Borborygmus recognition method and device, electronic equipment and storage medium

Abstract

According to the borborygmus recognition method and device, the electronic equipment and the storage medium, the borborygmus signal is acquired, the signal is recognized based on the preset borborygmus recognition model, the borborygmus characteristics can be efficiently and accurately analyzed, and therefore a scientific basis is provided for evaluation of the activity range and the lesion range of colitis diseases. According to the method, the diagnostic efficiency and accuracy are improved, through non-invasive borborygmus signal analysis, complexity of traditional endoscopy and discomfort of a patient are avoided, and meanwhile the diagnostic accuracy is improved; and secondly, dynamic monitoring of disease activity is realized, the activity and lesion range of colitis can be evaluated in real time by continuously collecting and identifying borborygmus signals, and dynamic illness state data support is provided for doctors.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data processing, and particularly to a method and device for identifying bowel sounds, an electronic device, and a storage medium. Background Art

[0002] Bowel sounds, i.e., abdominal sounds, are sounds caused by the movement of gas and liquid in the gastrointestinal tract. Bowel sounds can provide important physiological and pathological information to help doctors diagnose digestive system diseases such as intestinal obstruction and gastrointestinal motility disorders. Currently, doctors manually monitor bowel sounds through a stethoscope. This method relies on doctors' experience and subjective judgment, is difficult to perform continuous monitoring for a long time, is difficult to capture the dynamic changes of bowel sounds, and cannot provide comprehensive diagnostic information. Summary of the Invention

[0003] The present disclosure provides a method, device, electronic device, and storage medium for identifying bowel sounds. Its main purpose is to solve the problems of difficult long-term continuous monitoring, difficult to capture the dynamic changes of bowel sounds, and inability to provide comprehensive diagnostic information.

[0004] According to a first aspect of the present disclosure, there is provided a method for identifying bowel sounds, which includes:

[0005] Obtain bowel sound signals collected by a preset bowel sound acquisition device;

[0006] Based on a preset bowel sound recognition model, identify the bowel sound signals to obtain the recognition result of the bowel sound signals;

[0007] Compare the recognition result of the bowel sound signals to confirm the activity degree and lesion range of the colitis disease corresponding to the bowel sounds.

[0008] Optionally, the feature comparison includes at least one of the number of bowel sounds within a preset time, the duration of a single bowel sound signal, the dominant frequency range of bowel sounds, and the interval time.

[0009] Optionally, before identifying the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition result of the bowel sound signals, the method further includes:

[0010] Obtain training bowel sound data; wherein, the training bowel sound data includes normal data and data of different colitis activity degrees and lesion ranges;

[0011] Train the preset bowel sound recognition model according to the training bowel sound data to obtain the trained preset bowel sound recognition model; wherein, the training includes feature extraction based on time domain, frequency domain, and spatial domain.

[0012] Optionally, before comparing the recognition result of the bowel sound signal to confirm the disease activity and lesion range of colitis corresponding to the bowel sound, the method further includes:

[0013] Based on a preset classification algorithm, classify and evaluate the disease activity and lesion range of colitis, and establish an association relationship between the disease activity and lesion range of different colitis and bowel sound data with different characteristics.

[0014] Optionally, the recognition of the bowel sound signal based on a preset bowel sound recognition model to obtain the recognition result of the bowel sound signal includes:

[0015] Recognize at least one of the timbre, volume, and duration of the bowel sound signal based on a preset bowel sound recognition model.

[0016] According to a second aspect of the present disclosure, there is provided a bowel sound recognition device, including:

[0017] A first acquisition unit for acquiring a bowel sound signal collected by a preset bowel sound acquisition device;

[0018] A recognition unit for recognizing the bowel sound signal based on a preset bowel sound recognition model to obtain the recognition result of the bowel sound signal;

[0019] A confirmation unit for comparing the recognition result of the bowel sound signal to confirm the disease activity and lesion range of colitis corresponding to the bowel sound.

[0020] Optionally, the feature comparison includes at least one of the number of bowel sounds within a preset time, the duration of a single bowel sound signal, the dominant frequency range of the bowel sound, and the interval time.

[0021] Optionally, the device further includes:

[0022] A second acquisition unit for acquiring training bowel sound data before the recognition unit recognizes the bowel sound signal based on a preset bowel sound recognition model to obtain the recognition result of the bowel sound signal; wherein, the training bowel sound data includes normal data and data of different colitis activities and lesion ranges;

[0023] A training unit for training the preset bowel sound recognition model according to the training bowel sound data to obtain the trained preset bowel sound recognition model; wherein, the training includes feature extraction based on time domain, frequency domain, and spatial domain.

