Diagnosis script generation method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides a diagnosis script generation method and device, and relates to the technical field of computers, in particular to the technical fields of large models, deep learning and the like. According to the specific implementation scheme, vehicle fault information is obtained; generating a fault correlation factor based on the vehicle fault information and the large factor model; and the diagnosis script is generated based on the fault correlation factor and the diagnosis large model, so that the user experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computers, specifically to technical fields such as large models, deep learning, and image processing, and in particular to a diagnostic script generation method and device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] In the field of vehicle remote diagnosis, diagnostic scripts are generally used. Diagnostic scripts refer to scripts used to guide diagnostic tools to communicate with vehicle control units and perform specific diagnostic tasks during the vehicle diagnosis process. Operators select pre-written diagnostic scripts in the cloud based on diagnostic requirements and send the diagnostic scripts to the vehicle for execution, thereby diagnosing vehicle-side faults. Summary of the invention

[0003] The present disclosure provides a diagnostic script generation method and device, an electronic device, a computer-readable storage medium, and a computer program product.

[0004] According to a first aspect, a method for generating a diagnostic script is provided, the method comprising: acquiring vehicle fault information; generating fault correlation factors based on the vehicle fault information and a factor big model; generating a diagnostic script based on the fault correlation factors and the diagnostic big model.

[0005] According to the second aspect, a diagnostic script generating device is provided, which includes: an acquisition unit configured to acquire vehicle fault information; a factor generating unit configured to generate fault-related factors based on the vehicle fault information and a factor big model; and a script generating unit configured to generate a diagnostic script based on the fault-related factors and the diagnostic big model.

[0006] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner of the first aspect.

[0007] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect.

[0008] According to a fifth aspect, a computer program product is provided, comprising a computer program, which implements the method described in any implementation manner of the first aspect when executed by a processor.

[0009] The diagnostic script generation method and device provided by the embodiment of the present disclosure first obtain vehicle fault information; secondly, generate fault correlation factors based on the vehicle fault information and the factor big model; finally, generate a diagnostic script based on the fault correlation factors and the diagnostic big model. Thus, based on the vehicle fault information, the fault correlation factors are automatically generated, and based on the fault correlation factors, the diagnostic script is generated, which improves the efficiency of diagnostic script generation; and eliminates the need for operators to search for information, which improves the user experience.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0012] Figure 1 is a flow chart of an embodiment of a method for generating a diagnostic script according to the present disclosure;

[0013] Figure 2 It is a structural schematic diagram of the diagnostic script generation process disclosed in the present invention;

[0014] Figure 3 is a flow chart of another embodiment of the diagnostic script generating method according to the present disclosure;

[0015] Figure 4 is a flow chart of another embodiment of the diagnostic script generating method according to the present disclosure;

[0016] Figure 5 is a structural schematic diagram of an embodiment of a diagnostic script generating device according to the present disclosure;

[0017] Figure 6 The block diagram is a block diagram of an electronic device used to implement the diagnostic script generating method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0019] The core purpose of the remote diagnosis process of automobiles is to diagnose and analyze vehicle faults and troubleshoot and repair them. The vehicle fault information reported when a fault occurs mainly includes DTC (Diagnostic Trouble Code) and information about the faulty parts (part name, hardware version, software version, etc.). The diagnostic script also targets specific DTCs, obtains relevant signals in the vehicle, and draws conclusions based on a comprehensive judgment and analysis of the values ​​read from the signals.

[0020] Vehicle manufacturers have a set of troubleshooting manuals for all possible DTC failures of all parts, and they also accumulate many past case records for different troubleshooting.

[0021] At present, diagnostic scripts in the industry are all manually written by diagnostic operators and uploaded to the platform. In the manual writing process, it is necessary to consult a large amount of existing information (troubleshooting manuals and past cases), and write them in combination with one's own troubleshooting and maintenance experience. Manual writing of diagnostic scripts requires high technical requirements for script writers, and troubleshooting manuals and past cases need to be consulted during the script writing process. Generally, troubleshooting manuals are very complex, with a large amount of documents, and the workload of manual review is large. There are many past troubleshooting and maintenance cases, and the workload of manual troubleshooting is huge.

[0022] In view of the defects in the traditional technology, the present invention proposes a diagnostic script generation method, which can automatically generate diagnostic scripts and improve the user experience. Figure 1 A process 100 according to an embodiment of a diagnostic script generation method of the present disclosure is shown. The diagnostic script generation method includes the following steps:

[0023] Step 101, obtaining vehicle fault information.

[0024] In this embodiment, the execution subject on which the diagnostic script generation method runs may be a cloud, such as Figure 2 As shown, the cloud is a remote server that implements functions such as vehicle fault information processing, diagnostic script generation and distribution.

[0025] In this embodiment, the vehicle fault information is the information reported when the vehicle fault occurs, and the vehicle fault information includes: DTC, faulty parts information, wherein the parts information includes: part name, hardware version, software version, etc. The vehicle fault information can be information independently stored in the cloud, such as Figure 2 The vehicle fault information shown may also be fault information G sent by the vehicle diagnostic program of the vehicle to the execution subject when a fault occurs.

[0026] In the technical solution disclosed in this disclosure, the collection, storage, use, processing, transmission, provision and disclosure of vehicle fault information are carried out after authorization and in compliance with relevant laws and regulations. The vehicle fault information and user-related information are obtained after the user's permission, and the generation of diagnostic scripts related to the user is processed under confidentiality conditions.

[0027] Step 102: Generate a fault correlation factor based on the vehicle fault information and the factor big model.

[0028] In this embodiment, the fault association factor is a factor associated with the vehicle fault information, and the fault association factor may include a fault detection process sub-factor and a detection or association sub-factor in the fault detection process; wherein the fault detection process sub-factor is used to implement the detection process for the fault corresponding to the vehicle fault information; and the detection or association sub-factor may be the instructions involved in the monitoring process corresponding to the fault detection process sub-factor.

