Vehicle-mounted embedded software system demand analysis and detection method, device and equipment based on large model and storage medium

Abstract

The invention discloses a vehicle-mounted embedded software system demand analysis and detection method, device and equipment based on a large model and a storage medium, and relates to the technical field of software system demand analysis. Determining software system demand preprocessing data based on the software system demand data; determining a vehicle-mounted software system demand analysis detection model and a detection demand state based on the software system demand data and the software system demand preprocessing data; and detecting the performance of the system based on the vehicle-mounted software system demand analysis and detection model and the detection demand state to complete demand analysis and detection. According to the method, the software demand data is intelligently processed by using the automatic script, and the demand state of the vehicle-mounted software system is analyzed and detected in combination with the pre-trained large model, so that the system performance is evaluated, the demand analysis efficiency and accuracy are improved, and the model is continuously optimized through a feedback mechanism to adapt to the software demand change.

Description

Technical Field

[0001] The present application relates to the technical field of software system requirement analysis, and in particular to a large model-based vehicle-mounted embedded software system requirement analysis detection method, device, equipment and storage medium. Background Art

[0002] With the rapid development of smart car technology, vehicle-mounted embedded software systems are becoming more and more complex, involving more and more functional modules and requirements. Not only do they need to process large amounts of data, but they also need to meet high standards of real-time, security, and reliability. This puts higher demands on software demand analysis to support the development and optimization of software systems. Therefore, efficiently and accurately understanding and analyzing complex software requirements is a must.

[0003] At present, the existing practice is to rely on manual experience, and engineers need to manually read and understand a large number of technical documents and requirement specifications. However, the existing practice is not only inefficient, but also easily affected by human factors. Manual analysis is time-consuming and error-prone, making it difficult to ensure the accuracy and consistency of the analysis results. With the increasing complexity of software systems, manual analysis methods are increasingly difficult to meet the development model of rapid iteration and continuous integration. Therefore, how to intelligently perform software requirement analysis to improve analysis efficiency and accuracy has become an urgent problem to be solved.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a large-model-based vehicle embedded software system requirement analysis detection method, device, equipment and storage medium, aiming to solve the technical problem of how to intelligently perform software requirement analysis to improve analysis efficiency and accuracy.

[0006] To achieve the above objectives, the present application proposes a vehicle embedded software system requirements analysis and detection method based on a large model, the method comprising:

[0007] Encapsulate a data acquisition program script to automatically obtain software system requirement data from the cloud, and determine software system requirement preprocessing data based on the software system requirement data;

[0008] Determine a vehicle software system requirement analysis detection model and a detection requirement state based on the software system requirement data and the software system requirement preprocessing data;

[0009] The demand analysis detection is completed based on the vehicle software system demand analysis detection model and the detection demand status detection system performance.

[0010] In one embodiment, the encapsulated data acquisition program script automatically obtains software system requirement data from the cloud, and the step of determining software system requirement preprocessing data based on the software system requirement data includes:

[0011] Utilize the data acquisition program script to automatically obtain system diagnostic software requirement data, communication system software requirement data, and storage system software requirement data from the cloud;

[0012] Determining software system requirement data based on the system diagnostic software requirement data, the communication system software requirement data and the storage system software requirement data;

[0013] The software system requirement data is subjected to text data preprocessing to determine the software system requirement preprocessing data, wherein the text data preprocessing includes text cleaning, text segmentation and text word vector encoding.

[0014] In one embodiment, the step of determining the vehicle software system requirement analysis detection model and detecting the requirement status based on the software system requirement data and the software system requirement preprocessing data comprises:

[0015] Perform pre-training based on the software system requirement data to determine a pre-training model;

[0016] Determine a vehicle software system requirement analysis and detection model based on fitting the pre-trained model to the software system requirement preprocessing data;

[0017] Identify demand detection scenarios based on the vehicle software system demand analysis detection model, where the demand detection scenarios include system diagnostic software fault code anomalies, communication system software message anomalies, and storage system software storage space anomalies;

[0018] Building an agent execution tool based on the demand detection scenario;

[0019] Based on the agent execution tool identifying the detection requirement status, the detection requirement status includes a diagnostic trouble code system requirement analysis status, a diagnostic system requirement analysis status and a diagnostic read-write system requirement analysis status.

[0020] In one embodiment, the step of completing the demand analysis detection based on the vehicle software system demand analysis detection model and the detection demand state detection system performance includes:

[0021] Acquire a system performance parameter set, wherein the system performance parameter set includes a model prompt word and a model recognition data;

[0022] Determine a software requirement analysis result based on the vehicle software system requirement analysis detection model and the detection requirement status;

[0023] The system performance is verified based on the vehicle software system demand analysis detection model and the software demand analysis result to adjust the system performance parameter set to complete the demand analysis detection.

[0024] In one embodiment, the step of determining the software requirement analysis result based on the vehicle software system requirement analysis detection model and the detection requirement state includes:

[0025] Analyze the detection requirement status based on the vehicle software system requirement analysis detection model to locate the fault anomaly and determine the fault prompt word;

[0026] The software requirement analysis result is obtained by performing graphical display based on the fault prompt words.

[0027] In one embodiment, the step of verifying system performance based on the vehicle software system requirement analysis detection model and the software requirement analysis result and adjusting the system performance parameter set to complete the requirement analysis detection includes:

[0028] Get the number of model iterations;

[0029] When the software requirement analysis result shows that the model-generated prompt words are inaccurate, adjusting the model prompt words;

[0030] When the software requirement analysis result indicates that the model identification function is repeated, adjusting the model identification data;

[0031] When the software requirement analysis result is direct feedback from the user, the vehicle-mounted software system requirement analysis detection model is retrained based on the number of model iterations, and the requirement analysis detection is performed.

[0032] In one embodiment, the step of retraining the vehicle software system requirement analysis detection model based on the number of model iterations and performing requirement analysis detection includes:

[0033] Retrain the vehicle software system requirement analysis detection model based on the number of model iterations to determine the vehicle software system requirement analysis detection optimization model;

[0034] Scoring the vehicle software system requirement analysis detection optimization model to determine a scoring index;

[0035] Based on the scoring index, the vehicle-mounted software system demand analysis and detection optimization model is redeployed to perform demand analysis and detection.

