A vehicle diagnostic fault solution generation method and apparatus, device, medium

Abstract

The embodiment of the application provides a vehicle diagnostic fault solution generation method and device, equipment and medium, which obtain the diagnostic fault problem input by the user in response to the diagnostic fault problem input operation of the user; then query the target diagnostic document in the preset diagnostic knowledge base according to the diagnostic fault problem; and then determine the solution corresponding to the diagnostic fault problem based on the diagnostic fault problem and the target diagnostic document through a large language model, so as to realize the automatic generation of the diagnostic fault solution. Through the combination of the diagnostic knowledge base and the large language model, the diagnostic fault solution can be directly obtained through the dialogue question and answer mode, the human resource cost required when obtaining the diagnostic fault solution is reduced, the efficiency of obtaining the diagnostic fault solution is improved, and the operation complexity of the diagnostic personnel when working is reduced.

Description

Technical Field

[0001] This invention relates to the field of vehicle diagnostics, and in particular to a method, apparatus, equipment, and medium for generating vehicle diagnostic fault solutions. Background Technology

[0002] To ensure vehicle safety and performance compliance, vehicles typically require pre-sale diagnostics to determine if their functions are intact and to promptly identify and resolve any faults to ensure vehicle quality.

[0003] Generally, after completing vehicle diagnostics, common diagnostic fault scenarios are compiled into a diagnostic document. When diagnostic personnel discover a fault during subsequent vehicle diagnostics, they will first look for similar diagnostic problems and solutions in the compiled diagnostic document. If no solution is found, they will need to conduct independent analysis through methods such as drawing work orders to obtain a solution.

[0004] However, the above methods all require significant human resources for manual retrieval or analysis, resulting in high costs and low efficiency. Summary of the Invention

[0005] In view of the above problems, a method, apparatus, device, and medium for generating vehicle diagnostic fault solutions are proposed to overcome or at least partially solve the above problems, including:

[0006] A method for generating vehicle diagnostic fault solutions, the method comprising:

[0007] In response to a user's input of a diagnostic problem, obtain the diagnostic problem input by the user;

[0008] Based on the diagnosed fault problem, a query is performed in a preset diagnostic knowledge base to obtain the target diagnostic document;

[0009] Based on the diagnosed fault problem and the target diagnostic document, a solution corresponding to the diagnosed fault problem is determined using a large language model.

[0010] Optionally, determining the solution corresponding to the diagnosed fault problem based on the diagnosed fault problem and the target diagnostic document using a large language model includes:

[0011] The large language model is used to determine whether the diagnosed fault problem matches the target diagnostic document.

[0012] If the diagnosed fault problem matches the target diagnostic document, the solution in the target diagnostic document is sent to the user through the large language model.

[0013] Optionally, the method further includes:

[0014] If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, the solution corresponding to the fault code information is sent to the user through the large language model.

[0015] Optionally, when the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, sending the solution corresponding to the fault code information to the user through the large language model includes:

[0016] If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, and the fault code information includes fault code, vehicle model information, and electronic controller information, the large language model determines the solution corresponding to the fault code information based on the fault code, vehicle model information, and electronic controller information, and sends the solution corresponding to the fault code information to the user.

[0017] Optionally, the method further includes:

[0018] If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, and the fault code information is missing any one or more of the fault code, vehicle model information, and electronic controller information, the user is prompted to ask the question again based on the type of information missing in the fault code information.

[0019] Optionally, determining the solution corresponding to the diagnosed fault problem based on the diagnosed fault problem and the target diagnostic document using a large language model includes:

[0020] The diagnostic fault problem and the target diagnostic document are written into a preset prompt template to obtain prompt text; wherein, the prompt template includes at least a prompt question, and the prompt question includes at least a knowledge base matching result question and a diagnostic fault problem text information completeness question; the knowledge base matching result question is used to prompt the large language model to determine whether the diagnostic fault problem and the target diagnostic document match each other, and the diagnostic fault problem text information completeness question is used to determine whether the diagnostic fault problem is missing any one or more of fault codes, vehicle model information, and electronic controller information;

[0021] The prompt text is input into the large language model, and the large language model outputs the solution corresponding to the diagnosed fault problem based on the prompt text.

