Vehicle fault diagnosis method, device, equipment and medium

Abstract

The present application discloses a vehicle fault diagnosis method, device, equipment and medium, which relates to the field of automobile technology. The method includes: performing at least one fault diagnosis operation on the vehicle until the fault diagnosis stop condition is reached to determine the target fault category of the vehicle; generating a diagnosis report and repair suggestion for the vehicle according to the target fault category; the fault diagnosis operation includes: obtaining user input information and historical query information of the vehicle; parsing the user input information, determining multiple current fault categories and current probability information corresponding to each current fault category from the fault map; judging whether the fault diagnosis stop condition is reached according to the user input information, historical query information, current fault category and corresponding current probability information; when the fault diagnosis stop condition is not reached, obtaining updated user input information, and controlling to enter the next fault diagnosis operation. The present application improves the accuracy of vehicle fault diagnosis.

Description

Technical Field

[0001] The present application relates to the field of automobile technology, and in particular to a vehicle fault diagnosis method, device, equipment and medium. Background Art

[0002] With the rapid development of the automobile manufacturing industry, the complexity and functional diversity of automobiles are also increasing, resulting in the difficulty and importance of fault diagnosis. Modern cars integrate a large number of electronic control systems, which control almost all vehicle operations from engine management to safety features. However, when these complex systems fail, it will not only affect the driving experience, but may also bring safety hazards. Therefore, it is necessary to diagnose the fault of the car, which is mainly to determine whether the technical condition of the car is normal and find out the cause and location of the abnormal condition. In order to ensure the safety of the vehicle and extend the service life of the car, how to diagnose the fault of the car is crucial.

[0003] At present, the related technology uses a rule-based diagnosis system to diagnose vehicle faults. When the user inputs the vehicle symptom information, the system will match the information according to the pre-established rule base to determine the cause of the vehicle fault. However, the maintenance cost of the rule base in this solution is high and it can only perform preliminary fault diagnosis. Its fault detection is relatively single and one-sided, and it cannot diagnose complex faults, resulting in low accuracy in vehicle fault detection. Summary of the invention

[0004] The purpose of this application is to provide a vehicle fault diagnosis method, device, equipment and medium.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a vehicle fault diagnosis method, comprising:

[0007] Performing at least one fault diagnosis operation on the vehicle until a fault diagnosis stop condition is reached to determine a target fault category of the vehicle;

[0008] generating a diagnostic report and repair suggestions for the vehicle according to the target fault category;

[0009] The fault diagnosis operation includes:

[0010] Acquire user input information and historical query information of the vehicle; when the fault diagnosis operation is performed for the first time, the user input information is vehicle fault symptom information; when the fault diagnosis operation is not performed for the first time, the user input information is updated user input information obtained when the fault diagnosis operation was previously performed;

[0011] Analyze the user input information, and determine multiple current fault categories and current probability information corresponding to each current fault category from the fault spectrum;

[0012] Determining whether a fault diagnosis stopping condition is met according to the user input information, the historical query information, the current fault category and the current probability information corresponding to each current fault category;

[0013] When the fault diagnosis stop condition is not met, the updated user input information is obtained, and the control enters the next fault diagnosis operation; when the fault diagnosis stop condition is met, the control does not enter the next fault diagnosis operation.

[0014] Optionally, the user input information is parsed and processed to determine multiple current fault categories and current probability information corresponding to each current fault category from the fault map, including:

[0015] Using a language processing model to parse the user input information and extract key feature information;

[0016] According to the key characteristic information, searching for a fault path from a fault map; the fault map includes a plurality of nodes and a plurality of edges, each of the nodes is used to represent characteristic information, and each of the edges is used to represent an association relationship between each characteristic information;

[0017] Determine a plurality of fault nodes according to the fault path, and use information corresponding to the plurality of fault nodes as the plurality of current fault categories;

[0018] Based on the association between the fault node and each feature information, the current probability information corresponding to each current fault category is calculated; when the fault diagnosis operation is performed for the first time, the current fault category is the initial fault category, and the current probability information is the initial probability information corresponding to the initial fault category; when the fault diagnosis operation is not performed for the first time, the current fault category is the updated initial fault category obtained when the fault diagnosis operation was previously performed, and the current probability information is the updated initial probability information obtained when the fault diagnosis operation was previously performed, and the number of updated initial fault categories is less than or equal to the number of initial fault categories.

[0019] Optionally, judging whether a fault diagnosis stopping condition is met according to the user input information, the historical query information, the current fault category, and current probability information corresponding to each current fault category includes:

[0020] Determining a current diagnostic state of the vehicle according to the user input information, the historical query information, the current fault category and current probability information corresponding to each current fault category;

[0021] Determine whether a fault diagnosis stop condition is reached according to the current diagnosis state, the current fault type, and the historical query information;

[0022] Among them, the fault diagnosis stopping condition includes at least one of the following: the current probability information corresponding to the current fault category reaches a preset threshold, the number of inquiries corresponding to the historical inquiry information reaches a maximum number of inquiries, and the current diagnostic state is determined to be insufficient information gain.

[0023] Optionally, determine the target fault category of the vehicle, including:

[0024] If the current probability information corresponding to the current fault category reaches a preset threshold, the current fault category corresponding to the current probability information being greater than the preset threshold is used as the target fault category of the vehicle; or,

[0025] If the number of inquiries corresponding to the historical inquiry information reaches a maximum number of inquiries, a target fault category of the vehicle is determined according to the current diagnostic state.

[0026] Optionally, obtain updated user input information, including:

[0027] Generate current inquiry information according to the association relationship between the current diagnostic state and each feature information in the fault map, and send the current inquiry information to the user terminal;

[0028] Acquire the updated user input information; the updated user input information is generated and sent by the user terminal according to the current query information.

[0029] Optionally, after generating the diagnostic report and repair suggestions for the vehicle, the method further includes:

[0030] Acquire fault feedback data; the fault feedback data includes user feedback information and case data;

[0031] Extracting diagnosis and repair related information from the fault feedback data;

[0032] Determining the type of fault to be processed and the symptom information to be processed according to the diagnosis and repair association information;

[0033] The fault map is updated based on the to-be-processed fault category and the to-be-processed symptom information.

