Vehicle diagnosis report generation method and device, equipment and storage medium

Abstract

The invention discloses a vehicle diagnosis report generation method and device, equipment and a storage medium, and relates to the technical field of vehicle diagnosis, and the vehicle diagnosis report generation method comprises the steps: obtaining a first vehicle scanning result and a current vehicle diagnosis state; inputting the first vehicle scanning result and the current vehicle diagnosis state into a vehicle diagnosis analysis model to obtain a first vehicle diagnosis analysis result; and based on the current vehicle diagnosis state, inputting the first vehicle diagnosis analysis result into a vehicle diagnosis report generation model to obtain a vehicle diagnosis report. According to the method, the vehicle diagnosis data is analyzed and the report is generated through multiple models, so that the deep cause analysis of the vehicle fault is realized, the vehicle diagnosis report is flexibly generated, and the generation quality and efficiency of the diagnosis report are improved.

Description

Technical Field

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

[0002] In the field of modern automobile maintenance, technicians rely on automobile diagnostic equipment to directly generate diagnostic reports, which results in incomplete content of diagnostic reports and lack of analysis of the deep-seated causes of vehicle failures. At the same time, the page layout of the report is fixed and lacks flexibility, and cannot be adjusted according to the specific fault situation or the needs of technicians. Therefore, the existing diagnostic report generation quality and efficiency are not high, and cannot meet the growing demand for automobile maintenance professionalism and efficiency. Summary of the invention

[0003] The main purpose of this application is to provide a vehicle diagnostic report generation method, device, equipment and storage medium, aiming to solve the problem that the existing diagnostic report generation quality and efficiency are low and cannot meet the growing demand for automobile maintenance professionalism and efficiency.

[0004] To achieve the above objectives, the present application proposes a method for generating a vehicle diagnostic report, the method comprising:

[0005] Obtaining a first vehicle scan result and a current vehicle diagnostic status;

[0006] Inputting the first vehicle scanning result and the current vehicle diagnostic state into a vehicle diagnostic analysis model to obtain a first vehicle diagnostic analysis result;

[0007] Based on the current vehicle diagnostic state, the first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report.

[0008] In one embodiment, obtaining the first vehicle scanning result includes:

[0009] Obtain the target vehicle's fault code information and vehicle real-time data stream data within the preset recording time;

[0010] Extracting the fault code information and the vehicle fault data in the vehicle real-time data stream data;

[0011] The vehicle fault data are associated and combined to generate a first vehicle scanning result.

[0012] In one embodiment, the training process of the vehicle diagnostic analysis model includes:

[0013] Obtaining second vehicle scanning results of several groups of normal vehicles;

[0014] Extracting features from each of the second vehicle scanning results to obtain vehicle feature data;

[0015] Each of the vehicle feature data is input into an initial vehicle diagnosis and analysis model for iterative training to obtain the vehicle diagnosis and analysis model.

[0016] In one embodiment, extracting features from each second vehicle scanning result to obtain vehicle feature data includes:

[0017] performing data preprocessing on each of the second vehicle scanning results;

[0018] Vectorizing the preprocessed second vehicle scanning results to generate a plurality of groups of third vehicle scanning results;

[0019] Feature extraction is performed on each of the third vehicle scanning results to obtain vehicle feature data.

[0020] In one embodiment, the training process of the vehicle diagnostic report generation model includes:

[0021] Obtain several groups of historical vehicle diagnostic reports and historical report configuration information;

[0022] Each of the historical vehicle diagnostic reports and the historical report configuration information is input into an initial vehicle diagnostic report generation model for iterative training to obtain the vehicle diagnostic report generation model.

[0023] In one embodiment, the current vehicle diagnostic state includes a vehicle pre-maintenance state and a vehicle post-maintenance state;

[0024] The step of inputting the first vehicle diagnostic analysis result into a vehicle diagnostic report generation model based on the current vehicle diagnostic state to obtain a vehicle diagnostic report includes:

[0025] If the current vehicle diagnostic state is a vehicle pre-maintenance state, temporarily storing the second vehicle diagnostic analysis result corresponding to the vehicle pre-maintenance state in a preset database;

[0026] Acquire a third vehicle diagnostic analysis result of a vehicle post-maintenance state corresponding to the vehicle pre-maintenance state, and associate and integrate the second vehicle diagnostic analysis result with the third vehicle diagnostic analysis result to generate a first vehicle diagnostic analysis result;

[0027] The first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report.

[0028] In one embodiment, after inputting the first vehicle diagnostic analysis result into a vehicle diagnostic report generation model based on the current vehicle diagnostic state to obtain a vehicle diagnostic report, the method further includes:

[0029] Get report optimization suggestions from vehicle maintenance technicians;

[0030] Based on the report optimization suggestions, the vehicle diagnostic analysis model and the vehicle diagnostic report generation model are optimized.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle diagnostic report generating device, the vehicle diagnostic report generating device comprising:

[0032] An information acquisition module, used to obtain the first vehicle scanning result and the current vehicle diagnostic status;

[0033] A diagnostic analysis module, configured to input the first vehicle scanning result and the current vehicle diagnostic state into a vehicle diagnostic analysis model to obtain a first vehicle diagnostic analysis result;

[0034] The report generation module is used to input the first vehicle diagnosis analysis result into a vehicle diagnosis report generation model based on the current vehicle diagnosis state to obtain a vehicle diagnosis report.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle diagnostic report generating device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the vehicle diagnostic report generating method described above.