[0036] In addition, to achieve the above purpose, the present application also proposes a large model-based vehicle embedded software system requirements analysis and detection device, the large model-based vehicle embedded software system requirements analysis and detection device comprising:

[0037] An acquisition module, used to encapsulate a data acquisition program script to automatically acquire software system requirement data from the cloud, and determine software system requirement preprocessing data based on the software system requirement data;

[0038] A processing module, used to determine a vehicle software system requirement analysis detection model and a detection requirement state based on the software system requirement data and the software system requirement preprocessing data;

[0039] An execution module is used to complete the demand analysis detection based on the vehicle software system demand analysis detection model and the detection demand state detection system performance.

[0040] In addition, to achieve the above-mentioned objectives, the present application also proposes a large-model-based on-vehicle embedded software system requirement analysis and detection device, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the large-model-based on-vehicle embedded software system requirement analysis and detection method as described above.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the large model-based vehicle embedded software system requirements analysis and detection method as described above are implemented.

[0042] One or more technical solutions proposed in this application have at least the following technical effects:

[0043] The present application proposes a large-model-based vehicle embedded software system requirement analysis and detection method, which encapsulates a data acquisition program script to automatically obtain software system requirement data from the cloud, determines software system requirement preprocessing data based on the software system requirement data; determines a vehicle-mounted software system requirement analysis detection model and a detection requirement state based on the software system requirement data and the software system requirement preprocessing data; and detects system performance based on the vehicle-mounted software system requirement analysis detection model and the detection requirement state to complete the requirement analysis detection. The present application encapsulates a data acquisition program script to automatically obtain software system requirement data from the cloud and perform data preprocessing, and uses a pre-trained large-scale model to determine the vehicle-mounted software system requirement analysis detection model and the detection requirement state, thereby detecting system performance, completing requirement analysis detection, and automatically performing requirement analysis, thereby improving analysis efficiency. The learning ability of the large model is used to improve the accuracy of requirement analysis, and through feedback loops, the analysis model is continuously optimized to adapt to changing software requirements, significantly improving analysis efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 A flow chart of the first embodiment of the vehicle embedded software system requirement analysis and detection method based on a large model of the present application;

[0047] Figure 2 A flow chart is constructed for the scenario of the vehicle embedded software system requirements analysis and detection method based on a large model for this application;

[0048] Figure 3 A flow chart of the second embodiment of the vehicle embedded software system requirement analysis and detection method based on a large model of the present application;

[0049] Figure 4 A brief flow chart of a large model-based vehicle embedded software system requirements analysis and detection method provided in an embodiment of the present application;

[0050] Figure 5 This is a schematic diagram of the module structure of a large-model-based vehicle-mounted embedded software system requirement analysis and detection device according to an embodiment of the present application;

[0051] Figure 6 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the large model-based vehicle embedded software system requirements analysis and detection method in the embodiment of the present application.

[0052] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solution of the embodiment of the present application is: encapsulating the data acquisition program script to automatically obtain software system requirement data from the cloud, and determining the software system requirement preprocessing data based on the software system requirement data; determining the vehicle-mounted software system requirement analysis detection model and the detection requirement status based on the software system requirement data and the software system requirement preprocessing data; and completing the requirement analysis detection based on the vehicle-mounted software system requirement analysis detection model and the detection requirement status detection system performance.

[0056] In this embodiment, for ease of description, the following description is made by taking the identification of a large-model-based vehicle-mounted embedded software system requirement analysis and detection device as the execution subject.

[0057] Because existing technologies are not only inefficient but also easily affected by human factors, manual analysis is time-consuming and error-prone, making it difficult to ensure the accuracy and consistency of the analysis results. As the complexity of software systems increases, manual analysis methods are increasingly unable to meet the requirements of rapid iteration and continuous integration development models.

[0058] The present application provides a solution, which encapsulates a data acquisition program script to automatically obtain software system requirement data from the cloud, and determines software system requirement preprocessing data based on the software system requirement data; determines an in-vehicle software system requirement analysis detection model and a detection requirement status based on the software system requirement data and the software system requirement preprocessing data; and completes the requirement analysis detection based on the in-vehicle software system requirement analysis detection model and the detection requirement status detection system performance.

[0059] It can be seen from the above embodiments that the present application automatically obtains software system requirement data from the cloud and performs data preprocessing by encapsulating data acquisition program scripts, and uses pre-trained large-scale models to determine the vehicle-mounted software system requirement analysis detection model and detection requirement status, thereby detecting system performance, completing requirement analysis detection, and automating requirement analysis, thereby improving analysis efficiency. By utilizing the learning ability of large models, the accuracy of requirement analysis is improved, and through feedback loops, the analysis model is continuously optimized to adapt to changing software requirements, significantly improving analysis efficiency and quality.

[0060] Based on this, the embodiment of the present application provides a vehicle embedded software system demand analysis and detection method based on a large model, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle embedded software system requirement analysis and detection method based on a large model of the present application.

[0061] In this embodiment, the vehicle embedded software system requirement analysis and detection method based on a large model includes steps S10 to S30:

[0062] Step S10, encapsulating a data acquisition program script to automatically obtain software system requirement data from the cloud, and determining software system requirement preprocessing data based on the software system requirement data;

[0063] It should be noted that the software system requirement data reflects the characteristics of the requirement data obtained by diagnosing the functions and quantifying the system performance, including system diagnosis software requirements, communication system software requirements and storage system software requirements, and the software system requirement preprocessing data reflects the characteristics of the data obtained after preprocessing the software system requirement data.

[0064] In addition, it should be noted that the efficiency of demand analysis can be significantly improved through automated data collection and preprocessing. The preprocessed software demand data can enable the model to understand and analyze software requirements more accurately, thereby improving the quality and reliability of demand analysis.