[0022] Optionally, before obtaining the user-inputted diagnostic problem in response to the user's diagnostic problem input, the method further includes:

[0023] Obtain online diagnostic documents and construct the diagnostic knowledge base based on the online diagnostic documents; wherein, the diagnostic documents include at least the diagnostic problem and the corresponding solution;

[0024] The diagnostic question is set as a matching condition in the diagnostic knowledge base.

[0025] A vehicle diagnostic fault solution generation apparatus, the apparatus comprising:

[0026] The diagnostic fault problem acquisition module is used to acquire the diagnostic fault problem input by the user in response to the user's diagnostic fault problem input operation;

[0027] The target diagnostic document query module is used to query a preset diagnostic knowledge base based on the diagnosed fault problem to obtain the target diagnostic document;

[0028] The solution determination module is used to determine the solution corresponding to the diagnosed fault problem based on the diagnosed fault problem and the target diagnostic document using a large language model.

[0029] An electronic device includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the vehicle diagnostic fault solution generation method as described above.

[0030] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle diagnostic fault solution generation method as described above.

[0031] The embodiments of the present invention have the following advantages:

[0032] In this embodiment of the invention, the diagnostic fault question input by the user is obtained in response to the user's input operation; then, a query is performed in a preset diagnostic knowledge base based on the diagnostic fault question to obtain the target diagnostic document; and finally, the solution corresponding to the diagnostic fault question is determined by a large language model based on the diagnostic fault question and the target diagnostic document, thereby realizing the automated generation of diagnostic fault solutions. Through the combined application of diagnostic knowledge base and large language model, diagnostic fault solutions can be automatically obtained after the user inputs a diagnostic fault question, without the need for additional human resource costs to retrieve diagnostic fault solutions, thus improving the efficiency of obtaining diagnostic fault solutions and reducing the operational complexity of diagnostic personnel. Attached Figure Description

[0033] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart of the steps of a method for generating a vehicle diagnostic fault solution according to some embodiments of the present invention;

[0035] Figure 2 These are practical application examples of the present invention provided by some embodiments;

[0036] Figure 3 This is a schematic diagram of the overall execution flow of the present invention provided in some embodiments;

[0037] Figure 4 This is a schematic diagram of the structure of a vehicle diagnostic fault solution generation device provided in some embodiments of the present invention;

[0038] Figure 5 This is a block diagram of an electronic device provided in some embodiments of the present invention;

[0039] Figure 6 This is a schematic diagram of a computer-readable medium provided in some embodiments of the present invention. Detailed Implementation

[0040] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0041] To ensure vehicle safety and performance compliance, vehicles typically require pre-sale diagnostics to determine if their functions are intact and to promptly identify and resolve any faults to ensure vehicle quality.

[0042] Generally, when performing vehicle diagnostics, common diagnostic fault scenarios are compiled into a diagnostic document. After discovering a fault, the diagnostic personnel will first look for similar diagnostic problems and solutions in the diagnostic document. If no solution is found, they will need to conduct independent analysis through methods such as drawing work orders to obtain a solution.

[0043] However, the above methods all require significant human resources for manual retrieval or analysis, resulting in high costs and low efficiency.

[0044] In this embodiment of the invention, based on the core technical concept of automating the generation of diagnostic fault solutions through the combined application of a diagnostic knowledge base and a large language model, the method for generating vehicle diagnostic fault solutions in related technologies has been improved. The invention will be described in detail below with reference to the accompanying drawings:

[0045] Reference Figure 1 The diagram illustrates a flowchart of a method for generating a vehicle diagnostic fault solution according to some embodiments of the present invention, which may specifically include the following steps:

[0046] Step 101: In response to the user's diagnostic fault problem input operation, obtain the diagnostic fault problem input by the user;

[0047] In specific implementations, for ease of explanation, the following will provide explanations of some terms involved in the embodiments of the present invention:

[0048] RAG: RAG stands for "Retrieval-Augmented Generation," a deep learning model architecture for Natural Language Processing (NLP). It combines two main techniques: retrieval and generation.