[0036] 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 vehicle diagnostic report generation method described above are implemented.

[0037] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the vehicle diagnostic report generation method described above are implemented.

[0038] The present application provides a vehicle diagnostic report generation method, apparatus, device and storage medium. The vehicle diagnostic report generation method obtains a first vehicle scan result and a current vehicle diagnostic status, and then inputs the first vehicle scan result and the current vehicle diagnostic status into a vehicle diagnostic analysis model to obtain a first vehicle diagnostic analysis result. Based on the current vehicle diagnostic status, the first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report, thereby achieving an in-depth analysis of the causes of vehicle failures, and flexibly generating a vehicle diagnostic report, thereby improving the generation quality and efficiency of the diagnostic report. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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.

[0040] 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 work.

[0041] Figure 1 A flow chart of the first embodiment of the method for generating a vehicle diagnostic report of the present application;

[0042] Figure 2 A flow chart of the second embodiment of the vehicle diagnostic report generation method of the present application;

[0043] Figure 3 A flowchart of the third embodiment of the vehicle diagnostic report generation method of the present application is provided;

[0044] Figure 4 A flowchart of a fourth embodiment of the method for generating a vehicle diagnostic report of the present application is provided;

[0045] Figure 5 This is a schematic diagram of the module structure of the vehicle diagnostic report generating device according to an embodiment of the present application;

[0046] Figure 6 A schematic diagram of the device structure of the hardware operating environment involved in the vehicle diagnostic report generation method in the embodiment of the present application.

[0047] 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

[0048] 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.

[0049] 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.

[0050] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a big data service platform, a vehicle diagnostic report generation system, etc. The following takes the vehicle diagnostic report generation system as an example to illustrate this embodiment and the following embodiments.

[0051] Based on this, the embodiment of the present application provides a method for generating a vehicle diagnostic report, referring to Figure 1 , Figure 1 A flowchart diagram of the first embodiment of the method for generating a vehicle diagnostic report of the present application is provided.

[0052] In this embodiment, the vehicle diagnostic report generation method includes steps S11 to S13:

[0053] Step S11, obtaining the first vehicle scanning result and the current vehicle diagnostic status;

[0054] It should be noted that the first vehicle scanning result refers to the result obtained after a system scan of the vehicle that requires vehicle diagnosis, including fault codes, sensor readings, actuator status, real-time data streams (such as speed, temperature, pressure, etc.), vehicle usage history data, etc., without limitation here.

[0055] It should be further explained that the current vehicle diagnostic status refers to the current diagnostic status of the vehicle, such as before and after maintenance, where the maintenance behavior includes the status before and after daily component diagnosis of the vehicle, the status before and after updating the vehicle computer module, the status before and after vehicle maintenance, etc. There is no restriction here and it can be set according to actual conditions.

[0056] Specifically, the fault code information and vehicle real-time data stream data of the target vehicle within a preset recording time are obtained, and then the vehicle fault data in the fault code information and the vehicle real-time data stream data are extracted, so as to associate and combine each of the vehicle fault data to generate a first vehicle scanning result.

[0057] Step S12, inputting the first vehicle scanning result and the current vehicle diagnostic state into a vehicle diagnostic analysis model to obtain a first vehicle diagnostic analysis result;

[0058] It should be noted that the vehicle diagnostic analysis model is an algorithm or software model used to analyze vehicle scan results and diagnostic status, and is intended to identify problems and patterns from vehicle data. In addition, the first vehicle diagnostic analysis result refers to the output result obtained after processing by the vehicle diagnostic analysis model, including fault diagnosis conclusion, diagnosis cause, recommended maintenance measures, maintenance priority, estimated maintenance cost, etc.

[0059] Step S13: Based on the current vehicle diagnostic state, the first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report.

[0060] It should be noted that the vehicle diagnostic report generation model refers to a system that generates a formal report based on the diagnostic analysis results, and is used to convert technical data into an easy-to-understand report.

[0061] It should be further explained that the vehicle diagnostic report refers to a detailed report ultimately provided to users (such as technicians and car owners), including basic vehicle information (vehicle identification number (VIN), model, year of manufacture, etc.), fault diagnosis (fault description, fault code list, possible cause analysis), maintenance suggestions (recommended repair measures, replacement parts, repair steps), performance data (charts and trend analysis of key performance parameters), safety tips (safe driving suggestions based on diagnostic results), maintenance history (vehicle maintenance records and historical fault codes), cost estimates (estimated repair costs and time), follow-up action suggestions (suggestions for follow-up maintenance and inspections), and other information, thereby providing a more comprehensive and in-depth analysis perspective to help users understand the condition of the vehicle and provide a reference for the user's repair and maintenance work.

