Audio fault diagnosis method, system and equipment

Abstract

The invention provides an audio fault diagnosis method, system and device. The method comprises the following steps: synchronously acquiring current vehicle-mounted multi-source audio data and vehicle state information; based on the vehicle-mounted multi-source audio data and the vehicle state information, adopting a pre-deployed local diagnosis model to perform local fault diagnosis so as to generate a local diagnosis report; uploading the vehicle-mounted multi-source audio data, the vehicle state information and the local diagnosis report to a cloud, performing cloud fault diagnosis through a cloud diagnosis model, and obtaining a cloud diagnosis report; and generating a final fault diagnosis report based on the local diagnosis report and the cloud diagnosis report. According to the method provided by the invention, the technical problems that the audio fault detection efficiency is low and seriously depends on the experience of an engineer are effectively solved, the audio fault detection efficiency is improved, and the dependence on the experience of the engineer is reduced.

Description

Technical Field

[0001] This application belongs to the field of automotive electronics technology, specifically relating to an audio fault diagnosis method, system, and device. Background Technology

[0002] In-vehicle audio systems are the core medium for human-machine interaction in modern intelligent vehicles. They not only provide entertainment and communication functions such as music playback and voice assistant interaction, but also integrate safety warning functions such as navigation prompts, collision warnings, and blind spot monitoring.

[0003] However, as in-vehicle audio systems become increasingly complex and interact with multiple devices (such as mobile phone Bluetooth, vehicle-to-everything (V2X) protocols, rear-seat entertainment systems, and various microphone and speaker arrays), the compatibility, stability, and interactivity issues they face in real-world use are becoming increasingly prominent. Especially in real-world scenarios with diverse user device combinations, fluctuating environmental noise, and unstable network conditions, abnormal phenomena such as audio transmission delays, voice recognition failures, alarm tone distortion, and noise interference occur frequently. These faults can range from minor issues affecting user experience to serious problems such as delayed or misidentified safety alarms leading to driving risks.

[0004] Currently, the diagnosis of after-sales problems with in-vehicle audio systems mainly relies on users' subjective descriptions (such as "noise" or "unresponsive voice wake-up") and engineers' manual investigation and analysis of massive amounts of device logs and audio clips. This method is not only inefficient but also heavily dependent on engineers' experience, making it difficult to systematically and quickly locate the root cause of the fault from multi-dimensional data. Summary of the Invention

[0005] To address the aforementioned technical problems, this application proposes an audio fault diagnosis method, system, and device that is highly efficient and accurate in fault diagnosis and does not rely on engineers' experience.

[0006] Specifically, this application proposes an audio fault diagnosis method, including: The system synchronously collects current in-vehicle multi-source audio data and vehicle status information; performs local fault diagnosis using a pre-deployed local diagnostic model based on the in-vehicle multi-source audio data and vehicle status information to generate a local diagnostic report; uploads the in-vehicle multi-source audio data, vehicle status information, and local diagnostic report to the cloud to perform cloud fault diagnosis using a cloud diagnostic model to obtain a cloud diagnostic report; and generates a final fault diagnosis report based on the local diagnostic report and the cloud diagnostic report.

[0007] In the above technical solution, by simultaneously collecting multi-source audio data and vehicle status information, the temporal and spatial consistency of the collected data can be ensured. Through two different diagnostic methods—local fault diagnosis and cloud-based fault diagnosis—preliminary analysis can be performed on the vehicle's infotainment system, quickly locating common or obvious fault patterns and generating preliminary reports, supporting rapid on-site troubleshooting or providing immediate feedback to users. The cloud-based diagnostic model utilizes the powerful computing capabilities and storage resources of the cloud to perform deeper and more complex analysis on the uploaded complete dataset, without relying on engineer experience. This not only improves the efficiency of audio fault diagnosis but also ensures its accuracy.

[0008] As one implementation method, the step of performing local fault diagnosis using a pre-deployed local diagnostic model based on the in-vehicle multi-source audio data and the vehicle status information further includes: Based on the in-vehicle multi-source audio data, the local diagnostic model is used to perform fault diagnosis on various audio types to obtain local fault diagnosis results; based on the local fault diagnosis results and the vehicle status information, the local diagnostic report is generated.

[0009] By performing fault diagnosis on multi-source in-vehicle audio data from various audio sources, multi-dimensional parallel diagnosis was achieved, comprehensively covering fault diagnosis for various audio types and improving the breadth of fault detection. Local diagnostic reports were generated by combining local fault diagnosis results with vehicle status information, thus establishing a correlation between faults and the vehicle's operational context, making the diagnostic results more context-aware and interpretable.

