Vehicle fault diagnosis method and device, server and vehicle

Abstract

The invention relates to a vehicle fault diagnosis method and device, a server and a vehicle, and relates to the technical field of vehicle safety diagnosis. The technical problems that when the fault of the vehicle is diagnosed, the determined diagnosis result is one-sided, and the accuracy of the diagnosis result is poor are at least solved. The method is applied to a server, and comprises the steps of obtaining vehicle end data of a vehicle, and determining a data type of the vehicle end data; determining a cue word template corresponding to the data type of the vehicle end data, wherein the cue word template is used for constructing model input information; based on the vehicle end data and the cue word template, constructing model input information of the vehicle end data; and inputting the model input information into the first fault diagnosis model, and determining a fault diagnosis result of the vehicle. The method and the device are used for improving the accuracy of a determined diagnosis result when a fault of a vehicle is diagnosed.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle safety diagnosis, and in particular to a vehicle fault diagnosis method, device, server and vehicle. Background Art

[0002] As the number of new energy-intelligent vehicles in my country gradually increases, the intelligence level and safety performance of vehicles have attracted widespread attention from users. And with the rapid development of artificial intelligence technology, AI big models have made vehicles become the next generation of mobile terminals. AI big models have brought changes to vehicle fault diagnosis with their powerful data processing and analysis capabilities. At present, by collecting relevant data of various vehicle components, the status of the vehicle is monitored and maintenance suggestions are provided to maintenance personnel.

[0003] In the related art, the collected battery data is preprocessed, and then the processed data is converted into a format suitable for model input for use by the large language model. The input data is inferred and calculated using the loaded large language model to obtain the inference result of the battery state, and the result is parsed to parse the inference result of the model into information with actual physical meaning. This technical solution is aimed at the battery data of the vehicle, so as to infer the inference result of the battery state by inferring the battery data. In another related art, by obtaining the driving data, operation data and the current operating state of each component in the vehicle, the fault warning level corresponding to each component in the current vehicle is determined based on the operation data and driving data; the fault warning level is corrected based on the current operating state of each component, and the corrected fault warning level is used as the actual fault warning level. Then, the driving state of the current vehicle is determined based on the driving data, and based on the actual fault warning level, the actual fault display strategy corresponding to the current driving state is determined according to the preset corresponding relationship between the current driving state and the fault display strategy, and the fault warning state corresponding to the actual fault warning level is sent to the terminal device according to the actual fault display strategy. This technical solution determines the corresponding fault warning level and the corresponding fault warning state based on the vehicle's driving data, operating data and the operating status of each component. Its purpose is only to determine the vehicle's fault level, but does not determine the specific cause of the vehicle's fault and the corresponding maintenance and disposal plan. Therefore, when diagnosing vehicle faults, the diagnostic results determined are relatively one-sided and the accuracy of the diagnostic results is poor. Summary of the invention

[0004] The present application provides a vehicle fault diagnosis method, device, server and vehicle. The purpose of the present application is to at least solve the technical problem in the related art that when diagnosing vehicle faults, the diagnostic results determined are relatively one-sided and the accuracy of the diagnostic results is relatively poor.

[0005] To achieve the above object, the technical solution adopted by the present application is as follows:

[0006] According to the first aspect provided by the present application, a vehicle fault diagnosis method is provided, which is applied to a server. The method includes: obtaining vehicle end data of a vehicle and determining the data type of the vehicle end data; determining a prompt word template corresponding to the data type of the vehicle end data, where the prompt word template is used to construct model input information; constructing model input information of the vehicle end data based on the vehicle end data and the prompt word template; and inputting the model input information into a first fault diagnosis model to determine the vehicle fault diagnosis result.

[0007] According to the above technical means, the present application can determine a prompt word template corresponding to the data type of the vehicle end data based on the obtained data type of the vehicle end data, and thus construct model input information of the vehicle end data based on the vehicle end data and the determined prompt word template corresponding to the data type. Then, input the model input information into the first fault diagnosis model to determine the vehicle fault diagnosis result. In this way, by inputting the obtained vehicle end data into the determined prompt word template, the model input information corresponding to the vehicle end data can be constructed. In this way, the vehicle end data can be sorted out by an accurate prompt word template to obtain model input information in a format corresponding to the data type. Furthermore, by directly inputting the constructed model input information related to the vehicle end data of the vehicle into the fault diagnosis model, the vehicle fault diagnosis result can be determined. In this way, based on the vehicle end data of the vehicle, the vehicle fault can be comprehensively diagnosed, thereby improving the accuracy of the determined diagnosis result.

[0008] In a possible implementation manner, the above-mentioned inputting the model input information into the first fault diagnosis model to determine the vehicle fault diagnosis result includes: determining associated data of the model input information based on the Retrieval-Augmented Generation (RAG) technology, where the associated data is data in historical vehicle end data with an association degree greater than a preset association degree with the model input information; adding the associated data to the model input information to obtain updated model input information; and inputting the updated model input information into the first fault diagnosis model to determine the vehicle fault diagnosis result.

[0009] According to the above technical means, the present application can further determine the associated data of the model input information based on the Retrieval-Augmented Generation (RAG) technology, and thus further update the model input information based on the associated data in historical vehicle end data with an association degree greater than a preset association degree with the model input information. In this way, the amount of data included in the model input information can be further expanded based on historical data, so that by inputting the updated model input information into the first fault diagnosis model, a more accurate vehicle fault diagnosis result can be determined.

[0010] In a possible implementation manner, the above method further includes: when the fault diagnosis result indicates that there is an abnormality in the vehicle's controller, obtaining the historical fault diagnosis result of the controller, where the historical fault diagnosis result includes the fault diagnosis result of the controller in the vehicle and / or the fault diagnosis result of the controller in other vehicles; based on the historical fault diagnosis result of the controller, determining the fault cause and repair solution of the controller.

[0011] According to the above technical means, the present application can, when the fault diagnosis result indicates that there is an abnormality in the vehicle's controller, further obtain the historical fault diagnosis result of the controller. Thus, based on the historical fault diagnosis result of the controller, the fault cause and repair solution of the controller are determined. In this way, the fault cause and repair solution can be accurately determined with reference to historical data.

[0012] In a possible implementation manner, the above method further includes: when it is determined that the fault cause of the controller includes software defects and / or abnormal parameter settings, determining the repair solution as performing an update process on the software of the controller; sending the fault cause and repair solution of the controller to the vehicle.

[0013] According to the above technical means, the present application can, after determining the specific fault cause, further determine the repair solution corresponding to the fault cause. And further send the fault cause and repair solution to the vehicle to prompt the user of the specific content of the determined vehicle fault diagnosis result.

[0014] In a possible implementation manner, the above method further includes: updating the vehicle-end data, fault diagnosis result, and repair solution of the controller to the database of the server; sending a database update message to the vehicle, where the database update message includes the updated data in the database of the server, and the database update message is used to update the database of the vehicle.