[0034] Optionally, the method further comprises:

[0035] Acquire vehicle attribute information and vehicle operation information; the vehicle attribute information includes at least one of the following: mileage, most recent vehicle maintenance time, vehicle model, and purchase year;

[0036] Analyze the vehicle attribute information and the vehicle operation information to determine the health of the vehicle and user behavior data; the health of the vehicle includes at least one of the following: engine performance, fuel consumption, and wear of parts of the vehicle;

[0037] Generate a vehicle maintenance plan and driving reminder information based on the health of the vehicle and the user behavior data.

[0038] In a second aspect, the present application provides a vehicle fault diagnosis device, comprising:

[0039] a determination module, configured to perform at least one fault diagnosis operation on the vehicle until a fault diagnosis stop condition is reached, so as to determine a target fault category of the vehicle;

[0040] A generating module, used for generating a diagnostic report and repair suggestions for the vehicle according to the target fault category;

[0041] The fault diagnosis operation includes:

[0042] Acquire user input information and historical query information of the vehicle; when the fault diagnosis operation is performed for the first time, the user input information is vehicle fault symptom information; when the fault diagnosis operation is not performed for the first time, the user input information is updated user input information obtained when the fault diagnosis operation was previously performed;

[0043] Analyze the user input information, and determine multiple current fault categories and current probability information corresponding to each current fault category from the fault spectrum;

[0044] Determining whether a fault diagnosis stopping condition is met according to the user input information, the historical query information, the current fault category and the current probability information corresponding to each current fault category;

[0045] When the fault diagnosis stop condition is not met, the updated user input information is obtained, and the control enters the next fault diagnosis operation; when the fault diagnosis stop condition is met, the control does not enter the next fault diagnosis operation.

[0046] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned vehicle fault diagnosis methods.

[0047] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned vehicle fault diagnosis methods.

[0048] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0049] The present application provides a vehicle fault diagnosis method, apparatus, device and medium, which determines the target fault category of the vehicle by performing at least one fault diagnosis operation on the vehicle until the fault diagnosis stop condition is reached, and generates a diagnosis report and repair suggestions for the vehicle according to the target fault category. The fault diagnosis operation includes: obtaining user input information and historical query information of the vehicle, when the fault diagnosis operation is performed for the first time, the user input information is vehicle fault symptom information, when the fault diagnosis operation is not performed for the first time, the user input information is updated user input information obtained when the fault diagnosis operation was previously performed, the user input information is parsed and processed, and multiple current fault categories and current probability information corresponding to each current fault category are determined from a fault map; judging whether the fault diagnosis stop condition is reached according to the user input information, historical query information, current fault category and current probability information corresponding to each current fault category; when the fault diagnosis stop condition is not reached, obtaining updated user input information and controlling to enter the next fault diagnosis operation; when the fault diagnosis stop condition is reached, controlling not to enter the next fault diagnosis operation. Compared with the prior art, the present solution can parse and process the user input information by acquiring user input information and historical query information, and conduct a comprehensive analysis in combination with the constructed fault map, accurately determine the current fault category and the corresponding current probability information, thereby providing data guidance information for the next round of fault diagnosis operations; and automatically determine whether the fault diagnosis stop condition is met based on the user input information, historical query information, current fault category and probability information, and automatically enter the next round of fault diagnosis operations when the diagnosis stop condition is not met. By parsing the updated user input information and conducting fine-grained analysis and judgment in combination with the historical query information, multiple rounds of vehicle fault diagnosis are more comprehensively realized to narrow the scope of each fault category determination, which is suitable for handling complex fault problems, and determines the target fault category when the diagnosis stop condition is met, and then can generate a vehicle diagnosis report and repair suggestions based on the target fault category, thereby improving the accuracy of vehicle fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1This is an application environment diagram of a vehicle fault diagnosis method in an embodiment of the present application;

[0052] Figure 2 A schematic diagram of a vehicle fault diagnosis method according to an embodiment of the present application;

[0053] Figure 3 A schematic diagram of a vehicle fault diagnosis method flow chart provided in an embodiment of the present application;

[0054] Figure 4 A schematic diagram of a process for updating a fault map provided in an embodiment of the present application;

[0055] Figure 5 A schematic diagram of the modules and process processing of a vehicle fault diagnosis system provided in an embodiment of the present application;

[0056] Figure 6 A schematic diagram of functional modules of a vehicle fault diagnosis device provided in one embodiment of the present application;

[0057] Figure 7 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0060] The vehicle fault diagnosis method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the thermal parameters of the mold during the die-casting process to the server 104, and the server 104 performs a cyclic fault diagnosis operation on the vehicle to determine the target fault category of the vehicle, and generates a diagnostic report and repair suggestions for the vehicle based on the target fault category. The server 104 can feed back the obtained diagnostic report and repair suggestions for the vehicle to the terminal 102, so as to visualize the diagnostic report and repair suggestions for the vehicle through the terminal 102. In addition, in some embodiments, the vehicle fault diagnosis method can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can obtain user input information, perform at least one fault diagnosis operation on the vehicle based on the user input information to determine the target fault category of the vehicle, and generate a diagnostic report and repair suggestions for the vehicle based on the target fault category. The server 104 can also obtain user input information from a data storage system, and perform at least one fault diagnosis operation on the vehicle based on the user input information to determine the target fault category of the vehicle, and generate a diagnostic report and repair suggestions for the vehicle based on the target fault category.

[0061] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0062] In an exemplary embodiment, Figure 2 As shown, a vehicle fault diagnosis method is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 201 to 202. Among them:

[0063] Step 201 , performing at least one fault diagnosis operation on the vehicle until a fault diagnosis stop condition is reached, so as to determine a target fault category of the vehicle.

[0064] It should be noted that the above fault diagnosis operation is a fault diagnosis operation performed on the vehicle, which can be performed multiple times until the fault diagnosis stop condition is reached. The above fault diagnosis stop condition can be customized according to actual needs, which may include the number of diagnosis times meeting the preset conditions, insufficient vehicle information gain, etc. The target fault category of the above vehicle is the fault category of the vehicle finally determined, for example, it may include engine failure, fuel leakage, low battery, etc.

[0065] See also Figure 3 As shown, Figure 3 A schematic diagram of a process of performing a fault diagnosis operation provided in an embodiment of the present application, wherein the fault diagnosis operation includes:

[0066] Step 301, obtaining user input information and historical query information of the vehicle. When the fault diagnosis operation is performed for the first time, the user input information is vehicle fault symptom information, and when the fault diagnosis operation is not performed for the first time, the user input information is updated user input information obtained when the fault diagnosis operation was performed last time.