[0065] For ease of understanding, the following is explained by taking the determination of software system requirement preprocessing data as an example, wherein the information acquisition device is a requirement data collection module, and the storage device is a memory.

[0066] The demand data collection module encapsulates the corresponding data collection automation program script in the background, sends a request to the cloud server each time to automatically obtain the software system requirement file saved in the cloud and preliminarily parses it to obtain relevant useful demand data, that is, uses the data collection program script to automatically obtain system diagnostic software requirement data, communication system software requirement data and storage system software requirement data from the cloud, and determines the software system requirement data based on the system diagnostic software requirement data, the communication system software requirement data and the storage system software requirement data, including system diagnostic software requirements, CAN communication or Ethernet communication system software requirements and storage system software requirements, such as diagnostic software fault code data, CAN communication message signal data, Ethernet communication server or client communication information and storage memory size information of related modules in the storage system, performs text data preprocessing on the software system requirement data, determines the software system requirement preprocessing data, stores the software system requirement preprocessing data in the memory, and performs subsequent processing based on the software system requirement preprocessing data.

[0067] In a feasible implementation, step S10 may include steps A11 to A13:

[0068] Step A11, using the data acquisition program script to automatically obtain system diagnostic software requirement data, communication system software requirement data, and storage system software requirement data from the cloud;

[0069] It is understandable that most of the existing vehicle manufacturers' software system requirements are managed and saved in the cloud. If they are manually downloaded from the cloud each time, the operation process is rather cumbersome. Therefore, a demand data collection module is set up to encapsulate the corresponding data collection automation program script in the background, send a request to the cloud server, and automatically obtain system diagnostic software requirement data, communication system software requirement data, and storage system software requirement data from the cloud, thereby improving the efficiency and quality of source data acquisition.

[0070] Step A12, determining software system requirement data based on the system diagnosis software requirement data, the communication system software requirement data and the storage system software requirement data;

[0071] It is understandable that the automated and intelligent acquisition of software system requirement data reduces manual intervention, reduces errors and omissions caused by human factors, and significantly improves the accuracy of requirement analysis.

[0072] Step A13, performing text data preprocessing on the software system requirement data to determine the software system requirement preprocessing data, wherein the text data preprocessing includes text cleaning, text segmentation and text word vector encoding.

[0073] It can be understood that the text data preprocessing includes text cleaning, text segmentation and text word vector encoding. The purpose of the text cleaning is to remove irrelevant information and retain content that is valuable for analysis. The text segmentation is to divide continuous text strings into meaningful words or phrases. The text word vector encoding is to convert text into numerical form.

[0074] Additionally, it should be noted that the software system requirement preprocessing data may be used to train the vehicle-mounted software system requirement analysis detection model, so that the model can more accurately understand and analyze software requirements, thereby improving the quality and reliability of the requirement analysis.

[0075] Step S20, determining a vehicle-mounted software system requirement analysis detection model and a detection requirement state based on the software system requirement data and the software system requirement preprocessing data;

[0076] It should be noted that the vehicle-mounted software system requirement analysis detection model reflects the characteristics of the ability to intelligently perform software requirement analysis, and the detection requirement status reflects the characteristics of the diagnosed fault abnormality requirement analysis status.

[0077] It is understandable that the vehicle-mounted software system requirement analysis and detection model utilizes advanced machine learning technology, that is, a pre-trained large-scale model, such as GPT, can be selected. The GPT model is first pre-trained based on the software system requirement data, and then the GPT model is fine-tuned based on the software system requirement preprocessing data. The use of the pre-training and fine-tuning framework allows the GPT model to be applied to a variety of downstream tasks, improving the flexibility and adaptability of the analysis model, so that the vehicle-mounted software system requirement analysis and detection model can understand how to generate the corresponding system software requirement analysis and detection application scenarios based on the input data, and solve the problems of system engineers.

[0078] In addition, it should be noted that the detection requirement status can identify which type of diagnostic system requirement it is, including diagnostic fault code system requirement analysis, diagnostic RID system requirement analysis and diagnostic read-write DID system requirement analysis, automatically detect and identify the requirement status, and thus adjust and optimize the model so that the model can adapt to the ever-changing software requirements and environment.

[0079] For ease of understanding, the determination of the vehicle software system demand analysis detection model and the detection demand status are taken as an example for explanation, wherein the information collection device is the demand data collection module, the storage device is the memory, and the processing device is the processing module.

[0080] The demand data collection module obtains software system demand data and software system demand preprocessing data and stores them in a memory, performs pretraining based on the software system demand data to determine a pretraining model, determines a vehicle-mounted software system demand analysis and detection model by fitting the pretraining model based on the software system demand preprocessing data, identifies demand detection scenarios based on the vehicle-mounted software system demand analysis and detection model, and builds an agent execution tool based on the demand detection scenario, that is, realizes automatic parsing in the background code program, encapsulates each demand detection function in the code program in the form of a function, so that it completes automatic detection, such as identifying the demand detection scenario as the fault code redefinition problem in the diagnostic system software requirement, the message signal demand analysis and detection of the CAN communication matrix, and the memory size demand analysis and detection of the storage system software. Each demand detection scenario corresponds to the detection function implementation function of the respective back-end code program, that is, each demand analysis and detection scenario corresponds to an AI AGENT, and the AI ​​AGENT includes four capabilities, namely, building core capabilities, planning capabilities, memory capabilities, and execution tools, and the detection function implementation function of the back-end code program is the execution tool that the AGENT can call. After the back-end execution tool is built, it is necessary to implement the prompt word construction in the analysis model. Based on the vehicle software system requirement analysis detection model, the system performance parameter set can be determined, so that the analysis model can think according to the user's ideas and output the corresponding detection analysis results, that is, based on the agent execution tool to identify the detection requirement status, the detection requirement status includes the diagnostic fault code system requirement analysis status, the diagnostic RID system requirement analysis status and the diagnostic read-write DID system requirement analysis status, and subsequent processing is performed based on the vehicle software system requirement analysis detection model and the detection requirement status.