[0015] According to the above technical means, the present application can update the vehicle-end data, as well as the determined fault diagnosis result and repair solution of the controller, to the database of the server. And further send a database update message to the vehicle to update the database of the vehicle based on the updated data in the database of the server included in the database update message. In this way, after determining the specific fault diagnosis result and repair solution, the data can be updated to the database of the server and the database of the vehicle. Thus, when diagnosing the faults of the vehicle subsequently, it can be used as historical data for reference to improve the accuracy of subsequent vehicle fault diagnosis.

[0016] In a possible implementation manner, the obtaining of the vehicle end data of the vehicle includes: receiving the operation data sent by the vehicle; preprocessing the operation data to obtain the processed data, and the preprocessing includes at least one of the following: data format verification, data normalization processing, data cleaning, data deduplication, data parsing; classifying and storing the processed data into the database based on the data type of the processed data; obtaining the vehicle end data of the vehicle from the database.

[0017] According to the above technical means, the present application can perform preprocessing on the operation data sent by the vehicle received, including at least one of data format verification, data normalization processing, data cleaning, data deduplication, and data parsing, to obtain the processed data. And further, based on the data type of the processed data, the processed data is classified and stored in the database. In this way, based on the data classified and stored in the database, the vehicle end data of the vehicle can be accurately obtained.

[0018] According to the second aspect provided by the present application, a vehicle fault diagnosis method is provided, which is applied to a vehicle. The method includes: sending the operation data of the vehicle to the server, where the operation data is used for the server to determine the vehicle end data, the server is used to determine the data type of the vehicle end data, and determine the prompt word template corresponding to the data type of the vehicle end data, and based on the vehicle end data and the prompt word template, construct the model input information of the vehicle end data, and based on the model input information and the first fault diagnosis model, determine the vehicle fault diagnosis result; receive and output the vehicle fault diagnosis result sent by the server, where the fault diagnosis result indicates the fault cause and repair plan of the vehicle controller.

[0019] According to the above technical means, the present application can determine the prompt word template corresponding to the data type of the vehicle end data based on the data type of the vehicle end data, so as to construct the model input information of the vehicle end data based on the vehicle end data and the determined prompt word template corresponding to the data type. Then, the model input information is input into the first fault diagnosis model to determine the vehicle fault diagnosis result and send it to the vehicle. In this way, by inputting the vehicle end data into the determined prompt word template, the model input information corresponding to the vehicle end data can be constructed. In this way, the vehicle end data can be sorted through the accurate prompt word template to obtain the model input information in the format corresponding to the data type. Furthermore, by directly inputting the constructed model input information related to the vehicle end data into the fault diagnosis model, the vehicle fault diagnosis result can be determined. In this way, based on the vehicle end data of the vehicle, the faults of the vehicle can be comprehensively diagnosed, thereby improving the accuracy of the determined diagnosis result.

[0020] In a possible implementation, the above method further includes: receiving a database update message sent by a server, where the database update message includes updated data in the server's database; and updating the vehicle's database based on the database update message.

[0021] According to the above technical means, the present application can update vehicle data, as well as the determined fault diagnosis results and the maintenance solutions of the controller, to the database of the server. And further send a database update message to the vehicle to update the vehicle's database based on the updated data in the server's database included in the database update message. In this way, after determining the specific fault diagnosis results and maintenance solutions, the data can be updated to the database of the server and the vehicle's database. Thus, when diagnosing the faults of the vehicle subsequently, it can be used as historical data for reference to improve the accuracy of subsequent vehicle fault diagnosis.

[0022] In a possible implementation, the above method further includes: when the vehicle is not connected to the server, determining a fault diagnosis result of the vehicle based on the running data and the data included in the vehicle's database through a second fault diagnosis model deployed in the vehicle.

[0023] According to the above technical means, the present application can determine the fault diagnosis result of the vehicle at the vehicle end through the second fault diagnosis model deployed in the vehicle based on the running data and the data included in the vehicle's database when the vehicle is not connected to the server. In this way, even if the vehicle is disconnected from the server, the faults of the vehicle can be diagnosed based on the fault diagnosis model deployed in the vehicle, thereby improving the efficiency of fault diagnosis and enhancing the safety of the vehicle.

[0024] According to the third aspect provided by the present application, there is provided a vehicle fault diagnosis device applied to a server. The vehicle fault diagnosis device includes: an acquisition module, a processing module, and a sending module; the acquisition module is configured to acquire the vehicle end data of the vehicle and determine the data type of the vehicle end data; the processing module is configured to determine a prompt word template corresponding to the data type of the vehicle end data, and the prompt word template is used to construct model input information; the processing module is further configured to construct the model input information of the vehicle end data based on the vehicle end data and the prompt word template; the processing module is further configured to input the model input information into a first fault diagnosis model to determine the fault diagnosis result of the vehicle.

[0025] In a possible implementation, the processing module is specifically configured to determine associated data of the model input information based on the Retrieval-Augmented Generation (RAG) technology. The associated data is data in historical vehicle-end data with an association degree greater than a preset association degree with the model input information. The processing module is specifically configured to add the associated data to the model input information to obtain updated model input information. The processing module is specifically configured to input the updated model input information into a first fault diagnosis model to determine the fault diagnosis result of the vehicle.

[0026] In a possible implementation, the acquisition module is further configured to, when the fault diagnosis result indicates that there is an abnormality in the vehicle's controller, acquire the historical fault diagnosis result of the controller. The historical fault diagnosis result includes the fault diagnosis result of the controller in the vehicle and / or the fault diagnosis result of the controller in other vehicles. The processing module is further configured to determine the fault cause and repair solution of the controller based on the historical fault diagnosis result of the controller.

[0027] In a possible implementation, when the processing module determines that the fault cause of the controller includes software defects and / or abnormal parameter settings, the processing module determines that the repair solution is to update the software of the controller. The sending module is configured to send the fault cause and repair solution of the controller to the vehicle.

[0028] In a possible implementation, the processing module is further configured to update the vehicle-end data, the fault diagnosis result, and the repair solution of the controller to the database of the server. The sending module is further configured to send a database update message to the vehicle. The database update message includes the updated data in the database of the server, and the database update message is used to update the database of the vehicle.

[0029] In a possible implementation, the acquisition module is specifically configured to receive the operation data sent by the vehicle. The processing module is further configured to preprocess the operation data to obtain processed data. The preprocessing includes at least one of the following: data format verification, data normalization, data cleaning, data deduplication, and data parsing. The processing module is further configured to classify and store the processed data in the database based on the data type of the processed data. The acquisition module is specifically configured to acquire the vehicle-end data of the vehicle from the database.