[0067] Step 302 , parse the user input information, and determine multiple current fault categories and current probability information corresponding to each current fault category from the fault map.

[0068] Step 303 , judging whether the fault diagnosis stopping condition is met according to the user input information, the historical query information, the current fault category and the current probability information corresponding to each current fault category.

[0069] Step 304: when the fault diagnosis stop condition is not met, updated user input information is obtained, and control is performed to enter the next fault diagnosis operation.

[0070] Step 305 , when the fault diagnosis stop condition is reached, the control does not enter the next fault diagnosis operation, and determines the target fault category of the vehicle.

[0071] Specifically, the user input information of the above-mentioned vehicle may be the information after the user performs an input operation on the user terminal, and the input operation may include any of the following input methods: voice input method, manual press input method, touch input method, and the user input information may be displayed in the form of text. Historical inquiry information is used to characterize the inquiry information generated in all time periods before the current time. Optionally, the above-mentioned historical inquiry information may be imported and obtained from an external device, or may be obtained from a blockchain or database, or may be obtained by calling a system. This embodiment does not impose any limitation on the method for obtaining historical inquiry information.

[0072] During the process of diagnosing the fault of the vehicle, the user can describe the fault symptoms of the vehicle by voice or text, so that the computer device obtains the user input information of the vehicle, which is the fault symptom information of the vehicle, and then parses and processes the fault symptom information of the vehicle, and determines the fault list and the corresponding probability information from the fault map, wherein the fault list includes multiple initial fault categories, and the probability information is the initial probability information corresponding to each initial fault category. Then, according to the fault symptom information of the vehicle, the historical query information, the current fault category and the current probability information corresponding to each current fault category, it is judged whether the current operation reaches the fault diagnosis stop condition; when the fault diagnosis stop condition is not reached, the updated user input information is obtained, and the updated user input information is parsed and processed, and the current fault category and the probability information corresponding to each current fault category are determined from the fault map, wherein the current fault category can be the fault category after the initial fault category is reduced, and the probability information corresponding to each current fault category can be the probability information after the initial fault category is adjusted. Whether the fault diagnosis stop condition is met is determined based on historical query information, the current fault category and the current probability information corresponding to each current fault category. When the fault diagnosis stop condition is met, the target fault category of the vehicle is determined based on the current fault category and the corresponding probability information. When the fault diagnosis condition is not met, the next fault diagnosis operation is continued until the fault diagnosis stop condition is met, thereby determining the target fault category of the vehicle.

[0073] It is understandable that the above fault map is pre-built based on historical data. It is a dynamic map including fault symptom information, fault category, diagnostic steps and repair solutions. The fault map represents each element and its relationship in the form of nodes and edges. Among them, the node can represent the fault symptom information, fault category, diagnostic steps and repair solution, and the edge can represent the relationship between the fault symptom information, fault category, diagnostic steps and repair solution. The fault map is implemented as a dynamic data structure, which can flexibly add, modify and delete nodes and relationships.

[0074] In one embodiment, the user analysis process is performed to determine multiple current fault categories and current probability information corresponding to each current fault category from the fault map, including:

[0075] A language processing model is used to parse the user input information and extract key feature information; based on the key feature information, a fault path is searched from the fault map; the fault map includes multiple nodes and multiple edges, each node is used to represent feature information, and each edge is used to represent the association relationship between each feature information; multiple fault nodes are determined according to the fault path, and the information corresponding to the multiple fault nodes is used as multiple current fault categories; based on the association relationship between the fault nodes and each key feature information, the current probability information corresponding to each current fault category is calculated; when the fault diagnosis operation is executed for the first time, the current fault category is the initial fault category, and the current probability information is the initial probability information corresponding to the initial fault category; when the fault diagnosis operation is not executed for the first time, the current fault category is the updated initial fault category obtained when the fault diagnosis operation was previously executed, and the current probability information is the updated initial probability information obtained when the fault diagnosis operation was previously executed, and the number of updated initial fault categories is less than or equal to the number of initial fault categories.

[0076] In this embodiment, the above-mentioned language processing model may be a large language model, which is trained and constructed based on historical language data and corresponding annotation results. The language processing model has a strong language understanding ability and can deeply analyze the user input information to extract key feature information, which may include: vehicle fault symptoms, occurrence time, environmental conditions, etc. For example, if the user input information includes: "My car makes an abnormal sound when accelerating", the key feature information extracted by the language processing model may include: "When accelerating", "abnormal sound" and other information.

[0077] After extracting the key feature information, the fault path is searched from the fault map according to the key feature information, and then the fault map is searched according to the fault path to determine the corresponding fault node. The information corresponding to the fault node is the current fault category. When the fault diagnosis operation is performed for the first time, the information corresponding to the fault node is the initial fault category. After determining the current fault category, the fault map can be analyzed using the graph reasoning engine. Based on the association between the fault node and the graph data, the initial probability information corresponding to each initial fault category is calculated. The initial probability information is the probability that the vehicle belongs to the initial fault category, indicating the possibility of its occurrence. For example, the initial fault categories of the vehicle include: ignition system failure, fuel system failure and drive shaft failure, among which the probability that the vehicle belongs to the ignition system failure is 50%, the probability that the vehicle belongs to the fuel system failure is 40%, and the probability that the vehicle belongs to the drive shaft failure is 10%.

[0078] When the first fault diagnosis operation is completed and the diagnostic operation stop condition is not reached, the next fault diagnosis operation is performed, the computer device generates the current query information and displays it to the user, and then the user inputs the corresponding answer according to the current query information, so that the computer device obtains the updated user input information, and performs parsing processing according to the above fault diagnosis operation, extracts the next key feature information, and then performs fault path search and fault node determination, thereby obtaining the current fault category and the current probability information corresponding to each current fault category. The current fault category of the fault may include: ignition system fault and fuel system fault, and the corresponding current probability information may be that the probability of the vehicle belonging to the ignition system fault is 30%, and the probability of the vehicle belonging to the fuel system fault is 70%. Among them, after obtaining the updated user input information, the computer device dynamically adjusts the probability information of the fault category, thereby gradually narrowing the fault diagnosis range until the target fault category is determined.