[0029] In this embodiment, the factor big model is a generative big model. By inputting factor prompt words and vehicle fault information that prompt the generation of fault-related factors into the factor big model, the fault-related factors output by the factor big model can be obtained. The factor big model generates factor scripts under the prompt of the factor prompt words and analyzes the vehicle fault information. The above step 102 includes: inputting the fault-related factors and the factor generation prompt words into the factor big model to obtain the fault-related factors output by the factor big model.

[0030] Step 103: Generate a diagnosis script based on the fault correlation factors and the diagnosis big model.

[0031] In this embodiment, the diagnostic big model is a generative big model. By inputting diagnostic prompt words and fault-related factors that prompt the generation of the script into the diagnostic big model, the diagnostic script output by the diagnostic big model can be obtained. Among them, the diagnostic big model analyzes the fault-related factors under the prompt of the diagnostic prompt words to generate a diagnostic script.

[0032] In this embodiment, the diagnosis script is a script for diagnosing the fault corresponding to the vehicle fault information, and the fault correlation factor is input into the diagnosis big model to obtain the diagnosis script output by the diagnosis big model.

[0033] The diagnostic script generation method provided by the embodiment of the present disclosure first obtains vehicle fault information; secondly, generates fault correlation factors based on the vehicle fault information and the factor big model; finally, generates a diagnostic script based on the fault correlation factors and the diagnostic big model. Thus, the fault correlation factors are automatically generated based on the vehicle fault information, and the diagnostic script is generated based on the fault correlation factors, which improves the efficiency of diagnostic script generation; and eliminates the need for operators to search for information, which improves the user experience.

[0034] In some embodiments of the present disclosure, the above-mentioned generation of fault correlation factors based on the vehicle fault information and the factor big model includes: based on the diagnostic script library, detecting whether there is a diagnostic script matching the vehicle fault information; in response to not detecting a diagnostic script matching the vehicle fault information, generating a fault correlation factor based on the vehicle fault information and the factor big model.

[0035] In this embodiment, Figure 2 As shown, the diagnostic script library is a database for storing multiple diagnostic scripts in the cloud. Each diagnostic script in the diagnostic script library may have corresponding fault information. The execution entity on which the diagnostic script generation method runs compares the fault information in the diagnostic script library with the vehicle fault information for similarity to detect whether the diagnostic script library contains a diagnostic script that matches the vehicle fault information. When the similarity between the fault information in the diagnostic script library and the vehicle fault information is greater than or equal to a similarity threshold (for example, 90%), the diagnostic script corresponding to the fault information in the diagnostic script library is determined to be a diagnostic script that matches the vehicle fault information. When the similarity between the fault information in the diagnostic script library and the vehicle fault information is less than the similarity threshold, it is determined that no diagnostic script matching the vehicle fault information is detected.

[0036] The diagnostic script generation method provided by this optional implementation method detects whether there is a diagnostic script that matches the vehicle fault information based on the diagnostic script library; in response to not detecting a diagnostic script that matches the vehicle fault information, a fault correlation factor is generated based on the vehicle fault information, which provides a means for directly obtaining the diagnostic script and improves the reliability of obtaining the diagnostic script.

[0037] Optionally, the diagnostic script generation method further includes: in response to detecting that the diagnostic script library has a diagnostic script that matches the vehicle fault information, directly adopting the diagnostic script.

[0038] Optionally, before generating a fault correlation factor based on the vehicle fault information, the above-mentioned diagnostic script generation method also includes: in response to not detecting a diagnostic script matching the vehicle fault information from the diagnostic script library, detecting a diagnostic script matching the vehicle fault information from information other than the diagnostic script library; if no diagnostic script matching the vehicle fault information is detected, generating a fault correlation factor based on the vehicle fault information.

[0039] In some optional implementations of the present disclosure, the above-mentioned detection of whether there is a diagnostic script matching the vehicle fault information based on the diagnostic script library includes: vectorizing the diagnostic scripts in the diagnostic script library to obtain a first vector library; vectorizing the vehicle fault information to obtain a vehicle fault vector; matching the vehicle fault vector with the vector in the first vector library; in response to a successful match between the vehicle fault vector and the vector in the first vector library, determining that there is a diagnostic script matching the vehicle fault information.

[0040] In this optional implementation, if Figure 2 As shown, the diagnostic scripts in the diagnostic script library are vectorized, the vehicle fault information is vectorized, and the vectors in the first vector library are matched with the vehicle fault vectors, thus achieving Figure 2 Vector retrieval in the system can comprehensively search the diagnostic script library and the diagnostic scripts related to vehicle fault information, thus improving the accuracy and comprehensiveness of the diagnostic script search.

[0041] The diagnostic script generation method provided by this optional implementation vectorizes the diagnostic scripts in the diagnostic script library to obtain a first vector library; vectorizes the vehicle fault information to obtain a vehicle fault vector; matches the vehicle fault vector with the vector in the first vector library; in response to a successful match between the vehicle fault vector and the vector in the first vector library, determines that there is a diagnostic script that matches the vehicle fault information, thereby improving the accuracy and comprehensiveness of detecting whether there is a diagnostic script that matches the vehicle fault information through vector retrieval.

[0042] Optionally, the above-mentioned detection based on the diagnostic script library to determine whether there is a diagnostic script that matches the vehicle fault information includes: vectorizing the diagnostic scripts in the diagnostic script library to obtain a first vector library; vectorizing the vehicle fault information to obtain a vehicle fault vector; matching the vehicle fault vector with the vector in the first vector library; and in response to a successful match between the vehicle fault vector and the vector in the first vector library, determining that there is a diagnostic script that matches the vehicle fault information.

[0043] The method for detecting diagnostic scripts provided by this optional implementation manner vectorizes the diagnostic scripts in the diagnostic script library to obtain a first vector library; vectorizes the vehicle fault information to obtain a vehicle fault vector; matches the vehicle fault vector with the vector in the first vector library; in response to a successful match between the vehicle fault vector and the vector in the first vector library, determines a diagnostic script that matches the vehicle fault information, thereby matching the diagnostic scripts in the form of vector matching, and can comprehensively determine the diagnostic script that matches the vehicle fault information, thereby improving the reliability and accuracy of detecting the diagnostic script that matches the vehicle fault information.

