Data updating method of automobile diagnostic equipment and automobile diagnostic equipment

Abstract

The present invention relates to the technical field of automobile data update, and in particular to a data update method and automobile diagnostic equipment for automobile diagnostic equipment. The method comprises the following steps: obtaining a vehicle historical operation log; performing multi-point sampling of the owner's driving behavior on the vehicle historical operation log, and performing evolution of the behavioral characteristics of different scenarios, thereby obtaining the owner's driving behavior model in different scenarios; extracting the vehicle time series state parameters based on the vehicle historical operation log; performing multi-scenario operation simulation on the vehicle time series state parameters according to the owner's driving behavior model in different scenarios, and generating vehicle state operation simulation data for each scenario; performing rolling prediction of the vehicle state in the future period and calculation of the probability of the fault time window on the vehicle state operation simulation data of each scenario, and obtaining the vehicle abnormal fault location location point and the fault time window probability curve. The present invention realizes the efficiency and accuracy of data update of automobile diagnostic equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile data updating, and in particular to a data updating method of automobile diagnostic equipment and automobile diagnostic equipment. Background Art

[0002] In the modern automobile industry, with the continuous development of vehicle technology and the improvement of the level of intelligence, automobile diagnostic equipment, as an important tool for automobile repair and maintenance, plays an increasingly critical role. By collecting and analyzing the operating data of various systems of the vehicle, automobile diagnostic equipment can timely discover potential faults of the vehicle, provide accurate fault diagnosis information, and help maintenance personnel to efficiently troubleshoot. However, with the continuous advancement of automotive electronic technology and the emergence of various new types of automobile control systems, traditional automobile diagnostic equipment often faces the challenge of being unable to quickly adapt to new models and new technologies. In particular, traditional automobile diagnostic equipment has great limitations in data updating, and often relies on manual database updates or manual loading of the latest diagnostic programs, which is not only time-consuming and labor-intensive, but also easily leads to reduced diagnostic accuracy due to the lag of the database version, and even fails to identify certain new faults. Traditional methods usually rely on service stations or maintenance points to regularly download and update data. This method not only affects the efficiency of the equipment, but also limits its immediacy and convenience in the daily maintenance of car owners. In addition, with the gradual advancement of automobile electronics and intelligence, new diagnostic tools and technologies continue to emerge. How to ensure that automobile diagnostic equipment can continue to adapt to the replacement of these new technologies and new models has become an urgent problem to be solved in the industry. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a data updating method of an automobile diagnostic device and an automobile diagnostic device to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a data updating method for automobile diagnostic equipment, comprising the following steps:

[0005] Step S1: obtaining a vehicle historical operation log; performing multi-point sampling of the owner's driving behavior in the vehicle historical operation log, and performing behavior feature evolution in different scenarios, thereby obtaining a driving behavior model of the owner in different scenarios;

[0006] Step S2: extracting vehicle time-series state parameters based on the vehicle historical operation log; performing multi-scenario operation simulation on the vehicle time-series state parameters according to the vehicle owner's driving behavior model in different scenarios, and generating vehicle state operation simulation data for each scenario;

[0007] Step S3: Perform rolling prediction of vehicle status in future time periods and calculation of fault time window probability for the vehicle status operation simulation data of each scenario, and obtain the location point of abnormal fault part of the vehicle and the fault time window probability curve;

[0008] Step S4: performing fault attribution diagnosis analysis on the location points of abnormal fault parts of the vehicle, and mining the diagnostic equipment update requirements to generate fault diagnosis requirement update data;

[0009] Step S5: predicting the idle time of the vehicle based on the different driving behavior models of the vehicle owner according to the fault time window probability curve, calculating the optimal required update time, and extracting the optimal diagnostic equipment update time point;

[0010] Step S6: Update the data according to the fault diagnosis requirements to perform differentiated adaptation optimization of the current vehicle configuration, and perform real-time remote update processing based on the optimal diagnostic equipment update time point, thereby completing the data update operation of the automobile diagnostic equipment.

[0011] The present invention can provide more personalized diagnostic services by modeling the driving behavior of the vehicle owner, making subsequent fault prediction and diagnosis more accurate. Different driving scenarios have different impacts on the vehicle. Analyzing different driving behavior patterns is helpful to accurately evaluate the vehicle's operating health status in different scenarios. Based on multi-point sampling of driving behavior, more valuable data can be extracted, thereby avoiding invalid data that may appear in traditional diagnostic methods. Multi-scenario simulation based on the driving behavior model can provide more accurate vehicle operating status data and predict the vehicle's operating performance in different scenarios. Through scenario-based simulation, it can provide diagnostic equipment with operating data under a variety of different conditions, helping the equipment to adapt to diagnostic needs in different environments. Through rolling prediction and probability calculation of the fault time window, it can predict in advance the time and location of the vehicle's possible failure, thereby improving the accuracy of fault warning. The probability curve clearly defines the possibility and time point of the failure, helping to locate the fault site more quickly, providing High maintenance efficiency. Through fault attribution analysis, it can ensure that the cause of each fault point is fully understood and the accuracy of diagnosis is improved. According to the fault data, the system will automatically generate update requirements to avoid manual intervention and ensure that the diagnostic equipment can get the required updates in a timely manner. Through idle time prediction and update time optimization, the conflict between the update time of traditional diagnostic equipment and the driving needs of the owner is avoided. The update operation can be performed when the owner is not using the vehicle, minimizing the interference in the use of the vehicle and improving the owner's experience and satisfaction. Through differentiated adaptation optimization, it ensures that each vehicle can obtain the most accurate diagnosis, and can adjust the update strategy according to the specific configuration of the vehicle to improve the adaptability of the system. The remote update operation eliminates human intervention in the traditional update process, improves the update efficiency and accuracy, and ensures that the vehicle automatically completes the equipment update at the most appropriate time. With the continuous optimization of equipment and algorithms, the vehicle's diagnostic capabilities will continue to improve, achieving longer-term and more accurate fault diagnosis and early warning.

[0012] Preferably, step S1 comprises the following steps:

[0013] Step S11: Obtain vehicle historical operation log;

[0014] Step S12: Perform multi-point sampling of the vehicle owner's driving behavior in the vehicle's historical operation log to extract the vehicle owner's driving behavior data;

[0015] Step S13: mining the personalized driving characteristics of the vehicle owner on the vehicle owner's driving behavior data to generate a representation of the vehicle owner's driving behavior;

[0016] Step S14: performing vehicle operation multi-scenario identification based on the vehicle historical operation log, and extracting multiple vehicle operation scenarios;

[0017] Step S15: Evolving the behavior characteristics of different scenarios for multiple vehicle operation scenarios according to the driving behavior representation of the vehicle owner, thereby obtaining driving behavior models of different scenarios for the vehicle owner.

