the second signal waveform, and identify peaks with values ​​less than a first threshold as non-standard peaks; if the number of non-standard peaks is greater than the second threshold, determine that the pressure data does not meet the preset standard, and re-collect the lung sound data and the pressure data; otherwise, determine that the pressure data meets the preset standard. Alternatively, determine the second signal waveform corresponding to the pressure data within the first time period; Based on multiple adjacent peaks or troughs of the second signal waveform, multiple period values ​​are determined, and period values ​​with values ​​less than a third threshold are determined as non-standard period values. If the number of non-standard periodic values ​​is greater than the fourth threshold, then the pressure data is determined to be inconsistent with the preset standard; otherwise, the pressure data is determined to be consistent with the preset standard. The processing module is specifically used to determine the third signal waveform of the pressure data; determine multiple time division points based on multiple peaks or troughs of the third signal waveform; and divide the lung sound data into multiple lung sound sub-data in the time dimension based on the time division points, wherein each lung sound sub-data is used to indicate the lung sound data corresponding to the user in one breath.

9. A lung sound signal processing system, characterized in that, The system includes: Pressure sensors, audio stethoscopes, and processors; The pressure sensor is used to acquire the user's pressure data, the audio stethoscope is used to acquire the user's lung sound data, and the processor is able to implement the method as described in any one of claims 1 to 7 based on the pressure data and the lung sound data.

10. An electronic device, characterized in that, include: At least one processor; as well as At least one memory communicatively connected to the processor, wherein: The memory stores program instructions, and the processor invokes the program instructions to execute the method as described in any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images