[0079] After obtaining the updated user input information, natural language processing is performed on the updated user input information to extract new key feature information (new symptoms and time, etc.), and the extracted information set is updated. Then, based on the updated information set, the possible fault categories and their probability weights are recalculated in the fault map through the reasoning engine. Each round of query operation performed in this embodiment makes the system's diagnostic status more perfect, thereby gradually approaching the most likely fault cause and improving the fault diagnosis accuracy.

[0080] In this embodiment, by adopting a language processing module, it is possible to understand the user's vague or non-professional descriptions and convert them into structured information that can be used for diagnosis, thereby performing a comprehensive analysis of complex fault conditions, accurately understanding and processing user input information in natural language, and for each round of fault diagnosis operations, it is possible to generate a corresponding diagnostic path in a targeted manner based on the user input information, rather than a fixed consultation process, thereby improving the accuracy and efficiency of fault diagnosis.

[0081] Further, after determining multiple current fault categories and current probability information corresponding to each current fault category from the fault map, judging whether the fault diagnosis stop condition is reached based on user input information, historical query information, the current fault category and the current probability information corresponding to each current fault category may include the following method: determining the current diagnostic state of the vehicle based on user input information, historical query information, the current fault category and the current probability information corresponding to each current fault category; judging whether the fault diagnosis stop condition is reached based on the current diagnostic state, the current fault category and the historical query information; the fault diagnosis stop condition includes any one of the following: if the current probability information corresponding to the current fault category reaches a preset threshold, when the number of inquiries corresponding to the historical query information reaches the maximum number of inquiries, or if the current diagnostic state is determined to be insufficient information gain.

[0082] It should be noted that each time a vehicle performs a fault diagnosis operation, it corresponds to a current diagnostic state of the vehicle, and the current diagnostic state is continuously updated as the amount of information obtained from performing the fault diagnosis operation varies. The current diagnostic state is used to characterize many important information such as the current health status, working performance, and potential problems of various systems and components of the vehicle, and represents the real-time understanding and judgment of the vehicle during the fault diagnosis process. The current diagnostic state can be generated based on historical input information, historical query information, current fault categories, and current probability information corresponding to each current fault category. User input information includes information used to perform input operations, which may include vehicle fault symptoms, environmental conditions, time, vehicle model, etc.; historical query information may include questions raised during multiple rounds of consultations and user responses.

[0083] After determining the current diagnostic state of the vehicle, determine whether the fault diagnosis stop condition is met based on the current diagnostic state, check whether the current probability information corresponding to the current fault category reaches the preset threshold, or whether the number of inquiries corresponding to the historical inquiry information reaches the maximum number of inquiries, and whether the current diagnostic state is judged to be insufficient information gain; when any of the above three conditions is met, it indicates that the current fault diagnosis operation has reached the fault diagnosis stop condition; when none of the above three conditions are met, it indicates that the current fault diagnosis operation has not reached the fault diagnosis stop condition. Among them, if the user input information is insufficient in the current diagnostic state, it means that the information gain is insufficient, which indicates that the fault diagnosis stop condition has been met.

[0084] It is understandable that the above-mentioned preset thresholds and maximum number of inquiries can be customized according to actual needs. For example, they can be determined by historical data analysis, by conducting statistical analysis on a large number of historical diagnosis cases, and finding the optimal balance between diagnostic accuracy and number of inquiries under different thresholds; they can also be determined based on user experience, because too high a threshold may lead to too many inquiries and affect the user experience, and too low a threshold will lead to inaccurate diagnosis results. Therefore, the threshold needs to be determined after achieving a balance between accuracy and number of interactions; it can also be obtained by system adaptive adjustment, dynamically adjusting the threshold according to real-time diagnostic results and user feedback data to adapt to different usage scenarios and needs; it can also be determined through professional establishment, and the threshold that can meet industry characterization is set by referring to the opinions of experts in the field of automobile maintenance.

[0085] In this embodiment, users do not need to learn professional terms or use complex tools. They only need to describe the problem in everyday language. The computer device can understand the user input information and can quickly respond to the user input information, provide real-time diagnostic paths and suggestions, reduce user waiting time, and provide an intuitive user interface to display to the user, thereby greatly improving the user experience.

[0086] If the current probability information corresponding to the current fault category reaches a preset threshold, the current fault category corresponding to the current probability information greater than the preset threshold is used as the target fault category of the vehicle; or, when the number of inquiries corresponding to the historical inquiry information reaches the maximum number of inquiries, the target fault category of the vehicle is determined according to the current diagnostic status.

[0087] For example, taking the preset threshold of 90% as an example, when the probability of a certain fault category exceeds the preset threshold of 90%, the computer device will consider that the cause of the fault is very clear, and will stop asking the user, and use the current fault category exceeding 90% as the target fault category of the vehicle; the above maximum number of inquiries is set to avoid excessive interactions causing inconvenience to the user, and the maximum number of inquiries can be 5 or 10 rounds. When the maximum number of inquiries is reached, the computer device will output the most likely target fault category based on the current diagnostic state. If the computer device determines that in the current diagnostic state, continuing to ask questions to the user will obtain very little information gain and cannot significantly improve the diagnostic accuracy, it will also stop asking the user in advance, thereby determining the target fault category of the vehicle.

[0088] Among them, after obtaining the current diagnostic status, the current query information can be generated according to the current diagnostic status and the correlation in the fault map, and the current query information is sent to the user terminal; the updated user input information is obtained; the updated user input information is generated and sent by the user terminal according to the current query information.

[0089] It should be noted that the above current inquiry information can be generated based on the correlation between the current diagnostic state and the fault map, and the current inquiry information can help narrow the scope of fault diagnosis. In this embodiment, multiple rounds of inquiry operations can be used to communicate in depth with the user, and each round of inquiry information is dynamically generated based on the answers input by the user in the previous round and the fault map, ensuring that each round of fault detection can obtain more critical information to ensure the accuracy of fault diagnosis.

[0090] As an implementable method, the computer device analyzes the currently acquired known information, such as vehicle fault symptom information, key feature information, current fault category and probability information, determines the associated feature information to be acquired, and thus generates the corresponding current query information, which is very important for determining the fault category. As another implementable method, the information gain or entropy reduction principle can be used to screen out the current query content, which can maximize the diagnostic accuracy, and then the large language model is used to convert the selected current query content into natural language, and generate a question sentence that conforms to the human-computer interaction habits as the current query information.