[0062] Specifically, if the current vehicle diagnostic state is the vehicle pre-maintenance state, the second vehicle diagnostic analysis result corresponding to the vehicle pre-maintenance state is temporarily stored in a preset database, and then the third vehicle diagnostic analysis result of the vehicle post-maintenance state corresponding to the vehicle pre-maintenance state is obtained, and the second vehicle diagnostic analysis result is associated and integrated with the third vehicle diagnostic analysis result to generate a first vehicle diagnostic analysis result, and then the first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report.

[0063] This embodiment obtains the first vehicle scan result and the current vehicle diagnostic status, and then inputs the first vehicle scan result and the current vehicle diagnostic status into the vehicle diagnostic analysis model to obtain the first vehicle diagnostic analysis result, and then based on the current vehicle diagnostic status, the first vehicle diagnostic analysis result is input into the vehicle diagnostic report generation model to obtain a vehicle diagnostic report, thereby realizing in-depth analysis of the causes of vehicle failures, more accurately identifying specific problems of the vehicle, improving diagnostic accuracy, and being able to generate more personalized and relevant reports based on the current diagnostic status, thereby improving the practicality and pertinence of the report, thereby significantly reducing the workload of technicians, shortening diagnostic time, and improving work efficiency. In addition, by analyzing the vehicle diagnostic status through a large model, potential problems and failures can be predicted, predictive maintenance can be achieved, and unexpected failures can be reduced.

[0064] Based on this, the embodiment of the present application provides a method for generating a vehicle diagnostic report, referring to Figure 2 , Figure 2 A flow chart of the second embodiment of the vehicle diagnostic report generation method of the present application is provided.

[0065] In a feasible implementation manner, obtaining the first vehicle scanning result includes:

[0066] Step S21, obtaining the fault code information of the target vehicle and the real-time data stream data of the vehicle within a preset recording time;

[0067] It should be noted that the preset recording time refers to a specific time period set for collecting and analyzing data, including the most recent day or week, depending on the purpose and needs of the analysis, and is not limited here. In addition, the target vehicle refers to a specific vehicle that needs to be monitored, diagnosed or analyzed.

[0068] It should be further explained that the fault code information refers to the diagnostic trouble code (DTC) recorded by the vehicle control module (ECU) when an abnormal situation is detected, including the fault code, fault description, detection time, fault severity level, etc.

[0069] Furthermore, the vehicle real-time data stream data refers to data collected in real time from the vehicle's sensors and control units, including: engine performance parameters: such as speed (RPM), intake manifold pressure (MAP), coolant temperature (ECT), etc.; emission control parameters: such as oxygen sensor voltage, catalytic converter temperature, etc.; transmission system parameters: such as transmission oil temperature, clutch position, etc.; chassis and safety system parameters: such as brake pressure, steering angle, etc.; electrical system parameters: such as battery voltage, generator output, etc.; environmental parameters: such as external temperature, rain sensor data, etc.

[0070] Specifically, the fault code information of the target vehicle and the real-time data stream data of the vehicle within a preset recording time are obtained through the vehicle system and other means, and there is no limitation here.

[0071] Step S22, extracting the fault code information and the vehicle fault data in the vehicle real-time data stream data;

[0072] It should be noted that the vehicle fault data refers to data directly related to the vehicle fault extracted from the fault code information and real-time data stream data, including fault codes and related information, abnormal values ​​in real-time data streams, sudden changes in sensor readings, abnormal actuator responses, and degradation of system performance. For example, the gradual deterioration of performance parameters may indicate potential problems, which are not limited here.

[0073] Specifically, a multi-level, intelligent data extraction and analysis framework is adopted to achieve efficient and accurate fault diagnosis. In one embodiment, the fault code information and the vehicle real-time data stream data are captured in real time through the vehicle's OBD-II interface or directly communicate with the vehicle's ECU. They are updated at a high frequency, providing rich real-time information on the health status of the vehicle.

[0074] Furthermore, the fault code information and the vehicle real-time data stream data are preprocessed, such as filtering and normalization, to clean and standardize the data to eliminate noise and outliers and ensure data quality and consistency. Feature engineering techniques are used, such as deploying a deep learning model, in which a convolutional neural network (CNN) or a recurrent neural network (RNN) can be used, so that the time series data can be processed and analyzed by the model to identify patterns and anomalies therein, and then the differences between normal operation and abnormal behavior can be identified by training these models to accurately mark data points related to faults. In order to further identify abnormal patterns in the data, an anomaly detection algorithm, such as an isolation forest or an autoencoder, is introduced into the deep learning model, thereby enhancing the system's ability to identify unknown faults, and finally extracting the fault code information and the vehicle fault data in the vehicle real-time data stream data.

[0075] Step S23: Associating and combining the vehicle fault data to generate a first vehicle scanning result.

