Vehicle diagnostic software problem solving method and device, equipment and medium
Automatically analyze vehicle diagnostic software problems through the pre-built problem analysis model, which improves the troubleshooting efficiency and the effectiveness of solutions, and solves the complex problems of vehicle diagnostic software troubleshooting in the existing technology.
Patent Information
- Application Number
- CN202411209919.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-11-12
AI Technical Summary
The troubleshooting of existing vehicle diagnostic software is complicated, and it is difficult for software engineers to accurately determine the cause of the problem, resulting in poor solution effectiveness.
The pre-built problem analysis model is used to automatically analyze the cause of the problem and generate a solution through input models such as actual test cases, error status information and functional codes. The entire process does not require manual participation.
It improves the efficiency of troubleshooting and the effectiveness of solutions, and realizes the automated solution of vehicle diagnostic software problems.
Smart Images

Figure CN118938879A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle technology, and in particular to a solution, device, equipment and medium for solving vehicle diagnostic software problems. Background Art
[0002] With the development of automotive electronic technology, the complexity of automotive electronic control systems continues to increase, and vehicle fault diagnosis software has become increasingly complex. A domain controller of a vehicle may contain one or two thousand fault codes, hundreds of diagnostic DIDs (Data Identifiers) and RIDs (Routine Identifiers), and the logic design of each diagnostic function is becoming more and more complex. The difficulty of troubleshooting business problems for diagnostic software has increased accordingly.
[0003] In the related art, the business problems of the diagnostic software are usually checked item by item, the causes of the problems are analyzed, and then solutions to the problems are given. However, when the business problems of the diagnostic software are checked item by item, the software engineers will determine the causes of the problems based on their work experience. Even software engineers with very high work experience may occasionally make mistakes, resulting in poor effectiveness of the solutions given to solve the problems. Summary of the invention
[0004] In view of the above problems, the present invention is proposed to provide a solution, device, equipment and medium for solving the vehicle diagnostic software problems mentioned above. The problem analysis model can be used to determine the cause of the problem of the vehicle diagnostic software. The problem analysis model can also accurately generate a solution based on the cause. The entire solution process is fully automated without the need for human participation, thereby improving the efficiency of problem troubleshooting and the effectiveness of the solution.
[0005] In a first aspect, the present invention provides a method for solving vehicle diagnostic software problems, the method comprising:
[0006] Get the problems obtained when testing the diagnostic functions of vehicle diagnostic software using actual test cases;
[0007] According to the problem, the cause of the problem and the solution to the problem are output through a pre-built problem analysis model.
[0008] Optionally, outputting the cause of the problem and a solution to the problem through a pre-built problem analysis model according to the problem includes:
[0009] The actual test case and the corresponding diagnostic function are input into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual test case error and the solution includes a standard test case.
[0010] Optionally, outputting the cause of the problem and a solution to the problem through a pre-built problem analysis model according to the problem also includes:
[0011] Obtain error status information and actual execution conditions corresponding to the problem, and input the error status information and the actual execution conditions into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual execution condition error, the solution includes a standard execution condition, and the error status information includes a functional abnormality fault code and a diagnostic instruction negative response code.
[0012] Optionally, outputting the cause of the problem and a solution to the problem through a pre-built problem analysis model according to the problem also includes:
[0013] Get the actual function code corresponding to the problem;
[0014] The actual function code and the corresponding diagnostic function are input into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual function code error and the solution includes a standard function code.
[0015] Optionally, after inputting the actual test case and the corresponding diagnostic function into the problem analysis model, the method further includes:
[0016] If the actual test case output by the problem analysis model is correct, then the error status information and the actual execution condition corresponding to the problem are obtained, and the error status information and the actual execution condition are input into the problem analysis model, wherein the error status information includes a function abnormality fault code and a diagnostic instruction negative response code;
[0017] If the actual execution conditions output by the problem analysis model are correct, the actual function code corresponding to the problem is obtained, and the actual function code and the corresponding diagnostic function are input into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual function code error, and the solution includes the standard function code of the diagnostic function.