[0010] Furthermore, uploading the in-vehicle multi-source audio data, the vehicle status information, and the local diagnostic report to the cloud includes: The local diagnostic report, vehicle status information, and in-vehicle multi-source audio data are encrypted based on preset encryption rules, and the encrypted local diagnostic report, vehicle status information, and in-vehicle multi-source audio data are uploaded to the cloud.

[0011] By encrypting the local diagnostic report, vehicle status information, and in-vehicle multi-source audio data, the confidentiality and integrity of sensitive data during transmission and storage are ensured, mitigating the risk of complete privacy leakage. This maintains the authenticity and immutability of the diagnostic data chain, guaranteeing the credibility of diagnostic conclusions.

[0012] Furthermore, the cloud-based fault diagnosis using a cloud-based diagnostic model includes: The encrypted local diagnostic report, vehicle status information, and in-vehicle multi-source audio data are decrypted based on preset decryption rules. Cloud fault diagnosis is then performed on the decrypted in-vehicle multi-source audio data based on the cloud diagnostic model to obtain the cloud diagnostic report.

[0013] By decrypting encrypted local diagnostic reports, vehicle status information, and in-vehicle multi-source audio data, only legally authorized cloud providers can restore the encrypted data to its original form. This ensures data sovereignty and privacy while unleashing the powerful computing capabilities and data aggregation potential of the cloud. This allows cloud-based diagnostic models to perform in-depth, interference-free analysis of complete data, significantly improving the accuracy of fault diagnosis.

[0014] Furthermore, the cloud-based fault diagnosis includes: The cloud-based diagnostic model is used to perform multi-dimensional fault diagnosis on the in-vehicle multi-source audio data to obtain the cloud-based diagnostic results.

[0015] By using a cloud-based diagnostic model to perform multi-dimensional fault diagnosis on multi-source audio data in vehicles, a comprehensive diagnosis of audio faults can be achieved. This includes time-domain and frequency-domain diagnosis, which can accurately quantify the energy distribution of noise and identify anomalies that are difficult for the human ear to locate. Through time-domain diagnosis, the amplitude, waveform, and timing relationship of audio data can be analyzed, and transient pulses can be accurately detected, which can effectively distinguish and locate faults.

[0016] Furthermore, the cloud-based fault diagnosis via the cloud-based diagnostic model also includes: The cloud-based diagnostic results are correlated with the vehicle status information to obtain correlation analysis results. Based on the cloud-based diagnostic results, the correlation analysis results, and the vehicle status information, a historical fault database is retrieved to obtain a corresponding repair plan. A cloud-based diagnostic report is generated based on the maintenance plan and the cloud-based diagnostic results.

[0017] This system integrates cloud-based diagnostic results with vehicle status information. For example, when checking for audio interruptions, it can examine whether they are accompanied by DSP (Digital Signal Processing) errors or network disconnections. This enables deep reasoning from fault symptoms to specific causes, accurately locating the fault. This effectively improves the efficiency of fault diagnosis and repair.

[0018] Furthermore, after generating the final fault diagnosis report based on the local diagnostic report and the cloud-based diagnostic report, the process further includes: The final fault diagnosis report is pushed to the maintenance terminal, and a fault alarm is triggered based on the final fault diagnosis report. The maintenance results fed back by the maintenance terminal are obtained, and the historical fault database and the cloud-based diagnostic model are optimized based on the maintenance results.

[0019] By pushing the final fault diagnosis report to the maintenance end and issuing fault alerts based on the report, it ensures that users and maintenance personnel can promptly identify faults and perform corresponding repairs. This ensures that critical fault diagnosis results are not lost or delayed during information flow. A data-driven diagnostic validity verification and feedback loop has been established, enabling continuous, automated, and precise iterative optimization of the diagnostic system.

[0020] Based on the same inventive concept, this application also proposes an audio fault diagnosis system, the system comprising: The data acquisition module is used to simultaneously collect current in-vehicle multi-source audio data and vehicle status information.

[0021] The local diagnostic module is used to perform local fault diagnosis based on the in-vehicle multi-source audio data and the vehicle status information using a pre-deployed local diagnostic model, so as to generate a local diagnostic report.

[0022] The cloud diagnostic module is used to upload the in-vehicle multi-source audio data, the vehicle status information, and the local diagnostic report to the cloud, so as to perform cloud fault diagnosis through the cloud diagnostic model and obtain a cloud diagnostic report.