[0076] This embodiment obtains the fault code information and real-time data stream data of the target vehicle within a preset recording time, and then extracts the fault code information and the vehicle fault data in the real-time data stream data, thereby correlating and combining the vehicle fault data to generate a first vehicle scan result, and then combines the fault code and the real-time data stream to provide a comprehensive view of the vehicle's health status, including identified problems and potential risks, wherein the fault code provides a specific indication of the problem, and the real-time data stream provides the actual operating status of the vehicle when the problem occurs. The combination of the two can improve the accuracy of fault diagnosis, thereby quickly and accurately identifying faults, reducing diagnosis time, and improving the efficiency of maintenance work.

[0077] Based on this, the embodiment of the present application provides a method for generating a vehicle diagnostic report, referring to Figure 3 , Figure 3 A flowchart diagram of the third embodiment of the vehicle diagnostic report generation method of the present application is provided.

[0078] In a feasible implementation manner, the training process of the vehicle diagnosis analysis model includes:

[0079] Step S31, obtaining second vehicle scanning results of several groups of normal vehicles;

[0080] It should be noted that the second vehicle scanning result refers to the result obtained after a system scan of a normal vehicle, including fault codes, sensor readings, actuator status, real-time data streams (such as speed, temperature, pressure, etc.), vehicle usage history data, etc., and is not limited here.

[0081] Step S32, extracting features from each of the second vehicle scanning results to obtain vehicle feature data;

[0082] It should be noted that the vehicle characteristic data refers to the data extracted from the second vehicle scanning results, which is used to represent the normal operating characteristics of the vehicle, including key performance indicators: such as engine speed, coolant temperature, fuel pressure, etc.; statistical characteristics: such as the average, maximum, minimum, standard deviation, etc. of sensor readings; frequency domain characteristics: frequency components extracted from time series data through methods such as Fourier transform; time series characteristics: such as the changing trend of sensor readings over time; normal mode: a behavior mode that is significantly different from abnormal operation.

[0083] Specifically, data preprocessing is performed on each of the second vehicle scanning results, and then each of the preprocessed second vehicle scanning results is vectorized to generate a plurality of groups of third vehicle scanning results, and then feature extraction is performed on each of the third vehicle scanning results to obtain vehicle feature data.

[0084] Step S33: input each of the vehicle feature data into an initial vehicle diagnosis and analysis model for iterative training to obtain the vehicle diagnosis and analysis model.

[0085] It should be noted that the initial vehicle diagnostic analysis model refers to an initial algorithm or software model used to analyze vehicle scanning results and identify faults.

[0086] Specifically, each of the vehicle feature data and the sample labels corresponding to each of the vehicle feature data are input into the initial vehicle diagnostic analysis model to obtain the predicted value output by the initial vehicle diagnostic analysis model, and then based on the predicted value and the sample label, the model loss value is calculated using the loss function. In this embodiment, the loss function can be set according to actual needs and is not specifically limited here. After the model loss value is calculated, the training process ends, and the error back propagation algorithm is used to update the model parameters in the initial vehicle diagnostic analysis model before the next training is carried out. During the training process, it is determined whether the updated initial vehicle diagnostic analysis model meets the preset training end conditions. If so, the updated initial vehicle diagnostic analysis model is used as the vehicle diagnostic analysis model. If not, the model training continues, wherein the preset training end conditions include loss convergence and reaching the maximum number of iterations threshold.

[0087] This embodiment obtains second vehicle scanning results of several groups of normal vehicles, and then extracts features from each of the second vehicle scanning results to obtain vehicle feature data, and then inputs each of the vehicle feature data into an initial vehicle diagnostic analysis model for iterative training to obtain the vehicle diagnostic analysis model, and then uses the scanning results of normal vehicles to train the vehicle diagnostic analysis model to more accurately identify the features of normal vehicles, thereby more effectively identifying anomalies (overfitting characteristics) in actual diagnosis, while reducing the complexity of collecting abnormal vehicle data, saving data collection resources, and thus improving the efficiency of maintenance and diagnosis. Overfitting is a common problem in machine learning and statistical modeling, which refers to the phenomenon that the model performs well on training data but performs poorly on new, unseen data.

[0088] Based on this, the embodiment of the present application provides a method for generating a vehicle diagnostic report, referring to Figure 4 , Figure 4 A flowchart diagram of a fourth embodiment of the vehicle diagnostic report generation method of the present application is provided.

[0089] In a feasible implementation manner, extracting features from each second vehicle scanning result to obtain vehicle feature data includes:

[0090] Step S41, performing data preprocessing on each second vehicle scanning result;

[0091] Specifically, each of the second vehicle scanning results is subjected to thorough data preprocessing, including denoising, outlier detection and processing, and data normalization or standardization. In one embodiment, denoising reduces high-frequency noise in the data through filtering techniques such as low-pass filters; outlier detection uses statistical methods to identify and correct or delete data points that are far from the normal range; and normalization or standardization ensures that all data are on the same scale for easy comparison and analysis.

[0092] Step S42, vectorizing each of the pre-processed second vehicle scanning results to generate a plurality of groups of third vehicle scanning results;

[0093] It should be noted that the third vehicle scanning result refers to the result obtained after vectorization of each of the second vehicle scanning results.