[0018] Optionally, before obtaining the problem obtained when the diagnostic function of the vehicle diagnostic software is tested using an actual test case, the method further includes:
[0019] Acquire diagnostic service sample data and an initial model, wherein the diagnostic service sample data includes a standard functional requirement document of the vehicle diagnostic software, and standard function codes and standard test cases corresponding to each diagnostic function in the standard functional requirement document, wherein the standard functional requirement document includes error status information, a data identifier, and a routine identifier;
[0020] The problem analysis model is determined according to the diagnostic service sample data and the initial model.
[0021] Optionally, determining the problem analysis model according to the diagnostic service sample data and the initial model includes:
[0022] Preprocessing the diagnostic service sample data to obtain training data and verification data;
[0023] Training the initial model using the training data;
[0024] The verification data is used to verify the initial model after training, and the model that passes the verification is determined as the problem parsing model.
[0025] In a second aspect, the present invention provides a device for solving vehicle diagnostic software problems, the device comprising:
[0026] A first acquisition module is used to acquire problems obtained when the diagnostic function of the vehicle diagnostic software is tested using actual test cases;
[0027] The first determination module is used to output the cause of the problem and the solution to the problem through a pre-built problem analysis model according to the problem.
[0028] Optionally, the first determining module includes a first determining unit, configured to:
[0029] The actual test case and the corresponding diagnostic function are input into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual test case error and the solution includes a standard test case.
[0030] Optionally, the first determining module further includes a second determining unit, configured to:
[0031] Obtain error status information and actual execution conditions corresponding to the problem, and input the error status information and the actual execution conditions into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual execution condition error, the solution includes a standard execution condition, and the error status information includes a functional abnormality fault code and a diagnostic instruction negative response code.
[0032] Optionally, the first determining module further includes a third determining unit, configured to:
[0033] Get the actual function code corresponding to the problem;
[0034] The actual function code and the corresponding diagnostic function are input into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual function code error and the solution includes a standard function code of the diagnostic function.
[0035] Optionally, the device further includes a fourth determining unit, configured to:
[0036] If the actual test case output by the problem analysis model is correct, then the error status information and the actual execution condition corresponding to the problem are obtained, and the error status information and the actual execution condition are input into the problem analysis model, wherein the error status information includes a function abnormality fault code and a diagnostic instruction negative response code;
[0037] If the actual execution conditions output by the problem analysis model are correct, the actual function code corresponding to the problem is obtained, and the actual function code and the corresponding diagnostic function are input into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual function code error, and the solution includes the standard function code of the diagnostic function.
[0038] Optionally, the device further comprises:
[0039] A second acquisition module is used to acquire diagnostic service sample data and an initial model, wherein the diagnostic service sample data includes a standard functional requirement document of the vehicle diagnostic software, and standard function codes and standard test cases corresponding to each diagnostic function in the standard functional requirement document, wherein the standard functional requirement document includes error state information, a data identifier, and a routine identifier;
[0040] The second determination module is used to determine the problem analysis model according to the diagnostic business sample data and the initial model.
[0041] Optionally, the second determining module is further used for:
[0042] Preprocessing the diagnostic service sample data to obtain training data and verification data;
[0043] Training the initial model using the training data;
[0044] The verification data is used to verify the initial model after training, and the model that passes the verification is determined as the problem parsing model.
[0045] In a third aspect, the present invention provides an electronic device comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method described in the first aspect by executing the computer instructions.
[0046] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in the first aspect.
[0047] The technical solution provided in the embodiments of the present invention has at least the following technical effects or advantages:
[0048] The embodiments of the present invention provide a method, device, equipment and medium for solving vehicle diagnostic software problems, which obtains the problems obtained when the diagnostic function of the vehicle diagnostic software is tested using actual test cases, and understands what problems are generated when the vehicle diagnostic software is tested; according to the problems, the causes of the problems and solutions to the problems are output through a pre-built problem analysis model. The problem analysis model can not only determine the causes of different problems, but also generate solutions for the causes. The problems can be solved according to the solutions, so that the vehicle diagnostic software can pass the test. The entire solution process of this method is fully automated, without the need for human participation, which improves the efficiency of problem troubleshooting and the effectiveness of the solution.