[0081] In a feasible implementation, step S20 may include steps B11 to B15:

[0082] Step B11, performing pre-training based on the software system requirement data to determine a pre-training model;

[0083] It should be noted that the pre-trained model reflects the characteristics of the model trained in advance through autonomous learning based on the software system requirement data, and is used to capture and understand the complex patterns and semantic information in the vehicle embedded software system requirement data.

[0084] It can be understood that the use of the pre-trained model can quickly adapt to new tasks, reducing the time and resources required to train the model from scratch, and the high-level language understanding ability of the pre-trained model enables it to more accurately identify and analyze complex relationships and potential problems in demand data, thereby improving the quality of demand analysis and enhancing the reliability of the software system and user satisfaction.

[0085] Step B12, determining a vehicle software system requirement analysis and detection model based on fitting the pre-trained model to the software system requirement pre-processing data;

[0086] It can be understood that fine-tuning the pre-trained model based on the pre-processed data of the software system requirements can make the parameters of the model more accurately match the target tasks, more accurately predict and analyze software requirements, thereby improving the quality and efficiency of demand analysis.

[0087] Step B13, identifying demand detection scenarios based on the vehicle software system demand analysis detection model, wherein the demand detection scenarios include system diagnostic software fault code anomalies, communication system software message anomalies, and storage system software storage space anomalies;

[0088] It should be noted that the demand detection scenario reflects the characteristics of the detection scenario obtained by performing anomaly detection on the vehicle software system demand.

[0089] It can be understood that the demand detection scenario can simulate and identify potential software demand problems by conducting in-depth analysis of the preprocessed data, thereby providing system engineers with targeted analysis results and improvement suggestions, providing more accurate and comprehensive demand analysis results, timely discovering and solving potential software problems, and reducing risks and uncertainties in the software system development process.

[0090] Step B14, constructing an agent execution tool based on the demand detection scenario;

[0091] It is understandable that if Figure 2 As shown, Figure 2 A flowchart is constructed for the scenario of the large-model-based vehicle embedded software system requirement analysis and detection method for this application. The tool is defined and submitted to the analysis model through relevant parameters. The analysis model selects the tool through the dialogue content. The analysis model outputs information such as tool parameters. The user is required to execute the tool according to the model output parameters. The user submits the tool execution results to the analysis model, thereby completing the construction of the execution tool.

[0092] Step B15, based on the agent execution tool, identifying the detection requirement status, the detection requirement status includes the diagnostic trouble code system requirement analysis status, the diagnostic system requirement analysis status and the diagnostic read-write system requirement analysis status.

[0093] It can be understood that by accurately and intelligently identifying and detecting the demand status, the efficiency and accuracy of software demand analysis are greatly improved, the dependence on manual analysis is reduced, the error rate is reduced, and the analysis speed is accelerated.

[0094] Step S30, completing the demand analysis detection based on the vehicle software system demand analysis detection model and the detection demand state detection system performance.

[0095] It is understandable that if the detection system performance is poor, the model can be retrained and the system performance can be fine-tuned, and feedback loops and model iterations can be continuously performed to match the system software requirements, reduce possible problems and risks after system deployment, and adapt to changing needs and environments, thereby significantly improving the overall quality of the software system and user experience.

[0096] For ease of understanding, the example of obtaining the vehicle software system demand analysis detection model and detection demand status is used for explanation, wherein the information acquisition device is the demand data collection module, the storage device is the memory, and the execution device is the execution module.

[0097] The demand data collection module obtains a vehicle software system demand analysis detection model, identifies a demand detection scenario based on the vehicle software system demand analysis detection model, and builds an agent execution tool based on the demand detection scenario. After the back-end execution tool is built, it is necessary to implement the prompt word construction in the analysis model. Based on the vehicle software system demand analysis detection model, a system performance parameter set can be determined. The system performance parameter set includes model prompt words and model identification data. Based on the system performance parameter set, the fault problem in the demand analysis state can be redefined to locate the final problem type, such as when the detection demand state is a diagnostic fault code system demand analysis state, the model prompt word is a diagnostic fault code system demand analysis state, and the diagnostic fault code filling format specification detection analysis, fault code attribute detection analysis, and whether the diagnostic fault code is redefined analysis detection, the fault problem is finally located based on the model prompt word, the software demand analysis result is determined based on the vehicle software system demand analysis detection model and the detection demand state, and the system performance is verified based on the vehicle software system demand analysis detection model and the software demand analysis result. Adjust the system performance parameter set to complete the demand analysis detection.

[0098] The present application proposes a method for analyzing and detecting vehicle-mounted embedded software system requirements based on a large model, which encapsulates a data acquisition program script to automatically obtain software system requirement data from the cloud, determines software system requirement preprocessing data based on the software system requirement data; determines a vehicle-mounted software system requirement analysis detection model and a detection requirement state based on the software system requirement data and the software system requirement preprocessing data; and detects system performance based on the vehicle-mounted software system requirement analysis detection model and the detection requirement state to complete the requirement analysis detection. The technical problems of low efficiency and difficulty in ensuring accuracy of software requirement analysis are solved. Compared with the prior art, the present application automatically obtains software system requirement data from the cloud by encapsulating a data acquisition program script, and performs preprocessing based on these data to determine the preprocessing data, and then uses these data to determine the vehicle-mounted software system requirement analysis detection model and the detection requirement state, thereby detecting system performance to complete the requirement analysis detection, and improves the analysis efficiency and accuracy through automation and intelligent means, reduces human errors, and improves the overall quality of the software system and user experience.

[0099] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated later.

[0100] In this embodiment, refer to Figure 3 , Figure 3 The flowchart of the second embodiment of the vehicle embedded software system requirement analysis and detection method based on a large model of the present application is provided, and step S30 specifically includes steps S31 to S33:

[0101] Step S31, obtaining a system performance parameter set, wherein the system performance parameter set includes a model prompt word and a model recognition data;

[0102] It should be noted that the system performance parameter set reflects the characteristics of the performance state of the vehicle software system during operation.