[0091] Exemplarily, after obtaining the current diagnostic status, the user input information is initially parsed and processed to extract the key feature information "acceleration" and "abnormal noise", and the key feature information is parsed to determine the current diagnostic status of the vehicle based on the user input information, historical query information, initial fault category and initial probability information corresponding to each initial fault category. When it is determined that the fault diagnosis stop condition has not been met, the current diagnostic status is determined, and the current query information may be generated based on the current diagnostic status and the correlation relationship in the fault map, including, for example: "Does the abnormal noise come from the front or rear?", "Is the sound continuous or intermittent?", etc. The user can perform input operations based on the current query information, so that the computer device obtains the updated user input information, parses and processes the updated user input information, extracts the corresponding key feature information, and then searches the fault path from the fault map based on the key feature information, and then determines the corresponding current fault category and the corresponding current probability information, which is the probability information after adjusting the initial probability information, and then determines whether the fault diagnosis stop condition is met. When the fault diagnosis stop condition is met, the target probability category is determined based on the current fault category and the current probability information; when the fault diagnosis stop condition is not met, the current diagnostic state continues to be determined based on the updated user input information, historical query information, current fault category and corresponding probability information, and then generates the current query information, and executes the above-mentioned fault diagnosis operation until the fault diagnosis stop condition is met.

[0092] In this embodiment, by obtaining the user input information of the vehicle and using a language processing model to parse and process the user input information, key feature information can be accurately extracted, and then the fault path is searched from the fault map based on the key feature information, and then multiple fault nodes are determined based on the fault path to accurately determine the current fault category and corresponding probability information, and by dynamically generating query information, the user is prompted to provide more information, so as to further dynamically adjust the probability weight of each fault cause through the inference engine, thereby continuously narrowing the fault category each time, so as to quickly focus on the most likely fault cause, thereby improving the accuracy of fault determination.

[0093] Step 202 : Generate a vehicle diagnostic report and repair suggestions based on the target fault category.

[0094] It should be noted that the above diagnostic report is a diagnostic report corresponding to the target fault category, and the diagnostic report may include fault symptoms, diagnostic process and diagnostic results, wherein the diagnostic process may specifically include diagnostic items and corresponding results. Repair suggestions are suggestions corresponding to the target fault category.

[0095] After determining the target fault category, the fault node corresponding to the target fault category can be searched from the fault map to search for the corresponding diagnostic strategy and repair plan, and then the corresponding diagnostic report is generated according to the diagnostic strategy, and the repair plan is processed by natural language to generate the corresponding repair suggestion. The diagnostic report and repair suggestion are then sent to the user terminal for feedback to the user for review.

[0096] Exemplarily, the diagnostic report may include vehicle information, fault symptom description and diagnostic process, the diagnostic process including: preliminary inspection and substantive inspection of the vehicle, substantive inspection may include, for example: spark plug inspection, ignition coil inspection, fuel system inspection, intake system inspection, sensor inspection, etc.; repair suggestions may include: replacing spark plugs, replacing ignition coils, cleaning or replacing fuel filters, replacing air filter elements, checking and repairing air flow meters, thereby generating corresponding diagnostic reports and repair suggestions.

[0097] It should be noted that the above-mentioned computer device can provide an interactive interface, which is used to provide current inquiry information and can also display user input information. After obtaining the user input information, the user input information is processed using a language processing model, and the current inquiry information and target fault category can be generated instantly, thereby reducing the user's waiting time. At the same time, multiple different interfaces can also be set up, and different interfaces correspond to different channel services. Different channel services can include, for example, mobile applications, web pages, and voice assistants. By setting different channel service interfaces, it is convenient for users to obtain information on various channel services in a timely manner when encountering an emergency, thereby improving the user experience.

[0098] The present application provides a vehicle fault diagnosis method, which determines a target fault category of the vehicle by performing at least one fault diagnosis operation on the vehicle until a fault diagnosis stop condition is reached, and generates a diagnostic report and repair suggestions for the vehicle according to the target fault category. The fault diagnosis operation includes: obtaining user input information and historical query information of the vehicle, when the fault diagnosis operation is performed for the first time, the user input information is vehicle fault symptom information, and when the fault diagnosis operation is not performed for the first time, the user input information is updated user input information obtained when the fault diagnosis operation was previously performed, parsing the user input information, and determining multiple current fault categories and current probability information corresponding to each current fault category from a fault map; judging whether the fault diagnosis stop condition is reached according to the user input information, historical query information, the current fault category and the current probability information corresponding to each current fault category; when the fault diagnosis stop condition is not reached, obtaining the updated user input information and controlling the vehicle to enter the next fault diagnosis operation; when the fault diagnosis stop condition is reached, controlling the vehicle not to enter the next fault diagnosis operation. Compared with the prior art, the present solution can parse and process the user input information by acquiring user input information and historical query information, and conduct a comprehensive analysis in combination with the constructed fault map, accurately determine the current fault category and the corresponding current probability information, thereby providing data guidance information for the next round of fault diagnosis operations; and automatically determine whether the fault diagnosis stop condition is reached based on the user input information, historical query information, current fault category and probability information, and automatically enter the next round of fault diagnosis operations when the diagnosis stop condition is not reached. By parsing the updated user input information and analyzing and judging in combination with the historical query information, multiple rounds of fault diagnosis of the vehicle are more comprehensively realized to narrow the scope of each fault category determination, which is suitable for handling complex fault problems, and determines the target fault category when the diagnosis stop condition is reached, and then can generate a vehicle diagnosis report and repair suggestions based on the target fault category, thereby improving the accuracy of vehicle fault diagnosis.

[0099] In another exemplary embodiment of the present application, in order to accurately perform fault diagnosis and analysis based on the fault map, it is necessary to update the fault map in real time. Figure 4 As shown, after generating the vehicle diagnostic report and repair suggestions, the method further includes the following steps 401 to 404:

[0100] Step 401, obtaining fault feedback data; the fault feedback data includes user feedback information and case data.

[0101] Step 402: extracting diagnosis and repair related information from the fault feedback data.

[0102] Step 403: Determine the type of fault to be processed and the symptom information to be processed according to the diagnosis and repair association information.

[0103] Step 404: Update the fault map based on the to-be-processed fault category and the to-be-processed symptom information.