[0049] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0051] Figure 1 is a flow chart of a solution to a vehicle diagnostic software problem provided by an embodiment of the present invention;
[0052] Figure 2 The present invention is a structural block diagram of a device for solving vehicle diagnostic software problems provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0053] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0054] Figure 1 FIG. 1 is a flow chart of a solution to a vehicle diagnostic software problem provided by an embodiment of the present invention. Figure 1 As shown, the method includes step S110 and step S120.
[0055] Step S110: Obtain problems obtained when the diagnostic function of the vehicle diagnostic software is tested using actual test cases.
[0056] In this embodiment, when the vehicle diagnostic software is developed, the diagnostic function of the vehicle diagnostic software needs to be tested. Actual test cases are used during the test. Problems may arise during the test. These problems are recorded in a table. When the problem needs to be troubleshooted, the problem is directly retrieved from the table.
[0057] Among them, the vehicle diagnostic software is developed based on the actual functional requirement document. The actual functional requirement document includes the actual required diagnostic functions and actual execution conditions, and the diagnostic function is implemented through the actual function code when the actual execution conditions are met. The diagnostic function, actual execution conditions and actual function code can be stored one by one.
[0058] Step S120: Based on the problem, output the cause of the problem and the solution to the problem through a pre-built problem analysis model.
[0059] In this embodiment, a problem analysis model is pre-established, and the cause of the problem is automatically analyzed through the problem analysis model. A solution to the problem is also generated based on the cause, so that software developers can solve the problem based on the solution. Even if there are many problems, the cause can be quickly analyzed and the solution can be obtained through the problem analysis model, thereby improving the analysis efficiency and the effectiveness of the solution.
[0060] Among them, the model is an artificial intelligence large model, which refers to a machine learning model with ultra-large-scale parameters (usually more than one billion) and complex computing structure. It is usually able to process massive amounts of data and complete various complex tasks, such as natural language processing and image recognition.
[0061] Optionally, before step S110, the method further includes steps S101-S102.
[0062] Step S101: Acquire diagnostic service sample data and an initial model.
[0063] In this embodiment, industry-standard diagnostic service data can be collected as sample data, and the diagnostic service sample data can include the standard functional requirement document of the vehicle diagnostic software, and the standard function codes and standard test cases corresponding to each diagnostic function in the standard functional requirement document. The standard functional requirement document includes a diagnostic function requirement sub-document and a communication requirement sub-document. The diagnostic function requirement sub-document includes a diagnostic function, and data such as a diagnostic function abnormal fault code, a diagnostic instruction negative response code, a diagnostic data identifier, and a diagnostic routine identifier corresponding to the diagnostic function, and the diagnostic data identifier includes a diagnostic read-write DID and a diagnostic input-output DID. The communication requirement sub-document includes a communication function, and a communication function abnormal fault code corresponding to the communication function. For example, the communication function abnormal fault code includes a timeout fault code. The diagnostic function abnormal fault code and the communication function abnormal fault code are collectively referred to as a function abnormal fault code, and the function abnormal fault code and the diagnostic instruction negative response code are collectively referred to as error state information. The standard functional requirement document, the standard function code, and the standard test case are all standards referenced when developing diagnostic software in the industry.
[0064] Among them, the initial model can use pre-trained models such as BERT or GPT.
[0065] Step S102: Determine a problem analysis model based on the diagnostic service sample data and the initial model.
[0066] In this embodiment, the diagnostic service sample data may be used to train and verify the pre-trained model, thereby obtaining a problem analysis model.
[0067] Optionally, step S102 includes:
[0068] Preprocess the diagnostic business sample data to obtain training data and verification data; use the training data to train the initial model; use the verification data to verify the initial model after training, and determine the verified model as the problem analysis model.
[0069] In this embodiment, in order to make the diagnostic service sample data adapt to the input requirements of the initial model, the acquired diagnostic service sample data may be preprocessed, and the preprocessing includes text cleaning (for example, removing noise, punctuation marks and stop words, etc.), word segmentation, word vector encoding, etc. The preprocessed diagnostic service sample data is divided into training data and verification data.