[0030] According to a fourth aspect provided by the present application, a vehicle fault diagnosis device is provided, which is applied to a vehicle. The vehicle fault diagnosis device includes: a sending module, a receiving module, and a processing module; the sending module is configured to send the running data of the vehicle to a server, where the running data is used by the server to determine the vehicle-end data of the vehicle. The server is configured to determine the data type of the vehicle-end data, determine a prompt word template corresponding to the data type of the vehicle-end data, construct model input information of the vehicle-end data based on the vehicle-end data and the prompt word template, and determine the vehicle fault diagnosis result based on the model input information and a first fault diagnosis model; the receiving module is configured to receive and output the vehicle fault diagnosis result sent by the server, and the fault diagnosis result indicates the fault cause and repair plan of the vehicle controller.

[0031] In a possible implementation manner, the receiving module is further configured to receive a database update message sent by the server, where the database update message includes the updated data in the server's database; the processing module is configured to update the vehicle's database based on the database update message.

[0032] In a possible implementation manner, the processing module is further configured to, when the vehicle is not connected to the server, determine the vehicle fault diagnosis result based on the running data and the data included in the vehicle's database through a second fault diagnosis model, and the second fault diagnosis model is deployed in the vehicle.

[0033] According to a fifth aspect provided by the present application, a server is provided, including: a processor; a memory for storing processor-executable instructions; wherein, the processor is configured to execute the instructions to implement the method of the first aspect and any possible implementation manner thereof.

[0034] According to a sixth aspect provided by the present application, a computer-readable storage medium is provided. When computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is caused to execute the method of the first aspect and any possible implementation manner thereof, or the second aspect and any possible implementation manner thereof.

[0035] According to a seventh aspect provided by the present application, a computer program product is provided. The computer program product includes computer instructions. When the computer instructions run on an electronic device, the electronic device is caused to execute the method of the first aspect and any possible implementation manner thereof, or the second aspect and any possible implementation manner thereof.

[0036] According to an eighth aspect provided by the present application, a vehicle is provided. The vehicle includes the vehicle fault diagnosis device as described in the fourth aspect, and the vehicle is configured to implement the method of the second aspect and any possible implementation manner thereof.

[0037] It should be noted that for the technical effects brought about by any of the implementation manners in the second aspect to the eighth aspect, reference may be made to the technical effects brought about by the corresponding implementation manners in the first aspect, which will not be elaborated here.

[0038] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application, and do not constitute an improper limitation to this application.

[0040] Figure 1 is a schematic structural diagram of a vehicle fault diagnosis system shown according to an exemplary embodiment;

[0041] Figure 2 is another schematic structural diagram of a vehicle fault diagnosis system shown according to an exemplary embodiment;

[0042] Figure 3 is a flowchart of a vehicle fault diagnosis method shown according to an exemplary embodiment;

[0043] Figure 4 is another flowchart of a vehicle fault diagnosis method shown according to an exemplary embodiment;

[0044] Figure 5 is another flowchart of a vehicle fault diagnosis method shown according to an exemplary embodiment;

[0045] Figure 6 is another flowchart of a vehicle fault diagnosis method shown according to an exemplary embodiment;

[0046] Figure 7 is another flowchart of a vehicle fault diagnosis method shown according to an exemplary embodiment;

[0047] Figure 8 is a block diagram of a vehicle fault diagnosis device shown according to an exemplary embodiment;

[0048] Figure 9 is another block diagram of a vehicle fault diagnosis device shown according to an exemplary embodiment;

[0049] Figure 10 is a block diagram of an electronic device shown according to an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] To enable those of ordinary skill in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings.

[0051] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. On the contrary, they are only examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0052] Compared with traditional fuel vehicles, the structure and power consumption system of new energy vehicles are more complex and prone to safety failures. With the development of artificial intelligence technology and AI large models, the way of human-computer interaction has been redefined, helping the intelligent development of vehicles. Currently, the remote diagnosis system developed by the vehicle industry based on large models monitors the vehicle status by collecting relevant data of each component of the vehicle. The large model can also compare historical fault data in the database to provide maintenance suggestions for maintenance personnel. However, the current remote diagnosis system developed based on large models can only be implemented under the condition that the cloud (or server) is connected to the network (i.e., the vehicle is connected to the cloud). Under weak network or no-network conditions, the large model in the cloud cannot respond in time, which may cause serious safety problems and endanger the safety of drivers and passengers. Therefore, to timely warn and prevent vehicle failures, it is necessary to monitor the vehicle status through the cloud and the vehicle terminal to achieve the functions of active warning and active fault handling.

[0053] The vehicle fault diagnosis method provided in the embodiments of this application can be applied to a vehicle fault diagnosis system. Figure 1 The structural schematic diagram of a vehicle fault diagnosis system is shown. As Figure 1 shown, the vehicle fault diagnosis system 10 includes: a server 11, a network 12, and a vehicle 13. The server 11 is connected to the vehicle 13 through the network 12, and the network 12 can be a wired network or a wireless network.

[0054] Optionally, as Figure 2 shown, a first fault diagnosis model can be deployed in the server 11, and the first fault diagnosis model can include: a data processing module, a natural language processing module, a video module, an image module, an instruction retrieval module, a feature library management module, a large model inference module, a cloud warning module, and a maintenance vertical domain large model, etc.

[0055] Among them, the data processing module is used to automatically process data in formats such as text, images, voice, video, and CAN data uploaded by vehicle 13, and classify and store the processed data in the database. The data processing module may specifically include: a data receiving module, a data parsing module, and a data cleaning module.

[0056] The natural language processing module is used to convert text data into voice data, or convert voice data into text data.

[0057] The video module is used to generate videos, and the image module is used to generate images.

[0058] The instruction retrieval module is used to generate control instructions and send the control instructions to vehicle 13.

[0059] The feature library management module is used to extract and confirm the feature data and the trained and optimized data stored in the database. And process and encode the data according to the data type to facilitate the construction of a language that the large model can recognize. The feature library management module may specifically include: a feature data extraction module, a feature variable confirmation module, and a database update module.

[0060] The large model inference module is used to determine the vehicle's fault diagnosis result based on the vehicle-end data. The large model inference module may specifically include: a model input information construction module, an inference module, and a supervised fine-tuning (SFT) module.

[0061] The cloud warning module is used to judge the obtained inference result (fault diagnosis result). If it is determined that the state of vehicle 13 is abnormal, it will compare the corresponding maintenance plan in the database. The cloud warning module can also judge the fault level and the corresponding solution measures according to the fault data reported by vehicle 13 and the relevant data in the database.

[0062] Optionally, as Figure 2 shown, a second fault diagnosis model may be deployed in vehicle 13. The second fault diagnosis model may include: a data collection module, an instruction distribution and retrieval module, a vehicle-end warning module, and a natural language processing module, etc.

[0063] Among them, the data collection module has the functions of data collection and data upload, and is used to send the relevant information of the vehicle-end controller (such as the cockpit controller, other vehicle controllers) obtained to server 11. The data collection module may specifically include: a data collection module and a data upload module.

[0064] The instruction distribution and retrieval module is used to receive the instructions sent by server 11, transmit the instructions to the relevant controllers, and modify the vehicle's parameters according to the instructions sent by the server.