[0023] In addition, a report generation module is used to generate a final fault diagnosis report based on the local diagnostic report and the cloud diagnostic report.

[0024] Furthermore, the system also includes: The fault alarm module is used to generate fault alarms based on the final fault diagnosis report.

[0025] The optimization module is used to push the final fault diagnosis report to the maintenance terminal and obtain the maintenance results fed back by the maintenance terminal; and to optimize the historical fault database and the cloud-based diagnostic model based on the maintenance results.

[0026] Based on the same inventive concept, this application also proposes a computer device, which includes at least a processor and a memory, wherein the memory stores computer-executable instructions, and the computer-executable instructions can be read and executed by the processor to perform the audio fault diagnosis method.

[0027] Compared with the prior art, this application has at least the following beneficial effects: This application ensures temporal and spatial consistency of the collected data by simultaneously acquiring multi-source audio data and vehicle status information. Through both local and cloud-based fault diagnosis methods, preliminary analysis can be performed on the vehicle's infotainment system, quickly identifying common or obvious fault patterns and generating preliminary reports. This supports rapid on-site troubleshooting or provides immediate feedback to users. The cloud-based diagnostic model leverages the powerful computing and storage resources of the cloud to perform deeper and more complex analysis of the uploaded complete dataset, eliminating reliance on engineer experience. This not only improves the efficiency of audio fault diagnosis but also ensures its accuracy. Attached Figure Description

[0028] Figure 1 This is a flowchart illustrating an audio fault diagnosis method according to an embodiment of this application.

[0029] Figure 2 This is a schematic diagram of an audio fault diagnosis system shown in an embodiment of this application. Detailed Implementation

[0030] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. Example 1:

[0032] Please refer to Figure 1 The audio fault diagnosis method mainly includes steps S100 to S400.

[0033] Step S100 includes: synchronously acquiring current in-vehicle multi-source audio data and vehicle status information. The in-vehicle multi-source audio data mainly includes microphone input audio data and speaker output audio data, but is not limited to these. The vehicle status information mainly includes vehicle CAN bus data, ECU operating logs, network connection status, etc., but is not limited to these.

[0034] Step S200 includes: performing local fault diagnosis based on the in-vehicle multi-source audio data and the vehicle status information using a pre-deployed local diagnostic model to generate a local diagnostic report. This local diagnostic model can primarily employ a lightweight AI diagnostic model, such as a convolutional neural network model, and is not limited to any particular model. This local diagnostic model can primarily perform basic fault diagnosis on the in-vehicle multi-source audio data. For example, it can be used for audio signal quality diagnosis, voice interaction performance diagnosis, and audio signal integrity diagnosis.

[0035] Step S300 includes: uploading the in-vehicle multi-source audio data, the vehicle status information, and the local diagnostic report to the cloud, so as to perform cloud-based fault diagnosis through a cloud-based diagnostic model and obtain a cloud-based diagnostic report. This cloud-based diagnostic model can primarily perform in-depth fault diagnosis on the in-vehicle multi-source audio data. For example, it can perform time-domain and frequency-domain analysis on the in-vehicle multi-source audio data to obtain information such as a spectrogram, and then perform contextual correlation analysis based on the vehicle status information. Based on the correlation analysis results and the cloud-based diagnostic results, a cloud-based diagnostic report is obtained from a historical database.

[0036] Furthermore, step S400 includes generating a final fault diagnosis report based on the local diagnostic report and the cloud-based diagnostic report. This final fault diagnosis report may primarily include information such as the fault type, fault cause, and repair plan, but is not limited to these.

[0037] In the specific implementation process, when a user triggers audio diagnostics in the vehicle system, multi-source audio data, such as microphone input audio stream data and speaker output audio stream data, as well as vehicle status information, such as network connection status and user operation records, can be collected simultaneously. A locally deployed local diagnostic model performs basic audio fault diagnosis, including distortion, popping, background noise, audio interruption, and audio signal quality issues. This is combined with vehicle status information for correlation analysis; for example, when an audio interruption occurs, the network connection status is checked for disconnection. A local diagnostic report is generated based on the local diagnostic results and correlation analysis results. The multi-source audio data, vehicle status information, and the local diagnostic report are then encrypted and uploaded to the cloud. After decryption in the cloud, a cloud-based diagnostic model is used for cloud-based fault diagnosis. For example, time-domain and frequency-domain analysis is performed on the multi-source audio data to obtain spectrum diagrams and other information. Contextual correlation analysis is then performed based on the vehicle status information. Based on the correlation analysis results and cloud diagnostic results, corresponding repair strategies are retrieved from the historical fault database. The cloud diagnostic report is generated using the cloud diagnostic results, correlation analysis results, and repair plan. Finally, a final fault diagnosis report is generated based on the local diagnostic report and the cloud diagnostic report.