[0070] Next, use the training data to train the initial model; then use the verification data to verify the trained initial model, which can be verified by manual review or verification using an automated script tool. Among them, the manual review verification method is to manually determine whether the causes of the problems and the solutions to the problems output by the trained initial model are correct; the automated script tool verification method is to use an automated script tool to scan the causes of the problems and the solutions to the problems output by the initial model, and compare them with the actual causes and the actual solutions to automatically determine whether they are correct; when the accuracy meets the requirements, the verification passes, and the initial problem resolution model can be used as the problem resolution model. When the accuracy does not meet the requirements, the verification fails, and the initial problem resolution model needs to be fine-tuned to make the verification accuracy meet the requirements.
[0071] Optionally, step S120 includes step S1201.
[0072] Step S1201: input the actual test case and the corresponding diagnostic function into the problem analysis model to obtain the cause and solution of the problem output by the problem analysis model, wherein the cause includes the actual test case error and the solution includes the standard test case.
[0073] In this embodiment, when testing the vehicle diagnostic software, actual test cases will be used for testing. When a problem occurs during the test, the actual test cases used during the test can be found according to the problem. Then, the actual test cases and the corresponding diagnostic functions are input into the problem analysis model, and the problem analysis model automatically determines whether the actual test cases are wrong. If the cause of the problem analysis model output is an actual test case error, it means that the problem is caused by an actual test case error, that is, the cause of the problem is an actual test case error. At the same time, the problem analysis model will also output a solution to the cause. If the cause is a test case error, then the output solution is to output the correct test case, that is, the standard test case, so that the standard test case can be used for testing to prevent the same problem from occurring again.
[0074] In this embodiment, if the problem analysis model outputs that the actual test case is correct, it means that the problem is not caused by the actual test case, that is, the cause of the problem is not the actual test case.
[0075] Among them, the actual test case includes test steps and test parameters.
[0076] For example, when the diagnostic software is tested using an actual test case of the diagnostic function of switching the vehicle model, the vehicle mode switching fails after the diagnostic command is sent to the vehicle. In order to determine whether the vehicle mode switching fails due to an error in the actual test case, the actual test case of the diagnostic function of switching the vehicle model can be input into the problem analysis model, and the problem analysis model will directly output the result to inform whether the actual test case is wrong. If the actual test case is wrong, the problem analysis model will also find the standard test case corresponding to the diagnostic function and output it.
[0077] Optionally, after step S1201, step S120 includes step S1202.
[0078] Step S1202, obtain the error status information and actual execution conditions corresponding to the problem, and input the error status information and actual execution conditions into the problem analysis model to obtain the cause and solution of the problem output by the problem analysis model, wherein the cause includes an actual execution condition error, the solution includes a standard execution condition, and the error status information includes a functional abnormality fault code and a diagnostic instruction negative response code.
[0079] In this embodiment, the problem analysis model can also be used to determine whether the cause of the problem is an actual execution condition error. The actual execution condition is recorded in the actual functional requirement document. If the actual execution condition is wrong, it means that the actual requirement of the diagnostic software is wrong.
[0080] Specifically, the error status information set when the problem occurs is obtained, and the error status information and the corresponding actual execution conditions are input into the problem analysis model. The problem analysis model will look for the standard execution conditions corresponding to the error status information in the standard functional requirements document. The standard execution conditions are the standard conditions that need to be met for the implementation of the diagnostic function. Then, the problem analysis model compares the actual execution conditions with the standard execution conditions. If they are inconsistent, the cause of the problem output by the problem analysis model is an error in the actual execution conditions, indicating that the problem occurred due to an error in the actual execution conditions of the test. At the same time, the problem analysis model will also output the standard execution conditions as a solution. If the comparison is consistent, the problem analysis model will output that the actual execution conditions are correct, indicating that the cause of the problem is not the actual execution conditions, and the output solution is empty or is to check whether there is an error in the actual test case or the actual function code.