[0049] QDRANT: qdrant knowledge base, a database based on vector matching retrieval.

[0050] Remote PDI: Vehicles require pre-sale diagnostics to determine if their functions are working properly. Remote PDI allows diagnostic messages to be pushed to the vehicle remotely, and the vehicle automatically performs the diagnostics upon receiving the message.

[0051] Diagnostic fault codes: When errors occur during the diagnostic process, different fault codes will be reported to the cloud depending on the vehicle model, ECU, and the error. Each fault code includes information such as its cause and solution. Diagnostic personnel can use this information to perform repairs.

[0052] Based on this, such as Figure 2As shown, a UI interface can be built based on RAG technology in the form of a chatbot (such as Lark robot) for users to input diagnostic fault questions, thereby obtaining the user-input diagnostic fault questions and starting an automated analysis and processing flow. For example, after the user inputs the diagnostic fault question: "One-click PDI, air conditioning heater water pump failed to start: reported NRC-22", the chatbot can provide response information according to the order of historical questions, solutions, solution time, and vehicle series based on the user's input diagnostic fault question. It can also provide answer evaluation feedback buttons (such as providing both like and dislike options) to obtain user feedback, and can generate a dialogue ID for subsequent queries. In addition, to improve the accuracy of answer generation, the chatbot can be controlled to add diagnostic fault question format examples for user reference when answering, so that users can adjust the diagnostic fault questions, such as adding ECU name information to the diagnostic fault questions.

[0053] In some embodiments of the present invention, before obtaining the diagnostic fault problem input by the user in response to the user's diagnostic fault problem input operation, the method further includes:

[0054] Obtain online diagnostic documents and construct the diagnostic knowledge base based on the online diagnostic documents; wherein, the diagnostic documents include at least the diagnostic problem and the corresponding solution;

[0055] The diagnostic question is set as a matching condition in the diagnostic knowledge base.

[0056] In practical applications, each diagnostic question and solution from existing diagnostic documents can be pre-imported into the online page, and add, delete, and modify functions can be configured. This allows for the addition, modification, and deletion of diagnostic questions and solutions at any time. Furthermore, the online diagnostic documents can be imported into a diagnostic knowledge base, which can utilize the QDrant knowledge base to support vector retrieval matching. Diagnostic questions can then be set as matching conditions in the diagnostic knowledge base, using the diagnostic questions in the diagnostic documents as vector matching conditions. When the online diagnostic documents are modified, the knowledge base information is updated synchronously.

[0057] By acquiring online diagnostic documents and building a knowledge base, the system ensures the real-time updating and maintenance of these documents, guaranteeing users access to the latest and most accurate solutions. Furthermore, the construction and synchronized updating of online documents and the knowledge base ensure the system can efficiently handle query requests for different vehicle models and types of faults, enhancing its adaptability and scalability.

[0058] Step 102: Search the preset diagnostic knowledge base according to the diagnosed fault problem to obtain the target diagnostic document;

[0059] In practice, after obtaining the user's diagnosed fault problem, the system can search the diagnostic knowledge base for the most matching diagnostic document based on the content of the user's diagnosed fault problem, and use it as the target diagnostic document as one of the input data for the large language model in the subsequent process.

[0060] Step 103: Based on the diagnosed fault problem and the target diagnostic document, determine the solution corresponding to the diagnosed fault problem using a large language model.