[0065] The vehicle-end warning module is used to monitor the vehicle's faults in real time according to the fault diagnosis results sent by the server 11, in combination with the fault knowledge base, and can also adjust and correct the vehicle's parameters according to the fault diagnosis results sent by the server 11.

[0066] The natural language processing module is used to convert text data into speech data, or convert speech data into text data.

[0067] Optionally, as Figure 2 shown, the server 11 may further include a database, which specifically includes: a data storage module, an application service module, and a maintenance database. Specifically, the data storage module is used to store the vehicle-end raw data, store the feature data, store the large model knowledge base data, and store the data in other dimensions. The application service module is used to provide data for operation and maintenance personnel, marketing, 4S stores, and repair stations.

[0068] For ease of understanding, the vehicle fault diagnosis method provided in this application will be specifically introduced below with reference to the accompanying drawings.

[0069] Figure 3 is a flowchart of a vehicle fault diagnosis method shown according to an exemplary embodiment. As Figure 3 shown, the vehicle fault diagnosis method is applied to the server, and the method includes the following S301-S304:

[0070] S301. The server obtains the vehicle-end data of the vehicle and determines the data type of the vehicle-end data.

[0071] In the embodiment of the present application, the vehicle can be remotely connected to the server, so that the vehicle can upload the vehicle's operation data (such as cockpit data, controller data, sensor data, control signals, etc.) to the server in real time, so as to process the vehicle's operation data through the server and determine the vehicle's fault diagnosis results.

[0072] Optionally, the vehicle can send the collected vehicle operation data to the server once every preset time interval, so as to monitor the vehicle's health status in real time, diagnose the vehicle's health status based on the vehicle's operation parameters, and determine whether the vehicle has a fault.

[0073] Optionally, the data type can be any one of the following: controller data, sensor data, cockpit data, image data, speech data, intelligent driving data.

[0074] In some embodiments, the server obtains the vehicle-end data of the vehicle, which may specifically include: the server receives the operation data sent by the vehicle, preprocesses the operation data to obtain the processed data, and then classifies and stores the processed data in the database based on the data type of the processed data; thus, the vehicle-end data of the vehicle is obtained from the database.

[0075] Among them, the preprocessing includes at least one of the following: data format verification, data normalization processing, data cleaning, data deduplication, data parsing.

[0076] Optionally, the vehicle can collect the vehicle's cockpit data, controller data, sensor data, control signals, etc. in real time through the data acquisition module deployed at the vehicle end, and upload the collected operation data to the server.

[0077] In a possible implementation manner, after the server receives the operation data uploaded by the vehicle, it can determine what type of data the operation data belongs to and send it to different modules for unified processing.

[0078] It should be noted that the data content transmitted between the vehicle and the server can be any one of the following: the vehicle's operation data, control instructions, control responses, etc. Therefore, when the data content received by the server is the vehicle's operation data, the operation data needs to be processed by the data processing module in the server, and the operation data can be stored in the database in the server.

[0079] Specifically, when the data processing module in the server receives the vehicle's operation data, it can preprocess the operation data to perform data format verification, data normalization processing, data cleaning, data deduplication, data parsing, etc. on the operation data, and can extract information through key information, key frames, etc. to obtain the feature information of the data.

[0080] It should be noted that the data format of the operation data can be any one of the following: text, image, voice, video, CAN data, etc.

[0081] Optionally, an automated tool in the data processing module can be used to preprocess the operation data, and the data processing module can process and encode the data according to the data type to facilitate the construction of a language that the model can recognize.

[0082] In a possible implementation manner, the data processed automatically can also be sent to the operation and maintenance personnel for manual verification and evaluation. After manual verification and evaluation, the processed data is obtained, and it is classified and stored in the database according to the data type and usage of the data.

[0083] Optionally, the running data can also be processed by constructing a data processing layer, such as feature extraction, feature engineering construction, and feature engineering optimization. Then, using the data and models included in the distributed training framework, model training and data optimization processing are performed on the running data to obtain the processed data, which is then classified and stored in the database.

[0084] It can be understood that the database in the server can be a feature algorithm library, which stores the data features of historical faults, various empirical algorithms and models, and the fault diagnosis results determined during the process of historically disposing of vehicle faults. Therefore, the relevant data, data features, and disposal methods for each vehicle fault diagnosis can be stored in the feature algorithm library for later iterative upgrades.

[0085] In the embodiment of the present application, the present application can perform at least one preprocessing operation on the received running data of the vehicle, such as data format verification, data normalization, data cleaning, data deduplication, and data parsing, to obtain the processed data. Then, based on the data type of the processed data, the processed data is classified and stored in the database. In this way, based on the data classified and stored in the database, the vehicle's in-vehicle data can be accurately obtained.

[0086] S302. The server determines the prompt word template corresponding to the data type of the in-vehicle data.

[0087] Among them, the prompt word template is used to construct the model input information.

[0088] Optionally, the in-vehicle data can include data of multiple data types, and each data type can correspond to a prompt word template; or, multiple data types can correspond to the same prompt word template, and the prompt word template includes multiple modules, each module corresponding to one data type.

[0089] S303. The server constructs the model input information of the in-vehicle data based on the in-vehicle data and the prompt word template.

[0090] Optionally, the prompt word template can be a Prompt strategy (Prompt structure). Corresponding prompt word templates can be constructed in advance for different data types, and the data of the corresponding data type can be filled in the prompt word template.

[0091] It should be noted that after filling the data of the corresponding data type in the prompt word template, the obtained information is the model input information. Specifically, the model input information can be called Prompt engineering.

[0092] In a possible implementation, the vehicle - end data can be filled into the corresponding prompt template (or the corresponding module in the prompt template) based on the data type of each data included in the vehicle - end data, so as to construct the model input information of the vehicle - end data.

[0093] Optionally, after determining the data type of the vehicle - end data, the corresponding prompt template for each data type can be selected from a variety of pre - determined prompt templates, and then the data of the corresponding data type is input into the prompt template to obtain the model input information.

[0094] It can be understood that after the feature library management module in the server extracts the vehicle - end data (i.e., feature data and tuned data) from the database, it can automatically select the prompt template corresponding to the data type from a variety of pre - set prompt templates according to the data type.

[0095] It should be noted that the selection method of selecting the prompt template corresponding to the data type from a variety of pre - set prompt templates depends on the complexity of the diagnostic task and the characteristics of the data. For example, for simple fault diagnosis, a direct - instruction - type Prompt can be used; while for complex multi - step fault reasoning tasks, the Retrieval - augmented Generation (RAG) technology needs to be combined.

[0096] S304. The server inputs the model input information into the first fault diagnosis model, determines the fault diagnosis result of the vehicle, and sends the fault diagnosis result to the vehicle.

[0097] It can be understood that the constructed model input information corresponding to the data type (Prompt engineering) is input into the large model (i.e., the first fault diagnosis model) for reasoning, and the large model can output the result (i.e., the fault diagnosis result) according to the structure and content of the model input information.