[0104] It should be noted that the above-mentioned fault feedback data may include user feedback data and case data. The user feedback information includes any one of the following: whether the fault is resolved, whether the diagnosis is correct, whether the repair plan is effective, whether there is new symptom information, the content of new symptom information, whether there is a new fault category, the content of the new fault category, whether there is a new repair plan, the content of the new repair plan; the case data includes at least one of the following: data in the maintenance database, industry reports, and technical documents. The above-mentioned diagnostic and repair association information is used to characterize information associated with updating the fault map. The pending fault category is the fault category that needs to be processed in the fault map, and the pending symptom information is the symptom information that needs to be processed in the fault map. The pending fault category may include the to-be-updated fault category and the to-be-added fault category, and the to-be-processed symptom information may include the to-be-updated symptom information and the to-be-added symptom information.

[0105] Optionally, the user feedback data may be obtained by sending a request to a user terminal after the user performs fault repair according to a repair suggestion, or may be obtained by importing from an external device, or may be obtained from a blockchain or a database. This embodiment does not impose any limitation on the method of obtaining user feedback data.

[0106] As an implementable method, after obtaining user feedback data, the user feedback data is parsed and processed using a large language model to extract diagnosis and repair association information, which can improve the diagnosis accuracy and repair effect. Then, based on the diagnosis and repair association information, the fault category and symptom information to be updated are determined, and then the corresponding nodes to be updated and edges to be updated are determined to update the fault map. In the process of updating the fault map, the association relationship and weight between the nodes to be updated in the fault map can be updated.

[0107] For example, for cases where the fault diagnosis is correct in user feedback data, the association weight between the fault category to be updated and the symptom to be updated is enhanced to increase the priority of the path; for cases where the fault diagnosis is incorrect in user feedback data, the error association weight is adjusted or weakened, and the parts that need manual review are marked to further improve the fault map. If the user feedback data includes new symptom information content, new fault category content, and new repair solution content, it will be added to the fault map.

[0108] In this embodiment, after generating the vehicle's diagnostic report and repair suggestions, user feedback data is obtained, and the map can be appropriately adjusted according to whether the fault diagnosis is accurate. When the fault diagnosis is accurate, the weight of the relevant path is enhanced; when the fault diagnosis is inaccurate, the association relationship in the fault map is adjusted, so that the fault map is updated in real time in an automated manner without human intervention, ensuring the inclusion of the latest fault information and the integrity of the fault map knowledge base.

[0109] As a feasible method, after obtaining the case data, a large language model can be used to parse and process the case data, extract the diagnosis and repair related information, and then determine the fault category and symptom information to be updated, so as to add the fault category and symptom information to the fault map based on the fault category and symptom information to be added.

[0110] In this embodiment, by acquiring case data, it can automatically parse the case data without human intervention, thereby updating the knowledge base in the fault map in real time, adapting to the latest car models, the latest technologies and newly emerging fault modes, improving the accuracy and comprehensiveness of subsequent fault diagnosis, and has high scalability and compatibility, and can be compatible with different data sources, including maintenance cases in various formats, technical documents and other data, ensuring the richness of the knowledge base.

[0111] In one embodiment, in addition to being able to perform fault diagnosis, the present application also provides a specific implementation method for vehicle maintenance and driving prompts, the method comprising:

[0112] Obtain vehicle attribute information and vehicle operation information; the vehicle attribute information includes at least one of the following: mileage, most recent vehicle maintenance time, vehicle model, and purchase year.

[0113] Analyze vehicle attribute information and vehicle operation information to determine the vehicle's health and user behavior data; the vehicle's health includes at least one of the following: the vehicle's engine performance, fuel consumption, and component wear.

[0114] Generate vehicle maintenance plans and driving reminder information based on vehicle health and user behavior data.

[0115] Specifically, the above vehicle attribute information can be obtained through multiple rounds of inquiries, or can be obtained through external devices, or can be obtained from blockchain or database. Vehicle operation information is used to characterize the information generated by the vehicle during operation. It is obtained in real time by connecting to the OBD-II interface of the vehicle or the vehicle information system. The vehicle operation information may include vehicle mileage, operating speed, etc. The engine performance of the above vehicle may include: parameters such as engine power, torque, speed and compression ratio; the above fuel consumption status includes: parameters such as fuel consumption per 100 kilometers and instantaneous fuel consumption; the above parts wear degree may include: cylinder wear, piston ring wear rate, brake pad wear thickness and other parameters.

[0116] After obtaining the vehicle attribute information and vehicle operation information, the vehicle attribute information and vehicle operation information are analyzed to evaluate the vehicle's engine performance, fuel consumption, and component wear, etc. Then, the user's driving data and fault history data can be obtained. The driving data may include acceleration time, braking time, and idling time. The vehicle attribute information and user driving data are analyzed to generate user behavior data, which is used to characterize the user's driving behavior habits. Then, based on the health of the vehicle and the user's behavior data, a vehicle maintenance plan and driving prompt information are generated. The vehicle maintenance plan, for example, includes: recommending early replacement of engine oil, checking the brake system, cleaning the fuel system, etc. Driving prompt information is generated based on the user's driving data, for example, reminding to avoid frequent emergency braking, recommending reasonable speed control, and prompting correct tire pressure maintenance, etc. At the same time, the computer device can determine the vehicle's operating trend and operating mode based on the stored fault history data combined with time series analysis.

[0117] Optionally, the above-mentioned driving prompt information can be provided to the user in the form of voice prompts, picture prompts, or video prompts.

[0118] In this embodiment, by acquiring vehicle attribute information and vehicle operation information and analyzing the vehicle attribute information and vehicle operation information, a vehicle maintenance plan and driving reminder information are generated in a targeted manner, which greatly improves the user experience.