[0038] In some embodiments, the step of performing local fault diagnosis based on the in-vehicle multi-source audio data and the vehicle status information using a pre-deployed local diagnostic model further includes: Based on the in-vehicle multi-source audio data, the local diagnostic model is used to perform various audio fault diagnoses to obtain local fault diagnosis results. A local diagnostic report is generated based on the local fault diagnosis results and the vehicle status information.

[0039] This local diagnostic model primarily enables basic fault diagnosis of the in-vehicle multi-source audio data. For example, it can be used to diagnose audio signal quality, voice interaction performance, and audio signal integrity. It can also diagnose issues such as mute, distortion, popping sounds, and noise in the in-vehicle multi-source audio data, but is not limited to these. A local diagnostic report is generated based on the local fault diagnosis results and vehicle status information. For example, when a signal interruption is detected in the current audio, it may be accompanied by DSP errors or network disconnections. This local diagnostic report can mainly include the problem type, suspected fault cause, and a summary of key evidence, without limitation. The summary of key evidence can mainly include abnormal timestamps, spectrum segments, and error codes, but is not limited to these.

[0040] Preferably, uploading the in-vehicle multi-source audio data, the vehicle status information, and the local diagnostic report to the cloud includes: The local diagnostic report, vehicle status information, and in-vehicle multi-source audio data are encrypted based on preset encryption rules, and the encrypted local diagnostic report, vehicle status information, and in-vehicle multi-source audio data are uploaded to the cloud.

[0041] Those skilled in the art can adopt different encryption rules depending on the actual situation. For example, they can use asymmetric encryption, such as RSA-2048, or symmetric encryption, such as AES-256-GCM. However, they are not limited to these.

[0042] Preferably, the cloud-based fault diagnosis via a cloud-based diagnostic model includes: The encrypted local diagnostic report, vehicle status information, and in-vehicle multi-source audio data are decrypted based on preset decryption rules. Cloud fault diagnosis is then performed on the decrypted in-vehicle multi-source audio data based on the cloud diagnostic model to obtain the cloud diagnostic report.

[0043] The local diagnostic report, vehicle status information, and in-vehicle multi-source audio data obtained from the asymmetric private key can be decrypted using an asymmetric encryption algorithm, or a corresponding symmetric decryption algorithm can be used.

[0044] Preferably, the cloud-based fault diagnosis includes: performing multi-dimensional fault diagnosis on the in-vehicle multi-source audio data through the cloud-based diagnostic model to obtain the cloud-based diagnostic results.

[0045] This multi-dimensional fault diagnosis mainly includes frequency domain analysis and time domain analysis, but is not limited to these.

[0046] Preferably, the cloud-based fault diagnosis via a cloud-based diagnostic model further includes: The cloud-based diagnostic results are correlated with the vehicle status information to obtain correlation analysis results. Based on the cloud-based diagnostic results, the correlation analysis results, and the vehicle status information, a historical fault database is retrieved to obtain a corresponding repair plan. A cloud-based diagnostic report is generated based on the maintenance plan and the cloud-based diagnostic results.

[0047] For example, cloud-based diagnostic results can be correlated with ECU logs, vehicle network status, and operation sequences to obtain correlation analysis results. For instance, this analysis can determine whether a voice wake-up failure is caused by a combination of factors, such as poor microphone signal, DSP congestion, network interruption, or high-speed wind noise. Corresponding repair solutions can then be obtained by retrieving data from a historical fault database.

[0048] Preferably, after generating the final fault diagnosis report based on the local diagnostic report and the cloud diagnostic report, the method further includes: The final fault diagnosis report is pushed to the maintenance terminal, and a fault alarm is triggered based on the report. The maintenance results are then obtained from the maintenance terminal. Based on these results, the historical fault database and the cloud-based diagnostic model are optimized.