[0098] Optionally, the first fault diagnosis model can combine the data in the model input information, as well as information such as pictures, voices, and intelligent driving data uploaded by the vehicle, to determine the fault diagnosis result of the vehicle and send it to the cloud warning module.

[0099] It should be noted that information such as pictures, voices, and intelligent driving data uploaded by the vehicle can be uploaded to the server through the data acquisition module in the vehicle, so that the first fault diagnosis model can judge the data and determine to send the data to the corresponding module for data processing.

[0100] In a possible implementation, the first fault diagnosis model can also dynamically adjust the structure of the model input information (or prompt template) according to the output result of the model and the context information, so as to optimize the model input information (or prompt template) and improve the accuracy of the fault diagnosis result output by the first fault diagnosis model.

[0101] Optionally, the cloud warning module in the server can also comprehensively judge the fault diagnosis result output by the first fault diagnosis model and the status information reported by the vehicle in real time. If it is identified that the status of the current vehicle is abnormal, it will compare the maintenance plan in the database or match a suitable maintenance plan with the large model of the maintenance vertical domain.

[0102] It should be noted that the large model of the maintenance vertical domain is a large model trained based on historical maintenance plans, fault information and other data. This large model can match corresponding solutions, the models of vehicles with corresponding faults occurred in history, and corresponding data characteristics according to the fault information.

[0103] Optionally, relevant information (such as the fault diagnosis result) can also be sent to the operation and maintenance personnel through instant communication methods such as social software, emails, text messages, and phone calls. The operation and maintenance personnel can conduct a review based on the pushed information, corresponding data, and solutions (maintenance plans), and finally give solutions. If it is determined that there is no obvious abnormality in the vehicle, the characteristic result data (fault diagnosis result) can also be pushed to the vehicle to optimize the model and store data in the fault diagnosis model in the vehicle.

[0104] Optionally, the cloud warning module in the server can also determine the fault level of the vehicle and the corresponding solutions according to the fault data reported by the vehicle and the relevant data in the database, and broadcast them to the user through the in-vehicle computer.

[0105] In the embodiments of the present application, the present application can determine the prompt template corresponding to the data type of the vehicle-end data based on the data type of the acquired vehicle-end data, and thus construct the model input information of the vehicle-end data based on the vehicle-end data and the determined prompt template corresponding to the data type. The model input information is input into the first fault diagnosis model to determine the fault diagnosis result of the vehicle. In this way, by inputting the acquired vehicle-end data into the determined prompt template, the model input information corresponding to the vehicle-end data can be constructed. In this way, the vehicle-end data can be sorted out through an accurate prompt template to obtain model input information in a format corresponding to the data type. Furthermore, by directly inputting the constructed model input information related to the vehicle-end data of the vehicle into the fault diagnosis model, the fault diagnosis result of the vehicle can be determined. In this way, based on the vehicle-end data of the vehicle, the faults of the vehicle can be comprehensively diagnosed, thereby improving the accuracy of the determined diagnosis result.

[0106] In some embodiments, such as Figure 4 shown, in a vehicle fault diagnosis method provided by an embodiment of the present application, the above S304 may specifically include S401 - S403:

[0107] S401. The server determines the associated data of the model input information based on the Retrieval - Augmented Generation (RAG) technology.

[0108] Among them, the associated data is the data in the historical vehicle - end data whose association degree with the model input information is greater than the preset association degree.

[0109] S402. The server adds the associated data to the model input information to obtain the updated model input information.

[0110] In a possible implementation manner, in a complex reasoning process, the RAG technology can be used to retrieve the context information (i.e., associated data) associated with the model input information, and inject the context information into the model input information (i.e., combine the context information with the model input information), so as to obtain the updated model input information, thereby enhancing the accuracy and relevance of the first fault diagnosis model to determine the vehicle fault diagnosis result.

[0111] Optionally, according to the fault diagnosis result determined by the first fault diagnosis model and the context information associated with the model input information, the feature library management module in the server can also dynamically adjust the structure of the model input information (or the prompt word template).

[0112] S403. The server inputs the updated model input information into the first fault diagnosis model to determine the vehicle fault diagnosis result.

[0113] In the embodiment of the present application, the present application can further determine the associated data of the model input information based on the Retrieval - Augmented Generation (RAG) technology, and further update the model input information based on the associated data in the historical vehicle - end data whose association degree with the model input information is greater than the preset association degree. In this way, the amount of data included in the model input information can be further expanded based on historical data, so that when the updated model input information is input into the first fault diagnosis model, a more accurate fault diagnosis result can be determined.

[0114] In some embodiments, such as Figure 5 shown, in a vehicle fault diagnosis method provided by an embodiment of the present application, it may specifically further include S501 - S502:

[0115] S501. When the fault diagnosis result indicates that the vehicle controller is abnormal, the server obtains the historical fault diagnosis result of the controller.

[0116] Among them, the historical fault diagnosis results include the fault diagnosis results of the controllers in the vehicle and / or the fault diagnosis results of the controllers in other vehicles.

[0117] S502. Determine the cause of the controller's fault and the repair plan based on the historical fault diagnosis results of the controller.

[0118] In a possible implementation, the cloud warning module in the server can make a comprehensive judgment based on the fault diagnosis results and the data content reported by the vehicle in real time. If it is determined that there is an abnormality in the controller of the vehicle, relevant information in the database can be retrieved in real time to match the corresponding repair plan, cause of the fault, etc.

[0119] Optionally, the first fault diagnosis model in the server can push the determined fault diagnosis results to the operation and maintenance personnel in the form of emails, messages, etc. The operation and maintenance personnel can judge the vehicle's repair method and handling means based on the information pushed by the model.

[0120] In some embodiments, when it is determined that the cause of the controller's fault includes software defects and / or abnormal parameter settings, the determined repair plan is to update the software of the controller; and send the cause of the controller's fault and the repair plan to the vehicle.

[0121] Optionally, if the operation and maintenance personnel determine that the vehicle's fault is a software bug or a parameter setting problem, etc., the operation and maintenance personnel can upload the modified and verified software package to the server, so that the vehicle can pull the software from the server through the instruction distribution and retrieval module to update the controller software in the vehicle.

[0122] In the embodiments of the present application, after determining the specific cause of the fault, the present application can further determine the repair plan corresponding to the cause of the fault. And further send the cause of the fault and the repair plan to the vehicle to prompt the user of the specific content of the determined vehicle fault diagnosis results.

[0123] In some embodiments, in a vehicle fault diagnosis method provided by the embodiments of the present application, the method may further include: updating the vehicle-end data, the fault diagnosis results, and the repair plan of the controller to the database of the server; and sending a database update message to the vehicle, the database update message includes the updated data in the database of the server, and the database update message is used to update the database of the vehicle.