[0018] The present invention provides a large amount of actual driving data through historical operation logs, which provides a basis for subsequent data analysis and fault prediction. These data are usually based on the actual usage of the vehicle and can provide more realistic feedback than laboratory data. This is the first step in the entire data update process. Accurate data collection ensures the reliability and accuracy of subsequent analysis. Multi-point sampling can capture the owner's driving behavior from multiple dimensions to ensure that the data is more comprehensive and reflects the owner's diverse driving habits. The extracted driving behavior data will help subsequent diagnostic equipment better understand the owner's driving style, thereby improving the accuracy of vehicle status analysis and fault diagnosis. By analyzing the owner's personalized driving characteristics, the diagnostic system can perform personalized analysis of the vehicle, thereby improving the accuracy of fault prediction. Each owner has a different driving style. Personalized characterization helps the equipment better adapt to the needs of different driving styles and generate a personalized driving behavior model for the owner, which can help the diagnostic equipment learn the owner's driving habits from multiple dimensions and continuously optimize the algorithm to improve the accuracy of fault diagnosis. The vehicle's operating scenario can greatly affect its health status, and identify multiple The scenarios help to understand the performance and failure risk of the vehicle under different driving conditions, thereby providing more data support. Multi-scenario recognition provides more dimensional data for subsequent vehicle status analysis. The system can optimize fault diagnosis and fault prediction strategies according to different scenarios. By evolving the owner's driving behavior in different scenarios, the system can more accurately predict the owner's driving performance. For example, the owner may drive more smoothly in high-speed scenarios and more aggressively in urban road conditions. This step helps to capture these details, thereby providing more accurate diagnosis and prediction. Different driving behaviors will affect different parts of the vehicle. The evolved scenario behavior model can help the system predict the abnormal operations that the owner may produce in specific scenarios, thereby achieving more accurate fault warnings. Through historical logs and the owner's driving behavior data, the system can fully understand the vehicle's operating status and the owner's driving habits, providing a solid foundation for subsequent fault prediction and equipment updates. The owner's personalized behavior model and multi-scenario recognition provide personalized and diversified diagnostic solutions for automotive diagnostic equipment, improve the intelligence level of the equipment, and reduce misdiagnosis.

[0019] Preferably, the specific steps of step S14 are:

[0020] Perform vehicle location tracking calculations based on the vehicle's historical operation logs to generate the vehicle's time-series location trajectory;

[0021] Perform GPS map visualization based on the vehicle's time-series positioning trajectory to obtain a location trajectory visualization map;

[0022] The vehicle time series positioning position trajectory is segmented into multiple time periods to obtain the position trajectory of different time periods;

[0023] According to the location trajectories in different time periods, the location trajectory visualization map identifies the road section where the trajectory is located, and analyzes the road section status characteristics in each time period;

[0024] Based on the road state characteristics of each time period, multiple vehicle operation scenarios are identified and multiple vehicle operation scenarios are extracted.

[0025] The present invention ensures that the actual driving trajectory of the vehicle is accurately captured by calculating and tracking historical data, which is the basis for subsequent analysis and diagnosis, provides detailed geographic information, and uses high-precision GPS data combined with timestamps to ensure that each location of the vehicle is accurately recorded, providing reliable data support for subsequent fault diagnosis. Through map visualization, complex vehicle positioning data can be presented in an intuitive manner, greatly improving the readability and operability of the data. The visualized map can help diagnostic equipment identify the performance of the vehicle in a specific geographical location, such as whether there is a fault or anomaly in a specific road section. The visualized information helps to quickly locate the problem area. By dividing the trajectory into time periods, the operating status of the vehicle in different time periods can be more clearly analyzed. For example, the driving behavior and fault risk during high-speed driving and urban road driving will be different. According to the trajectory analysis in different time periods, it is possible to more accurately identify the possible faults that may occur in a specific time period. The system can identify the types of faults that may occur, which helps to provide early warning and formulate maintenance plans in actual operations. Through road section status analysis, the system can identify the impact of different road sections on the vehicle. For example, some sections may have frequent traffic jams, road damage or large slopes, which will affect the vehicle's operating status and the probability of faults. The status characteristics of different road sections affect the vehicle's operation. Through this identification, the system can dynamically adjust the fault prediction according to the characteristics of different road sections to improve the prediction accuracy. In different scenarios, the vehicle's operating status will be affected by multiple factors such as road conditions and traffic conditions. Through scene recognition, potential fault risks can be discovered in advance and targeted diagnosis can be performed. According to different driving scenarios, the diagnostic system can intelligently adjust the diagnostic strategy. For example, in the highway scenario, the system may pay more attention to factors such as engine temperature and tire pressure, while in the city congestion scenario, it pays more attention to the braking system, engine load and other issues.

[0026] Preferably, the specific steps of step S2 are:

[0027] Step S21: extracting vehicle time sequence state parameters based on the vehicle historical operation log;

[0028] Step S22: performing a multi-time point vehicle operation state analysis on the vehicle time sequence state parameters to generate vehicle operation state characteristics at multiple time points;

[0029] Step S23: performing state scenario matching on vehicle operation state characteristics at multiple time points based on multiple vehicle operation scenarios, and performing scene state change mining to generate a vehicle state change trend for each operation scenario;

[0030] Step S24: Perform multi-scenario operation simulation on the vehicle state change trend of each operation scenario according to the vehicle owner's driving behavior model in different scenarios, and generate vehicle state operation simulation data for each scenario.

[0031] By using historical operation logs, the present invention can comprehensively capture various status information of the vehicle under different driving conditions, such as speed, engine speed, fuel consumption, temperature, etc. These time-series state parameters provide more accurate basic data for subsequent diagnosis. Data can be automatically extracted from the vehicle system without manual intervention, which improves data collection efficiency and reduces human errors. By analyzing the vehicle status at different time points, the law of vehicle performance changes over time can be found, such as fluctuations in engine efficiency, changing trends in fuel consumption, etc. Through multi-time point state analysis, potential signs of vehicle failure can be identified, such as abnormal behavior that occurs during specific periods or conditions, providing early warning for subsequent diagnosis and maintenance. By identifying different operating scenarios, the vehicle's status data can be matched with specific scenarios (such as urban roads, highways, mountainous areas, etc.), thereby ensuring that the diagnosis is more targeted and has practical application value. By mining the changing trends of the vehicle status under different scenarios, it is possible to gain an in-depth understanding of the vehicle's performance in different usage environments and identify potential problems that may exist in the vehicle in certain scenarios. According to the different driving behavior models of the car owner, the vehicle status under different driving habits can be simulated in a targeted manner, thereby providing personalized maintenance and suggestions for the car owner. Through multi-scenario simulation, it is possible to accurately predict changes in vehicle performance under different environments and driving conditions, providing car owners with more reference data to optimize vehicle use and improve the efficiency of repair and maintenance.

[0032] Preferably, the specific steps of step S22 are:

[0033] Identify key time points of vehicle timing state parameters and mark multiple key time points of vehicle operation;

[0034] Calculate the engine speed based on multiple key time points of vehicle operation to obtain the engine speed characteristics at each time point;

[0035] Perform engine temperature time series variation analysis on vehicle time series state parameters to generate engine temperature variation characteristics;

[0036] Perform discrete fitting of temperature fluctuations on the engine temperature variation characteristics and construct the engine temperature variation curve;

[0037] Perform real-time tire pressure situation analysis on vehicle time sequence state parameters to generate vehicle tire pressure situation characteristics;

[0038] Calculating the vehicle speeds at the plurality of key time points of vehicle operation;

[0039] A multi-time point vehicle operation state analysis is performed on the vehicle speed, engine temperature curve, vehicle tire pressure situation characteristics and engine speed characteristics at each time point to generate vehicle operation state characteristics at multiple time points.