[0103] It is understandable that by adjusting the system performance parameter set, the stability and reliability of the software system can be improved, ensuring that the software system can adapt to changing needs and environments, and improving overall development efficiency and user satisfaction.

[0104] For ease of understanding, the example of obtaining a system performance parameter set is used for explanation, wherein the information collection device is a demand data collection module, the storage device is a memory, and the execution device is an execution module.

[0105] The demand data collection module obtains the vehicle software system demand analysis and detection model, identifies the demand detection scenario based on the vehicle software system demand analysis and detection model, and builds an agent execution tool based on the demand detection scenario. After the back-end execution tool is built, it is necessary to implement the prompt word construction in the analysis model. Based on the vehicle software system demand analysis and detection model, the system performance parameter set can be determined. The system performance parameter set includes model prompt words and model identification data, and subsequent processing is performed based on the system performance parameter set.

[0106] Step S32, determining a software requirement analysis result based on the vehicle-mounted software system requirement analysis detection model and the detection requirement state;

[0107] It should be noted that the software requirement analysis result reflects the characteristics of the specific fault state detected.

[0108] It can be understood that by determining the software requirement analysis results, potential software problems can be quickly identified and fixed, reducing the cost and time of subsequent modifications, and providing clear feedback to guide the optimization and improvement of the software system.

[0109] For ease of understanding, the following is explained by taking determining software requirement analysis results as an example, wherein the information collection device is a requirement data collection module, the storage device is a memory, and the execution device is an execution module.

[0110] The demand data collection module obtains the vehicle software system demand analysis detection model and the detection demand status, analyzes the detection demand status based on the vehicle software system demand analysis detection model to locate the fault anomaly, determines the fault prompt word, and obtains the software demand analysis result by graphically displaying the fault prompt word.

[0111] The fault problem is finally located based on the model prompt word, and the software requirement analysis results are determined based on the vehicle-mounted software system requirement analysis detection model and the detection requirement status, such as requirement change detection analysis results, risk prediction analysis results, anomaly detection analysis results, priority assessment analysis results and resource allocation suggestion analysis results. The requirement change detection analysis result is to output the newly added system software requirements and the differences between this version of the software requirements and the previous version of the software requirements. The risk prediction analysis result is that through the analysis of historical software requirement data, the large model can predict the risks and problems that may be encountered in the software system development process, thereby informing the user to adjust the software system requirements. The anomaly detection analysis result is that the model can identify abnormal patterns in the system software requirement data, and these anomalies may indicate potential software design defects or implementation problems. The priority assessment analysis result is based on the analysis result of the model, and the identified system software requirements can be prioritized to determine which requirements are the most important and which requirements can be postponed or optimized. The resource allocation suggestion analysis result is based on the priority of the requirements and the project resources. The model can provide resource allocation suggestions to help the software development project team plan and execute projects more effectively.

[0112] In a feasible implementation, step S32 may include steps C11 to C12:

[0113] Step C11, analyzing the detection requirement state based on the vehicle software system requirement analysis detection model to locate the fault anomaly and determine the fault prompt word;

[0114] It should be noted that the fault prompt word reflects the characteristics of the type of fault that is prompted.

[0115] It can be understood that based on the fault prompt words, fault anomalies in the system can be accurately identified, thereby significantly improving the response speed and processing efficiency of system faults, quickly and accurately identifying problems in the system, avoiding the spread and amplification of problems, and thus reducing potential risks and losses.

[0116] Step C12, obtaining software requirement analysis results by graphically displaying the fault prompt words.

[0117] It is understandable that the final system software requirement analysis results are presented to users in a graphical manner, including requirement change detection analysis results, risk prediction analysis results, anomaly detection analysis results, priority assessment analysis results and resource allocation recommendation analysis results. The PyQT5 library can be used to create and develop a corresponding interactive interface, allowing users to interact with the analysis results of the model, and display the analysis results in charts, graphs or other visual formats, so that system engineers with non-technical backgrounds can also fully understand the requirement analysis results.

[0118] Step S33, verifying the system performance based on the vehicle software system demand analysis detection model and the software demand analysis result, and adjusting the system performance parameter set to complete the demand analysis detection.

[0119] It can be understood that a feedback loop can be obtained based on the vehicle software system requirement analysis detection model and the software requirement analysis results to verify the system performance. The feedback loop is evaluated based on the software requirement analysis results, allowing users to directly feedback on the model analysis results for retraining the model and fine-tuning the system performance.

[0120] In addition, it should be noted that after retraining, the analysis model is tested and evaluated again, and the model is redeployed after verifying the changes to characterize the better performance of the model, that is, to report new real data for demand analysis, thereby improving the user experience, and then the analysis model is continuously monitored using indicators to identify potential deterioration characteristics, such as drift. At this time, a feedback loop is continuously performed to ensure that the analysis model can adapt to new system software demand data and environmental changes.

[0121] For ease of understanding, the following is explained by taking the completion of demand analysis and testing as an example, wherein the information collection device is a demand data collection module, the storage device is a memory, and the execution device is an execution module.

[0122] The requirement data collection module obtains the number of model iterations and model generation prompt words. If the model generation prompt words are not accurate enough, the analysis scenario in the model analysis process will be inaccurate and there will be an offset. The prompt word generation fine-tuning is performed, that is, when the software requirement analysis result shows that the model generation prompt words are inaccurate, the model prompt words are adjusted.

[0123] If there is a problem with redefining fault codes or there is a problem with storage space system requirements, such as there are requirements for the use of the same fault code in three functional domains, but the model only recognizes that the fault code has duplication problems and cannot locate which functional domains have duplication of fault code requirements, the input data is fine-tuned. At this time, the functional domain source of each fault code is added to more accurately analyze and locate the problem. For example, there are inconsistent memory space allocation plans for different models, and one plan is not suitable for multiple memory demand allocations. The analysis system is fine-tuned and more vehicle model memory allocation plan data is added to allow the recognition and detection results to adapt to multi-model projects. That is, when the software requirement analysis result is that the model recognition function is repeated, the model recognition data is adjusted.