[0119] In one embodiment, see Figure 5As shown, the computer device may include a user input module, a natural language processing module, a fault map module, an inference engine module, a question generation module and a result output module. The user can perform input operations through the user input module to obtain user input information, and analyze the user input information through the natural language processing module to extract key feature information, which may include fault symptoms, time, working conditions and other information, and process some simulation descriptions in the user input information, and then process it through the fault map module, which stores the fault-cause-repair relationship. After obtaining the key feature information, find the associated symptoms and possible causes according to the key feature information, and dynamically infer the fault cause based on the fault map through the inference engine module, and generate a diagnosis list according to the probability weight, and adjust the inference path in combination with user feedback, and then dynamically generate the current inquiry information for subsequent questions according to the current diagnosis state through the inquiry generation module. The current inquiry information is used to deeply obtain the detailed information of the vehicle fault symptoms to personalize and adapt the user's answer, and then continue to process through the user input module, natural language processing module, fault map module, inference engine module, and inquiry generation module in sequence. When the fault diagnosis reaches the fault diagnosis stop condition, the target fault category is output according to the current fault category and the corresponding probability information through the result output module. After obtaining the target fault category, a diagnostic report and repair suggestions for the vehicle are generated according to the target fault category. The above-mentioned reasoning engine module can use algorithms such as probabilistic reasoning and Bayesian networks to process uncertainty and simulation information.

[0120] In this embodiment, an inference engine is integrated, and data analysis is performed in combination with user input information and historical query information to dynamically adjust the weights between nodes and edges in the fault graph, thereby optimizing the fault diagnosis reasoning process and improving the accuracy of fault diagnosis.

[0121] Based on the same inventive concept, the embodiment of the present application also provides a vehicle fault diagnosis device for implementing the above-mentioned vehicle fault diagnosis method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more vehicle fault diagnosis device embodiments provided below can refer to the limitations of the vehicle fault diagnosis method above, and will not be repeated here.

[0122] In an exemplary embodiment, Figure 6 As shown, a vehicle fault diagnosis device is provided, comprising:

[0123] A determination module 510 is used to perform at least one fault diagnosis operation on the vehicle until a fault diagnosis stop condition is reached to determine a target fault category of the vehicle;

[0124] A generating module 520, for generating a vehicle diagnostic report and repair suggestions according to the target fault category;

[0125] Troubleshooting operations include:

[0126] Obtaining user input information and historical query information of the vehicle; when the fault diagnosis operation is performed for the first time, the user input information is the vehicle fault symptom information; when the fault diagnosis operation is not performed for the first time, the user input information is the updated user input information obtained when the fault diagnosis operation was previously performed;

[0127] Parse the user input information and determine multiple current fault categories and current probability information corresponding to each current fault category from the fault map;

[0128] Determine whether the fault diagnosis stop condition is met based on user input information, historical query information, current fault category and current probability information corresponding to each current fault category;

[0129] When the fault diagnosis stop condition is not reached, the updated user input information is obtained, and the control enters the next fault diagnosis operation; when the fault diagnosis stop condition is reached, the control does not enter the next fault diagnosis operation.

[0130] As an optional implementation, the above device is specifically used for:

[0131] Use language processing models to parse user input information and extract key feature information;

[0132] According to the key characteristic information, the fault path is searched from the fault map; the fault map includes multiple nodes and multiple edges, each node is used to represent the characteristic information, and each edge is used to represent the association relationship between the characteristic information;

[0133] Determine multiple fault nodes according to the fault path, and use information corresponding to the multiple fault nodes as multiple current fault categories;

[0134] Based on the correlation between the fault node and each key feature information, the current probability information corresponding to each current fault category is calculated; when the fault diagnosis operation is performed for the first time, the current fault category is the initial fault category, and the current probability information is the initial probability information corresponding to the initial fault category; when the fault diagnosis operation is not performed for the first time, the current fault category is the updated initial fault category obtained when the fault diagnosis operation was previously performed, and the current probability information is the updated initial probability information obtained when the fault diagnosis operation was previously performed, and the number of updated initial fault categories is less than or equal to the number of initial fault categories.

[0135] As an optional implementation, the above device is specifically used for:

[0136] Determine the current diagnostic state of the vehicle based on user input information, historical query information, current fault category, and current probability information corresponding to each current fault category;

[0137] Determine whether the fault diagnosis stopping conditions are met based on the current diagnostic state, current fault category, and historical query information; the fault diagnosis stopping conditions include any one of the following: if the current probability information corresponding to the current fault category reaches a preset threshold, when the number of inquiries corresponding to the historical query information reaches the maximum number of inquiries, or when the current diagnostic state is determined to be insufficient information gain.

[0138] As an optional implementation, the above device is specifically used for:

[0139] If the current probability information corresponding to the current fault category reaches a preset threshold, the current fault category corresponding to the current probability information being greater than the preset threshold is taken as the target fault category of the vehicle; or,

[0140] When the number of inquiries corresponding to the historical inquiry information reaches the maximum number of inquiries, the target fault category of the vehicle is determined according to the current diagnosis state.

[0141] As an optional implementation, the above device is specifically used for:

[0142] Generate current inquiry information according to the current diagnosis state and the correlation relationship in the fault map, and send the current inquiry information to the user terminal;

[0143] Get updated user input information; the updated user input information is generated and sent by the user terminal according to the current query information.

[0144] As an optional implementation, the above device is also used for:

[0145] Obtain fault feedback data; fault feedback data includes user feedback information and case data;

[0146] Extracting diagnosis and repair related information from fault feedback data;

[0147] Determine the fault category and symptom information to be processed based on the diagnosis and repair association information;

[0148] Update the fault map based on the pending fault categories and pending symptom information.

[0149] As an optional implementation, the above device is also used for:

[0150] Obtain vehicle attribute information and vehicle operation information; the vehicle attribute information includes at least one of the following: mileage, most recent vehicle maintenance time, vehicle model, and purchase year;

[0151] Analyze vehicle attribute information and vehicle operation information to determine the vehicle's health and user behavior data; the vehicle's health includes at least one of the following: the vehicle's engine performance, fuel consumption, and component wear;

[0152] Generate vehicle maintenance plans and driving reminder information based on vehicle health and user behavior data.

[0153] Among them, the vehicle fault diagnosis device provided in the embodiment of the present application can parse and process the user input information by obtaining user input information and historical query information, and conduct a comprehensive analysis in combination with the constructed fault map to accurately determine the current fault category and the corresponding current probability information, thereby providing data guidance information for the next round of fault diagnosis operations; and automatically determine whether the fault diagnosis stop condition is met based on the user input information, historical query information, current fault category and probability information, and automatically enter the next round of fault diagnosis operations when the diagnosis stop condition is not met. By parsing the updated user input information and analyzing and judging in combination with the historical query information, multiple rounds of fault diagnosis of the vehicle are more comprehensively realized to narrow the scope of each fault category determination, which is suitable for handling complex fault problems, and determines the target fault category when the diagnosis stop condition is met, and then can generate a vehicle diagnosis report and repair suggestions based on the target fault category, thereby improving the accuracy of vehicle fault diagnosis.