[0044] Optionally, based on the diagnostic script library, detecting whether there is a diagnostic script that matches the vehicle fault information includes: matching the diagnostic script in the diagnostic script library with the vehicle fault vector; in response to a successful match between the vehicle fault vector and the diagnostic script in the diagnostic script library, determining that there is a diagnostic script that matches the vehicle fault information.

[0045] Optionally, the above-mentioned detection based on the diagnostic script library to determine whether there is a diagnostic script that matches the vehicle fault information includes: determining a fault instance that matches the diagnostic script in the diagnostic script library to obtain a fault instance library; matching the fault examples in the fault example library with the vehicle fault information, and in response to a fault example matching the vehicle fault information, determining that there is a diagnostic script that matches the vehicle fault information.

[0046] In some embodiments of the present disclosure, the vehicle fault information is fault information sent by the target vehicle, and the above diagnostic script generation method further includes: sending the diagnostic script to the target vehicle. Specifically, Figure 3 A process 300 according to another embodiment of the diagnostic script generation method of the present disclosure is shown. The diagnostic script generation method includes the following steps:

[0047] Step 301, obtaining vehicle fault information.

[0048] In this embodiment, the vehicle fault information is the fault information sent by the target vehicle to the execution subject on which the diagnostic script generation method runs after a fault occurs.

[0049] Step 302: Generate a fault correlation factor based on vehicle fault information and a factor macro model.

[0050] Step 303: Generate a diagnosis script based on the fault correlation factors and the diagnosis big model.

[0051] It should be understood that the operations and features in the above steps 301-303 correspond to the operations and features in steps 101-103 respectively. Therefore, the above descriptions of the operations and features in steps 101-103 are also applicable to steps 301-303 and will not be repeated here.

[0052] Step 304: Send the diagnostic script to the target vehicle.

[0053] In this embodiment, after the target vehicle obtains the diagnostic script sent by the execution entity, it obtains the vehicle signal related to the diagnostic script on its own vehicle, and performs a comprehensive analysis on the vehicle based on the value of the vehicle signal to give a diagnostic conclusion.

[0054] The diagnostic script generation method provided in this embodiment sends the diagnostic script to the target vehicle after obtaining the diagnostic script, so that the target vehicle can obtain the diagnostic script in time and diagnose itself, thereby improving the efficiency of vehicle diagnosis.

[0055] Optionally, the diagnostic script generation method further includes: detecting whether the diagnostic script is a script executed during a power-off operation; and sending a power-off prompt message to the target vehicle in response to the diagnostic script being a script executed during a power-off operation.

[0056] The diagnostic script generation method provided by this optional implementation sends a power-off prompt message to the target vehicle after detecting that the diagnostic script is a script to be executed during power-off, so that the target vehicle can be powered off in time after receiving and running the diagnostic script, thereby improving the reliability of the diagnostic script operation.

[0057] In some embodiments of the present disclosure, the above-mentioned diagnostic script generation method also includes: receiving diagnostic results sent by the target vehicle, and sending the diagnostic results and diagnostic script to the client; receiving feedback information related to the diagnostic results and diagnostic script sent by the client; in response to the feedback information indicating that the vehicle diagnosis is qualified, adding the diagnostic script to the diagnostic script library.

[0058] In this embodiment, the diagnostic result is that after the target vehicle obtains the diagnostic script, it obtains the vehicle signal related to the diagnostic script on its own vehicle, and makes a comprehensive analysis of the vehicle based on the value of the vehicle signal to give a diagnostic conclusion, for example, the diagnostic result is that the engine is difficult to start, or the steering wheel shakes at high speed. Specifically, Figure 2 As shown, the diagnosis result J is information sent to the cloud by the vehicle diagnosis program of the target vehicle after obtaining the diagnosis script Z sent from the cloud.

[0059] In this embodiment, specifically, after the target vehicle obtains the diagnostic script sent by the execution entity, it obtains the vehicle signal related to the diagnostic script on its own vehicle, and performs a comprehensive analysis on the vehicle based on the value of the vehicle signal to provide a diagnostic result.

[0060] In this embodiment, the feedback information includes: the vehicle diagnosis is qualified or the vehicle diagnosis is unqualified, and the diagnostic results and diagnostic scripts are sent to the client, so that the operator can analyze the diagnostic scripts and diagnostic results to determine whether the diagnostic scripts meet the diagnostic requirements and whether the diagnostic scripts and diagnostic results correspond. When the diagnostic scripts meet the diagnostic requirements and the diagnostic scripts correspond to the diagnostic results, feedback information indicating that the vehicle diagnosis is qualified is generated; when the diagnostic scripts do not meet the diagnostic requirements, or the diagnostic scripts do not correspond to the diagnostic results, feedback information indicating that the vehicle diagnosis is unqualified is generated.

[0061] The diagnostic script generation method provided in this embodiment receives the diagnostic results sent by the target vehicle, and sends the diagnostic results and the diagnostic script to the client; receives feedback information related to the diagnostic results and the diagnostic script sent by the client; in response to the feedback information indicating that the vehicle diagnosis is qualified, adds the diagnostic script to the diagnostic script library, enriches the diagnostic script library, and improves the reliability of the diagnostic script.

[0062] In some embodiments of the present disclosure, the diagnostic script generation method further includes: in response to the feedback information indicating that the vehicle diagnosis is unqualified, obtaining an optimized script based on the feedback information; and sending the optimized script as a diagnostic script to the target vehicle. Specifically, Figure 4 A process 400 of another embodiment of a diagnostic script generation method according to the present disclosure is shown. The diagnostic script generation method includes the following steps:

[0063] Step 401, obtain vehicle fault information, then execute step 402.

[0064] Step 402 , based on the vehicle fault information and the factor big model, generate the fault correlation factor, then execute step 403 .

[0065] Step 403 , generating a diagnosis script based on the fault correlation factors and the diagnosis big model, and then executing step 404 .

[0066] Step 404 , sending the diagnostic script to the target vehicle, and then executing step 405 .

[0067] It should be understood that the operations and features in the above steps 401 to 404 correspond to the operations and features in steps 301 to 304, respectively. Therefore, the above descriptions of the operations and features in steps 301 to 304 are also applicable to steps 401 to 404 and will not be repeated here.