[0124] The vehicle-mounted software system requirement analysis and detection model is retrained based on the number of model iterations to determine a vehicle-mounted software system requirement analysis and detection optimization model, the vehicle-mounted software system requirement analysis and detection optimization model is scored to determine a scoring index, and the vehicle-mounted software system requirement analysis and detection optimization model is redeployed based on the scoring index to perform requirement analysis and detection.

[0125] In a feasible implementation, step S33 may include steps D11 to D14:

[0126] Step D11, obtaining the number of model iterations;

[0127] It should be noted that the number of model iterations reflects the characteristics of the number of times the model is cyclically trained.

[0128] It can be understood that training a model based on the number of model iterations can adapt to the latest changes in software system requirements, and is used to improve the model's predictive accuracy and analysis quality, thereby making software requirement analysis more reliable, and enhancing the model's generalization capabilities, so that it can make accurate analysis and predictions when faced with unknown or new software requirement data, continuously optimize and iterate the model, and ultimately improve the quality and performance of the software system, reduce the risks caused by changes in requirements, and enhance users' trust and satisfaction with the software system.

[0129] Step D12, when the software requirement analysis result shows that the model-generated prompt words are inaccurate, adjusting the model prompt words;

[0130] It is understandable that the prompt words generated by the model directly affect the accuracy and efficiency of the software requirement analysis. When the prompt words generated by the model are inaccurate, it will lead to deviations in the requirements analysis results, and the analysis scenario will be imprecise and offset. By adjusting the prompt words generated by the model, the accuracy and efficiency of the software requirement analysis can be improved.

[0131] Step D13, when the software requirement analysis result is that the model identification function is repeated, adjusting the model identification data;

[0132] It is understandable that adjusting the model identification data can increase the analysis data of the selection plan to accurately identify abnormal problems, thereby making the requirements analysis results more reliable, and improving the accuracy of the entire requirements analysis detection process, reducing the risks caused by changes in requirements, and enhancing users' trust and satisfaction with the software system.

[0133] Step D14, when the software requirement analysis result is direct feedback from the user, retrain the vehicle-mounted software system requirement analysis detection model based on the number of model iterations, and perform requirement analysis detection.

[0134] It is understandable that the vehicle software system requirement analysis detection model can be retrained based on direct feedback from users and combined with the number of model iterations, thereby significantly improving the adaptability and accuracy of the model, improving user satisfaction, and improving the overall quality and performance of the system.

[0135] In a feasible implementation, step D14 may include steps E11 to E13:

[0136] Step E11, retraining the vehicle software system requirement analysis detection model based on the number of model iterations to determine the vehicle software system requirement analysis detection optimization model;

[0137] It should be noted that the vehicle-mounted software system demand analysis detection optimization model reflects the characteristics of the model optimized after multiple iterations and user feedback.

[0138] It is understandable that retraining the vehicle software system requirement analysis detection model based on the number of model iterations can significantly improve the adaptability and accuracy of the model, which can not only improve the efficiency of software requirement analysis, but also make the analysis results more in line with the actual needs of users, thereby improving user satisfaction and improving the overall quality and performance of the software system.

[0139] Step E12, scoring the vehicle software system requirement analysis detection optimization model to determine a scoring index;

[0140] It should be noted that the scoring indicators reflect the characteristics of the performance score of the vehicle software system requirement analysis detection optimization model after retraining.

[0141] It can be understood that the scoring indicators can quantify the performance of the model, including the accuracy, response time and predictive ability of the model. By scoring the vehicle software system demand analysis, detection and optimization model, the performance and effect of the model can be objectively evaluated, so as to carry out targeted optimization and improvement.

[0142] Step E13, redeploying the vehicle software system requirement analysis and detection optimization model to perform requirement analysis and detection based on the scoring index.

[0143] It can be understood that by scoring the vehicle software system requirement analysis detection optimization model and redeploying the model based on the scoring indicators, the performance and effect of the model in actual applications can be ensured, and the accuracy and efficiency of software requirement analysis can be improved.

[0144] The present application proposes a large-model-based vehicle embedded software system requirement analysis and detection method, which obtains a system performance parameter set, the system performance parameter set including model prompt words and model recognition data; determines the software requirement analysis result based on the vehicle software system requirement analysis detection model and the detection requirement state; verifies the system performance based on the vehicle software system requirement analysis detection model and the software requirement analysis result, and adjusts the system performance parameter set to complete the requirement analysis detection. The technical problem of how to perform intelligent requirement analysis more accurately is solved. Compared with the prior art, the present application automatically obtains the system performance parameter set, including model prompt words and model recognition data, uses the vehicle software system requirement analysis detection model and the detection requirement state to determine the software requirement analysis result, thereby verifying the system performance and adjusting the system performance parameter set, optimizing the model based on the number of iterations, completing the requirement analysis detection, significantly improving the accuracy of the requirement analysis, making the system performance more stable and reliable, while reducing human intervention and improving the development efficiency and quality of the software system.

[0145] For example, in order to help understand the implementation process of the vehicle embedded software system requirement analysis and detection method based on a large model obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 4 , Figure 4 A brief flow chart of a large model-based vehicle embedded software system requirements analysis and detection method is provided, specifically:

[0146] Automatically collect system software requirement data, preprocess software requirement data, train software requirement analysis model, automatically identify analysis requirements based on model, and output analysis results in graphical form. See Example 1, encapsulate data acquisition program script to automatically obtain software system requirement data from the cloud, determine software system requirement preprocessing data based on the software system requirement data; determine the vehicle-mounted software system requirement analysis detection model and detection requirement status based on the software system requirement data and the software system requirement preprocessing data; and complete requirement analysis detection based on the vehicle-mounted software system requirement analysis detection model and the detection requirement status detection system performance.

[0147] Verify the analysis model to see whether it meets business requirements, deploy the model online, and iterate the model optimization. Refer to Example 2 to obtain a system performance parameter set, which includes model prompt words and model recognition data; determine the software requirement analysis result based on the vehicle-mounted software system requirement analysis detection model and the detection requirement status; verify the system performance based on the vehicle-mounted software system requirement analysis detection model and the software requirement analysis result, and adjust the system performance parameter set to complete the requirement analysis detection.