[0094] Specifically, the preprocessed data is vectorized, that is, the structured and unstructured data are converted into a unified numerical vector. For example, the time series data is converted into a set of features (such as mean, variance, skewness, kurtosis, etc.), the image data (such as vehicle sensor images) is converted into feature vectors through image processing technology, and the text data (such as maintenance logs) is converted into word vectors through natural language processing technology, so that each set of second vehicle scan results is converted into a set of third vehicle scan results, and the third vehicle scan results exist in the form of numerical vectors.

[0095] Step S43, extracting features from each of the third vehicle scanning results to obtain vehicle feature data.

[0096] Specifically, feature extraction is performed on each of the third vehicle scanning results, wherein machine learning algorithms such as principal component analysis (PCA) are used to reduce dimensionality and extract the most influential features, and cluster analysis is used to identify patterns and associations in the data, and deep learning techniques such as convolutional neural networks (CNN) are used to automatically learn features from complex data patterns. These features include not only traditional statistical features, but also deep features extracted from deep learning models, which can capture complex and nonlinear relationships in the data to obtain vehicle feature data. The vehicle feature data includes not only direct measurements of the vehicle, but also abstract features extracted by advanced analysis techniques, so that the model can accurately identify the health status of the vehicle, predict potential failures, and provide timely maintenance suggestions.

[0097] This embodiment performs data preprocessing on each of the second vehicle scanning results, and then vectorizes the preprocessed second vehicle scanning results to generate several groups of third vehicle scanning results, thereby performing feature extraction on each of the third vehicle scanning results to obtain vehicle feature data, and then cleans the data through data preprocessing to remove noise and outliers, improve data quality, and unify data in different formats into numerical data through vectorization to facilitate machine learning model processing, while reducing the dimension of the data, reducing the complexity of the model, and improving computing efficiency, thereby effectively identifying and extracting key information and patterns in the data, which helps to improve the performance of the model and thus improve the accuracy of vehicle fault diagnosis.

[0098] In a feasible implementation manner, the training process of the vehicle diagnostic report generation model includes:

[0099] Step S51, obtaining several groups of historical vehicle diagnostic reports and historical report configuration information;

[0100] It should be noted that the historical vehicle diagnostic report refers to a series of reports generated after diagnosing the vehicle in the past, including fault diagnosis results, vehicle information, maintenance history, performance data, inspection results, safety tips, follow-up action suggestions and user feedback.

[0101] It should be further explained that the historical report configuration information refers to the configuration and setting information related to the historical vehicle diagnostic report corresponding to the current maintenance technician, including report template (template used to generate diagnostic report, including layout, format and content structure), report parameters (parameter settings used when generating report, such as level of detail, language selection, etc.), user preferences (specific requirements and preferences of different users or technicians for reports), data source information (data source used in the report, such as sensor type, data collection frequency, etc.) and analysis method (analysis method and algorithm used to generate report), etc., which are not restricted here and can be set according to actual conditions.

[0102] Step S52: input each of the historical vehicle diagnostic reports and the historical report configuration information into an initial vehicle diagnostic report generation model for iterative training to obtain the vehicle diagnostic report generation model.

[0103] It should be noted that the initial vehicle diagnostic report generation model refers to an initial algorithm or software model used to generate a vehicle diagnostic report.

[0104] Specifically, data preprocessing is performed on each of the historical vehicle diagnostic reports and historical report configuration information and the sample labels corresponding to each of the historical vehicle diagnostic reports and historical report configuration information, such as data cleaning, normalization, etc., so that each of the historical vehicle diagnostic reports and historical report configuration information and the sample labels corresponding to each of the historical vehicle diagnostic reports and historical report configuration information are input into the initial vehicle diagnostic report generation model after knowledge injection, and the predicted value output by the initial vehicle diagnostic report generation model is obtained, and then based on the predicted value and the sample label, the model loss value is calculated using the loss function. In this embodiment, the loss function can be set according to actual needs and is not specifically limited here. After the model loss value is calculated, the training process ends, and the error back propagation algorithm is used to update the model parameters in the initial vehicle diagnostic report generation model, and then the next training is performed. During the training process, it is determined whether the updated initial vehicle diagnostic report generation model meets the preset training end condition. If it does, the updated initial vehicle diagnostic report generation model is used as the vehicle diagnostic report generation model. If it does not, the model training continues, wherein the preset training end condition includes loss convergence and reaching the maximum iteration number threshold.

[0105] This embodiment obtains several groups of historical vehicle diagnostic reports and historical report configuration information, and then inputs each of the historical vehicle diagnostic reports and historical report configuration information into an initial vehicle diagnostic report generation model for iterative training to obtain the vehicle diagnostic report generation model, thereby improving the generalization ability of the model by learning diverse historical reports to adapt to different vehicle models and fault conditions and generate accurate diagnostic reports. At the same time, personalized diagnostic reports that better meet specific needs and preferences are generated based on the historical report configuration information, and the structure and content of the report are optimized through a large model to make it clearer, more organized, easier to understand and use, thereby improving the overall diagnostic efficiency and improving the scientific nature of maintenance work.