[0124] In a possible implementation, after updating the vehicle-end data, fault diagnosis results, and the maintenance plan of the controller to the database of the server, if the cloud warning module in the server identifies the same fault problem with the vehicle, it can synchronize the vehicle information with the same fault problem in history to the operation and maintenance personnel. After the operation and maintenance personnel confirm it, the vehicle can pull the corresponding software package from the server for update.

[0125] Optionally, if the operation and maintenance personnel determine that the vehicle fault is a hardware fault or a fault that requires component replacement, the cloud warning module can notify the after-sales personnel to invite the vehicle for handling (that is, the after-sales personnel send an invitation message to the user to notify the user to send the vehicle to the after-sales for maintenance), or notify the user to perform maintenance in the form of in-vehicle voice reminder.

[0126] Exemplarily, the server can retrieve the information of the nearest after-sales service station of the specific vehicle and send it back to the in-vehicle unit for the user to select. If the vehicle has a serious fault (affecting the normal driving of the vehicle), the in-vehicle unit can directly notify the after-sales service station to handle the vehicle. Thus, the after-sales service station can directly view the information of the faulty vehicle and the solution measures recommended by the model. If the vehicle has a general fault (not affecting the normal driving of the vehicle), the in-vehicle unit can voice broadcast the temporary solution measures of the fault to the user.

[0127] Optionally, if the cloud warning module determines that the vehicle status is normal (the vehicle has no fault), it can send the model initialization data (fault diagnosis results) to the vehicle, and the in-vehicle warning module in the second fault diagnosis model in the vehicle will monitor the vehicle according to the initialization data sent by the server.

[0128] In this way, by judging, warning, determining the cause of the fault and the maintenance plan of the vehicle, it is possible to handle the vehicle fault in advance before the fault occurs, and it is also possible to appease the user's emotions and provide corresponding solutions after the fault occurs, and it can also provide ideas for after-sales maintenance personnel to solve the fault.

[0129] In the embodiment of the present application, the present application can update the vehicle-end data, as well as the determined fault diagnosis results and the maintenance plan of the controller, to the database of the server. And further send a database update message to the vehicle to update the database of the vehicle based on the updated data in the database of the server included in the database update message. In this way, after determining the specific fault diagnosis results and maintenance plan, the data can be updated to the database of the server and the database of the vehicle. Thus, when diagnosing the vehicle fault subsequently, it can be used as historical data for reference to improve the accuracy of subsequent vehicle fault diagnosis.

[0130] In an embodiment of the present application, when the fault diagnosis result indicates that there is an abnormality in the vehicle's controller, the present application can further obtain the historical fault diagnosis results of the controller. Then, based on the historical fault diagnosis results of the controller, the fault cause and repair plan of the controller can be determined. In this way, the fault cause and repair plan can be accurately determined with reference to historical data.

[0131] Figure 6 is a flowchart of a vehicle fault diagnosis method shown according to an exemplary embodiment, as Figure 6 shown, the vehicle fault diagnosis method is applied to a vehicle, and the method includes the following S601 - S602:

[0132] S601. The vehicle sends the operation data of the vehicle to the server.

[0133] Among them, the operation data is used for the server to determine the vehicle - end data of the vehicle. The server is used to determine the data type of the vehicle - end data, determine the prompt word template corresponding to the data type of the vehicle - end data, construct the model input information of the vehicle - end data based on the vehicle - end data and the prompt word template, and determine the fault diagnosis result of the vehicle based on the model input information and the first fault diagnosis model.

[0134] Optionally, the operation data may include: cockpit data, controller data, sensor data, control signals, etc.

[0135] Optionally, a second fault diagnosis model is deployed in the vehicle. The data acquisition module included in the second fault diagnosis model can acquire the operation data of the vehicle and upload it to the server.

[0136] It should be noted that the relevant content of the server's processing of the operation data or the relevant content of the server's determination of the vehicle's fault diagnosis result can refer to the above - mentioned embodiments and will not be elaborated here.

[0137] S602. The vehicle receives and outputs the fault diagnosis result of the vehicle sent by the server.

[0138] Among them, the fault diagnosis result indicates the fault cause and repair plan of the vehicle's controller.

[0139] Optionally, the second fault diagnosis model deployed in the vehicle can receive the instruction sent by the server (including the fault diagnosis result), then transmit the instruction to the relevant controller, and modify the setting parameters of the vehicle according to the instruction sent by the server.

[0140] In the embodiments of the present application, the present application can determine a prompt word template corresponding to the data type of the vehicle-end data based on the data type of the vehicle-end data, so as to construct model input information of the vehicle-end data based on the vehicle-end data and the prompt word template corresponding to the determined data type. The model input information is input into the first fault diagnosis model to determine the fault diagnosis result of the vehicle and send it to the vehicle. In this way, by inputting the vehicle-end data into the determined prompt word template, the model input information corresponding to the vehicle-end data can be constructed. In this way, the vehicle-end data can be sorted through an accurate prompt word template to obtain model input information in a format corresponding to the data type. Furthermore, by directly inputting the constructed model input information related to the vehicle-end data into the fault diagnosis model, the fault diagnosis result of the vehicle can be determined. In this way, based on the vehicle-end data of the vehicle, the faults of the vehicle can be comprehensively diagnosed, thereby improving the accuracy of the determined diagnosis result.

[0141] In some embodiments, the vehicle can also receive a database update message sent by the server. The database update message includes the updated data in the server's database, and the vehicle's database is updated based on the database update message.

[0142] It should be noted that after the server determines the fault diagnosis result of the vehicle, relevant data information (vehicle-end data, fault diagnosis result, and maintenance plan of the controller) can be updated to the server's database and the vehicle's database.

[0143] In the embodiments of the present application, the present application can update the vehicle-end data, as well as the determined fault diagnosis result and the maintenance plan of the controller, to the server's database. And further send a database update message to the vehicle to update the vehicle's database based on the updated data in the server's database included in the database update message. In this way, after determining the specific fault diagnosis result and maintenance plan, the data can be updated to the server's database and the vehicle's database. Thus, when diagnosing the faults of the vehicle subsequently, it can be used as historical data for reference to improve the accuracy of diagnosing the faults of the vehicle subsequently.

[0144] In some embodiments, in the case where the vehicle is not connected to the server, based on the operation data and the data included in the vehicle's database, the fault diagnosis result of the vehicle is determined through a second fault diagnosis model, and the second fault diagnosis model is deployed in the vehicle.

[0145] Optionally, the vehicle-end warning module in the second fault diagnosis model deployed in the vehicle can monitor the faults of the vehicle in real time under the condition of no network (the vehicle is not connected to the server) according to the fault diagnosis result fed back by the server, and determine the fault diagnosis result of the vehicle through the second fault diagnosis model.

[0146] It can be understood that under the condition of no network, if a vehicle breaks down, the second fault diagnosis model in the vehicle can determine the fault diagnosis result of the vehicle based on the database in the vehicle, provide solutions for users, and protect the safety of users' lives and property.