[0148] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the large-model-based vehicle-mounted embedded software system requirement analysis and detection method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0149] This application also provides a vehicle-mounted embedded software system demand analysis and detection device based on a large model, please refer to Figure 5 The vehicle-mounted embedded software system requirements analysis and detection device based on a large model includes:

[0150] An acquisition module 10 is used to encapsulate a data acquisition program script to automatically acquire software system requirement data from the cloud, and determine software system requirement preprocessing data based on the software system requirement data;

[0151] A processing module 20, configured to determine a vehicle-mounted software system requirement analysis detection model and a detection requirement state based on the software system requirement data and the software system requirement preprocessing data;

[0152] The execution module 30 is used to complete the demand analysis detection based on the vehicle software system demand analysis detection model and the detection demand state detection system performance.

[0153] The acquisition module 10 is further used to automatically acquire system diagnostic software requirement data, communication system software requirement data and storage system software requirement data from the cloud using the data acquisition program script;

[0154] Determining software system requirement data based on the system diagnostic software requirement data, the communication system software requirement data and the storage system software requirement data;

[0155] The software system requirement data is subjected to text data preprocessing to determine the software system requirement preprocessing data, wherein the text data preprocessing includes text cleaning, text segmentation and text word vector encoding.

[0156] The processing module 20 is further used to perform pre-training based on the software system requirement data to determine a pre-training model;

[0157] Determine a vehicle software system requirement analysis and detection model based on fitting the pre-trained model to the software system requirement preprocessing data;

[0158] Identify demand detection scenarios based on the vehicle software system demand analysis detection model, where the demand detection scenarios include system diagnostic software fault code anomalies, communication system software message anomalies, and storage system software storage space anomalies;

[0159] Building an agent execution tool based on the demand detection scenario;

[0160] Based on the agent execution tool identifying the detection requirement status, the detection requirement status includes a diagnostic trouble code system requirement analysis status, a diagnostic system requirement analysis status and a diagnostic read-write system requirement analysis status.

[0161] The execution module 30 is further used to obtain a system performance parameter set, wherein the system performance parameter set includes a model prompt word and a model recognition data;

[0162] Determine a software requirement analysis result based on the vehicle software system requirement analysis detection model and the detection requirement status;

[0163] The system performance is verified based on the vehicle software system demand analysis detection model and the software demand analysis result to adjust the system performance parameter set to complete the demand analysis detection.

[0164] The execution module 30 is further used to analyze the detection requirement state based on the vehicle software system requirement analysis detection model to locate the fault anomaly and determine the fault prompt word;

[0165] The software requirement analysis result is obtained by performing graphical display based on the fault prompt words.

[0166] The execution module 30 is also used to obtain the number of model iterations;

[0167] When the software requirement analysis result shows that the model-generated prompt words are inaccurate, adjusting the model prompt words;

[0168] When the software requirement analysis result indicates that the model identification function is repeated, adjusting the model identification data;

[0169] When the software requirement analysis result is direct feedback from the user, the vehicle-mounted software system requirement analysis detection model is retrained based on the number of model iterations, and the requirement analysis detection is performed.

[0170] The execution module 30 is further used to retrain the vehicle software system requirement analysis detection model based on the number of model iterations to determine the vehicle software system requirement analysis detection optimization model;

[0171] Scoring the vehicle software system requirement analysis detection optimization model to determine a scoring index;

[0172] Based on the scoring index, the vehicle-mounted software system demand analysis and detection optimization model is redeployed to perform demand analysis and detection.

[0173] The large-model-based vehicle-mounted embedded software system requirement analysis and detection device provided by the present application adopts the large-model-based vehicle-mounted embedded software system requirement analysis and detection method in the above-mentioned embodiment, which can solve the technical problem of how to intelligently perform software requirement analysis to improve analysis efficiency and accuracy. Compared with the prior art, the beneficial effects of the large-model-based vehicle-mounted embedded software system requirement analysis and detection device provided by the present application are the same as the beneficial effects of the large-model-based vehicle-mounted embedded software system requirement analysis and detection method provided by the above-mentioned embodiment, and the other technical features of the large-model-based vehicle-mounted embedded software system requirement analysis and detection device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0174] The present application provides a large-model-based vehicle-mounted embedded software system requirement analysis and detection device, and the large-model-based vehicle-mounted embedded software system requirement analysis and detection device includes: at least one processor; and 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 so that the at least one processor can execute the large-model-based vehicle-mounted embedded software system requirement analysis and detection method in the above-mentioned embodiment one.

[0175] Reference below Figure 6 , which shows a schematic diagram of the structure of a large-model-based vehicle-mounted embedded software system requirement analysis and detection device suitable for implementing the embodiment of the present application. The large-model-based vehicle-mounted embedded software system requirement analysis and detection device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), PMPs (Portable Media Players: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The large model-based vehicle-mounted embedded software system requirement analysis and detection device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0176] like Figure 6As shown, the vehicle-mounted embedded software system requirement analysis detection device based on the large model may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: ReadOnly Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: RandomAccess Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle-mounted embedded software system requirement analysis detection device based on the large model are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the large-model-based vehicle-mounted embedded software system requirement analysis and detection device to communicate wirelessly or wired with other devices to exchange data. Although the large-model-based vehicle-mounted embedded software system requirement analysis and detection device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0177] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0178] The large-model-based vehicle-mounted embedded software system requirement analysis and detection device provided by the present application adopts the large-model-based vehicle-mounted embedded software system requirement analysis and detection method in the above-mentioned embodiment, which can solve the technical problem of how to intelligently perform software requirement analysis to improve analysis efficiency and accuracy. Compared with the prior art, the beneficial effects of the large-model-based vehicle-mounted embedded software system requirement analysis and detection device provided by the present application are the same as the beneficial effects of the large-model-based vehicle-mounted embedded software system requirement analysis and detection method provided by the above-mentioned embodiment, and the other technical features in the large-model-based vehicle-mounted embedded software system requirement analysis and detection device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0179] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0180] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0181] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the large model-based vehicle-mounted embedded software system requirements analysis and detection method in the above-mentioned embodiment.