[0040] The present invention can capture the performance changes of the vehicle at a specific moment by identifying key time points, ensure that the focus of data analysis is placed on key periods, thereby improving the accuracy of fault diagnosis. Identifying key time points in vehicle operation (such as sudden acceleration, braking, engine load changes, etc.) can help diagnostic equipment perform more detailed data analysis at these moments. The engine speed is one of the important indicators of vehicle performance. By calculating the speed at multiple key time points, the working state of the engine can be effectively captured, especially at load changes, acceleration or braking moments. The speed characteristics can be used to identify the running performance of the engine under different working conditions, and possible performance problems can be discovered in advance, such as abnormal conditions of too high or too low speed. The change in engine temperature directly affects the operating efficiency and life of the engine. By analyzing its time series change characteristics, it can be understood in real time whether the engine is in an overheated state, helping to diagnose potential problems (such as cooling system failures) in advance. By performing time series analysis on the engine temperature, the temperature fluctuation trend and change pattern can be identified, helping to optimize the vehicle's operating state and reduce damage caused by abnormal temperature. The temperature change curve can provide more detailed temperature fluctuations through discrete fitting, help identify nonlinear temperature change trends, and more accurately grasp the engine temperature fluctuations. The temperature change curve can reveal potential temperature fluctuations. mode, which helps to diagnose problems such as overheating and poor temperature control, and predict and avoid engine damage in advance. Tire pressure is a key parameter that affects vehicle safety and performance. Through real-time tire pressure situation analysis, you can grasp the status of the tire in real time and promptly detect abnormal conditions such as low tire pressure or high tire pressure. Abnormal tire pressure often leads to accidents or accelerated tire wear. Real-time analysis can provide car owners with abnormal tire pressure warnings to improve driving safety. By calculating the vehicle speed at key time points, you can fully understand the vehicle's performance in different driving scenarios (such as city driving, highway driving, etc.), and help determine whether there is abnormal acceleration or braking behavior. Vehicle speed is an important reflection of the health of the vehicle's power system. The multi-point analysis can not only detect the current status of the vehicle, but also track its changing trends, which helps to more accurately identify potential faults and the time periods when they occur. Through the analysis of status characteristics at multiple time points, the diagnostic equipment can automatically identify the operating characteristics of the vehicle at different stages, and give personalized maintenance suggestions and fault warnings based on driving behavior and environmental factors.

[0041] Preferably, step S3 specifically comprises the following steps:

[0042] Step S31: Perform rolling prediction of vehicle status in future time periods on the vehicle status operation simulation data of each scenario to generate vehicle status characteristics in future time periods;

[0043] Step S32: predicting potential abnormal faults based on vehicle state characteristics in a future time period, thereby obtaining potential abnormal faults of the vehicle state;

[0044] Step S33: locating the fault part of the potential abnormal fault of the vehicle state, and marking the location point of the abnormal fault part of the vehicle;

[0045] Step S34: Calculate the failure time window probability of the potential abnormal failure of the vehicle state, so as to obtain a failure time window probability curve.

[0046] The present invention can provide the vehicle owner with the vehicle status characteristics in the future through rolling prediction of the vehicle status. This helps to understand the possible performance of the vehicle in future use in advance and discover potential risks in advance. Through rolling prediction, the diagnostic equipment can detect abnormalities in the state changes at different time points in advance, such as vehicle performance degradation, increased fuel consumption, etc., so as to provide the owner with more dynamic maintenance suggestions. Based on the vehicle status characteristics of the future time period, the potential abnormal fault prediction can accurately identify the faults that the vehicle may encounter in the future, intervene in advance, and avoid the occurrence of major faults. Through the careful analysis of the vehicle status characteristics, the potential problems that may exist in the vehicle can be discovered. For example, signs such as abnormal engine temperature and tire pressure fluctuations may indicate engine failure, tire problems or other system failures. Predicting these faults in advance can reduce maintenance costs and improve safety. Fault location is one of the core tasks in fault diagnosis. By locating potential abnormal faults, the specific part of the fault (such as engine, transmission, brake system, etc.) can be accurately identified, making maintenance more efficient and avoiding ineffective inspection and maintenance. By marking the fault location point, maintenance personnel can quickly locate the problem area, reducing unnecessary time waste and resource consumption, thereby improving the efficiency of troubleshooting. By calculating the probability of the fault time window, it is possible to analyze the time period when the vehicle fault occurs, helping car owners and maintenance personnel understand the high-risk period when the fault occurs, so as to formulate corresponding preventive measures. According to the fault time window probability curve, car owners can perform preventive maintenance in the time period when the probability of fault occurrence is higher, avoiding vehicle downtime or accidents caused by faults.

[0047] Preferably, the specific steps of step S4 are:

[0048] Step S41: performing fault attribution diagnosis analysis on the abnormal fault location points of the vehicle, thereby generating abnormal fault diagnosis data;

[0049] Step S42: performing vehicle fault decision on the abnormal fault diagnosis data, thereby generating vehicle fault diagnosis decision data;

[0050] Step S43: mining diagnostic equipment update requirements based on vehicle fault diagnosis decision data to generate diagnostic equipment update requirement data;

[0051] Step S44: Synchronize the latest update data on the cloud based on the diagnostic device update requirement data to generate fault diagnosis requirement update data.

[0052] The present invention can accurately determine the root cause of the fault, rather than just the fault symptom, through fault attribution diagnosis and analysis. By in-depth analysis of the diagnostic data of the fault location, it can accurately identify the specific problem in the vehicle system (such as the electronic control system, mechanical components, transmission system, etc.). By performing refined diagnosis on the fault location, the probability of misdiagnosis is reduced, the accuracy and reliability of fault identification are improved, and unnecessary repairs or replacement of parts due to inaccurate diagnosis are avoided. The decision data generated based on abnormal fault diagnosis data can provide specific decision support for maintenance personnel and vehicle owners. The equipment can recommend whether emergency maintenance is needed and when to perform maintenance based on information such as the fault type and fault severity, so as to help vehicle owners make correct maintenance decisions. Through fault decision-making, the equipment can automatically determine the severity and urgency of the fault, and provide appropriate treatment plans, such as whether the vehicle needs to be taken out of service immediately, or can continue to drive but needs to be repaired in the near future. Periodic maintenance is carried out. By analyzing the fault diagnosis decision data, the specific needs of the automotive diagnostic equipment that need to be updated can be excavated to ensure that the equipment remains efficient and accurate in the ever-changing automotive technology environment. According to the vehicle fault diagnosis results, the equipment's diagnostic algorithms, data analysis models, etc. can be updated and improved, so that the equipment can better adapt to the diagnosis needs of new models and new fault types. By excavating the equipment update needs, it can be ensured that the diagnostic equipment keeps up with the latest trends in vehicle technology and fault diagnosis, and improve the adaptability and processing capabilities of the equipment. Through cloud synchronization processing, the latest update data of the diagnostic equipment can be pushed to the vehicle diagnostic equipment in real time, ensuring that the equipment always has the latest fault diagnosis capabilities and avoiding the inability to detect new faults due to outdated equipment. Cloud synchronization updates ensure that the update process of the diagnostic equipment is seamless, and car owners and maintenance personnel can automatically receive equipment updates without manual intervention, ensuring that the equipment is always kept up to date.

[0053] Preferably, the specific steps of step S5 are:

[0054] Step S51: predicting the idle time of the vehicle based on the driving behavior model of the vehicle owner in different scenarios, and generating the predicted idle time of the vehicle;

[0055] Step S52: performing idle time distribution analysis on the predicted idle time of the vehicle and constructing a vehicle idle time distribution map;

[0056] Step S53: Calculate the optimal demand update time for the vehicle idle time distribution diagram according to the failure time window probability curve, and extract the optimal diagnostic equipment update time point.