[0147] In the embodiment of the present application, the present application can, when the vehicle is not connected to the server, based on the operation data and the data included in the vehicle's database, determine the fault diagnosis result of the vehicle at the vehicle end through the second fault diagnosis model deployed in the vehicle. In this way, even if the vehicle is disconnected from the server, the fault of the vehicle can be diagnosed based on the fault diagnosis model deployed in the vehicle, thereby improving the efficiency of fault diagnosis and enhancing the safety of the vehicle.

[0148] In a complete embodiment, as Figure 7 shown, after the second fault diagnosis model in the vehicle obtains the operation data of the vehicle, it needs to first perform network management to determine whether the vehicle is connected to the server. Thus, when it is determined that the vehicle is connected to the server, the vehicle sends the operation data to the server to determine the fault diagnosis result of the vehicle through the cloud warning module in the server, and determine whether the fault level is a serious fault (affecting the normal driving of the vehicle) or a general fault (not affecting the normal driving of the vehicle). If it is a general fault, a temporary solution can be determined (or the maintenance site can be notified); if it is a serious fault, the maintenance site (or maintenance personnel) needs to be notified. And a prompt message (including the solution) can be sent to the user through the vehicle head unit. If it is determined that the vehicle is not connected to the server, the fault diagnosis result of the vehicle can be determined through the vehicle-end warning module in the vehicle, and the solution to the fault can be determined based on the database in the vehicle, and then a prompt message (including the solution) is sent to the user through the vehicle head unit.

[0149] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. To implement the above functions, the vehicle fault diagnosis device or electronic device includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraint conditions of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but this kind of implementation should not be considered to exceed the scope of the present application.

[0150] Embodiments of the present application can, according to the above method, exemplarily divide the functional modules of a vehicle fault diagnosis device or an electronic device. For example, the vehicle fault diagnosis device or the electronic device may include respective functional modules corresponding to each functional division, or two or more functions may be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the division of modules in the embodiments of the present application is illustrative, merely a logical functional division, and there may be other division methods in actual implementation.

[0151] Figure 8 is a block diagram of a vehicle fault diagnosis device shown according to an exemplary embodiment. Referring to Figure 8 , the vehicle fault diagnosis device 800 is applied to a server. The vehicle fault diagnosis device 800 includes: an acquisition module 801, a processing module 802, and a sending module 803; the acquisition module 801 is configured to acquire vehicle end data of a vehicle and determine the data type of the vehicle end data; the processing module 802 is configured to determine a prompt word template corresponding to the data type of the vehicle end data, and the prompt word template is used to construct model input information; the processing module 802 is further configured to construct model input information of the vehicle end data based on the vehicle end data and the prompt word template; the processing module 802 is further configured to input the model input information into a first fault diagnosis model to determine a fault diagnosis result of the vehicle.

[0152] In a possible implementation manner, the processing module 802 is specifically configured to determine associated data of the model input information based on the retrieval-augmented generation (RAG) technology, where the associated data is data in historical vehicle end data whose association degree with the model input information is greater than a preset association degree; the processing module 802 is specifically configured to add the associated data to the model input information to obtain updated model input information; the processing module 802 is specifically configured to input the updated model input information into the first fault diagnosis model to determine a fault diagnosis result of the vehicle.

[0153] In a possible implementation manner, the acquisition module 801 is further configured to, when the fault diagnosis result indicates that there is an abnormality in the controller of the vehicle, acquire the historical fault diagnosis result of the controller, where the historical fault diagnosis result includes the fault diagnosis result of the controller in the vehicle and / or the fault diagnosis result of the controller in other vehicles; the processing module 802 is further configured to determine the fault cause and repair solution of the controller based on the historical fault diagnosis result of the controller.

[0154] In a possible implementation manner, the processing module 802 is further configured to, when it is determined that the fault cause of the controller includes software defects and / or abnormal parameter settings, determine that the repair solution is to update the software of the controller; the sending module 803 is configured to send the fault cause and repair solution of the controller to the vehicle.

[0155] In a possible implementation, the processing module 802 is further configured to update the vehicle-end data, the fault diagnosis result, and the maintenance plan of the controller to the database of the server; the sending module 803 is further configured to send a database update message to the vehicle, and the database update message includes the updated data in the database of the server, and the database update message is used to update the database of the vehicle.

[0156] In a possible implementation, the obtaining module 801 is specifically configured to receive the operation data sent by the vehicle; the processing module 802 is further configured to preprocess the operation data to obtain processed data, and the preprocessing includes at least one of the following: data format verification, data normalization, data cleaning, data deduplication, data parsing; the processing module is further configured to classify and store the processed data in the database based on the data type of the processed data; the obtaining module 801 is specifically configured to obtain the vehicle-end data of the vehicle from the database.

[0157] Figure 9 is a block diagram of a vehicle fault diagnosis device shown according to an exemplary embodiment. Refer to Figure 9 The vehicle fault diagnosis device 900 is applied to a vehicle. The vehicle fault diagnosis device 900 includes: a sending module 901, a receiving module 902, and a processing module 903; the sending module 901 is configured to send the operation data of the vehicle to the server, and the operation data is used for the server to determine the vehicle-end data of the vehicle. The server is configured to determine the data type of the vehicle-end data, determine the prompt word template corresponding to the data type of the vehicle-end data, construct the model input information of the vehicle-end data based on the vehicle-end data and the prompt word template, and determine the fault diagnosis result of the vehicle based on the model input information and the first fault diagnosis model; the receiving module 902 is configured to receive and output the fault diagnosis result of the vehicle sent by the server, and the fault diagnosis result indicates the fault cause and the maintenance plan of the controller of the vehicle.

[0158] In a possible implementation, the receiving module 902 is further configured to receive the database update message sent by the server, and the database update message includes the updated data in the database of the server; the processing module 903 is configured to update the database of the vehicle based on the database update message.

[0159] In a possible implementation, the processing module 903 is further configured to determine the fault diagnosis result of the vehicle based on the operation data and the data included in the database of the vehicle through the second fault diagnosis model when the vehicle is not connected to the server, and the second fault diagnosis model is deployed in the vehicle.

[0160] Regarding the device in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

[0161] Figure 10 is a block diagram of an electronic device (server) shown according to an exemplary embodiment. As Figure 10 shown, the electronic device 1000 includes but is not limited to: a processor 1001 and a memory 1002.

[0162] Among them, the above-mentioned memory 1002 is used to store the executable instructions of the above-mentioned processor 1001. It can be understood that the above-mentioned processor 1001 is configured to execute instructions to implement the vehicle fault diagnosis method in the above embodiments.

[0163] It should be noted that those skilled in the art can understand that Figure 10 the structure of the electronic device shown in Figure 10 does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than

[0164] shown, or combine certain components, or have different component arrangements.

[0165] The processor 1001 is the control center of the electronic device, connecting various parts of the entire electronic device using various interfaces and lines. By running or executing software programs and / or modules stored in the memory 1002, and calling data stored in the memory 1002, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 1001 may include one or more processing units. Optionally, the processor 1001 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 1001 either.