[0024] Optionally, the device further includes:

[0025] A building unit, configured to classify and evaluate the disease activity degree and lesion range of colitis based on a preset classification algorithm before the confirmation unit compares the recognition result of the bowel sound signal for feature comparison and confirms the disease activity degree and lesion range of colitis corresponding to the bowel sound, and establish an association relationship between the disease activity degree and lesion range of different colitis and bowel sound data with different features.

[0026] Optionally, the recognition unit is further configured to:

[0027] Recognize at least one of the timbre, volume, and duration of the bowel sound signal based on a preset bowel sound recognition model.

[0028] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0029] At least one processor; and

[0030] A memory communicatively connected to the at least one processor; wherein,

[0031] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method described in the foregoing first aspect.

[0032] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method described in the foregoing first aspect.

[0033] According to a fifth aspect of the present disclosure, there is provided a computer program product, including a computer program, which when executed by a processor, implements the method described in the foregoing first aspect.

[0034] The identification method, device, electronic device and storage medium for bowel sounds provided by the present disclosure mainly include the following technical solutions: obtaining bowel sound signals collected by a preset bowel sound acquisition device; identifying the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition result of the bowel sound signals; comparing the features of the recognition result of the bowel sound signals to confirm the activity degree and lesion range of colitis corresponding to the bowel sounds. Compared with the related technologies, in the embodiments of the present application, by obtaining bowel sound signals and identifying the signals based on a preset bowel sound recognition model, the features of bowel sounds can be analyzed efficiently and accurately, thereby providing a scientific basis for the evaluation of the activity degree and lesion range of colitis. The diagnostic efficiency and accuracy are improved. Through non-invasive bowel sound signal analysis, the complexity and patient discomfort of traditional endoscopic examinations are avoided, and at the same time, the diagnostic accuracy is improved. Secondly, the dynamic monitoring of the disease activity degree is realized. By continuously collecting and identifying bowel sound signals, the activity degree and lesion range of colitis can be evaluated in real time, providing dynamic disease condition data support for doctors.

[0035] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0037] Figure 1 is a schematic flowchart of a method for identifying bowel sounds provided by an embodiment of the present disclosure;

[0038] Figure 2 is a schematic structural diagram of a device for identifying bowel sounds provided by an embodiment of the present disclosure;

[0039] Figure 3 is a schematic structural diagram of a device for identifying bowel sounds provided by an embodiment of the present disclosure;

[0040] Figure 4 is a schematic block diagram of an exemplary electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to assist understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0042] The method, apparatus, electronic device, and storage medium for identifying bowel sounds according to embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0043] Figure 1 FIG. is a schematic flowchart of a method for identifying bowel sounds provided by an embodiment of the present disclosure.

[0044] As Figure 1 shown, the method includes the following steps:

[0045] Step 101: Obtain bowel sound signals collected by a preset bowel sound acquisition device.

[0046] By combining high-precision hardware devices with intelligent data processing, efficient and accurate acquisition and analysis of bowel sound signals are achieved. Specifically, the preset bowel sound acquisition device usually uses highly sensitive sensors that can capture the vibration signals of the human abdominal intestine and convert them into electrical signals for recording. In some embodiments, the device may include a portable patch sensor, a wearable device, or a flexible patch with good skin adhesion, which can perform long-term and continuous data acquisition in the natural state of the patient to ensure the integrity and authenticity of the signals.

[0047] During the acquisition process, the device will preprocess the original signal through technologies such as filtering and noise reduction to eliminate the interference of environmental noise and other physiological signals of the human body, thereby extracting pure bowel sound signals. In some embodiments, the preset bowel sound acquisition device may also be equipped with a wireless transmission function to upload the collected data to the cloud or a local server in real time, providing a high-quality data basis for subsequent intelligent identification and analysis.

[0048] Step 102: Identify the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition result of the bowel sound signals.

[0049] The collected bowel sound signals are intelligently analyzed and classified through artificial intelligence technology to extract feature information related to colitis disease. The preset bowel sound recognition model is usually constructed based on deep learning algorithms such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), or Transformers. These models are trained with a large amount of labeled bowel sound data and can learn the key features in the bowel sound signals and their associations with disease states.