[0057] The present invention can accurately predict the idle time of the vehicle by analyzing different driving scenarios of the car owner (such as commuting, long-distance driving, etc.). This means that the car diagnostic equipment can be updated during the idle time of the car owner's vehicle without interfering with the normal use of the car owner, reducing the impact of the update process on daily life. By combining the driving behavior model, peak hours and periods of frequent driving can be avoided to ensure that the equipment update is performed when the vehicle is idle. This can avoid driving interruptions caused by equipment updates, thereby improving the satisfaction of the car owner. By analyzing the distribution of the vehicle's idle time, the periodic characteristics and laws of vehicle idleness can be better understood. Based on these data, the update task can be performed at the most suitable time point. Arrangements can be made to avoid untimely equipment downtime caused by inappropriate selection of update timing. The construction of an idle time distribution map can intuitively display the period, duration and high-frequency idle time of the vehicle's idleness. This allows the owner or manager to clearly see when the vehicle is most idle, providing an effective time reference for equipment updates. By combining the failure time window probability curve, it can be predicted when the possibility of failure is greatest, so as to select the optimal time point in the vehicle's idle period for equipment updates. This approach ensures that the equipment update will not only not affect the owner's use, but also maximize the benefits of the equipment update - that is, update before the potential high-risk period of vehicle failure to avoid the occurrence of failures.

[0058] Preferably, the specific steps of step S6 are:

[0059] Step S61: performing differential adaptation optimization of the current vehicle configuration according to the fault diagnosis requirement update data, and generating differential adaptation optimization update data;

[0060] Step S62: Identify independently executable data blocks for the differentiated adaptation optimization update data, and mark multiple independently executable data blocks;

[0061] Step S63: performing data segmentation processing based on a plurality of independently executable data blocks to generate a plurality of segmentation update data packets;

[0062] Step S64: performing instant remote update processing on multiple segment update data packets based on the optimal diagnostic device update time point, thereby completing the data update operation of the automobile diagnostic device.

[0063] The present invention can ensure that the updated data and diagnostic algorithms are personalized for the unique configuration and needs of each vehicle through differentiated adaptation and optimization according to different vehicle models, configurations and fault diagnosis requirements, which avoids a "one-size-fits-all" update method and improves the accuracy and adaptability of the diagnostic equipment. Through differentiated adaptation, the diagnostic equipment can optimize the update content, reduce unnecessary data and algorithm adjustments, avoid inappropriate update operations, and improve the equipment update efficiency. By identifying independently executable data blocks of the update data, the update task is split into multiple smaller independent modules, avoiding the risks that may be caused by a one-time update. These independent data blocks can be executed separately to ensure that each module can be updated independently and stably, reducing the failure probability of the entire update process. Independent data blocks can be selected for updating as needed, allowing customized updates for different needs of different vehicles, optimizing the update process, avoiding unnecessary waste of resources, and dividing the update data into multiple segmented data packets. The update task of each segment can be prioritized according to its importance, timeliness and complexity, so that When necessary, update key data first to ensure that the equipment resumes normal operation in the shortest time possible. Data segmentation can reduce the size of each data transmission, making the remote update process more efficient and faster, especially in an unstable network environment, which can reduce the risk of failure during the transmission process and ensure the smooth completion of the update task. By combining the optimal equipment update time point, it can ensure that the data update is carried out during the period when the vehicle is idle and the risk of failure is low, minimizing interference with vehicle use and improving the owner's satisfaction. Even if the owner is not at the repair station, the diagnostic equipment can automatically update the data through remote update, which makes the update operation more flexible and does not require the owner to be present, greatly improving the convenience of the update. Through instant remote update processing, it can quickly start and complete the data update during the vehicle's idle period, ensuring that the equipment's diagnostic capabilities are improved or repaired in the shortest time possible, avoiding long-term downtime or misdiagnosis. Remote update ensures that the update process is not restricted by the location and physical location of the equipment, reducing update failures caused by equipment location problems or errors in the manual update process.

[0064] In this specification, an automobile diagnostic device is provided, which is used to execute the data updating method of the automobile diagnostic device as described above, including:

[0065] The multi-scenario driving behavior module is used to obtain the vehicle's historical operation logs; perform multi-point sampling of the owner's driving behavior in the vehicle's historical operation logs, and perform behavior feature evolution in different scenarios, thereby obtaining the owner's driving behavior model in different scenarios;

[0066] The multi-scenario operation simulation module is used to extract the vehicle time-series state parameters based on the vehicle's historical operation logs; perform multi-scenario operation simulation on the vehicle time-series state parameters according to the owner's different scenario driving behavior models, and generate vehicle state operation simulation data for each scenario;

[0067] The fault prediction module is used to perform rolling prediction of vehicle status in future periods and calculate the probability of fault time window for the vehicle status operation simulation data of each scenario, and obtain the location point of abnormal fault part of the vehicle and the probability curve of fault time window;

[0068] The demand update module is used to perform fault attribution diagnosis and analysis on the location points of abnormal faults in vehicles and to mine the demand for diagnostic equipment updates to generate fault diagnosis demand update data;

[0069] The idle time prediction module is used to predict the idle time of the vehicle based on the failure time window probability curve and the driving behavior model of the vehicle owner in different scenarios, calculate the optimal demand update time, and extract the optimal diagnostic equipment update time point;

[0070] The real-time remote update module is used to update data according to fault diagnosis requirements to perform differentiated adaptation and optimization of the current vehicle configuration, and to perform real-time remote update processing based on the optimal diagnostic equipment update time point, thereby completing the data update operation of the vehicle diagnostic equipment.

[0071] The present invention can comprehensively capture the driving behavior of the car owner in different scenarios (such as urban driving, high-speed driving, etc.) through multi-point sampling, which enables the system to accurately construct the driving behavior model of the car owner, ensuring that the actual driving style of the car owner is taken into account in the subsequent vehicle state simulation. In different driving scenarios, the behavioral differences of the car owner will affect the vehicle state. Through the evolution of behavioral characteristics, personalized driving behavior models can be generated for different driving scenarios, providing a more accurate basis for subsequent vehicle state simulation and fault prediction. Based on the multi-scenario driving behavior model, the time series state of the vehicle can be simulated more carefully to ensure that the simulation results are closer to the actual usage. These simulation data can reflect the different driving scenarios. The vehicle operation characteristics under different scenarios can help predict the vehicle's operating status and potential faults. By extracting the vehicle's timing state parameters, the various operating states of the vehicle (such as engine speed, temperature, speed, etc.) can be accurately identified. These data provide a basis for subsequent fault prediction, equipment updates, etc. Through rolling prediction, the future state of the vehicle can be predicted and possible anomalies can be discovered in a timely manner. The probability calculation of the fault time window can help identify which time periods have a higher risk of failure, and then take preventive measures in advance. Through the combination of vehicle state simulation and fault time window, the part where the failure may occur can be accurately located, which provides a direct basis for subsequent fault diagnosis and repair, and improves the diagnostic accuracy. The accuracy of diagnosis can be improved by analyzing the fault location point, accurately identifying the root cause of the problem, helping maintenance personnel understand the specific cause of the fault, and quickly taking repair measures. While determining the fault location, the update requirements can be excavated according to the vehicle status and fault type, providing accurate update direction and content for diagnostic equipment. This accurate demand analysis can improve the pertinence of equipment updates and avoid unnecessary updates or erroneous updates. By combining the owner's driving behavior model and the fault time window, the idle time prediction module can accurately identify the idle time of the vehicle. Equipment updates during these time periods can minimize interference to the owner. By combining the analysis of the owner's driving behavior and fault risk, it can provide each owner with a precise update direction and content. The optimal diagnostic equipment update time is tailored for each vehicle to ensure that the equipment update can be performed when the owner least needs to use the vehicle. Through instant remote updates, the vehicle does not need to go to the repair station or factory for equipment updates, which greatly improves the convenience and flexibility of the update. This provides car owners with a convenient seamless update experience. According to the different configurations and diagnostic needs of the vehicles, differentiated adaptation and optimization are performed to ensure that the update content meets the specific requirements of each vehicle, avoiding unnecessary update content and waste of resources. Through the optimal update time point and differentiated adaptation, the diagnostic equipment can be updated when the vehicle is idle without interfering with the normal use of the vehicle. Remote updates can be completed in real time during the use of the vehicle, improving the efficiency and accuracy of equipment updates. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A schematic flow chart of the steps of a data updating method for automobile diagnostic equipment according to the present invention;