[0061] In practical implementation, an interface for querying fault code details can be pre-configured for the large language model. For example, an interface can be provided to query fault code details by vehicle model information, ECU (electronic controller) name information, and fault code. Furthermore, the target diagnostic document, the diagnosed fault problem, and even the interface information for querying fault code details obtained from the diagnostic knowledge base can be combined into prompt words and sent to the large language model so that the large language model can determine the solution corresponding to the diagnosed fault problem based on the prompt words.

[0062] In some embodiments of the present invention, determining the solution corresponding to the diagnosed fault problem based on the diagnosed fault problem and the target diagnostic document using a large language model includes:

[0063] The large language model is used to determine whether the diagnosed fault problem matches the target diagnostic document.

[0064] If the diagnosed fault problem matches the target diagnostic document, the solution in the target diagnostic document is sent to the user through the large language model.

[0065] In practical applications, the large language model can automatically determine whether a user's diagnosed problem matches a target diagnostic document in the diagnostic knowledge base based on prompt words using the `function_call` capability. If the large language model determines that the user's diagnosed problem matches the target diagnostic document, it can send the solution from the target diagnostic document to the user. This ensures that the solution provided to the user is the most relevant solution in the diagnostic knowledge base, thereby improving diagnostic accuracy and reducing the possibility of misdiagnosis or incorrect guidance.

[0066] In some embodiments of the present invention, the method further includes:

[0067] If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, the solution corresponding to the fault code information is sent to the user through the large language model.

[0068] In practical applications, when the diagnosed fault problem does not match the target diagnostic document, the large language model can automatically determine whether it is necessary to call the interface to query fault code details. For example, if fault code information exists in the diagnosed fault problem, it can determine that it is necessary to call the interface to query fault code details, and further automatically extract the fault code information from the user's problem, call the interface to query fault code details, and send the solution corresponding to the fault code information to the user.

[0069] When the diagnosed fault does not completely match the target diagnostic document in the knowledge base, the system can extract the fault code information and automatically call the relevant interface to query the solution, avoiding manual searching and multiple queries, and improving the automation level of fault diagnosis.

[0070] In some embodiments of the present invention, when the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, sending the solution corresponding to the fault code information to the user through the large language model includes:

[0071] If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, and the fault code information includes fault code, vehicle model information, and electronic controller information, the large language model determines the solution corresponding to the fault code information based on the fault code, vehicle model information, and electronic controller information, and sends the solution corresponding to the fault code information to the user.

[0072] In practical applications, an interface for querying fault code details can be pre-configured for the large language model. The fault code information can include at least the fault code, vehicle model information, and electronic controller information. This allows the large model to provide an interface for querying fault code details using vehicle model information, ECU name information, and fault code. Based on the fault codes, vehicle model information, and electronic controller information present in the user's input diagnostic problem, the large model can comprehensively determine the most matching fault code details, and then determine the corresponding solution from the fault code details and send it to the user. To ensure that the large model can obtain the above information, corresponding prompts can be provided on the application interface to ensure that the user's input diagnostic problem includes the necessary fault code information.

[0073] By integrating multiple information dimensions such as fault codes, vehicle model information, and electronic controller information, the large language model can more accurately determine the most suitable solution, thus improving the accuracy of fault diagnosis.

[0074] In some embodiments of the present invention, the method further includes:

[0075] If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, and the fault code information is missing any one or more of the fault code, vehicle model information, and electronic controller information, the user is prompted to ask the question again according to the type of information missing in the fault code information.

[0076] In practical applications, although users can be prompted in advance to input diagnostic fault questions containing the necessary information dimensions, there may still be cases where the text information of the diagnostic fault question input by the user is insufficient. Therefore, if the user's input of diagnostic fault questions lacks any one or more of the fault codes, vehicle model information, and electronic controller information, the user can be notified to supplement the missing information and ask the question again. Furthermore, the large language model can be set to still attempt to call the interface to find relevant information when information is missing, and can prompt the user to supplement the missing information and ask the question again if a suitable solution cannot be found. Alternatively, the found reference solution can be sent to the user along with the prompt to supplement the missing information and ask the question again based on the existing information.