[0049] The final fault diagnosis report primarily includes, but is not limited to, the fault type, fault cause, and repair plan. Fault types can mainly include hardware, software, and environmental faults. It can also include graphical evidence chains, such as spectrum diagrams. After the final fault diagnosis report is pushed to the maintenance end, maintenance personnel can quickly locate the fault, obtain information such as the fault type and cause, and thus perform efficient fault repair. Fault alarms can be triggered based on the final fault diagnosis report; for example, when a decrease in high-frequency response in the audio is detected, an alarm can be issued to suggest that the user check the speakers during maintenance. This enables efficient fault location and maintenance based on precise repair plans. Fast and accurate repairs directly improve customer satisfaction and enhance user trust in the brand and its technological appeal. Example 2:

[0050] Please refer to Figure 2 This application also proposes a system using the audio fault diagnosis method described in Embodiment 1, which mainly includes: a data acquisition module, a local diagnosis module, a cloud diagnosis module, and a report generation module.

[0051] The data acquisition module is used to simultaneously collect current in-vehicle multi-source audio data and vehicle status information. Users can trigger the system for fault diagnosis through the diagnostic interface of the in-vehicle application. For example, clicking "Start Diagnosis" in the in-vehicle application will immediately activate the system to begin fault diagnosis, simultaneously collecting in-vehicle multi-source audio data and vehicle status information, such as microphone input audio streams and speaker output audio streams. Vehicle status information may include CAN bus data, key ECU operating logs, network connection status, user operation records, vehicle dynamic information, etc., but is not limited to these.

[0052] The local diagnostic module is used to perform local fault diagnosis based on the in-vehicle multi-source audio data and the vehicle status information using a pre-deployed local diagnostic model to generate a local diagnostic report. This local diagnostic model can primarily be a locally deployed lightweight AI diagnostic model. It performs basic fault detection on the in-vehicle multi-source audio data, such as detecting features like silence, distortion, popping sounds, and background noise, as well as audio interruption fault detection, audio signal quality fault detection, etc., without limitation.

[0053] The cloud-based diagnostic module uploads the in-vehicle multi-source audio data, vehicle status information, and local diagnostic reports to the cloud for cloud-based fault diagnosis using a cloud-based diagnostic model, generating a cloud-based diagnostic report. This module primarily utilizes the cloud-based diagnostic model for in-depth fault diagnosis, such as audio spectrum analysis and audio time-domain analysis, and performs full-context dynamic correlation analysis based on vehicle status information to obtain the cloud-based diagnostic report. For example, it analyzes whether voice wake-up failure is caused by a combination of factors, including poor microphone signal, DSP blocking, and network interruption. The cloud-based diagnostic report mainly includes fault diagnosis results, repair plans, and fault causes obtained through correlation analysis, among other things; no specific limitations are imposed here.

[0054] In addition, a report generation module is used to generate a final fault diagnosis report based on the local diagnostic report and the cloud diagnostic report.

[0055] Furthermore, the system also includes a fault alarm module for issuing fault alarms based on the final fault diagnosis report. The fault alarm module can primarily display current fault information and solutions on the in-vehicle display screen based on the final fault diagnosis report; for example, if a decrease in high-frequency audio response is detected, it may suggest checking the speakers during maintenance. While a display screen combined with a speaker can be used for alarms, it is not limited to this method.

[0056] The optimization module is used to push the final fault diagnosis report to the maintenance end and obtain the repair results fed back by the maintenance end; based on the repair results, it optimizes the historical fault database and the cloud-based diagnostic model. Specifically, optimizing the historical fault database and the cloud-based diagnostic model based on the repair results makes the system more accurate with repeated use. For example, when an engineer discovers a more effective repair solution during fault repair, they can feed that solution back to the system, updating the historical fault database accordingly, thereby effectively improving the accuracy and efficiency of the system's audio fault diagnosis. Example 3:

[0057] This application also proposes a computer device, which includes at least a processor and a memory, wherein the memory stores computer-executable instructions that can be read by the processor and executed as the audio fault diagnosis method described in Embodiment 1.

[0058] The computer device can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The memory can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0059] In summary, the method provided in this application effectively solves the technical problems of low efficiency and heavy reliance on engineer experience in audio fault detection. By simultaneously collecting multi-source audio data and vehicle status information, the temporal and spatial consistency of the collected data can be ensured. Through two different diagnostic methods—local fault diagnosis and cloud-based fault diagnosis—preliminary analysis can be performed on the vehicle's infotainment system, quickly locating common or obvious fault patterns and generating preliminary reports, supporting rapid on-site troubleshooting or providing immediate feedback to users. The cloud-based diagnostic model utilizes the powerful computing capabilities and storage resources of the cloud to perform deeper and more complex analysis on the uploaded complete dataset, eliminating the need for engineer experience. This not only improves the efficiency of audio fault diagnosis but also ensures its accuracy.