[0050] In practical applications, the model will segment, extract features, and perform pattern recognition on the preprocessed bowel sound signals, analyze parameters such as the frequency, amplitude, and duration of the signals, and capture the dynamic change patterns of the signals in combination with time series data. Through this process, the model can accurately identify abnormal patterns in the bowel sound signals, such as specific frequency characteristics or rhythm changes related to the activity of colitis, and output the corresponding recognition results. These results may include classification labels of the bowel sound signals (such as normal, mild inflammation, moderate inflammation, severe inflammation) or specific quantitative indicators (such as disease activity scores), providing a scientific basis for subsequent disease assessment. This step not only greatly improves the automation level of bowel sound signal analysis but also significantly enhances the accuracy and reliability of recognition, providing strong technical support for the early diagnosis and condition monitoring of colitis.

[0051] Step 103: Compare the recognition results of the bowel sound signals to confirm the disease activity and lesion scope of the colitis corresponding to the bowel sounds.

[0052] By comparing and analyzing the recognition results with a preset disease feature database, the disease state is further quantified and the lesion scope is clarified. In this process, the results output by the bowel sound recognition model (such as frequency characteristics, amplitude changes, rhythm patterns, etc.) are matched and compared with the known colitis disease feature database. These feature databases are constructed based on a large amount of clinical data and contain typical bowel sound characteristics under different disease activities (such as remission, mild activity, moderate activity, severe activity) and lesion scopes (such as local lesions, extensive lesions). Through intelligent algorithms (such as cluster analysis, pattern matching, or regression analysis), the similarity between the current bowel sound signal and various disease states is calculated, and the corresponding disease activity score and lesion scope distribution map are generated. For example, high-frequency and irregular bowel sounds may indicate that the disease is in the active phase, while low-frequency and sparse signals may indicate the remission of the condition; at the same time, the spatial distribution characteristics of the signals can help locate the specific intestinal segments of the lesions.

[0053] The method for identifying bowel sounds provided by the present disclosure mainly includes the following technical solutions: obtaining bowel sound signals collected by a preset bowel sound acquisition device; identifying the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition result of the bowel sound signals; comparing the features of the recognition result of the bowel sound signals to confirm the activity degree and lesion range of the colitis corresponding to the bowel sounds. Compared with the related art, the embodiment of the present application can efficiently and accurately analyze the bowel sound features by obtaining the bowel sound signals and identifying the signals based on the preset bowel sound recognition model, thereby providing a scientific basis for the evaluation of the activity degree and lesion range of colitis. The diagnostic efficiency and accuracy are improved. Through non-invasive bowel sound signal analysis, the complexity and patient discomfort of traditional endoscopic examinations are avoided, and at the same time, the diagnostic accuracy is improved; secondly, the dynamic monitoring of the disease activity degree is realized. By continuously collecting and identifying bowel sound signals, the activity degree and lesion range of colitis can be evaluated in real time, providing dynamic disease condition data support for doctors.

[0054] In some embodiments, the feature comparison includes at least one of the number of bowel sounds within a preset time, the duration of a single bowel sound signal, the dominant frequency range of bowel sounds, and the interval time.

[0055] In some embodiments, before identifying the bowel sound signals based on the preset bowel sound recognition model to obtain the recognition result of the bowel sound signals, the method further includes:

[0056] obtaining training bowel sound data; wherein, the training bowel sound data includes normal data and data of different colitis activity degrees and lesion ranges;

[0057] training the preset bowel sound recognition model according to the training bowel sound data to obtain the trained preset bowel sound recognition model; wherein, the training includes feature extraction based on time domain, frequency domain, and spatial domain.

[0058] Obtaining training bowel sound data is the basis for constructing a high-precision bowel sound recognition model. The core lies in collecting a diverse and high-quality data set to cover the bowel sound features in the normal state and different colitis activity degrees and lesion ranges. Training bowel sound data is usually obtained through clinical cooperation or public databases and includes bowel sound records from healthy individuals and colitis patients. These data need to be labeled to clarify the physiological state (such as normal, mild active stage, moderate active stage, severe active stage) and lesion range (such as local lesion, extensive lesion) corresponding to each signal segment to ensure the training effect of the model. During the data acquisition process, a high-precision bowel sound acquisition device needs to be used to ensure the clarity and integrity of the signals. At the same time, interference is eliminated through preprocessing techniques such as filtering and noise reduction to provide high-quality input for subsequent analysis.