[0106] In a feasible implementation manner, the current vehicle diagnostic state includes a vehicle state before maintenance and a vehicle state after maintenance; based on the current vehicle diagnostic state, the first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report, including:

[0107] Step S61, if the current vehicle diagnostic state is a vehicle pre-maintenance state, temporarily storing a second vehicle diagnostic analysis result corresponding to the vehicle pre-maintenance state in a preset database;

[0108] It should be noted that the vehicle pre-maintenance state refers to the state of the vehicle before receiving maintenance services. The second vehicle diagnostic analysis result refers to the vehicle diagnostic analysis result corresponding to the vehicle pre-maintenance state.

[0109] Step S62, obtaining a third vehicle diagnostic analysis result of a vehicle post-maintenance state corresponding to the vehicle pre-maintenance state, and associating and integrating the second vehicle diagnostic analysis result with the third vehicle diagnostic analysis result to generate a first vehicle diagnostic analysis result;

[0110] It should be noted that the vehicle post-repair state refers to the state of the vehicle after receiving repair services. The third vehicle diagnostic analysis result refers to the vehicle diagnostic analysis result corresponding to the vehicle post-repair state.

[0111] Specifically, a third vehicle diagnostic analysis result of a vehicle post-maintenance state corresponding to the vehicle pre-maintenance state is obtained, and the second vehicle diagnostic analysis result is associated and integrated with the third vehicle diagnostic analysis result to generate a first vehicle diagnostic analysis result.

[0112] In one embodiment, in order to associate and integrate the second vehicle diagnostic analysis result (pre-repair status) with the third vehicle diagnostic analysis result (post-repair status), the vehicle identification number (VIN) or other unique identifier is first used to ensure that the two diagnostic analysis results correspond to the same vehicle, and then the diagnostic data before and after the repair are matched according to the time sequence and parameter type using data fusion technology, and the changes in fault codes, differences in sensor readings, and improvements in performance parameters are compared and analyzed, without limitation here, so that the matched data is deeply analyzed through a decision tree or a neural network to identify the repair effect and potential remaining problems, and natural language processing technology is used to convert the technical data into an easy-to-understand language description, which is integrated to generate the first vehicle diagnostic analysis result, thereby providing technicians with comprehensive feedback on the repair effect and providing car owners with a transparent repair report.

[0113] Step S63: input the first vehicle diagnostic analysis result into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report.

[0114] In this embodiment, if the current vehicle diagnostic state is the vehicle pre-maintenance state, the second vehicle diagnostic analysis result corresponding to the vehicle pre-maintenance state is temporarily stored in a preset database, and then a third vehicle diagnostic analysis result of the vehicle post-maintenance state corresponding to the vehicle pre-maintenance state is obtained, and the second vehicle diagnostic analysis result is associated and integrated with the third vehicle diagnostic analysis result to generate a first vehicle diagnostic analysis result, and the first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report, thereby ensuring the continuity and integrity of the diagnostic process, and by comparing the diagnostic results before and after maintenance, effectively monitoring the maintenance quality and ensuring the effectiveness of the maintenance measures. At the same time, integrating the diagnostic data before and after maintenance helps to track the development and changes of faults, provide a more comprehensive vehicle condition analysis, and increase the accuracy and completeness of the report, thereby achieving closed-loop management.

[0115] In a feasible implementation manner, after inputting the first vehicle diagnostic analysis result into a vehicle diagnostic report generation model based on the current vehicle diagnostic state and obtaining the vehicle diagnostic report, the method further includes:

[0116] Step S71, obtaining report optimization suggestions from vehicle maintenance technicians;

[0117] It should be noted that the report optimization suggestions refer to a series of improvement suggestions put forward by vehicle maintenance technicians based on actual work experience and feedback on the use of vehicle diagnostic reports, aiming to improve the accuracy, readability, practicality and overall quality of diagnostic reports. Among them, report optimization suggestions include but are not limited to adding or reducing certain diagnostic information, such as specific fault code explanations, maintenance suggestions, safety tips, etc.; adjusting the presentation of data in the report to make it more intuitive and easy to understand; report structure: reorganizing the layout and structure of the report so that key information is more prominent and easy to identify quickly; classifying or paginating different parts of the report to improve the retrievability of information; data visualization: making improvement suggestions for charts, graphs and other visual elements to better display complex data; it is recommended to add or optimize data comparison views, such as comparison of performance parameters before and after maintenance.

[0118] Step S72: Optimizing the vehicle diagnostic analysis model and the vehicle diagnostic report generation model based on the report optimization suggestion.

[0119] Specifically, the report optimization suggestions are classified and prioritized to determine which suggestions are most critical to improving report quality and diagnostic accuracy, and then the vehicle diagnostic analysis model is adjusted based on these suggestions, including updating the fault code database, optimizing diagnostic logic, adding new data analysis dimensions, etc., to ensure that the model can more accurately identify and explain vehicle problems. At the same time, the vehicle diagnostic report generation model is optimized, including modifying the report template, enhancing data visualization functions, improving natural language processing technology to improve report readability, and adding user interaction functions to meet personalized needs, etc., which are not limited here.