[0182] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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 above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0183] The above-mentioned computer-readable storage medium can be included in the large-model-based vehicle-mounted embedded software system requirement analysis and detection device; or it can exist independently without being assembled into the large-model-based vehicle-mounted embedded software system requirement analysis and detection device.

[0184] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the large-model-based vehicle-mounted embedded software system requirement analysis and detection device, the large-model-based vehicle-mounted embedded software system requirement analysis and detection device: encapsulates the data acquisition program script to automatically obtain software system requirement data from the cloud, and determines the software system requirement preprocessing data based on the software system requirement data; determines the vehicle-mounted software system requirement analysis and detection model and the detection requirement status based on the software system requirement data and the software system requirement preprocessing data; and completes the requirement analysis and detection of system performance based on the vehicle-mounted software system requirement analysis and detection model and the detection requirement status.

[0185] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0186] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0187] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0188] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned large-model-based vehicle embedded software system requirements analysis and detection method, and can solve the technical problem of how to intelligently perform software requirements analysis to improve analysis efficiency and accuracy. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the large-model-based vehicle embedded software system requirements analysis and detection method provided by the above-mentioned embodiment, and will not be repeated here.

[0189] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A large model-based vehicle embedded software system requirements analysis and detection method, characterized in that: The method comprises: Encapsulate a data acquisition program script to automatically obtain software system requirement data from the cloud, and determine software system requirement preprocessing data based on the software system requirement data; Determine a vehicle software system requirement analysis detection model and a detection requirement state based on the software system requirement data and the software system requirement preprocessing data; The demand analysis detection is completed based on the vehicle software system demand analysis detection model and the detection demand status detection system performance.

2. The method according to claim 1, characterized in that The encapsulated data acquisition program script automatically obtains software system requirement data from the cloud, and the steps of determining software system requirement preprocessing data based on the software system requirement data include: Utilize the data acquisition program script to automatically obtain system diagnostic software requirement data, communication system software requirement data, and storage system software requirement data from the cloud; Determining software system requirement data based on the system diagnostic software requirement data, the communication system software requirement data and the storage system software requirement data; The software system requirement data is subjected to text data preprocessing to determine the software system requirement preprocessing data, wherein the text data preprocessing includes text cleaning, text segmentation and text word vector encoding.

3. The method according to claim 1, characterized in that The step of determining the vehicle software system requirement analysis detection model and detecting the requirement status based on the software system requirement data and the software system requirement preprocessing data comprises: Perform pre-training based on the software system requirement data to determine a pre-training model; Determine a vehicle software system requirement analysis and detection model based on fitting the pre-trained model to the software system requirement preprocessing data; Identify demand detection scenarios based on the vehicle software system demand analysis detection model, where the demand detection scenarios include system diagnostic software fault code anomalies, communication system software message anomalies, and storage system software storage space anomalies; Building an agent execution tool based on the demand detection scenario; Based on the agent execution tool identifying the detection requirement status, the detection requirement status includes a diagnostic trouble code system requirement analysis status, a diagnostic system requirement analysis status and a diagnostic read-write system requirement analysis status.

4. The method according to claim 1, characterized in that The step of completing the demand analysis detection based on the vehicle software system demand analysis detection model and the detection demand state detection system performance includes: Acquire a system performance parameter set, wherein the system performance parameter set includes a model prompt word and a model recognition data; Determine a software requirement analysis result based on the vehicle software system requirement analysis detection model and the detection requirement status; The system performance is verified based on the vehicle software system demand analysis detection model and the software demand analysis result to adjust the system performance parameter set to complete the demand analysis detection.

5. The method according to claim 4, characterized in that The step of determining the software requirement analysis result based on the vehicle software system requirement analysis detection model and the detection requirement state comprises: Analyze the detection requirement status based on the vehicle software system requirement analysis detection model to locate the fault anomaly and determine the fault prompt word; The software requirement analysis result is obtained by performing graphical display based on the fault prompt words.

6. The method according to claim 4, characterized in that The step of verifying system performance based on the vehicle software system demand analysis detection model and the software demand analysis result and adjusting the system performance parameter set to complete demand analysis detection includes: Get the number of model iterations; When the software requirement analysis result shows that the model-generated prompt words are inaccurate, adjusting the model prompt words; When the software requirement analysis result indicates that the model identification function is repeated, adjusting the model identification data; When the software requirement analysis result is direct feedback from the user, the vehicle-mounted software system requirement analysis detection model is retrained based on the number of model iterations, and the requirement analysis detection is performed.

7. The method according to claim 6, characterized in that The step of retraining the vehicle software system demand analysis detection model based on the number of model iterations and performing demand analysis detection includes: Retrain the vehicle software system requirement analysis detection model based on the number of model iterations to determine the vehicle software system requirement analysis detection optimization model; Scoring the vehicle software system requirement analysis detection optimization model to determine a scoring index; Based on the scoring index, the vehicle-mounted software system demand analysis and detection optimization model is redeployed to perform demand analysis and detection.

8. A vehicle-mounted embedded software system requirements analysis and detection device based on a large model, characterized in that: The device comprises: An acquisition module, used to encapsulate a data acquisition program script to automatically acquire software system requirement data from the cloud, and determine software system requirement preprocessing data based on the software system requirement data; A processing module, used to determine a vehicle software system requirement analysis detection model and a detection requirement state based on the software system requirement data and the software system requirement preprocessing data; An execution module is used to complete the demand analysis detection based on the vehicle software system demand analysis detection model and the detection demand state detection system performance.

9. A vehicle-mounted embedded software system requirements analysis and detection device based on a large model, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the large model-based vehicle embedded software system requirement analysis and detection method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the large model-based vehicle embedded software system requirement analysis and detection method as described in any one of claims 1 to 7 are implemented.

Images