[0059] After obtaining the training data, the preset bowel sound recognition model is trained based on these data. The training process includes feature extraction based on the time domain, frequency domain, and spatial domain to comprehensively capture the multi-dimensional information of bowel sound signals. In time domain analysis, the model extracts features such as the amplitude, period, and waveform changes of the signal to reflect the time dynamic characteristics of bowel sounds; in frequency domain analysis, methods such as Fourier transform or wavelet transform are used to extract features such as the frequency distribution and energy spectrum of the signal to identify the frequency patterns under different disease states; in spatial domain analysis, combined with the data of multi-channel acquisition devices, the spatial distribution characteristics of the signal are analyzed to locate the lesion range. During the training process, the model learns the complex relationships between these features and disease states through deep learning algorithms (such as convolutional neural networks and recurrent neural networks) and continuously improves the recognition accuracy through iterative optimization. Finally, the trained preset bowel sound recognition model can efficiently and accurately analyze bowel sound signals, providing reliable support for the evaluation of the disease activity and lesion range of colitis.

[0060] In some embodiments, before comparing the recognition results of the bowel sound signals to confirm the disease activity and lesion range of colitis corresponding to the bowel sounds, the method further includes:

[0061] Based on a preset classification algorithm, the disease activity and lesion range of colitis are classified and evaluated, and the association relationships between the disease activity and lesion range of different colitis and bowel sound data with different features are established.

[0062] An accurate association relationship between bowel sound features and disease states is established through an intelligent algorithm, thereby realizing accurate disease evaluation. The preset classification algorithm usually adopts machine learning or deep learning methods, such as support vector machine (SVM), random forest (Random Forest), gradient boosting decision tree (GBDT), or deep neural network (DNN). These algorithms can efficiently process the complex features of bowel sound signals and classify them. During the classification and evaluation process, the algorithm constructs a multi-dimensional feature space based on the time domain, frequency domain, and spatial domain features extracted by the trained bowel sound recognition model, combined with clinically annotated disease activity (such as remission period, mild activity period, moderate activity period, severe activity period) and lesion range (such as local lesion, extensive lesion) data. Through feature selection, dimensionality reduction, and pattern recognition techniques, the algorithm can match bowel sound data with different features to specific disease states and generate classification results. For example, bowel sounds with high frequency, irregularity, and concentrated energy distribution may be classified as the severe activity period, while signals with low frequency, regularity, and uniform energy distribution may be classified as the remission period. At the same time, the algorithm can further locate the specific intestinal segment range of the lesion through spatial domain feature analysis, such as left half colon, right half colon, or total colon lesion.

[0063] Through this process, the system can establish the correlation between different colitis disease activities and lesion scopes and the characteristics of bowel sounds, forming a scientific classification and evaluation system. This system can not only provide doctors with intuitive disease state evaluation results but also provide data support for the formulation of personalized treatment plans. For example, for patients in the severe active stage, the system may recommend strengthening drug treatment or adjusting the treatment plan; for patients with local lesions, the system may recommend targeted local treatment measures. In addition, this classification and evaluation system can continuously improve its accuracy and applicability through continuous learning and optimization, providing strong technical support for the early diagnosis, condition monitoring, and efficacy evaluation of colitis, and promoting the development of intelligent medicine.

[0064] In some embodiments, the recognition of the bowel sound signal based on the preset bowel sound recognition model to obtain the recognition result of the bowel sound signal includes:

[0065] Recognizing at least one of the timbre, volume, and duration of the bowel sound signal based on the preset bowel sound recognition model.

[0066] Extract multi-dimensional features of the bowel sound signal through intelligent analysis, so as to provide more comprehensive data support for the evaluation of colitis disease activity and lesion scope.

[0067] In the recognition process, the model first preprocesses the bowel sound signal, including noise reduction, segmentation, and normalization, to ensure the quality of the input data. Subsequently, the model will extract and analyze at least one of the features of timbre, volume, and duration:

[0068] Timbre is one of the important features of the bowel sound signal, reflecting the spectral distribution and harmonic components of the signal. The model extracts the frequency components of the signal through frequency domain analysis (such as Fourier transform or wavelet transform) to identify its timbre characteristics. For example, bowel sounds with more high-frequency components may indicate enhanced intestinal activity, while signals with more low-frequency components may indicate weakened intestinal activity. Timbre recognition helps to distinguish the bowel sound patterns in different disease states.