[0073] Figure 2 Detailed implementation flow chart of step S1;

[0074] Figure 3 Detailed implementation flow chart of step S2;

[0075] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0076] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0077] The present application example provides a data update method for automobile diagnostic equipment and automobile diagnostic equipment. The execution subjects of the data update method for automobile diagnostic equipment and automobile diagnostic equipment include but are not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio image management system, an information management system, and a cloud data management system.

[0078] See also Figures 1 to 4 The present invention provides a data updating method for automobile diagnostic equipment, the data updating method for automobile diagnostic equipment comprising the following steps:

[0079] Step S1: obtaining a vehicle historical operation log; performing multi-point sampling of the owner's driving behavior in the vehicle historical operation log, and performing behavior feature evolution in different scenarios, thereby obtaining a driving behavior model of the owner in different scenarios;

[0080] Step S2: extracting vehicle time-series state parameters based on the vehicle historical operation log; performing multi-scenario operation simulation on the vehicle time-series state parameters according to the vehicle owner's driving behavior model in different scenarios, and generating vehicle state operation simulation data for each scenario;

[0081] Step S3: Perform rolling prediction of vehicle status in future time periods and calculation of fault time window probability for the vehicle status operation simulation data of each scenario, and obtain the location point of abnormal fault part of the vehicle and the fault time window probability curve;

[0082] Step S4: performing fault attribution diagnosis analysis on the location points of abnormal fault parts of the vehicle, and mining the diagnostic equipment update requirements to generate fault diagnosis requirement update data;

[0083] Step S5: predicting the idle time of the vehicle based on the different driving behavior models of the vehicle owner according to the fault time window probability curve, calculating the optimal required update time, and extracting the optimal diagnostic equipment update time point;

[0084] Step S6: Update the data according to the fault diagnosis requirements to perform differentiated adaptation optimization of the current vehicle configuration, and perform real-time remote update processing based on the optimal diagnostic equipment update time point, thereby completing the data update operation of the automobile diagnostic equipment.

[0085] The present invention can provide more personalized diagnostic services by modeling the driving behavior of the vehicle owner, making subsequent fault prediction and diagnosis more accurate. Different driving scenarios have different impacts on the vehicle. Analyzing different driving behavior patterns is helpful to accurately evaluate the vehicle's operating health status in different scenarios. Based on multi-point sampling of driving behavior, more valuable data can be extracted, thereby avoiding invalid data that may appear in traditional diagnostic methods. Multi-scenario simulation based on the driving behavior model can provide more accurate vehicle operating status data and predict the vehicle's operating performance in different scenarios. Through scenario-based simulation, it can provide diagnostic equipment with operating data under a variety of different conditions, helping the equipment to adapt to diagnostic needs in different environments. Through rolling prediction and probability calculation of the fault time window, it can predict in advance the time and location of the vehicle's possible failure, thereby improving the accuracy of fault warning. The probability curve clearly defines the possibility and time point of the failure, helping to locate the fault site more quickly, providing High maintenance efficiency. Through fault attribution analysis, it can ensure that the cause of each fault point is fully understood and the accuracy of diagnosis is improved. According to the fault data, the system will automatically generate update requirements to avoid manual intervention and ensure that the diagnostic equipment can get the required updates in a timely manner. Through idle time prediction and update time optimization, the conflict between the update time of traditional diagnostic equipment and the driving needs of the owner is avoided. The update operation can be performed when the owner is not using the vehicle, minimizing the interference in the use of the vehicle and improving the owner's experience and satisfaction. Through differentiated adaptation optimization, it ensures that each vehicle can obtain the most accurate diagnosis, and can adjust the update strategy according to the specific configuration of the vehicle to improve the adaptability of the system. The remote update operation eliminates human intervention in the traditional update process, improves the update efficiency and accuracy, and ensures that the vehicle automatically completes the equipment update at the most appropriate time. With the continuous optimization of equipment and algorithms, the vehicle's diagnostic capabilities will continue to improve, achieving longer-term and more accurate fault diagnosis and early warning.

[0086] In the embodiment of the present invention, refer to Figure 1 , is a flowchart of the steps of a data updating method for automobile diagnostic equipment of the present invention. In this example, the steps of the data updating method for automobile diagnostic equipment include:

[0087] Step S1: obtaining a vehicle historical operation log; performing multi-point sampling of the owner's driving behavior in the vehicle historical operation log, and performing behavior feature evolution in different scenarios, thereby obtaining a driving behavior model of the owner in different scenarios;

[0088] In this embodiment, historical operation logs are extracted from the vehicle's onboard system or connected smart device. These logs usually record the vehicle's driving time, speed, acceleration, use of the accelerator and brake pedals, engine speed, GPS coordinates and other information. Ensure that the timestamp of the data is accurate for subsequent analysis. In order to enhance the representativeness of the data, it is recommended to collect at least one month of operation logs, and the sample size should reach thousands of records to cover sufficient driving scenarios and conditions. Clean and format the collected raw log data. Remove invalid data (such as records when the sensor fails), fill in missing values ​​(mean or median can be used to fill), and ensure data consistency and integrity. Design the data structure to ensure that each record contains at least key fields such as timestamp, speed, acceleration, accelerator and brake status, and vehicle location. Multi-point sampling based on time windows. You can choose fixed time intervals (such as every minute) or event-based sampling (such as recording when the speed change exceeds a certain threshold) to ensure the diversity and representativeness of the sample. Sampling is performed in different driving scenarios (such as cities, rural areas, highways, and roads) to ensure that various driving conditions are covered. GPS data can be used to mark time periods to distinguish different driving environments. Use clustering algorithms (such as K-means or DBSCAN) to analyze the sampled data and identify different driving scenarios. By clustering features such as speed, acceleration, and steering angle, the data can be divided into categories such as urban driving, highway driving, and rural driving. In each scenario, record the characteristic parameters of driving behavior, such as frequent acceleration and many braking times in urban driving, and smooth acceleration and high speed in highway driving. For each driving scenario, extract key driving behavior features. Common features include the number of accelerations, the number of sudden braking times, the average speed, the speed fluctuation amplitude, the frequency of accelerator and brake use, etc. These features can reflect the driver's behavioral tendencies in different scenarios. By calculating statistics such as the mean, standard deviation, and frequency distribution of each feature, analyze the changing trend of driving behavior. Based on the extracted features, build a variety of driving behavior models. Machine learning algorithms (such as decision trees, random forests, or support vector machines) can be used for training to identify and predict driver behavior patterns. Through cross-validation and model evaluation, select the best model parameters and structure to ensure that the model has good generalization ability. Use new historical data to verify the constructed driving behavior model to ensure its effectiveness and accuracy. Evaluate the performance of the model in predicting driving behavior, including metrics such as precision, recall, and F1 score.