[0060] In the several embodiments provided in this application, it will be understood that each block in the flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.

[0061] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0062] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application for those skilled in the art.

Claims

1. An audio fault diagnosis method, characterized in that, include: Simultaneously collect current in-vehicle multi-source audio data and vehicle status information; Based on the in-vehicle multi-source audio data and the vehicle status information, a pre-deployed local diagnostic model is used to perform local fault diagnosis to generate a local diagnostic report. The in-vehicle multi-source audio data, the vehicle status information, and the local diagnostic report are uploaded to the cloud to perform cloud-based fault diagnosis through a cloud-based diagnostic model and obtain a cloud-based diagnostic report. In addition, a final fault diagnosis report is generated based on the local diagnostic report and the cloud diagnostic report.

2. The audio fault diagnosis method according to claim 1, characterized in that, The method of performing local fault diagnosis based on the in-vehicle multi-source audio data and the vehicle status information using a pre-deployed local diagnostic model also includes: Based on the in-vehicle multi-source audio data, the local diagnostic model is used to perform fault diagnosis on various audio types in order to obtain local fault diagnosis results. The local diagnostic report is generated based on the local fault diagnosis results and the vehicle status information.

3. The audio fault diagnosis method according to claim 2, characterized in that, The step of uploading the in-vehicle multi-source audio data, the vehicle status information, and the local diagnostic report to the cloud includes: The local diagnostic report, vehicle status information, and in-vehicle multi-source audio data are encrypted based on preset encryption rules, and the encrypted local diagnostic report, vehicle status information, and in-vehicle multi-source audio data are uploaded to the cloud.

4. The audio fault diagnosis method according to claim 3, characterized in that, The cloud-based fault diagnosis using a cloud-based diagnostic model includes: Based on preset decryption rules, the encrypted local diagnostic report, the vehicle status information, and the in-vehicle multi-source audio data are decrypted. Based on the cloud diagnostic model, cloud fault diagnosis is performed on the decrypted in-vehicle multi-source audio data to obtain the cloud diagnostic report.

5. The audio fault diagnosis method according to claim 4, characterized in that, The cloud-based fault diagnosis includes: The cloud-based diagnostic model is used to perform multi-dimensional fault diagnosis on the in-vehicle multi-source audio data to obtain the cloud-based diagnostic results.

6. The audio fault diagnosis method according to claim 5, characterized in that, The cloud-based fault diagnosis via a cloud-based diagnostic model also includes: The cloud-based diagnostic results are correlated with the vehicle status information to obtain correlation analysis results; Based on the cloud-based diagnostic results, the correlation analysis results, and the vehicle status information, a historical fault database is retrieved to obtain the corresponding repair plan. The cloud diagnostic report is generated based on the maintenance plan and the cloud diagnostic results.

7. The audio fault diagnosis method according to claim 6, characterized in that, After generating the final fault diagnosis report based on the local diagnostic report and the cloud diagnostic report, the process also includes: The final fault diagnosis report is pushed to the maintenance terminal, and a fault alarm is generated based on the final fault diagnosis report. Obtain the maintenance results fed back by the maintenance terminal; The historical fault database and the cloud-based diagnostic model are optimized based on the maintenance results.

8. A system based on the audio fault diagnosis method according to any one of claims 1 to 7, characterized in that, The system includes: The data acquisition module is used to simultaneously collect current in-vehicle multi-source audio data and vehicle status information; The local diagnostic module is used to perform local fault diagnosis based on the in-vehicle multi-source audio data and the vehicle status information using a pre-deployed local diagnostic model, so as to generate a local diagnostic report. The cloud diagnostic module is used to upload the in-vehicle multi-source audio data, the vehicle status information and the local diagnostic report to the cloud, so as to perform cloud fault diagnosis through the cloud diagnostic model and obtain a cloud diagnostic report; In addition, a report generation module is used to generate a final fault diagnosis report based on the local diagnostic report and the cloud diagnostic report.

9. The system of the audio fault diagnosis method according to claim 8, characterized in that, The system also includes: The fault alarm module is used to generate fault alarms based on the final fault diagnosis report; The optimization module is used to push the final fault diagnosis report to the maintenance terminal and obtain the maintenance results fed back by the maintenance terminal; and to optimize the historical fault database and the cloud-based diagnostic model based on the maintenance results.

10. A computer device, characterized in that, The computer device includes at least a processor and a memory, wherein the memory stores computer-executable instructions that can be read by the processor and executed as described in any one of claims 1-7.

Images