[0068] Step 405 , receiving the diagnostic result sent by the target vehicle, and sending the diagnostic result and the diagnostic script to the client, and then executing step 406 .

[0069] In this embodiment, the diagnostic result is the result obtained by the target vehicle executing the diagnostic script to diagnose its own vehicle. Specifically, after the target vehicle obtains the diagnostic script issued by the execution subject, it obtains the vehicle signal related to the diagnostic script on its own vehicle, and performs a comprehensive analysis on the vehicle based on the value of the vehicle signal to give a diagnostic result.

[0070] In this embodiment, the diagnostic results and diagnostic scripts are sent to the client, so that the operating personnel can analyze the diagnostic scripts and diagnostic results to determine whether the diagnostic scripts meet the diagnostic requirements and whether the diagnostic scripts and diagnostic results correspond. When the diagnostic scripts meet the diagnostic requirements and the diagnostic scripts correspond to the diagnostic results, feedback information is given that the generated diagnostic information is qualified; when the diagnostic scripts do not meet the diagnostic requirements, or the diagnostic scripts do not correspond to the diagnostic results, feedback information is given that the generated diagnostic information is unqualified.

[0071] Step 406, receiving feedback information sent by the client, and then executing step 407.

[0072] In this embodiment, the feedback information is information related to the diagnosis result and the diagnosis script, and the feedback information includes: the vehicle diagnosis is qualified or the vehicle diagnosis is unqualified. When the diagnosis result corresponds to the diagnosis script and the diagnosis script meets the diagnosis requirements, it is determined that the diagnosis of the target vehicle is qualified, and feedback information indicating that the diagnosis is qualified is given. When the diagnosis result does not correspond to the diagnosis script, or the diagnosis script does not meet the diagnosis requirements, it is determined that the diagnosis of the target vehicle is unqualified.

[0073] Step 407 , determining whether the feedback information indicates that the diagnosis result is qualified; if the feedback information indicates that the diagnosis result is qualified, executing step 408 ; otherwise, executing step 410 .

[0074] Step 408 , adding the diagnostic script to the diagnostic script library, and then executing step 409 .

[0075] Step 409, end.

[0076] Step 410 , based on the feedback information, obtain an optimization script, and use the optimization script as a diagnostic script to execute step 404 .

[0077] In this embodiment, the optimized script is a script obtained after optimizing the diagnostic script (for example, modifying instructions, replacing instructions).

[0078] Optionally, the optimization script can also be a script obtained from the client. The operator optimizes the diagnostic script on the client to obtain the optimized script, and encapsulates the optimized script and other information into feedback information, and feeds back the feedback information to the execution entity, so that the execution entity can obtain the optimized script of the diagnostic script from a specific area of ​​the feedback information when the feedback information indicates that the vehicle diagnosis is unqualified.

[0079] The diagnostic script generation method provided in this embodiment obtains an optimized script based on the feedback information in response to feedback information indicating that the vehicle diagnosis is unqualified; and sends the optimized script as a diagnostic script to the target vehicle, thereby improving the reliability of the diagnostic script generation.

[0080] In some optional implementations of the present disclosure, the above-mentioned factor large model includes: a first large model, based on vehicle fault information and the factor large model, generating a fault correlation factor including: matching the vehicle fault information with the fault repair information; in response to a successful match between the vehicle fault information and the fault repair information, inputting the first large model based on the vehicle fault information, the fault repair information and the selected prompt word, to obtain the fault correlation factor output by the first large model.

[0081] In this optional implementation, the first large model is a pre-trained multimodal large model, and the first large model is a model for selecting relevant data from the diagnostic database to obtain the fault correlation factor, and the multimodal information and prompt words are input into the first large model to obtain the fault correlation factor output by the first large model. Among them, the diagnostic database is a database related to vehicle diagnosis, and the data in the diagnostic database includes: fault repair information, which is multimodal information related to vehicle diagnosis and repair, and the fault repair information includes: fault repair manual, DTC repair case.

[0082] In this optional implementation, when the vehicle fault information matches the fault repair information successfully, it is determined that the vehicle fault information has information related to the vehicle fault information. At this time, a diagnostic script can be obtained by analyzing the vehicle fault information.

[0083] In this optional implementation, the selected prompt word is prompt information that prompts the large model to select relevant information from pre-prepared data. When the pre-accurate data is vehicle fault information, the selected prompt word is used to prompt the large model to select fault correlation factors from the vehicle fault information.

[0084] The method for generating fault correlation factors provided by this optional implementation method, after the vehicle fault information and the fault repair information are successfully matched, inputs the first large model based on the vehicle fault information, the fault repair information and the selected prompt words, and obtains the fault correlation factors output by the first large model, thereby providing a reliable implementation means for obtaining the fault correlation factors and improving the reliability and accuracy of obtaining the fault correlation factors.

[0085] In an optional implementation, when both the vehicle fault information and the fault repair information are text data, the first large model is a large language model.

[0086] In an optional implementation, when the vehicle fault information and the fault repair information are both images, videos or audios, the first large model is an image, video or audio large model.

[0087] In some optional implementations of the present disclosure, the above-mentioned factor large model also includes: a second large model, based on the vehicle fault information and the factor large model, generating a fault correlation factor also includes: in response to the vehicle fault information and the fault repair information not being successfully matched, inputting the vehicle fault information and the generated prompt word into the second large model to obtain the fault correlation factor output by the second large model.

[0088] In this optional implementation, the second largest model is a pre-trained multimodal large model, and the second largest model is a model that can directly generate fault correlation factors.

[0089] In this optional implementation, the generated prompt word is prompt information that prompts the large model to generate relevant information. When the relevant information is a fault correlation factor, the generated prompt word is used to prompt the large model to generate the fault correlation factor.

[0090] The method for generating fault correlation factors provided by this optional implementation mode, after the vehicle fault information and the fault repair information fail to match successfully, inputs the vehicle fault information and the generated prompt words into the second largest model to obtain the fault correlation factor output by the second largest model, thereby providing another reliable implementation means for obtaining the fault correlation factor and improving the reliability and accuracy of obtaining the fault correlation factor.