[0120] Furthermore, after the model is optimized, the vehicle diagnostic analysis model and the vehicle diagnostic report generation model are rigorously tested and verified to ensure that the optimized model can produce the expected results in actual applications, such as improving the accuracy, readability and user satisfaction of the diagnostic report. The optimized model is then deployed to the actual diagnosis and report generation process, and a continuous feedback mechanism is established to continuously collect user feedback and achieve continuous iteration and optimization of the model, thereby ensuring that the vehicle diagnostic analysis model and the vehicle diagnostic report generation model are always kept up to date, meet user needs and improve service quality.

[0121] This embodiment obtains report optimization suggestions from vehicle maintenance technicians, and then optimizes the vehicle diagnostic analysis model and the vehicle diagnostic report generation model based on the report optimization suggestions, which helps to improve the practicality and operability of the report, while helping the optimization model adapt to the ever-changing actual maintenance environment and technological advances, and improving the applicability and accuracy of the model.

[0122] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0123] This application also provides a vehicle diagnostic report generation device, please refer to Figure 5 , the vehicle diagnostic report generating device comprises:

[0124] The information acquisition module 51 is used to obtain the first vehicle scanning result and the current vehicle diagnosis status;

[0125] A diagnostic analysis module 52, configured to input the first vehicle scanning result and the current vehicle diagnostic state into a vehicle diagnostic analysis model to obtain a first vehicle diagnostic analysis result;

[0126] The report generating module 53 is used to input the first vehicle diagnostic analysis result into a vehicle diagnostic report generating model based on the current vehicle diagnostic state to obtain a vehicle diagnostic report.

[0127] The vehicle diagnostic report generating device is also used for:

[0128] Obtain the target vehicle's fault code information and vehicle real-time data stream data within the preset recording time;

[0129] Extracting the fault code information and the vehicle fault data in the vehicle real-time data stream data;

[0130] The vehicle fault data are associated and combined to generate a first vehicle scanning result.

[0131] The vehicle diagnostic report generating device is also used for:

[0132] Obtaining second vehicle scanning results of several groups of normal vehicles;

[0133] Extracting features from each of the second vehicle scanning results to obtain vehicle feature data;

[0134] Each of the vehicle feature data is input into an initial vehicle diagnosis and analysis model for iterative training to obtain the vehicle diagnosis and analysis model.

[0135] The vehicle diagnostic report generating device is also used for:

[0136] performing data preprocessing on each of the second vehicle scanning results;

[0137] Vectorizing the preprocessed second vehicle scanning results to generate a plurality of groups of third vehicle scanning results;

[0138] Feature extraction is performed on each of the third vehicle scanning results to obtain vehicle feature data.

[0139] The vehicle diagnostic report generating device is also used for:

[0140] Obtain several groups of historical vehicle diagnostic reports and historical report configuration information;

[0141] Each of the historical vehicle diagnostic reports and historical report configuration information is input into an initial vehicle diagnostic report generation model for iterative training to obtain the vehicle diagnostic report generation model.

[0142] The vehicle diagnostic report generating device is also used for:

[0143] If the current vehicle diagnostic state is a vehicle pre-maintenance state, temporarily storing the second vehicle diagnostic analysis result corresponding to the vehicle pre-maintenance state in a preset database;

[0144] Acquire a third vehicle diagnostic analysis result of a vehicle post-maintenance state corresponding to the vehicle pre-maintenance state, and associate and integrate the second vehicle diagnostic analysis result with the third vehicle diagnostic analysis result to generate a first vehicle diagnostic analysis result;

[0145] The first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report.

[0146] The vehicle diagnostic report generating device is also used for:

[0147] Get report optimization suggestions from vehicle maintenance technicians;

[0148] Based on the report optimization suggestions, the vehicle diagnostic analysis model and the vehicle diagnostic report generation model are optimized.

[0149] The vehicle diagnostic report generation device provided by the present application adopts the vehicle diagnostic report generation method in the above embodiment, which can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the vehicle diagnostic report generation device provided by the present application are the same as the beneficial effects of the vehicle diagnostic report generation method provided by the above embodiment, and the other technical features in the vehicle diagnostic report generation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0150] The present application provides a vehicle diagnostic report generating device, which includes: at least one processor; and a memory that is 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 vehicle diagnostic report generating method in the above-mentioned embodiment one.

[0151] Reference below Figure 6 , which shows a schematic diagram of the structure of a vehicle diagnostic report generating device suitable for implementing the embodiment of the present application. The vehicle diagnostic report generating 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), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The vehicle diagnostic report generating 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.

[0152] like Figure 6 As shown, the vehicle diagnostic report generating device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle diagnostic report generating device 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. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle diagnostic report generating device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a vehicle diagnostic report generating device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0153] 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.

[0154] The vehicle diagnostic report generation device provided by the present application adopts the vehicle diagnostic report generation method in the above embodiment, which can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the vehicle diagnostic report generation device provided by the present application are the same as the beneficial effects of the vehicle diagnostic report generation method provided by the above embodiment, and the other technical features in the vehicle diagnostic report generation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0155] 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.