[0154] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a vehicle fault diagnosis method is implemented.

[0155] Those skilled in the art will understand that Figure 7The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0156] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0157] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0158] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0159] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0160] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0161] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0162] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A vehicle fault diagnosis method, characterized in that: The vehicle fault diagnosis method comprises: Performing at least one fault diagnosis operation on the vehicle until a fault diagnosis stop condition is reached to determine a target fault category of the vehicle; generating a diagnostic report and repair suggestions for the vehicle according to the target fault category; The fault diagnosis operation includes: Acquire user input information and historical inquiry information of the vehicle; when the fault diagnosis operation is performed for the first time, the user input information is vehicle fault symptom information; when the fault diagnosis operation is not performed for the first time, the user input information is updated user input information obtained when the fault diagnosis operation was previously performed; Analyze the user input information, and determine multiple current fault categories and current probability information corresponding to each current fault category from the fault spectrum; Determining whether a fault diagnosis stopping condition is met according to the user input information, the historical query information, the current fault category and the current probability information corresponding to each current fault category; When the fault diagnosis stop condition is not met, the updated user input information is obtained, and the control enters the next fault diagnosis operation; when the fault diagnosis stop condition is met, the control does not enter the next fault diagnosis operation.

2. The vehicle fault diagnosis method according to claim 1, characterized in that: The user input information is parsed and processed, and a plurality of current fault categories and current probability information corresponding to each of the current fault categories are determined from the fault map, including: Using a language processing model to parse the user input information and extract key feature information; According to the key characteristic information, searching for a fault path from a fault map; the fault map includes a plurality of nodes and a plurality of edges, each of the nodes is used to represent characteristic information, and each of the edges is used to represent an association relationship between each characteristic information; Determine a plurality of fault nodes according to the fault path, and use information corresponding to the plurality of fault nodes as the plurality of current fault categories; Based on the association between the fault node and each key feature information, the current probability information corresponding to each current fault category is calculated; when the fault diagnosis operation is performed for the first time, the current fault category is the initial fault category, and the current probability information is the initial probability information corresponding to the initial fault category; when the fault diagnosis operation is not performed for the first time, the current fault category is the updated initial fault category obtained when the fault diagnosis operation was previously performed, and the current probability information is the updated initial probability information obtained when the fault diagnosis operation was previously performed, and the number of updated initial fault categories is less than or equal to the number of initial fault categories.

3. The vehicle fault diagnosis method according to claim 1, characterized in that: Determining whether a fault diagnosis stopping condition is met according to the user input information, the historical query information, the current fault category, and the current probability information corresponding to each current fault category includes: Determining a current diagnostic state of the vehicle according to the user input information, the historical query information, the current fault category and current probability information corresponding to each current fault category; Determine whether a fault diagnosis stop condition is reached according to the current diagnosis state, the current fault type, and the historical query information; Among them, the fault diagnosis stopping condition includes at least one of the following: the current probability information corresponding to the current fault category reaches a preset threshold, the number of inquiries corresponding to the historical inquiry information reaches a maximum number of inquiries, and the current diagnostic state is determined to be insufficient information gain.

4. The vehicle fault diagnosis method according to claim 3, characterized in that: Determine the target fault categories for the vehicle, including: If the current probability information corresponding to the current fault category reaches a preset threshold, the current fault category corresponding to the current probability information being greater than the preset threshold is used as the target fault category of the vehicle; or, If the number of inquiries corresponding to the historical inquiry information reaches a maximum number of inquiries, a target fault category of the vehicle is determined according to the current diagnostic state.

5. The vehicle fault diagnosis method according to claim 3, characterized in that: Get updated user input information, including: Generate current inquiry information according to the association relationship between the current diagnostic state and each feature information in the fault map, and send the current inquiry information to the user terminal; Acquire the updated user input information; the updated user input information is generated and sent by the user terminal according to the current query information.

6. The vehicle fault diagnosis method according to claim 1, characterized in that: After generating the diagnostic report and repair suggestions for the vehicle, the method further includes: Acquire fault feedback data; the fault feedback data includes user feedback information and case data; Extracting diagnosis and repair related information from the fault feedback data; Determining the type of fault to be processed and the symptom information to be processed according to the diagnosis and repair association information; The fault map is updated based on the to-be-processed fault category and the to-be-processed symptom information.

7. The vehicle fault diagnosis method according to claim 1, characterized in that: The method further comprises: Acquire vehicle attribute information and vehicle operation information; the vehicle attribute information includes at least one of the following: mileage, most recent vehicle maintenance time, vehicle model, and purchase year; Analyze the vehicle attribute information and the vehicle operation information to determine the health of the vehicle and user behavior data; The health of the vehicle includes at least one of the following: engine performance, fuel consumption, and wear of parts of the vehicle; Generate a vehicle maintenance plan and driving reminder information based on the health of the vehicle and the user behavior data.

8. A vehicle fault diagnosis device, characterized in that: The vehicle fault diagnosis device comprises: A determination module, configured to perform at least one fault diagnosis operation on the vehicle until a fault diagnosis stop condition is reached, so as to determine a target fault category of the vehicle; A generating module, used for generating a diagnostic report and repair suggestions for the vehicle according to the target fault category; The fault diagnosis operation includes: Acquire user input information and historical inquiry information of the vehicle; when the fault diagnosis operation is performed for the first time, the user input information is vehicle fault symptom information; when the fault diagnosis operation is not performed for the first time, the user input information is updated user input information obtained when the fault diagnosis operation was previously performed; Analyze the user input information, and determine multiple current fault categories and current probability information corresponding to each current fault category from the fault spectrum; Determining whether a fault diagnosis stopping condition is met according to the user input information, the historical query information, the current fault category and the current probability information corresponding to each current fault category; When the fault diagnosis stop condition is not met, the updated user input information is obtained, and the control enters the next fault diagnosis operation; when the fault diagnosis stop condition is met, the control does not enter the next fault diagnosis operation.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the vehicle fault diagnosis method described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle fault diagnosis method described in any one of claims 1 to 7 are implemented.

Images