[0091] In an optional implementation, when the vehicle fault information is text data, the second largest model is a large language model.

[0092] In an optional implementation, when the vehicle fault information is an image, video or audio, the second largest model is an image, video or audio large model.

[0093] In an optional implementation, when the vehicle fault information is multimodal data, the second largest model is a multimodal large model.

[0094] In some optional implementations of the present disclosure, the above-mentioned fault correlation factors include: fault detection process sub-factors. Based on the fault correlation factors and the diagnostic big model, generating a diagnostic script includes: inputting the fault detection process sub-factors and diagnostic prompt words into the diagnostic big model to obtain the diagnostic script output by the diagnostic big model.

[0095] In this optional implementation, the fault detection process sub-factor is the flow step process information of detecting the fault corresponding to the vehicle fault information, and the specific process of the vehicle detecting the fault can be determined through the fault detection process sub-factor. The fault detection process sub-factor can be represented by multiple data modes, such as images, text, etc.

[0096] In this optional implementation, the diagnostic big model is a big model that generates a diagnostic script from the fault correlation factors. When the fault correlation factors are multimodal data, the diagnostic big model is a multimodal big model.

[0097] In another optional implementation, the diagnostic big model is a big model that generates a diagnostic script from the fault correlation factors. When the fault correlation factors are text data, the diagnostic big model is a big language model.

[0098] In another optional implementation, the diagnostic big model is a big model that generates a diagnostic script from the fault correlation factor. When the fault correlation factor is an image, video or audio, the diagnostic big model is an image, video or audio big model.

[0099] In this optional implementation, the diagnosis prompt word is a prompt word that prompts the diagnosis large model to generate a diagnosis script.

[0100] The method for generating a diagnostic script provided by this optional implementation inputs the fault detection process sub-factors and diagnostic prompt words into the diagnostic large model to obtain the diagnostic script output by the diagnostic large model, thereby providing a reliable implementation means for obtaining the diagnostic script and improving the reliability and accuracy of the diagnostic script.

[0101] In some optional implementations of the present disclosure, the above-mentioned fault correlation factors also include: instruction key sub-factors. Based on the fault correlation factors and the diagnostic big model, generating a diagnostic script also includes: obtaining an instruction list based on the instruction key sub-factors and the script instruction library; inputting the instruction list, fault detection process sub-factors and diagnostic prompt words into the diagnostic big model to obtain a diagnostic script output by the diagnostic big model.

[0102] In this optional implementation, the instruction key sub-factor is a factor related to the instruction of the implementation fault detection process sub-factor. Specifically, the instruction key sub-factor includes: the in-vehicle CAN signal involved in the fault corresponding to the vehicle fault information; the vehicle state involved in the fault; the Ethernet message involved in the fault; the acquisition conditions, time periods and frequencies corresponding to the above factors (in-vehicle CAN signal, vehicle state, Ethernet message).

[0103] In this optional implementation, the script instruction library is a database for storing script instructions, and the script instructions in the script instruction library can be queried through an index, wherein the script instructions are instructions related to the vehicle script.

[0104] In this optional implementation, the instruction list is a list including at least one script instruction, and the script instructions in the instruction list are all script instructions related to the instruction key sub-factor.

[0105] The method for obtaining diagnostic script instructions provided by this optional implementation method obtains an instruction list based on instruction key sub-factors and a script instruction library; the instruction list, fault detection process sub-factors, and diagnostic prompt words are input into the diagnostic big model together to obtain a diagnostic script output by the diagnostic big model. Compared with directly generating a diagnostic script through fault detection process sub-factors, diagnostic prompt words, and the diagnostic big model, the big model can be more aware of the script instructions that make up the diagnostic script, and a diagnostic script can be generated based on these script instructions, thereby further improving the accuracy of diagnostic script generation.

[0106] In some optional implementations of the present disclosure, the above-mentioned instruction key sub-factors include: instruction keywords and acquisition attributes of instruction keywords. Based on the instruction key sub-factors and the script instruction library, obtaining the instruction list includes: based on the acquisition attributes, obtaining the instruction set related to the instruction keyword from the script instruction library; vectorizing the instruction set to obtain an instruction vector set; matching the instruction vector set with the vector of the instruction keyword; and obtaining the instruction list based on the matching result between the instruction vector set and the vector of the instruction keyword.

[0107] In this optional implementation, the instruction keywords are words related to the instructions of the fault detection process sub-factor, such as the in-vehicle CAN signal involved in the fault corresponding to the vehicle fault information; the vehicle status involved in the fault; the Ethernet message involved in the fault.

[0108] In this optional implementation, the acquisition attribute of the instruction keyword is to obtain the attribute information of the instruction keyword, for example, the acquisition condition, time period and frequency of the instruction keyword.

[0109] In this optional implementation, the above-mentioned matching of the instruction vector set with the vector of the instruction keyword is shown in Figure 2 The vector index shown.

[0110] The method for obtaining an instruction list provided by this optional implementation method obtains an instruction set related to instruction keywords from a script instruction library based on acquisition attributes; vectorizes the instruction set to obtain an instruction vector set; matches the instruction vector set with a vector of the instruction keyword; obtains an instruction list based on the matching result between the instruction vector set and the vector of the instruction keyword, limits the instruction list based on the acquisition attributes and the instruction keywords, and improves the accuracy of obtaining the instruction list.

[0111] In some optional implementations of the present disclosure, the above-mentioned large diagnosis model is a fine-tuned code generation model, and the above-mentioned fine-tuning includes inputting script syntax information into the code generation model so that the code generation model can output code corresponding to the diagnosis script.

[0112] In this optional implementation, large model fine-tuning refers to the process of adjusting the parameters of a large language model to adapt to a specific task. This process is completed by training a large model on a dataset for a specific task, aiming to optimize the performance of the model on a specific task. The importance of fine-tuning lies in enabling the large model to adapt more finely to specific tasks, reducing inference costs, and improving the performance of the model in a specific domain.