[0156] 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.

[0157] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle diagnostic report generating method in the above-mentioned embodiment.

[0158] 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.

[0159] The computer-readable storage medium may be included in the vehicle diagnostic report generating device; or may exist independently without being assembled into the vehicle diagnostic report generating device.

[0160] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the vehicle diagnostic report generating device, the vehicle diagnostic report generating device:

[0161] Obtain a first vehicle scan result and a current vehicle diagnostic status; input the first vehicle scan result and the current vehicle diagnostic status into a vehicle diagnostic analysis model to obtain a first vehicle diagnostic analysis result; based on the current vehicle diagnostic status, input the first vehicle diagnostic analysis result into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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 vehicle diagnostic report generation method, and can solve the technical problems in the background technology. 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 vehicle diagnostic report generation method provided by the above-mentioned embodiment, and will not be repeated here.

[0166] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the above-mentioned vehicle diagnostic report generation method when executed by a processor.

[0167] The computer program product provided in this application can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the vehicle diagnostic report generation method provided in the above embodiment, which will not be repeated here.

[0168] 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 method for generating a vehicle diagnostic report, characterized in that: include: Obtaining a first vehicle scan result and a current vehicle diagnostic status; Inputting the first vehicle scanning result and the current vehicle diagnostic state into a vehicle diagnostic analysis model to obtain a first vehicle diagnostic analysis result; Based on the current vehicle diagnostic state, the first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report.

2. The vehicle diagnostic report generating method according to claim 1, characterized in that: The obtaining of the first vehicle scanning result includes: Obtain the target vehicle's fault code information and vehicle real-time data stream data within the preset recording time; Extracting the fault code information and the vehicle fault data in the vehicle real-time data stream data; The vehicle fault data are associated and combined to generate a first vehicle scanning result.

3. The vehicle diagnostic report generating method according to claim 1, characterized in that: The training process of the vehicle diagnosis analysis model includes: Obtaining second vehicle scanning results of several groups of normal vehicles; Extracting features from each of the second vehicle scanning results to obtain vehicle feature data; Each of the vehicle feature data is input into an initial vehicle diagnosis and analysis model for iterative training to obtain the vehicle diagnosis and analysis model.

4. The vehicle diagnostic report generating method according to claim 3, characterized in that: The extracting features of each second vehicle scanning result to obtain vehicle feature data includes: performing data preprocessing on each of the second vehicle scanning results; Vectorizing the preprocessed second vehicle scanning results to generate a plurality of groups of third vehicle scanning results; Feature extraction is performed on each of the third vehicle scanning results to obtain vehicle feature data.

5. The vehicle diagnostic report generating method according to claim 1, characterized in that: The training process of the vehicle diagnostic report generation model includes: Obtain several groups of historical vehicle diagnostic reports and historical report configuration information; Each of the historical vehicle diagnostic reports and the historical report configuration information is input into an initial vehicle diagnostic report generation model for iterative training to obtain the vehicle diagnostic report generation model.

6. The vehicle diagnostic report generating method according to claim 1, characterized in that: The current vehicle diagnostic state includes a vehicle pre-maintenance state and a vehicle post-maintenance state; The step of inputting the first vehicle diagnostic analysis result into a vehicle diagnostic report generation model based on the current vehicle diagnostic state to obtain a vehicle diagnostic report includes: If the current vehicle diagnostic state is a vehicle pre-maintenance state, temporarily storing the second vehicle diagnostic analysis result corresponding to the vehicle pre-maintenance state in a preset database; Acquire a third vehicle diagnostic analysis result of a vehicle post-maintenance state corresponding to the vehicle pre-maintenance state, and associate and integrate the second vehicle diagnostic analysis result with the third vehicle diagnostic analysis result to generate a first vehicle diagnostic analysis result; The first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model to obtain a vehicle diagnostic report.

7. The vehicle diagnostic report generating method according to claim 1, characterized in that: After the first vehicle diagnostic analysis result is input into a vehicle diagnostic report generation model based on the current vehicle diagnostic state to obtain a vehicle diagnostic report, the method further includes: Get report optimization suggestions from vehicle maintenance technicians; Based on the report optimization suggestions, the vehicle diagnostic analysis model and the vehicle diagnostic report generation model are optimized.

8. A vehicle diagnostic report generating device, characterized in that: include: An information acquisition module, used to obtain the first vehicle scanning result and the current vehicle diagnostic status; A diagnostic analysis module, configured to input the first vehicle scanning result and the current vehicle diagnostic state into a vehicle diagnostic analysis model to obtain a first vehicle diagnostic analysis result; The report generation module is used to input the first vehicle diagnosis analysis result into a vehicle diagnosis report generation model based on the current vehicle diagnosis state to obtain a vehicle diagnosis report.

9. A vehicle diagnostic report generating device, characterized in that: The vehicle diagnostic report generating device comprises: 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 vehicle diagnostic report generating method according to 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 vehicle diagnostic report generation method according to any one of claims 1 to 7 are implemented.

Images