[0081] In this embodiment, after step S1201 and before step S1202, the method further includes:
[0082] The diagnostic function corresponding to the problem is re-tested using the standard test case. If the problem still occurs after the re-test, step S1202 is executed.
[0083] In other words, you can directly test whether the actual execution conditions are wrong through the problem analysis model, or you can test whether the problem will be eliminated after testing the actual test case. If the problem still exists when using the standard test case, it means that there may be other reasons that cause the problem. Then test whether the actual execution conditions are wrong through the problem analysis model. This allows the entire problem troubleshooting process to be carried out in a hierarchical manner.
[0084] For example, when testing the diagnostic function of the sleep and power-on of the actual vehicle, some functional abnormality fault codes are set. The cause of the unexpected reporting of these functional abnormality fault codes can be analyzed through the problem analysis model, and one or more solutions can be generated.
[0085] In this embodiment, after obtaining the standard execution conditions, the diagnostic function can be functionally tested again using standard test cases under the standard execution conditions. If no problem occurs after the functional test is performed again, it further indicates that the cause of the problem is an actual execution adjustment error and an actual requirement error of the diagnostic software, and the actual functional requirement document of the diagnostic software can be modified. In other words, the problem analysis model can locate the problem in the actual functional requirement document based on the standard functional requirement document. At this time, the relevant technical person in charge can be notified to modify the problematic requirements in the actual functional requirement document.
[0086] Optionally, after step S1202, step S120 also includes steps S1203-S1204.
[0087] Step S1203: Obtain the actual function code corresponding to the question.
[0088] Step S1204: input the actual function code and the corresponding diagnostic function into the problem analysis model to obtain the cause and solution of the problem output by the problem analysis model, wherein the cause includes an actual function code error and the solution includes a standard function code of the diagnostic function.
[0089] In this embodiment, the problem analysis model can also be used to determine whether the cause of the problem is an actual function code error. Specifically, the diagnostic function corresponding to the problem is obtained, and the corresponding actual function code is determined according to the diagnostic function. Then, the actual function code and the corresponding diagnostic function are input into the problem analysis model, or only the key variables of the actual function code and the corresponding diagnostic function are input into the problem analysis model. The problem analysis model will compare the actual function code with the standard function code of the corresponding diagnostic function to determine whether the actual function code is wrong. If the key variables are the same during the comparison, it means that the actual function code is correct, and the problem analysis model will output that the actual function code is correct; if the key variables are different, it means that the actual function code is wrong, and the problem analysis model will output that the actual function code is wrong, that is, the cause is the actual function code error. At the same time, the standard function code will be output as a solution, so that the software switch personnel can modify the actual function code according to the standard function code, so that the modified actual function code adapts to the current test environment.
[0090] In this embodiment, it is possible to directly determine whether the cause of the problem is an actual function code error through the problem analysis model. It is also possible to perform a functional test on the diagnostic function again under standard execution conditions using a standard test case. If the problem still occurs after the functional test is performed again, steps S1203-S1204 are executed. At this time, it is determined whether the cause of the problem is an actual function code error through the problem analysis model, so that the whole process is gradual, that is, first determine whether the actual test case has an error, then determine whether the actual execution condition has an error, and finally determine whether the actual function code has an error, and eliminate the cause of the problem step by step.
[0091] For example, when the communication of a node of the test vehicle is lost, the communication timeout fault code is set to TRUE. After the communication of the node is restored, the timeout fault code is normally set to False; but in reality, the timeout fault code is still TRUE after the communication is restored. The previous investigation found that there were no problems with the actual test cases and the actual execution conditions. Next, it is checked whether the problem is caused by the error in the function code of the diagnostic function. Therefore, the cause of the problem is queried through the problem analysis model, and the actual function code corresponding to the diagnostic function and the corresponding diagnostic function are input into the problem analysis model. The problem analysis model will query the standard function code corresponding to the diagnostic function, and then compare the two. It is found that the timeout recovery function is missing in the actual function code. Therefore, the problem analysis model finally outputs the analysis result of the actual function code error, and outputs the standard function code at the same time, so that the actual function code can be modified according to the standard function code.