[0113] In this optional implementation, the code generation model is a large language model that can generate script code, and the fine-tuning of the above-mentioned code generation model refers to inputting script syntax information into the code generation model while adjusting the parameters of the large language model to adapt to specific diagnostic script generation tasks; wherein the script syntax information refers to an executable file written in a certain format using a specific descriptive language, which is generally used to control the behavior of software applications and can be interpreted or compiled for execution when called.

[0114] Since the script has corresponding writing rules, in order to adapt to the writing rules, the script syntax information is input into the code generation model during the fine-tuning process of the code generation model, so that the code generation model can output the diagnostic script corresponding to the current script syntax information, thereby improving the accuracy of diagnostic script generation.

[0115] The diagnostic big model provided by this optional implementation inputs syntax information into the code generation model when the code generation model is fine-tuned, thereby improving the accuracy of the diagnostic big model in generating diagnostic scripts.

[0116] It can be seen from the above embodiments that the diagnosis generation method provided by the present disclosure can be a complete set of script automatic generation and optimization processes, and complete the script library automatic construction process method, and finally realize the logical closed loop of script automatic retrieval, generation, optimization, and storage. The complete process diagram is shown in Figure 2 As shown:

[0117] 1) After the vehicle reports the vehicle fault information, the cloud uses vector retrieval technology to filter the diagnostic script that matches the current vehicle fault information based on the existing diagnostic script library (including diagnostic scripts, corresponding DTCs, and fault phenomena). If the match is successful, the diagnostic script is directly returned, so that the vehicle diagnostic program of the vehicle directly executes the diagnostic script.

[0118] Among them, the vector retrieval technology vectorizes all diagnostic scripts, corresponding DTCs and fault phenomena in the existing diagnostic script library, and then compares the similarity with the vectors corresponding to the DTCs and fault phenomena in the vehicle fault information uploaded by the vehicle. If the similarity is higher than a certain threshold, the script with the highest similarity is selected for successful matching, otherwise it is considered that there is no successful matching script.

[0119] 2) When the vector search technology fails to match successfully, the "fault correlation factor" corresponding to the vehicle fault information is analyzed based on the factor big model. The "fault correlation factor" includes two parts, the first part and the second part. Each part includes but is not limited to the following description:

[0120] Part 1: The in-vehicle CAN signal involved in the fault corresponding to the vehicle fault information; the vehicle status involved in the fault; the CAN and Ethernet messages involved in the fault; the acquisition conditions, time periods and frequencies corresponding to the above factors.

[0121] Part II: Fault detection process.

[0122] 3) In the process of analyzing the "fault correlation factor", the fault repair manual and DTC repair case provided by the OEM are used as the input of the factor model, and appropriate prompt words are constructed to make the factor model output the required "fault correlation factors". This process can be achieved by fine-tuning the model or by using vector retrieval technology plus the summary of the large model.

[0123] In addition to using fault repair manuals and DTC repair cases for analysis, for unmatched faults, you can also construct appropriate prompt words and use a general large model to query, or use other data sources to obtain the required information.

[0124] 4) Based on the vector retrieval technology, the script instructions for each factor in the first part of the current "fault correlation factor" are obtained from the script instruction library on the vehicle side.

[0125] The cloud contains a script instruction library, and the diagnostic control program on the vehicle includes a vehicle diagnostic program that executes all instructions. The script instruction library includes the definition and function description of all diagnostic scripts, and matches which script instruction should be used for each factor through the description of the fault correlation factor and the diagnostic script.

[0126] 5) Based on the "fault detection process" sub-factor in the fault diagnosis factor and the instruction list, a diagnostic script is constructed using the diagnostic model. The diagnostic model used in this step is a fine-tuned code generation model, and the fine-tuning process requires the input of all script syntax definitions.

[0127] 6) Sending the diagnostic script generated in step 5) to the target vehicle, so that the vehicle diagnostic program of the target vehicle executes the diagnostic script.

[0128] 7) The target vehicle returns the executed diagnostic results to the cloud and enters a process for manual judgment.

[0129] 8) Manually analyze the generated diagnostic script and the executed diagnostic results. If they do not meet the diagnostic requirements, optimize the script and send it to the vehicle for execution again until the expected results are obtained.

[0130] 9) Add the manually confirmed scripts to the script library. Next time you encounter a similar problem, you can directly return the script from the script library for automated execution.

[0131] Through the diagnostic script generation method provided by the present invention, the required scripts can be automatically retrieved from the script library and sent to the vehicle side for execution, thereby realizing the automated diagnostic function; for diagnostic scripts that are not available in the diagnostic script library, diagnostic scripts can be automatically generated, without the need for experienced R&D personnel to spend a lot of time consulting a large number of fault repair manuals and fault repair cases, thereby improving the efficiency of diagnostic script generation; the automatically generated diagnostic scripts will be manually reviewed and optimized before being put into the database, forming a logical closed loop, thereby improving the optimization effect of the diagnostic script.

[0132] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a diagnostic script generating device, which is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically implemented in various electronic devices.

[0133] like Figure 5 As shown, the diagnostic script generating device 500 provided in this embodiment includes: an acquisition unit 501, a factor generating unit 502, and a script generating unit 503. The acquisition unit 501 can be configured to acquire vehicle fault information. The factor generating unit 502 can be configured to generate fault correlation factors based on vehicle fault information and a factor big model. The script generating unit 503 can be configured to generate a diagnostic script based on the fault correlation factors and the diagnostic big model.

[0134] In this embodiment, in the diagnostic script generating device 500, the specific processing of the acquisition unit 501, the factor generating unit 502, and the script generating unit 503 and the technical effects thereof can be referred to in Figure 1 The relevant descriptions of step 101, step 102, and step 103 in the corresponding embodiment are not repeated here.

[0135] In some optional implementations of the present embodiment, the factor generation unit 502 is configured to detect, based on a diagnostic script library, whether there is a diagnostic script that matches the vehicle fault information; in response to not detecting a diagnostic script that matches the vehicle fault information, generate a fault correlation factor based on the vehicle fault information.

[0136] In some optional implementations of the present embodiment, the factor generation unit 502 is further configured to: vectorize the diagnostic scripts in the diagnostic script library to obtain a first vector library; vectorize the vehicle fault information to obtain a vehicle fault vector; match the vehicle fault vector with the vector in the first vector library; in response to a successful match between the vehicle fault vector and the vector in the first vector library, determine a diagnostic script that matches the vehicle fault information.