[0165] The memory 1002 can be used to store software programs and various data. The memory 1002 may mainly include a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required by at least one functional module (such as a processing module, etc.). In addition, the memory 1002 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0166] In an exemplary embodiment, there is also provided a computer-readable storage medium including instructions, such as the memory 1002 including instructions, and the above instructions can be executed by the processor 1001 of the electronic device 1000 to implement the vehicle fault diagnosis method in the above embodiments.

[0167] In actual implementation, Figure 8 the obtaining module 801, the processing module 802, and the sending module 803 in Figure 9 or the functions of the sending module 901, the receiving module 902, and the processing module 903 in Figure 10 can be implemented by the processor 1001 in

[0168] calling a computer program stored in the memory 1002. For the specific execution process, reference can be made to the description in the vehicle fault diagnosis method part of the foregoing embodiment, which will not be elaborated here.

[0169] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium. For example, the non-transitory computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0169] In an exemplary embodiment, the embodiments of the present application further provide a computer program product including one or more instructions, and the one or more instructions can be executed by the processor 1001 of the electronic device 1000 to complete the vehicle fault diagnosis method in the foregoing embodiments.

[0170] It should be noted that when the instructions in the foregoing computer-readable storage medium or the one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the vehicle fault diagnosis method embodiment are implemented, and the same technical effects as those of the vehicle fault diagnosis method can be achieved. To avoid repetition, it will not be elaborated here.

[0171] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional module is used as an example. In actual application, the above functions can be allocated to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0172] In several embodiments provided by the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point, the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0173] The unit described as a separate component may or may not be physically separated. The component shown as a unit may be a single physical unit or multiple physical units, that is, it may be located in one place or may be distributed to multiple different places. Some or all of the classification units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0174] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, can also exist separately as individual physical units, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0175] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs and other various media that can store program codes.

[0176] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A vehicle fault diagnosis method, characterized in that Applied to a server, the method includes: Obtain the vehicle-end data of the vehicle and determine the data type of the vehicle-end data; Determine the prompt word template corresponding to the data type of the vehicle-end data, where the prompt word template is used to construct model input information; Based on the vehicle-end data and the prompt word template, construct the model input information of the vehicle-end data; Input the model input information into the first fault diagnosis model to determine the fault diagnosis result of the vehicle.

2. The vehicle fault diagnosis method according to claim 1, wherein The step of inputting the model input information into the first fault diagnosis model to determine the fault diagnosis result of the vehicle includes: Determine the associated data of the model input information based on the Retrieval-Augmented Generation (RAG) technology, where the associated data is the data in the historical vehicle-end data with an association degree greater than the preset association degree with the model input information; Add the associated data to the model input information to obtain the updated model input information; Input the updated model input information into the first fault diagnosis model to determine the fault diagnosis result of the vehicle.

3. The vehicle fault diagnosis method according to claim 1, characterized in that The method further includes: When the fault diagnosis result indicates that there is an abnormality in the controller of the vehicle, obtain the historical fault diagnosis results of the controller, where the historical fault diagnosis results include the fault diagnosis results of the controller in the vehicle and / or the fault diagnosis results of the controllers in other vehicles; Based on the historical fault diagnosis results of the controller, determine the fault cause and repair plan of the controller.

4. The vehicle fault diagnosis method according to claim 3, wherein, The method further includes: When it is determined that the fault cause of the controller includes software defects and / or abnormal parameter settings, determine the repair plan as updating the software of the controller; Send the fault cause and the repair plan of the controller to the vehicle.

5. The vehicle fault diagnosis method according to claim 3, wherein, The method further includes: Update the vehicle-end data, the fault diagnosis result, and the repair plan of the controller to the database of the server; Send a database update message to the vehicle, where the database update message includes the updated data in the database of the server, and the database update message is used to update the database of the vehicle.

6. The vehicle fault diagnosis method according to claim 1, wherein The step of obtaining the vehicle-end data of the vehicle includes: Receive the operation data sent by the vehicle; Perform preprocessing on the operation data to obtain processed data, where the preprocessing includes at least one of the following: data format verification, data normalization, data cleaning, data deduplication, data parsing; Based on the data type of the processed data, classify and store the processed data in the database; Obtain the vehicle-end data of the vehicle from the database.

7. A vehicle fault diagnosis method, characterized in that, Applied to a vehicle, the method includes: Send the operation data of the vehicle to the server, where the operation data is used by the server to determine the vehicle-end data of the vehicle. The server is used to determine the data type of the vehicle-end data, determine the prompt word template corresponding to the data type of the vehicle-end data, construct the model input information of the vehicle-end data based on the vehicle-end data and the prompt word template, and determine the fault diagnosis result of the vehicle based on the model input information and the first fault diagnosis model; Receive and output the fault diagnosis result of the vehicle sent by the server.

8. The vehicle fault diagnosis method according to claim 7, characterized in that, The method further includes: Receive the database update message sent by the server, where the database update message includes the updated data in the server's database; Update the vehicle's database based on the database update message.

9. The vehicle fault diagnosis method according to claim 8, characterized in that The method further includes: In the case where the vehicle is not connected to the server, determine the fault diagnosis result of the vehicle based on the operation data and the data included in the vehicle's database through a second fault diagnosis model, and the second fault diagnosis model is deployed in the vehicle.

10. A vehicle fault diagnosis device, characterized in that, Applied to a server, the vehicle fault diagnosis device includes: an acquisition module and a processing module; The acquisition module is used to acquire the vehicle-end data of the vehicle and determine the data type of the vehicle-end data; The processing module is used to determine the prompt word template corresponding to the data type of the vehicle-end data, and the prompt word template is used to construct the model input information; The processing module is further used to construct the model input information of the vehicle-end data based on the vehicle-end data and the prompt word template; The processing module is further used to input the model input information into the first fault diagnosis model to determine the fault diagnosis result of the vehicle.

11. A vehicle fault diagnosis device, characterized in that, Applied to a vehicle, the vehicle fault diagnosis device includes: a sending module and a receiving module; The sending module is used to send the operation data of the vehicle to the server, where the operation data is used by the server to determine the vehicle-end data of the vehicle. The server is used to determine the data type of the vehicle-end data, determine the prompt word template corresponding to the data type of the vehicle-end data, construct the model input information of the vehicle-end data based on the vehicle-end data and the prompt word template, and determine the fault diagnosis result of the vehicle based on the model input information and the first fault diagnosis model; The receiving module is used to receive and output the fault diagnosis result of the vehicle sent by the server, and the fault diagnosis result indicates the fault cause and repair plan of the vehicle's controller.

12. A server, characterized in that, Includes: A processor; A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the instructions to implement the vehicle fault diagnosis method according to any one of claims 1-6.

13. A vehicle, characterized in that, The vehicle includes the vehicle fault diagnosis device according to claim 11, and the vehicle is used to implement the vehicle fault diagnosis method according to any one of claims 7-9.

Images