[0092] Optionally, step S120 also includes S1205-S1206.
[0093] S1205: If the actual test case output by the problem analysis model is correct, then the error status information and the actual execution condition corresponding to the problem are obtained, and the error status information and the actual execution condition are input into the problem analysis model.
[0094] In this implementation, if the result output by the problem analysis model at the beginning is that the actual test case is correct, it means that the problem is not caused by the actual test case, but may be caused by actual requirement errors or functional code errors or other reasons, so the next step is to check the causes one by one through the problem analysis model.
[0095] First, the error status information and actual execution conditions corresponding to the problem are input into the problem analysis model. The problem analysis model will look for the corresponding information of the error status information in the standard functional requirements document. The information includes the corresponding standard execution conditions. The problem analysis model compares the actual execution conditions with the standard execution conditions. If they are inconsistent, the cause of the problem analysis model output is an actual execution condition error, indicating that the problem is caused by an actual execution condition error of the test.
[0096] S1206. If the actual execution conditions output by the problem analysis model are correct, the actual function code corresponding to the problem is obtained, and the actual function code and the corresponding diagnostic function are input into the problem analysis model to obtain the cause and solution of the problem output by the problem analysis model. The cause includes an actual function code error, and the solution includes a standard function code of the diagnostic function.
[0097] In this embodiment, if the problem analysis model outputs that the actual execution conditions are correct, it means that the problem may be caused by an error in the actual function code. Therefore, next, the actual function code and the corresponding diagnostic function are input into the problem analysis model. The problem analysis model will compare the actual function code with the standard function code. If the problem analysis model outputs that the actual function code is wrong, that is, the cause is the error in the actual function code. At the same time, the standard function code will be output as a solution, so that the software switch personnel can modify the actual function code according to the standard function code, so that the modified actual function code is adapted to the current test environment.
[0098] In this embodiment, if the result output by the problem analysis model is that the actual function code is correct, and the actual test case and the actual execution condition are also outputted correctly, the software engineer is reminded to troubleshoot the cause of the problem from other aspects. Other aspects refer to aspects other than the actual test case, actual requirements and actual function code.
[0099] For example, the diagnostic function of writing configuration words is tested. After sending the corresponding diagnostic instruction to the vehicle, it is found that the writing of the vehicle configuration words fails. Next, the cause and solution of the failure are queried through the problem analysis model.
[0100] First, the problem analysis model is used to determine whether the actual test case for writing the configuration word is correct. If the cause of the problem analysis model output is an error in the actual test case, the standard test case output by the problem analysis model is used to perform the write test again, but the write still fails. Then, determine whether the actual execution condition of the diagnostic software is wrong. When the write fails, a negative response code will be replied. The negative response code and the actual execution condition are input into the problem analysis model. The cause of the problem analysis model output is an error in the actual execution condition, and the solution is the standard execution condition, that is, what prerequisites need to be met before writing the vehicle configuration word. Finally, after the environment of the standard execution condition is built, the standard test case is used for the write test, but the write configuration word still fails. Finally, the actual function code for writing the vehicle configuration word and the write configuration word are input into the problem analysis model. The cause of the problem analysis model output is an error in the actual function code, and the output solution is the standard function code. Therefore, there are three reasons for the write failure, the actual test case error, the actual execution condition error, and the actual function code error.
[0101] In this embodiment, the problem analysis model can also be updated regularly to adapt to new needs. The method in this embodiment allows engineers who initially take over the on-board diagnostic software business to use the problem analysis model to quickly and efficiently troubleshoot problems, thereby improving the efficiency of problem solving. This reduces the company's R&D investment costs, improves the engineers' troubleshooting efficiency, and shortens the overall product development cycle.
[0102] Based on the same inventive concept, an embodiment of the present invention also provides a device for solving vehicle diagnostic software problems. Figure 2 is a structural block diagram of a device for solving vehicle diagnostic software problems provided by an embodiment of the present invention, such as Figure 2 As shown, the device 200 includes an acquisition module 201 and a determination module 202 .