[0137] In some optional implementations of this embodiment, the vehicle fault information is fault information sent by the target vehicle, and the device 500 further includes: a sending unit (not shown in the figure), and the sending unit is configured to: send a diagnostic script to the target vehicle.

[0138] In some optional implementations of this embodiment, the above-mentioned device 500 also includes: an adding unit (not shown in the figure), and the above-mentioned adding unit is configured to: receive the diagnostic results sent by the target vehicle, and send the diagnostic results and diagnostic scripts to the client; receive feedback information sent by the client, and the feedback information is related to the diagnostic results and the diagnostic script; in response to the feedback information indicating that the vehicle diagnosis is qualified, add the diagnostic script to the diagnostic script library.

[0139] In some optional implementations of this embodiment, the above-mentioned device 500 also includes: an optimization unit (not shown in the figure), and the above-mentioned optimization unit is configured to: in response to feedback information characterizing that the vehicle diagnosis is unqualified, obtain an optimization script based on the feedback information; and send the optimization script as a diagnostic script to the target vehicle.

[0140] In some optional implementations of the present embodiment, the above-mentioned factor large model includes: a first large model, and the above-mentioned factor generation unit 502 is configured to: match the vehicle fault information with the fault repair information; in response to the vehicle fault information and the fault repair information being successfully matched, based on the vehicle fault information, the fault repair information and the selected prompt word input into the first large model, obtain the fault correlation factor output by the first large model.

[0141] In some optional implementations of this embodiment, the above-mentioned factor large model also includes: a second large model, and the above-mentioned factor generation unit 502 is configured to: in response to the vehicle fault information and the fault repair information not being successfully matched, input the vehicle fault information and the generated prompt word into the second large model to obtain the fault correlation factor output by the second large model.

[0142] In some optional implementations of this embodiment, the above-mentioned fault association factors include: fault detection process sub-factors, and the above-mentioned script generation unit 503 is configured to: input the fault detection process sub-factors and diagnostic prompt words into the diagnostic big model to obtain the diagnostic script output by the diagnostic big model.

[0143] In some optional implementations of the present disclosure, the above-mentioned fault association factors also include: instruction key sub-factors, and the above-mentioned script generation unit 503 is further configured to: obtain an instruction list based on the instruction key sub-factors and the script instruction library; input the instruction list, fault detection process sub-factors and diagnostic prompt words into the diagnostic big model to obtain the diagnostic script output by the diagnostic big model.

[0144] In some optional implementations of the present disclosure, the above-mentioned instruction key sub-factors include: instruction keywords and acquisition attributes of instruction keywords, and the above-mentioned script generation unit 503 is further configured to: based on the acquisition attributes, obtain an instruction set related to the instruction keyword from the script instruction library; vectorize the instruction set to obtain an instruction vector set; match the instruction vector set with the vector of the instruction keyword; and obtain an instruction list based on the matching result of the instruction vector set and the vector of the instruction keyword.

[0145] In some optional implementations of the present disclosure, the above-mentioned large diagnosis model is a fine-tuned code generation model; the fine-tuning includes inputting script syntax information into the code generation model so that the code generation model can output code corresponding to the diagnosis script.

[0146] The diagnostic script generation device provided by the embodiment of the present disclosure, first, the acquisition unit 501 acquires vehicle fault information; secondly, the factor generation unit 502 generates fault correlation factors based on the vehicle fault information and the factor big model; finally, the script generation unit 503 generates a diagnostic script based on the fault correlation factors and the diagnostic big model. Thus, based on the vehicle fault information, the fault correlation factors are automatically generated, and based on the fault correlation factors, the diagnostic script is generated, which improves the efficiency of diagnostic script generation; there is no need for operators to search for information, which improves the user experience.

[0147] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0148] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0149] Figure 6A schematic block diagram of an example electronic device 40600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0150] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 40603 are connected to each other via a bus 40604. An input / output (I / O) interface 40605 is also connected to the bus 604.

[0151] A number of components in the device 600 are connected to the I / O interface 40605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0152] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the diagnostic script generation method. For example, in some embodiments, the diagnostic script generation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the diagnostic script generation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the diagnostic script generation method by any other appropriate means (e.g., by means of firmware).

[0153] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0154] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable diagnostic script generating device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0155] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0156] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0157] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an information server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0158] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0159] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0160] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A diagnostic script generation method, comprising: Obtain vehicle fault information; generating a fault correlation factor based on the vehicle fault information and the factor macro model; A diagnosis script is generated based on the fault correlation factors and the diagnosis big model.

2. The method according to claim 1, wherein generating a fault correlation factor based on the vehicle fault information and the factor big model comprises: Based on the diagnostic script library, detecting whether there is a diagnostic script matching the vehicle fault information; In response to not detecting a diagnostic script matching the vehicle fault information, a fault correlation factor is generated based on the vehicle fault information and a factor big model.

3. The method according to claim 2, wherein: The step of detecting whether there is a diagnostic script matching the vehicle fault information based on the diagnostic script library includes: Vectorizing the diagnostic scripts in the diagnostic script library to obtain a first vector library; Performing vector processing on the vehicle fault information to obtain a vehicle fault vector; Matching the vehicle fault vector with the vectors in the first vector library; In response to the vehicle fault vector successfully matching the vector in the first vector library, a diagnosis script matching the vehicle fault information is determined.

4. The method according to claim 1, wherein the vehicle fault information is fault information sent by the target vehicle, and the method further comprises: The diagnostic script is sent to the target vehicle.

5. The method according to claim 4, further comprising: Receiving the diagnostic result sent by the target vehicle, and sending the diagnostic result and the diagnostic script to the client; receiving feedback information sent by the client, wherein the feedback information is respectively related to the diagnosis result and the diagnosis script; In response to the feedback information indicating that the vehicle diagnosis is qualified, the diagnostic script is added to a diagnostic script library.