[0069] Volume reflects the intensity of the bowel sound signal, and usually extracts the amplitude characteristics of the signal through time domain analysis. The model will calculate parameters such as the average amplitude and peak amplitude of the signal, and perform normalization processing in combination with the background noise level. The change in volume can reflect the intensity of intestinal peristalsis. For example, bowel sounds with a higher volume may indicate hyperactive intestinal activity, while signals with a lower volume may indicate inhibited intestinal activity.

[0070] Duration refers to the time length of a single bowel sound signal, and usually the start point and end point of the signal are extracted through time-domain analysis. The model calculates the duration of each bowel sound and analyzes its distribution pattern. For example, a bowel sound with a longer duration may indicate slow intestinal peristalsis, while a signal with a shorter duration may suggest accelerated intestinal peristalsis. Duration recognition helps to evaluate the motor function state of the intestine.

[0071] By recognizing timbre, volume, and duration, the model can comprehensively capture the characteristics of bowel sound signals and conduct correlation analysis with the disease activity and lesion range of colitis. For example, bowel sounds with high frequency, high volume, and short duration may indicate that the disease is in the active stage, while signals with low frequency, low volume, and long duration may suggest remission of the disease. These recognition results provide multi-dimensional data support for disease assessment, significantly improving the accuracy and scientific nature of diagnosis and providing a strong basis for clinical decision-making.

[0072] Corresponding to the above bowel sound recognition method, the present invention also proposes a bowel sound recognition device. Since the device embodiment of the present invention corresponds to the above method embodiment, details not disclosed in the device embodiment can be referred to the above method embodiment and will not be elaborated in the present invention.

[0073] Figure 2 The structural schematic diagram of a bowel sound recognition device provided by an embodiment of the present disclosure is shown as Figure 2 shown, including:

[0074] A first acquisition unit 21, configured to acquire bowel sound signals collected by a preset bowel sound acquisition device;

[0075] A recognition unit 22, configured to recognize the bowel sound signals based on a preset bowel sound recognition model to obtain recognition results of the bowel sound signals;

[0076] A confirmation unit 23, configured to perform feature comparison on the recognition results of the bowel sound signals to confirm the disease activity and lesion range of colitis corresponding to the bowel sound.

[0077] The bowel sound recognition method provided by the present disclosure mainly includes the following technical solutions: obtaining bowel sound signals collected by a preset bowel sound acquisition device; recognizing the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition results of the bowel sound signals; comparing the features of the recognition results of the bowel sound signals to confirm the activity degree and lesion range of the colitis corresponding to the bowel sounds. Compared with the related technologies, the embodiments of the present application can efficiently and accurately analyze the bowel sound features by obtaining bowel sound signals and recognizing the signals based on a preset bowel sound recognition model, thereby providing a scientific basis for the evaluation of the activity degree and lesion range of colitis. The diagnostic efficiency and accuracy are improved. Through non-invasive bowel sound signal analysis, the complexity and patient discomfort of traditional endoscopic examinations are avoided, and the diagnostic accuracy is improved at the same time. Secondly, the dynamic monitoring of the disease activity degree is realized. By continuously collecting and recognizing bowel sound signals, the activity degree and lesion range of colitis can be evaluated in real time, providing dynamic condition data support for doctors.

[0078] Further, in a possible implementation manner of the embodiments of the present disclosure, the feature comparison includes at least one of the number of bowel sounds within a preset time, the duration of a single bowel sound signal, the dominant frequency range of bowel sounds, and the interval time.

[0079] Further, in a possible implementation manner of the embodiments of the present disclosure, as Figure 3 shown, the device further includes:

[0080] A second acquisition unit 24, configured to obtain training bowel sound data before the recognition unit 22 recognizes the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition results of the bowel sound signals; wherein, the training bowel sound data includes normal data and data of different colitis activity degrees and lesion ranges;

[0081] A training unit 25, configured to train the preset bowel sound recognition model according to the training bowel sound data to obtain the trained preset bowel sound recognition model; wherein, the training includes feature extraction based on time domain, frequency domain, and spatial domain.