[0089] Step S2: extracting vehicle time-series state parameters based on the vehicle historical operation log; performing multi-scenario operation simulation on the vehicle time-series state parameters according to the vehicle owner's driving behavior model in different scenarios, and generating vehicle state operation simulation data for each scenario;

[0090] In this embodiment, the required time series state parameters are extracted from the historical operation logs obtained. These parameters usually include speed, acceleration, engine speed, position of the accelerator and brake pedals, fuel consumption, GPS positioning, etc. Ensure that the timestamps of the data are consistent for subsequent analysis. The extracted time series state parameters are organized into a structured data frame (DataFrame), each row represents the state at a time point, and the columns include timestamp, speed, acceleration, speed, etc. This data frame will be used for subsequent multi-scenario simulation. The definitions of different scenarios are extracted from the obtained driving behavior model. For example, urban driving, highway driving, and rural driving. Each scenario should contain specific driving characteristics, such as acceleration mode, deceleration habits, and driving frequency. The time series state parameters are adjusted according to the driving behavior characteristics of each scenario. Scenario-specific parameters can be set, such as: Urban driving: increase frequent acceleration and deceleration events, set the average speed to 30 km / h, and the frequency of emergency braking to 2 times per kilometer. High-speed driving: reduce acceleration and deceleration events, set the average speed to 100 km / h, and the frequency of emergency braking to 1 time per 10 kilometers. Rural driving: Set the average speed to 50 km / h, allowing occasional acceleration and deceleration. Use simulation tools (such as MATLAB Simulink or the SimPy library in Python) to perform multi-scenario operation simulations. Generate vehicle state operation data for each scenario by inputting the adjusted timing state parameters. In the simulation, consider the impact of environmental factors (such as slope, traffic signals) and driving behavior (such as overtaking, frequent stops) on the vehicle state to ensure the realism of the simulation. After each scenario simulation, record the output vehicle state operation data, including timestamp, speed, acceleration, engine speed, etc. Ensure that the simulation data for each scenario is stored in a separate file for subsequent analysis. Arrange the simulation data for each scenario into a data frame and perform preliminary analysis. For example, calculate statistics such as the average speed, total driving distance, frequency of acceleration and deceleration for each scenario to evaluate the driving characteristics in different scenarios.

[0091] Step S3: Perform rolling prediction of vehicle status in future time periods and calculation of fault time window probability for the vehicle status operation simulation data of each scenario, and obtain the location point of abnormal fault part of the vehicle and the fault time window probability curve;

[0092] In this embodiment, the vehicle state of each scene is extracted and run simulation data is extracted. These data should include key parameters such as timestamp, speed, acceleration, engine speed, etc. The simulation data of different scenes are merged into a comprehensive data set to ensure that the timestamps of the data are consistent for subsequent rolling prediction. For fault prediction, key feature parameters such as acceleration change rate, speed fluctuation, engine speed, etc. are selected, which have a high correlation with the occurrence of faults. The importance of each feature is confirmed by correlation analysis (such as Pearson correlation coefficient). A suitable time series prediction model is selected for rolling prediction of future states. Commonly used models include ARIMA (autoregressive integrated moving average model), LSTM (long short-term memory network) and SARIMA (seasonal autoregressive integrated moving average model). For more complex nonlinear time series data, LSTM may be more suitable because it can capture time dependencies in long time series. The selected prediction model is trained using historical running simulation data. The data set is divided into a training set and a test set (for example, 70% for training and 30% for testing) to ensure the generalization ability of the model. The model performance is evaluated by cross-validation, and the accuracy of the prediction results is measured by indicators such as root mean square error (RMSE) and mean absolute error (MAE). If LSTM is used, the input data usually needs to be normalized to improve the training effect. Once the training is completed, the trained model is used to make rolling predictions of the future vehicle status. Set the prediction time window (for example, the next 30 minutes or 1 hour) and gradually predict the state parameters at each time point. Record the prediction results at each time point to form a complete vehicle status prediction sequence for the future period. Collect historical fault data, including information such as the time when the fault occurred, the type of fault, and the affected components. This data will provide basic information on the occurrence of the fault for probability calculation. Based on the historical fault data, a probability model for the fault time window is established. Statistical methods (such as Poisson distribution or Weibull distribution) can be used to describe the probability of fault occurrence. By analyzing the time intervals of historical faults, the frequency and probability of fault occurrence in each time window are calculated. For example, if 5 out of the past 100 records of a certain fault occurred in a specific time period, the probability of failure in that time period is 5%. Use the calculated fault probability data to draw a probability curve for the fault time window. Generate a line chart or bar chart using the time window as the horizontal axis and the probability of failure as the vertical axis. Display the failure probability curve through visualization tools (such as Matplotlib or Seaborn) for easy analysis and understanding. Identify the location point of abnormal failure based on the rolling predicted vehicle status and failure time window probability. For example, when the predicted acceleration change rate exceeds a certain threshold and the failure probability is high in the same time window, it can be considered that the component has a failure risk. Combine the failure probability with the state parameter to generate a comprehensive judgment model to automatically identify potential fault locations.

[0093] Step S4: performing fault attribution diagnosis analysis on the location points of abnormal fault parts of the vehicle, and mining the diagnostic equipment update requirements to generate fault diagnosis requirement update data;

[0094] In this embodiment, a suitable fault analysis method is selected for diagnosis and attribution. Commonly used methods include fault tree analysis (FTA), cause-and-effect diagrams (such as stone diagrams), and root cause analysis (RCA). These methods can help identify the root causes of faults and their influencing factors. For each abnormal fault location, its possible fault cause is analyzed. For example, if the engine fails frequently, the possible causes include sensor failure, fuel quality problems, or mechanical wear. Through logical reasoning and comparison of historical fault data, the fault scope is gradually narrowed down, and the results of the diagnostic analysis are systematically recorded. The attribution cause, impact degree, and recommended repair measures of each fault are classified and stored. This information will provide a basis for subsequent equipment update needs. The status of the current vehicle's diagnostic equipment is evaluated to confirm its performance and applicability. The equipment's usage records, fault history, and operating parameters are collected to analyze whether the equipment meets the current fault diagnosis needs. According to the results of the fault attribution analysis , combined with the status assessment of the equipment, a demand analysis model is established. A decision tree or logistic regression model can be used to identify which equipment needs to be updated or replaced. For each fault location, the corresponding update requirements are identified. For example, if a sensor frequently fails and affects the accuracy of fault diagnosis, it is necessary to consider updating the sensor or its related software. The update requirements for each fault are recorded, including the updated device type, model, recommended update timing and expected effect. The above analysis and mining results are organized into a structured data format to ensure the integrity and logic of the data. The data should include the fault location, fault cause, diagnostic equipment status, update requirements and recommended measures. A fault diagnosis requirement update report is generated, which lists the diagnostic analysis results of each fault and the corresponding equipment update requirements in detail. This report will serve as the basis for subsequent decision-making and resource allocation. The generated fault diagnosis requirement update data is stored in the database to ensure that relevant personnel can easily access and query this data.