[0077] In this embodiment, when the diagnostic information entered by the user is incomplete, the system can intelligently determine the missing information and remind the user to supplement the relevant data, ensuring that a complete and accurate diagnostic solution can be provided to the user, avoiding situations where there is no solution or incorrect answers, thereby improving the user experience.

[0078] Based on the above, in an example, taking the user input question as: "One-click PDI, air conditioner heater pump failed to start: NRC-22 reported", the prompt words sent to the large language model could be:

[0079]

[0080]

[0081]

[0082]

[0083] It is important to emphasize that if a suitable solution cannot be found after exhausting the above processes, the large language model can request manual intervention by providing a support ticket button to ensure that the problem is effectively resolved.

[0084] In some embodiments of the present invention, determining the solution corresponding to the diagnosed fault problem based on the diagnosed fault problem and the target diagnostic document using a large language model includes:

[0085] The diagnostic fault problem and the target diagnostic document are written into a preset prompt template to obtain prompt text; wherein, the prompt template includes at least a prompt question, and the prompt question includes at least a knowledge base matching result question and a diagnostic fault problem text information completeness question; the knowledge base matching result question is used to prompt the large language model to determine whether the diagnostic fault problem and the target diagnostic document match each other, and the diagnostic fault problem text information completeness question is used to determine whether the diagnostic fault problem is missing any one or more of fault codes, vehicle model information, and electronic controller information;

[0086] The prompt text is input into the large language model, and the large language model outputs the solution corresponding to the diagnosed fault problem based on the prompt text.

[0087] In the specific implementation, the diagnostic fault question and the target diagnostic document can be written into a preset prompt template to obtain the prompt text (i.e., prompt words). The preset prompt template should at least include a prompt question, which should at least include a knowledge base matching result question and a question on the completeness of the diagnostic fault question text information. The knowledge base matching result question can be used to prompt the large language model to determine whether the diagnostic fault question and the target diagnostic document are sufficiently matched, that is, to determine whether the matching result between the two is qualified. The question on the completeness of the diagnostic fault question text information can be used to determine whether the user's input diagnostic fault question is missing any one or more of the fault codes, vehicle model information, and electronic controller information. That is, to determine whether it is necessary to remind the user to ask the question again based on the type of missing information in the diagnostic fault question, so as to ensure that the diagnostic fault question contains fault codes, vehicle model information, and electronic controller information, so that the large language model can further determine the solution based on the fault codes, vehicle model information, and electronic controller information.

[0088] In one example, taking the user input question as: "One-click PDI, air conditioning heater pump failed to start: NRC-22 reported", the prompt text obtained by writing it into the preset prompt template can be:

[0089]

[0090]

[0091]

[0092] The section "\n- Please judge whether the historical problems in the knowledge base match the actual problem based on the semantics of the actual problem or the fault codes in the actual problem. If there is even a slight match (such as both appearing with "air conditioning" or "nrc"), do not summarize, do not modify the content in the knowledge base, and do not return to the knowledge base tags. Format the historical problems, solutions, solution time, and vehicle series content in the knowledge base into Markdown format, such as **historical problems**:\\n-xxx\\n\\n**solutions**:\\n-xxx\\n\\n**solution time**:xxx\\n**vehicle series**:xxx. If there is no match, please ignore this line" is an example of the knowledge base matching result problem. The section "\n- When deciding to use a function in functions, if the parameter does not exist, please ask me in the form of (if you want to query fault code information, please provide the vehicle series, ECU name, and fault code, for example: X01 ACCM U007388). If you do not use functions, please ignore this line. Do not use information from the knowledge base for the parameters in function_call." is an example of the completeness of the diagnostic fault problem text information problem.

[0093] The following will combine Figure 3 The embodiments of the present invention will be further described, such as... Figure 3 The diagram shown illustrates the overall execution flow of the present invention, which can be summarized as follows:

[0094] Step 1: Upon receiving a message (diagnostic fault problem) from the user, the chatbot forwards the diagnostic fault problem to the cloud big model service. The cloud big model service then queries the diagnostic knowledge base for the most matching diagnostic document (record) based on the diagnostic fault problem sent by the user.