[0082] Further, in a possible implementation manner of the embodiments of the present disclosure, as Figure 3 shown, the device further includes:

[0083] A establishing unit 26, configured to classify and evaluate the activity degree and lesion range of colitis based on a preset classification algorithm before the confirmation unit 23 compares the features of the recognition results of the bowel sound signals to confirm the activity degree and lesion range of the colitis corresponding to the bowel sounds, and establish an association relationship between the activity degree and lesion range of different colitis and bowel sound data with different features.

[0084] Further, in a possible implementation manner of the embodiments of the present disclosure, as Figure 3 shown, the recognition unit is further configured to:

[0085] Based on a preset bowel sound recognition model, recognize at least one of the timbre, volume, and duration of the bowel sound signal.

[0086] It should be noted that the foregoing explanations of the method embodiments are also applicable to the devices of the embodiments of the present disclosure. Since the principles are the same, they are not limited in the embodiments of the present disclosure.

[0087] According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0088] Figure 4 FIG. shows a schematic block diagram of an exemplary electronic device 300 that can be used to implement the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0089] As Figure 4 shown, the device 300 includes a computing unit 301, which can execute various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 302 or a computer program loaded from a storage unit 308 into a RAM (Random Access Memory) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An I / O (Input / Output) interface 305 is also connected to the bus 304.

[0090] A plurality of components in the device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0091] The computing unit 301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any suitable processor, controller, microcontroller, etc. The computing unit 301 executes the various methods and processes described above, such as the bowel sound recognition method. For example, in some embodiments, the bowel sound recognition method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method described above can be executed. Alternatively, in other embodiments, the computing unit 301 can be configured to execute the aforementioned bowel sound recognition method in any other suitable manner (e.g., by means of firmware).

[0092] The various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SoCs (System On Chip), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0093] The program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0094] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only Memory), or a flash memory, an optical fiber, a CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0095] To provide for interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0096] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, and a blockchain network.

[0097] A computer system may include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system or a server combined with a blockchain.

[0098] Here, it should be noted that artificial intelligence is a discipline that studies to make a computer simulate certain thinking processes and intelligent behaviors of humans (such as learning, reasoning, thinking, planning, etc.), and there are both hardware-level technologies and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include several major directions such as computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, and knowledge graph technology.

[0099] It should be understood that various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0100] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A method for identifying bowel sounds, characterized in that, including: Obtaining bowel sound signals collected by a preset bowel sound acquisition device; Identifying the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition results of the bowel sound signals; Comparing the features of the recognition results of the bowel sound signals to confirm the activity degree and lesion range of colitis corresponding to the bowel sounds.

2. The method according to claim 1, characterized in that The feature comparison includes at least one of the number of bowel sounds within a preset time, the duration of a single bowel sound signal, the dominant frequency range of bowel sounds, and the interval time.

3. The method according to claim 1, wherein Before identifying the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition results of the bowel sound signals, the method further includes: Obtaining training bowel sound data; wherein, the training bowel sound data includes normal data and data of different activity degrees and lesion ranges of colitis; Training the preset bowel sound recognition model according to the training bowel sound data to obtain the trained preset bowel sound recognition model; wherein, the training includes feature extraction based on time domain, frequency domain, and spatial domain.

4. The method according to claim 1, wherein Before comparing the features of the recognition results of the bowel sound signals to confirm the activity degree and lesion range of colitis corresponding to the bowel sounds, the method further includes: Based on a preset classification algorithm, classifying and evaluating the activity degree and lesion range of colitis, and establishing an association relationship between the activity degree and lesion range of different colitis and bowel sound data with different features.

5. The method according to claim 1, wherein The identifying the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition results of the bowel sound signals includes: Identifying at least one of the timbre, volume, and duration of the bowel sound signals based on a preset bowel sound recognition model.

6. An identifying device for bowel sounds, characterized in that, including: A first obtaining unit for obtaining bowel sound signals collected by a preset bowel sound acquisition device; An identifying unit for identifying the bowel sound signals based on a preset bowel sound recognition model to obtain the recognition results of the bowel sound signals; A confirming unit for comparing the features of the recognition results of the bowel sound signals to confirm the activity degree and lesion range of colitis corresponding to the bowel sounds.

7. The device according to claim 6, characterized in that, The feature comparison includes at least one of the number of bowel sounds within a preset time, the duration of a single bowel sound signal, the dominant frequency range of bowel sounds, and the interval time.

8. An electronic device, characterized in that, including: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-5.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

10. A computer program product, characterized in that, including a computer program, which when executed by a processor, implements the method according to any one of claims 1-5.

Images