[0095] Step S5: predicting the idle time of the vehicle based on the different driving behavior models of the vehicle owner according to the fault time window probability curve, calculating the optimal required update time, and extracting the optimal diagnostic equipment update time point;

[0096] In this embodiment, the relationship between the failure probability and different driving scenarios is identified through statistical analysis. For example, correlation analysis (such as Pearson correlation coefficient) can be used to evaluate the correlation between the failure time window and driving behavior characteristics (such as acceleration and emergency braking frequency). Based on the driving behavior model of the owner, a vehicle idle time prediction model is constructed. Regression analysis (such as linear regression or multiple regression) can be used to predict the vehicle idle time in a certain time period in the future. The predicted time period (such as daily or weekly) is set, and the driving frequency and behavior characteristics of different scenarios are considered. For example, city driving may lead to shorter idle time, while high-speed driving may lead to longer idle time. Combined with the failure time window probability, the predicted value of idle time is dynamically adjusted. For example, if the probability of failure in a certain time period is high, it may be necessary to arrange equipment updates in advance, resulting in a reduction in idle time. Through the weighted model, the failure probability is used as a weight factor to affect the prediction result of idle time, ensure the accuracy of the prediction, and the prediction value is adjusted according to the failure time window probability. The rate curve can be used to identify time periods with high probability of failure and use them as candidate time windows for the optimal update time. For example, if the probability of failure exceeds a threshold (such as 10%) within a certain time period, it can be regarded as a high-risk window. Combined with the idle time prediction of the vehicle, the optimal diagnostic equipment update time point can be extracted. This can be achieved through optimization algorithms (such as linear programming or genetic algorithms) to ensure that the time period with the longest idle time is selected for equipment update under an acceptable failure risk. If the vehicle idle time is long from 7 to 9 pm on a certain weekday and the failure probability is relatively low, this time period can be used as the best choice for equipment update. The extracted optimal diagnostic equipment update time point and the corresponding idle time prediction results are organized into a structured data format, recording the failure probability, idle time and recommended operation steps at each time point, and generating a report containing the optimal update time point and related analysis results for team members to understand and execute. This report should include the parameters of the prediction model, failure probability analysis and update requirements.

[0097] Step S6: Update the data according to the fault diagnosis requirements to perform differentiated adaptation optimization of the current vehicle configuration, and perform real-time remote update processing based on the optimal diagnostic equipment update time point, thereby completing the data update operation of the automobile diagnostic equipment.

[0098] In this embodiment, the current vehicle configuration is compared with the fault diagnosis requirement to identify the devices and configurations with differences. A comparative analysis method can be used to list the devices that need to be updated or replaced. If it is found that the sensor model used in the vehicle is outdated, and the fault diagnosis requirement recommends updating to a new model, it will be included in the update list. An optimization strategy is formulated for the identified differences. The priority ranking method can be used to determine which devices should be updated first. Usually, the importance of the device, the frequency of failures, and the urgency of the update are considered, and a detailed update plan is formulated to clarify the update steps, required time, and resources for each device. A suitable remote update tool (such as an OTA update system) is selected to ensure that the device and software can be updated safely and effectively, and to ensure that the tool has version management, rollback mechanism, and security verification functions. According to step S5, The optimal diagnostic equipment update time point extracted from the data is used to arrange specific update operations to ensure that the update is performed during the vehicle's idle time to reduce the impact on normal driving. For example, if the time point is from 7 to 9 p.m., the update process is started during this time period, the remote update program is started, and the new diagnostic equipment firmware and software versions are uploaded. The data transmission encryption during the update process is ensured to prevent data leakage or tampering. During the update process, the update status is monitored in real time, and the update progress and results of each device are recorded. If an abnormality occurs, measures should be taken immediately to troubleshoot the fault. After the update is completed, the new device and software are functionally tested to ensure their normal operation. The update effect can be verified by running the self-test program or performing actual driving tests. The status of each device is recorded to confirm whether it meets the expected performance indicators. Feedback from vehicle owners or operation and maintenance personnel on the use of the updated equipment is collected to evaluate the effectiveness and reliability of the update. These feedbacks will provide important references for subsequent updates and maintenance. The updated device status, version number, update log and other information are organized into structured data and stored in the database to ensure subsequent query and management. An update report is generated, including the update content, implementation steps, result verification and feedback information, for reference by relevant personnel.

[0099] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0100] Step S11: Obtain vehicle historical operation log;

[0101] Step S12: Perform multi-point sampling of the vehicle owner's driving behavior in the vehicle's historical operation log to extract the vehicle owner's driving behavior data;

[0102] Step S13: mining the personalized driving characteristics of the vehicle owner on the vehicle owner's driving behavior data to generate a representation of the vehicle owner's driving behavior;

[0103] Step S14: performing vehicle operation multi-scenario identification based on the vehicle historical operation log, and extracting multiple vehicle operation scenarios;

[0104] Step S15: Evolving the behavior characteristics of different scenarios for multiple vehicle operation scenarios according to the driving behavior representation of the vehicle owner, thereby obtaining driving behavior models of different scenarios for the vehicle owner.

[0105] In this embodiment, it is confirmed that the vehicle's intelligent system (such as an on-board computer, GPS module, OBD-II interface, etc.) can record and store historical operation data. The data source should include information such as the vehicle's speed, acceleration, fuel consumption, mileage, driving time, etc. Set the data collection cycle, such as recording data once per second, to ensure that a high-frequency detailed log is obtained. Acquire data from sensors through the vehicle's communication protocol (such as CAN bus). During implementation, a data recorder or on-board diagnostic tool (such as ELM327) can be used to export data to CSV or JSON format for subsequent processing. Store the collected historical operation logs in a database, and design a reasonable database table structure to support subsequent data query and analysis. The table structure should include fields such as timestamp, speed, fuel consumption, GPS coordinates, etc.

[0106] {

[0107] "timestamp": "2024-12-30T08:00:00Z",

[0108] "speed": 60,

[0109] "fuel_consumption": 5.2,

[0110] "gps_coordinates": {

[0111] "latitude": 34.0523,

[0112] "longitude": -118.2437

[0113] }

[0114] }

[0115] Filter out data points related to driving behavior from historical logs, such as sharp changes in acceleration, braking force, steering angle, etc. Set filtering conditions, such as recording data when the vehicle speed is higher than 30 km / h. Use time window technology for multi-point sampling. Set a time window (such as 5 minutes) and record driving behavior data at fixed time intervals (such as every 30 seconds) within this window. The recorded data should include the vehicle's speed, acceleration, fuel consumption, steering angle, etc., to form a complete driving behavior sample. Store the sampled data in a database for subsequent analysis. At the same time, data visualization tools (such as Matplotlib) can be used to generate a time series diagram of driving behavior to facilitate the observation of driving behavior patterns. Extract personalized driving features from the sampled data, including but not limited to driving style (such as aggressive, stable), average speed, number of sudden accelerations, number of sudden brakes, etc. Set a specific feature calculation formula. Aggressive driving style can be defined as the frequency of acceleration exceeding a certain threshold (such as 3 m / s²). Perform statistical analysis on the extracted features and calculate the mean, standard deviation, etc. of each feature to form the basic data of the owner's personalized driving features. Use cluster analysis (such as K-Means) to classify driving behaviors into different categories and identify groups of car owners with similar driving styles. Generate personalized representations of car owners' driving behaviors and record them in the database. The representation should include information such as car owner ID, driving style category, and key feature values. Define different operating scenarios, such as urban driving, highway driving, and rural road driving. Each scenario should have a clear feature description, such as the typical speed range of urban driving, frequent braking and acceleration. Use machine learning algorithms (such as decision trees and random forests) to classify historical operating logs. Input features include speed, acceleration, driving time, GPS coordinates, etc. When training the model, use labeled datasets to ensure that the model can accurately identify different driving scenarios. Use the trained model to perform scene recognition on the vehicle's historical operating logs and record the driving scene corresponding to each time period. Store the recognition results in the database for subsequent analysis. Define the driving feature evolution rules under different scenarios. For example, in urban driving scenarios, car owners may be more inclined to brake and accelerate frequently, while maintaining a stable speed on highways. Build a personalized driving behavior model based on the owner's driving behavior representation and the identified scene features. Using regression analysis or decision tree methods, driving characteristics are mapped to scene types to form a dynamic model.