[0095] Step 2: Based on the results of the knowledge base query in Step 1, combine the user's diagnosed fault problem with the interface information for querying fault code details into prompt words, and send them together to the large language model (such as GPT4).

[0096] Step 3: The large language model can use the function_call capability to determine whether the user's diagnosed fault problem matches the target diagnostic document in the diagnostic knowledge base based on the prompt words. If the two are determined to match, the corresponding data (solution) in the knowledge base can be returned to the user.

[0097] Step 4: If the match fails, the large model can automatically determine whether it is necessary to call the interface to query fault code details.

[0098] Step 5: If it is determined that a call is needed, the large model can return the input parameters for querying the fault code details. After assembling the input parameters, the fault code details can be queried, thereby extracting the fault code information in the user's problem, calling the fault code details interface, and returning the result (the solution corresponding to the fault code details) to the user.

[0099] Step 6: If no data is found during the call, or if the user's question lacks the necessary information to query the solution by calling the fault code details interface, such as any one or more of the fault codes, vehicle model information, and electronic controller information, the user can be prompted to ask the question again based on the type of information missing in the user's question.

[0100] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0101] Reference Figure 4 The diagram shows a structural schematic of a vehicle diagnostic fault solution generation device provided by some embodiments of the present invention, which may specifically include the following modules:

[0102] The diagnostic fault problem acquisition module 401 is used to acquire the diagnostic fault problem input by the user in response to the user's diagnostic fault problem input operation;

[0103] The target diagnostic document query module 402 is used to query a preset diagnostic knowledge base based on the diagnosed fault problem to obtain the target diagnostic document;

[0104] Solution determination module 403 is used to determine the solution corresponding to the diagnosed fault problem based on the diagnosed fault problem and the target diagnostic document using a large language model.

[0105] In some embodiments of the present invention, the solution determination module 403 includes:

[0106] The matching result judgment submodule is used to determine whether the diagnosed fault problem matches the target diagnostic document through the large language model.

[0107] The first solution sending submodule is used to send the solution in the target diagnostic document to the user through the large language model when the diagnosed fault problem matches the target diagnostic document.

[0108] In some embodiments of the present invention, the solution determination module 403 further includes:

[0109] The second solution sending submodule is used to send the solution corresponding to the fault code information to the user through the large language model when the diagnosed fault problem does not match the target diagnostic document and the diagnosed fault problem contains fault code information.

[0110] In some embodiments of the present invention, the fault code information includes at least fault codes, vehicle model information, and electronic controller information, and the second sending submodule of the solution includes:

[0111] The fault code information parsing unit is used to determine the solution corresponding to the fault code information based on the fault code, vehicle model information and electronic controller information when the diagnosed fault problem does not match the target diagnostic document, the diagnosed fault problem contains fault code information, and the fault code information includes fault code, vehicle model information and electronic controller information, and then send the solution corresponding to the fault code information to the user.

[0112] In some embodiments of the present invention, the solution determination module 403 further includes:

[0113] The Re-ask Reminder Submodule is used to remind the user to re-ask the question when the diagnosed fault problem does not match the target diagnostic document, the diagnosed fault problem contains fault code information, and the fault code information is missing any one or more of the fault code, vehicle model information, and electronic controller information, based on the type of missing information in the fault code information.

[0114] In some embodiments of the present invention, the solution determination module 403 includes:

[0115] The prompt text generation submodule is used to write the diagnosed fault problem and the target diagnostic document into a preset prompt template to obtain prompt text; wherein, the prompt template includes at least a prompt question, and the prompt question includes at least a knowledge base matching result question and a diagnostic fault problem text information completeness question; the knowledge base matching result question is used to prompt the large language model to determine whether the diagnosed fault problem and the target diagnostic document match each other, and the diagnostic fault problem text information completeness question is used to determine whether the diagnosed fault problem is missing any one or more of fault codes, vehicle model information, and electronic controller information;

[0116] The prompt text input submodule is used to input the prompt text into the large language model, and the large language model outputs the solution corresponding to the diagnosed fault problem based on the prompt text.