6. The method according to claim 5, further comprising: In response to the feedback information indicating that the vehicle diagnosis is unqualified, obtaining an optimization script based on the feedback information; The optimization script is sent to the target vehicle as a diagnostic script.

7. The method according to any one of claims 1 to 6, wherein: The factor big model includes a first big model, and the generating of the fault correlation factor based on the vehicle fault information and the factor big model includes: Matching the vehicle fault information with the fault repair information; In response to the vehicle fault information successfully matching the fault repair information, the first large model is input based on the vehicle fault information, the fault repair information and a selection prompt word to obtain a fault correlation factor output by the first large model.

8. The method according to claim 7, wherein: The factor big model also includes a second big model, and the generating of the fault correlation factor based on the vehicle fault information and the factor big model also includes: In response to the vehicle fault information and the fault repair information not being matched successfully, the vehicle fault information and the generated prompt word are input into the second large model to obtain the fault correlation factor output by the second large model.

9. The method according to claim 1, wherein: The fault correlation factor includes a fault detection process sub-factor, and generating a diagnosis script based on the fault correlation factor and the diagnosis big model includes: The fault detection process sub-factors and diagnostic prompt words are input into the diagnostic big model to obtain the diagnostic script output by the diagnostic big model.

10. The method according to claim 9, wherein: The fault correlation factor also includes an instruction key sub-factor, and the generating of a diagnosis script based on the fault correlation factor and the diagnosis big model also includes: Based on the instruction key sub-factors and the script instruction library, obtaining an instruction list; The instruction list, the fault detection process sub-factors and the diagnosis prompt words are input into the diagnosis big model together to obtain the diagnosis script output by the diagnosis big model.

11. The method according to claim 10, wherein: The instruction key sub-factor includes an instruction keyword and an acquisition attribute of the instruction keyword. The instruction list obtained based on the instruction key sub-factor and the script instruction library includes: Based on the acquisition attribute, an instruction set related to the instruction keyword is acquired from a script instruction library; Performing vectorization processing on the instruction set to obtain an instruction vector set; Matching the instruction vector set with the vector of the instruction keyword; Based on the matching result between the instruction vector set and the vector of the instruction keyword, an instruction list is obtained.

12. The method according to any one of claims 9 to 11, wherein: The diagnostic large model is a fine-tuned code generation model; the fine-tuning includes inputting script syntax information into the code generation model so that the code generation model can output code corresponding to the diagnostic script.

13. A diagnostic script generating device, the device comprising: An acquisition unit, configured to acquire vehicle fault information; A factor generating unit configured to generate a fault correlation factor based on the vehicle fault information and the factor big model; The script generating unit is configured to generate a diagnosis script based on the fault correlation factor and the diagnosis big model.

14. The apparatus according to claim 13, wherein the factor generation unit is configured to: Based on a diagnostic script library, detecting whether there is a diagnostic script matching the vehicle fault information; in response to not detecting a diagnostic script matching the vehicle fault information, generating a fault correlation factor based on the vehicle fault information.

15. The device according to claim 14, wherein: The factor generation unit is further configured to: vectorize the diagnostic scripts in the diagnostic script library to obtain a first vector library; vectorize the vehicle fault information to obtain a vehicle fault vector; match the vehicle fault vector with a vector in the first vector library; in response to a successful match between the vehicle fault vector and the vector in the first vector library, determine a diagnostic script that matches the vehicle fault information.

16. The device according to claim 13, wherein the vehicle fault information is fault information sent by the target vehicle, and the device further comprises: A sending unit is configured to send the diagnostic script to the target vehicle.

17. The device according to claim 16, wherein: The device also includes: an adding unit, which is configured to: receive a diagnostic result sent by the target vehicle, and send the diagnostic result and the diagnostic script to a client; receive feedback information sent by the client, wherein the feedback information is related to the diagnostic result and the diagnostic script; and add the diagnostic script to a diagnostic script library in response to the feedback information indicating that the vehicle diagnosis is qualified.

18. The device according to claim 17, wherein: The device further includes: an optimization unit configured to: in response to the feedback information indicating that the vehicle diagnosis is unqualified, obtain an optimization script based on the feedback information; and send the optimization script to the target vehicle as a diagnosis script.

19. The device according to any one of claims 13 to 18, wherein: The factor large model includes: a first large model, and the factor generation unit is configured to: match the vehicle fault information with the fault repair information; in response to the vehicle fault information and the fault repair information being successfully matched, based on the vehicle fault information, the fault repair information and the selection prompt word input into the first large model, obtain the fault correlation factor output by the first large model.

20. The device according to claim 19, wherein The factor large model also includes: a second large model, and the factor generation unit is configured to: in response to the vehicle fault information and the fault repair information not being successfully matched, input the vehicle fault information and the generated prompt word into the second large model to obtain the fault correlation factor output by the second large model.

21. The device according to claim 13, wherein: The fault correlation factor includes a fault detection process sub-factor, and the script generation unit is configured to input the fault detection process sub-factor and the diagnosis prompt word into the diagnosis big model to obtain the diagnosis script output by the diagnosis big model.

22. The device according to claim 21, wherein The fault-related factors also include: instruction key sub-factors, and the script generation unit is further configured to: obtain an instruction list based on the instruction key sub-factors and the script instruction library; input the instruction list, the fault detection process sub-factors and the diagnostic prompt words into the diagnostic big model to obtain the diagnostic script output by the diagnostic big model.

23. The device according to claim 22, wherein: The instruction key sub-factor includes: instruction keywords and acquisition attributes of the instruction keywords, and the script generation unit is further configured to: based on the acquisition attributes, obtain an instruction set related to the instruction keyword from a script instruction library; vectorize the instruction set to obtain an instruction vector set; match the instruction vector set with the vector of the instruction keyword; and obtain an instruction list based on the matching result between the instruction vector set and the vector of the instruction keyword.

24. The device according to any one of claims 21 to 23, wherein: The diagnostic large model is a fine-tuned code generation model; the fine-tuning includes inputting script syntax information into the code generation model so that the code generation model can output code corresponding to the diagnostic script.

25. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 12.

26. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 12.

27. A computer program product, comprising a computer program, which, when executed by a processor, implements the method of any one of claims 1 to 12.

Images