[0103] A first acquisition module 201 is used to acquire problems obtained when the diagnostic function of the vehicle diagnostic software is tested using actual test cases;
[0104] The first determination module 202 is used to output the cause of the problem and the solution to the problem according to the problem through a pre-built problem analysis model.
[0105] Optionally, the first determining module 202 includes a first determining unit, configured to:
[0106] The actual test cases and the corresponding diagnostic functions are input into the problem analysis model to obtain the causes and solutions of the problems output by the problem analysis model, wherein the causes include actual test case errors and the solutions include standard test cases.
[0107] Optionally, the first determining module 202 further includes a second determining unit, configured to:
[0108] The error status information and actual execution conditions corresponding to the problem are obtained, and the error status information and actual execution conditions are input into the problem analysis model to obtain the cause and solution of the problem output by the problem analysis model, wherein the cause includes an actual execution condition error, the solution includes a standard execution condition, and the error status information includes a functional abnormality fault code and a diagnostic instruction negative response code.
[0109] Optionally, the first determining module 202 further includes a third determining unit, configured to:
[0110] Get the actual function code corresponding to the problem;
[0111] The actual function code and the corresponding diagnostic function are input into the problem analysis model to obtain the cause and solution of the problem output by the problem analysis model, wherein the cause includes an actual function code error and the solution includes a standard function code of the diagnostic function.
[0112] Optionally, the apparatus 200 further includes a fourth determining unit, configured to:
[0113] If the actual test case output by the problem analysis model is correct, the error status information and the actual execution condition corresponding to the problem are obtained, and the error status information and the actual execution condition are input into the problem analysis model, wherein the error status information includes the function abnormality fault code and the diagnosis instruction negative response code;
[0114] If the actual execution conditions output by the problem analysis model are correct, the actual function code corresponding to the problem is obtained, and the actual function code and the corresponding diagnostic function are input into the problem analysis model to obtain the cause and solution of the problem output by the problem analysis model. The cause includes an actual function code error, and the solution includes the standard function code of the diagnostic function.
[0115] Optionally, the device 200 further includes:
[0116] A second acquisition module is used to acquire diagnostic service sample data and an initial model, wherein the diagnostic service sample data includes a standard functional requirement document of the vehicle diagnostic software, and standard function codes and standard test cases corresponding to each diagnostic function in the standard functional requirement document, wherein the standard functional requirement document includes error status information, a data identifier, and a routine identifier;
[0117] The second determination module is used to determine the problem analysis model according to the diagnosis business sample data and the initial model.
[0118] Optionally, the second determining module is further used for:
[0119] Preprocess the diagnostic service sample data to obtain training data and verification data;
[0120] Train the initial model using the training data;
[0121] The verification data is used to verify the initial model after training, and the model that passes the verification is determined as the problem parsing model.
[0122] It can be understood that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0123] An embodiment of the present invention further provides an electronic device, which may include a processor and a memory, wherein the processor and the memory may be communicatively connected to each other via a bus or other means.
[0124] The processor may be a central processing unit (CPU) or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0125] The memory may include a large capacity memory for data or instructions. By way of example and not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory may include a removable or non-removable (or fixed) medium. Where appropriate, the memory may be inside or outside the electronic device. In a particular embodiment, the memory may be a non-volatile solid-state memory.
[0126] In one example, the memory may be a read-only memory (ROM). In one example, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.
[0127] The processor implements any one of the solutions to the vehicle diagnostic software problems in the above embodiments by reading and executing computer program instructions stored in the memory.
[0128] In one example, the electronic device may further include a communication interface and a bus. Among them, the processor, memory, and communication interface are connected through a bus and communicate with each other. The communication interface is mainly used to realize the communication between the modules, devices, units and / or devices in the embodiment of the present application. Where appropriate, the bus may include one or more buses.
[0129] In addition, in combination with the solution to the vehicle diagnostic software problem in the above embodiment, the embodiment of the present invention can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any solution to the vehicle diagnostic software problem in the above embodiment is implemented.