[0117] In some embodiments of the present invention, the apparatus further includes:

[0118] A diagnostic knowledge base construction module is used to acquire online diagnostic documents and construct the diagnostic knowledge base based on the online diagnostic documents; wherein, the diagnostic documents include at least a diagnostic problem and a corresponding solution to the diagnostic problem;

[0119] The matching condition setting module allows users to set the diagnostic questions as matching conditions in the diagnostic knowledge base.

[0120] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0121] Some embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the above-described method for generating vehicle diagnostic fault solutions.

[0122] In addition, embodiments of the present invention also provide an electronic device, such as... Figure 5 As shown, it includes a processor 501, a communication interface 502, a memory 503, and a communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 communicate with each other through the communication bus 504.

[0123] Memory 503 is used to store computer programs;

[0124] When processor 501 executes the program stored in memory 503, it performs the following steps:

[0125] In response to a user's input of a diagnostic problem, obtain the diagnostic problem input by the user;

[0126] Based on the diagnosed fault problem, a query is performed in a preset diagnostic knowledge base to obtain the target diagnostic document;

[0127] Based on the diagnosed fault problem and the target diagnostic document, a solution corresponding to the diagnosed fault problem is determined using a large language model.

[0128] In an optional embodiment of the present invention, determining the solution corresponding to the diagnosed fault problem based on the diagnosed fault problem and the target diagnostic document using a large language model includes:

[0129] The large language model is used to determine whether the diagnosed fault problem matches the target diagnostic document.

[0130] If the diagnosed fault problem matches the target diagnostic document, the solution in the target diagnostic document is sent to the user through the large language model.

[0131] In an optional embodiment of the present invention, the method further includes:

[0132] If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, the solution corresponding to the fault code information is sent to the user through the large language model.

[0133] In an optional embodiment of the present invention, when the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, sending the solution corresponding to the fault code information to the user through the large language model includes:

[0134] If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, and the fault code information includes fault code, vehicle model information, and electronic controller information, the large language model determines the solution corresponding to the fault code information based on the fault code, vehicle model information, and electronic controller information, and sends the solution corresponding to the fault code information to the user.

[0135] In an optional embodiment of the present invention, the method further includes:

[0136] If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, and the fault code information is missing any one or more of the fault code, vehicle model information, and electronic controller information, the user is prompted to ask the question again according to the type of information missing in the fault code information.

[0137] In an optional embodiment of the present invention, determining the solution corresponding to the diagnosed fault problem based on the diagnosed fault problem and the target diagnostic document using a large language model includes:

[0138] The diagnostic fault problem and the target diagnostic document are written into a preset prompt template to obtain prompt text; wherein, the prompt template includes at least a prompt question, and the prompt question includes at least a knowledge base matching result question and a diagnostic fault problem text information completeness question; the knowledge base matching result question is used to prompt the large language model to determine whether the diagnostic fault problem and the target diagnostic document match each other, and the diagnostic fault problem text information completeness question is used to determine whether the diagnostic fault problem is missing any one or more of fault codes, vehicle model information, and electronic controller information;

[0139] The prompt text is input into the large language model, and the large language model outputs the solution corresponding to the diagnosed fault problem based on the prompt text.

[0140] In an optional embodiment of the present invention, before obtaining the diagnostic fault problem input by the user in response to the user's diagnostic fault problem input operation, the method further includes:

[0141] Obtain online diagnostic documents and construct the diagnostic knowledge base based on the online diagnostic documents; wherein, the diagnostic documents include at least the diagnostic problem and the corresponding solution;

[0142] The diagnostic question is set as a matching condition in the diagnostic knowledge base.

[0143] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0144] The communication interface is used for communication between the aforementioned terminal and other devices.

[0145] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0146] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0147] like Figure 6 As shown, in another embodiment of the present invention, a computer-readable storage medium 601 is also provided, which stores instructions that, when executed on a computer, cause the computer to execute the vehicle diagnostic fault solution generation method described in the above embodiments.

[0148] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0149] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0150] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0151] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0153] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0154] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the aforementioned element.

[0155] The above provides a detailed description of the vehicle diagnostic fault solution generation method, apparatus, equipment, and medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for generating vehicle diagnostic fault solutions, characterized in that, The method includes: In response to a user's input of a diagnostic problem, obtain the diagnostic problem input by the user; Based on the diagnosed fault problem, a query is performed in a preset diagnostic knowledge base to obtain the target diagnostic document; Based on the diagnosed fault problem and the target diagnostic document, a solution corresponding to the diagnosed fault problem is determined using a large language model.

2. The method according to claim 1, characterized in that, The step of determining the solution corresponding to the diagnosed fault problem based on the large language model and the target diagnostic document includes: The large language model is used to determine whether the diagnosed fault problem matches the target diagnostic document. If the diagnosed fault problem matches the target diagnostic document, the solution in the target diagnostic document is sent to the user through the large language model.

3. The method according to claim 2, characterized in that, The method further includes: If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, the solution corresponding to the fault code information is sent to the user through the large language model.

4. The method according to claim 3, characterized in that, When the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, the solution corresponding to the fault code information is sent to the user through the large language model, including: If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, and the fault code information includes fault code, vehicle model information, and electronic controller information, the large language model determines the solution corresponding to the fault code information based on the fault code, vehicle model information, and electronic controller information, and sends the solution corresponding to the fault code information to the user.

5. The method according to claim 4, characterized in that, The method further includes: If the diagnosed fault problem does not match the target diagnostic document, and the diagnosed fault problem contains fault code information, and the fault code information is missing any one or more of the fault code, vehicle model information, and electronic controller information, the user is prompted to ask the question again based on the type of information missing in the fault code information.

6. The method according to claim 1, characterized in that, The step of determining the solution corresponding to the diagnosed fault problem based on the large language model and the target diagnostic document includes: The diagnostic fault problem and the target diagnostic document are written into a preset prompt template to obtain prompt text; wherein, the prompt template includes at least a prompt question, and the prompt question includes at least a knowledge base matching result question and a diagnostic fault problem text information completeness question; the knowledge base matching result question is used to prompt the large language model to determine whether the diagnostic fault problem and the target diagnostic document match each other, and the diagnostic fault problem text information completeness question is used to determine whether the diagnostic fault problem is missing any one or more of fault codes, vehicle model information, and electronic controller information; The prompt text is input into the large language model, and the large language model outputs the solution corresponding to the diagnosed fault problem based on the prompt text.

7. The method according to claim 1, characterized in that, Before obtaining the diagnostic problem input by the user in response to the user's input, the method further includes: Obtain online diagnostic documents and construct the diagnostic knowledge base based on the online diagnostic documents; wherein, the diagnostic documents include at least the diagnostic problem and the corresponding solution; The diagnostic question is set as a matching condition in the diagnostic knowledge base.

8. A vehicle diagnostic fault solution generation device, characterized in that, The device includes: The diagnostic fault problem acquisition module is used to acquire the diagnostic fault problem input by the user in response to the user's diagnostic fault problem input operation; The target diagnostic document query module is used to query a preset diagnostic knowledge base based on the diagnosed fault problem to obtain the target diagnostic document; The solution determination module is used to determine the solution corresponding to the diagnosed fault problem based on the diagnosed fault problem and the target diagnostic document using a large language model.

9. An electronic device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the vehicle diagnostic fault solution generation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the vehicle diagnostic fault solution generation method as described in any one of claims 1 to 7.

Images