[0130] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:
[0131] The embodiments of the present invention provide a method, device, equipment and medium for solving vehicle diagnostic software problems, which obtains the problems obtained when the diagnostic function of the vehicle diagnostic software is tested using actual test cases, and understands what problems are generated when the vehicle diagnostic software is tested; according to the problems, the causes of the problems and solutions to the problems are output through a pre-built problem analysis model. The problem analysis model can not only determine the causes of different problems, but also generate solutions for the causes. The problems can be solved according to the solutions, so that the vehicle diagnostic software can pass the test. The entire solution process of this method is fully automated, without the need for human participation, which improves the efficiency of problem troubleshooting and the effectiveness of the solution.
[0132] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.
[0133] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.
[0134] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "one" or "an" preceding a component does not exclude the presence of a plurality of such components. The present invention may be implemented by means of hardware comprising a number of different components and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.
Claims
1. A solution to vehicle diagnostic software problems, characterized in that: The method comprises: Get the problems obtained when testing the diagnostic functions of vehicle diagnostic software using actual test cases; According to the problem, the cause of the problem and the solution to the problem are output through a pre-built problem analysis model.
2. The method for solving the vehicle diagnostic software problem according to claim 1, characterized in that: According to the problem, the cause of the problem and the solution to the problem are output through a pre-built problem analysis model, including: The actual test case and the corresponding diagnostic function are input into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual test case error and the solution includes a standard test case.
3. The method for solving the vehicle diagnostic software problem according to claim 1, characterized in that: According to the problem, outputting the cause of the problem and the solution to the problem through a pre-built problem analysis model also includes: Obtain error status information and actual execution conditions corresponding to the problem, and input the error status information and the actual execution conditions into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual execution condition error, the solution includes a standard execution condition, and the error status information includes a functional abnormality fault code and a diagnostic instruction negative response code.
4. The method for solving the vehicle diagnostic software problem according to claim 1, characterized in that: According to the problem, outputting the cause of the problem and the solution to the problem through a pre-built problem analysis model also includes: Get the actual function code corresponding to the problem; The actual function code and the corresponding diagnostic function are input into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual function code error and the solution includes a standard function code.
5. The method for solving the problem of vehicle diagnostic software according to claim 2, characterized in that: After inputting the actual test case and the corresponding diagnostic function into the problem analysis model, the method further includes: If the actual test case output by the problem analysis model is correct, then the error status information and the actual execution condition corresponding to the problem are obtained, and the error status information and the actual execution condition are input into the problem analysis model, wherein the error status information includes a function abnormality fault code and a diagnostic instruction negative response code; If the actual execution conditions output by the problem analysis model are correct, the actual function code corresponding to the problem is obtained, and the actual function code and the corresponding diagnostic function are input into the problem analysis model to obtain the cause of the problem and the solution output by the problem analysis model, wherein the cause includes an actual function code error, and the solution includes a standard function code.
6. The method for solving the vehicle diagnostic software problem according to claim 1, characterized in that: Before obtaining the problems obtained when the diagnostic function of the vehicle diagnostic software is tested using the actual test case, the method further includes: Acquire diagnostic service sample data and an initial model, wherein the diagnostic service sample data includes a standard functional requirement document of the vehicle diagnostic software, and standard function codes and standard test cases corresponding to each diagnostic function in the standard functional requirement document, wherein the standard functional requirement document includes error status information, a data identifier, and a routine identifier; The problem analysis model is determined according to the diagnostic service sample data and the initial model.
7. The method for solving the problem of vehicle diagnostic software according to claim 6, characterized in that: The step of determining the problem analysis model according to the diagnostic service sample data and the initial model includes: Preprocessing the diagnostic service sample data to obtain training data and verification data; Using the training data to train the initial model; The verification data is used to verify the initial model after training, and the model that passes the verification is determined as the problem parsing model.
8. A device for solving vehicle diagnostic software problems, characterized in that: The device comprises: A first acquisition module is used to acquire problems obtained when the diagnostic function of the vehicle diagnostic software is tested using actual test cases; The first determination module is used to output the cause of the problem and the solution to the problem through a pre-built problem analysis model according to the problem.
9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.