[0116] {

[0117] "user_id": "1",

[0118] "scene_behavior_model": {

[0119] "urban": {

[0120] "avg_speed": 30,

[0121] "hard_accelerations": 5,

[0122] "hard_brakes": 12

[0123] },

[0124] "highway": {

[0125] "avg_speed": 80,

[0126] "hard_accelerations": 2,

[0127] "hard_brakes": 1

[0128] }

[0129] }

[0130] }

[0131] The constructed driving behavior model is verified, and the accuracy and effectiveness of the model are evaluated by comparing it with actual driving data. The model parameters are adjusted according to the verification results, and the behavior evolution rules are continuously optimized to improve the adaptability and predictive ability of the model.

[0132] In this embodiment, the specific steps of step S14 are:

[0133] Perform vehicle location tracking calculations based on the vehicle's historical operation logs to generate the vehicle's time-series location trajectory;

[0134] Perform GPS map visualization based on the vehicle's time-series positioning trajectory to obtain a location trajectory visualization map;

[0135] The vehicle time series positioning position trajectory is segmented into multiple time periods to obtain the position trajectory of different time periods;

[0136] According to the location trajectories in different time periods, the location trajectory visualization map identifies the road section where the trajectory is located, and analyzes the road section status characteristics in each time period;

[0137] Based on the road state characteristics of each time period, multiple vehicle operation scenarios are identified and multiple vehicle operation scenarios are extracted.

[0138] In this embodiment, the historical operation log of the vehicle is collected, including timestamp, GPS coordinates (longitude, latitude), speed, acceleration and other information. To ensure the integrity and accuracy of the data, the data format should be CSV or JSON. Position tracking calculation is performed based on the GPS coordinates. The GPS coordinates of each time point are connected to form a continuous trajectory. The Haversine formula can be used to calculate the distance between two adjacent points to ensure the true reflection of the trajectory.

[0139] {

[0140] "vehicle_id": "1",

[0141] "trajectory": [

[0142] {"timestamp": "2024-12-30T08:00:00Z", "latitude": 34.0523, "longitude": -118.2437},

[0143] {"timestamp": "2024-12-30T08:01:00Z", "latitude": 34.0524, "longitude": -118.2438} ]

[0145] }Choose a suitable visualization tool, such as Folium, Matplotlib, Plotly or Leaflet, which can help plot the GPS coordinates on the map. Set the initial view and zoom level of the map to ensure that the vehicle's movement trajectory can be clearly displayed. Using the selected visualization tool, plot the vehicle's location trajectory points on the map one by one to form a continuous movement trajectory. You can set different colors and markers to distinguish different driving states.

[0146] import folium

[0147] m = folium.Map(location=[34.0523, -118.2437], zoom_start=13)

[0148] trajectory = [(34.0523, -118.2437), (34.0524, -118.2438)]

[0149] folium.PolyLine(trajectory, color='blue').add_to(m)

[0150] m.save('trajectory_map.html')

[0151] Determine the rules for time division, such as by hour, by weekday / weekend, or by specific events (such as starting the vehicle, parking, etc.). The time window can be set to 1 hour.

[0152] Example time period division:

[0153] 08:00 - 09:00;

[0154] 09:00 - 10:00;

[0155] Traverse the time series location trajectory and divide the trajectory data according to the set time period rules. The data of each time period can be stored in a separate array or database table.

[0156] from datetime import datetime, timedelta

[0157] trajectory = [...] # Assume there is already trajectory data

[0158] time_slots = {}

[0159] for entry in trajectory:

[0160] timestamp = datetime.strptime(entry['timestamp'], '%Y-%m-%dT%H:%M:%SZ')

[0161] slot_key = timestamp.strftime('%Y-%m-%d %H:00')

[0162] if slot_key not in time_slots:

[0163] time_slots[slot_key] = []

[0164] time_slots[slot_key].append(entry)

[0165] The trajectory data of different time periods are stored in the database for subsequent analysis and use. The records of each time period should include information such as the time period and trajectory points. Create a database containing road section information, including the road section name, starting and ending coordinates, road section type (urban roads, highways, etc.) and traffic conditions (smooth, congested, etc.). Perform road section identification on the location trajectory of different time periods to determine the specific road section where the vehicle is located in each time period. Spatial matching algorithms (such as the K nearest neighbor algorithm) can be used to match trajectories with road sections. For example, traverse each location point, calculate its distance from the starting point and the end point of the road section, and determine whether it is within the road section range. Based on the identified road section information, analyze the road section status characteristics of each time period, including the traffic flow, speed limit and traffic accident records of the road section. Store the analysis results in the database for subsequent use and query. Define different vehicle operation scenarios, such as urban driving, highway driving, rural driving, etc., and specify features for each scenario (such as speed, acceleration, road section type). Set feature weighting rules to give different scene features different weights according to different road section status features. Use machine learning algorithms (such as support vector machines and decision trees) to build a scene classification model. Input features include speed, acceleration, road type, time period, etc. When training the model, use labeled data sets to ensure that the model can accurately identify different driving scenarios. Use the trained model to perform scene recognition on the road state features of each time period and record the vehicle behavior in each scenario.

[0166] "time_slot": "2024-12-30 08:00",

[0167] "driving_scene": "urban",

[0168] "average_speed": 25,

[0169] "congestion_level": "high"

[0170] }

[0171] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0172] Step S21: extracting vehicle time sequence state parameters based on the vehicle historical operation log;

[0173] Step S22: performing a multi-time point vehicle operation state analysis on the vehicle time sequence state parameters to generate vehicle operation state characteristics at multiple time points;

[0174] Step S23: performing state scenario matching on vehicle operation state characteristics at multiple time points based on multiple vehicle operation scenarios, and performing scene state change mining to generate a vehicle state change trend for each operation scenario;

[0175] Step S24: Perform multi-scenario operation simulation on the vehicle state change trend of each operation scenario according to the vehicle owner's driving behavior model in different scenarios, and generate vehicle state operation simulation data for each scenario.

[0176] In this embodiment, the historical operation log data is ensured to be complete, and the data should contain key time series information, such as speed, throttle, brake status, steering angle, GPS location, etc. Clearly define the vehicle time series state parameters that need to be extracted, acceleration (calculated by speed change), throttle and brake usage (expressed as a percentage), frequent changes in driving direction, and set the calculation formula for each state parameter. Acceleration = current speed − previous speed / Δt, where Δt is the time interval (for example, 1 second). Traverse the historical operation log, record and calculate the required time series state parameters one by one. Python or R language can be used for data processing to ensure the accuracy of the calculation.

[0177] [{"timestamp": "2024-01-15T08:00:00", "acceleration": 2.0, "throttle_usage": 30, "brake_usage": 0},

[0178] {"timestamp": "2024-01-15T08:01:00", "acceleration": 1.5, "throttle_usage": 35, "brake_usage": 0} ]

[0180] Determine the time points that need to be analyzed, such as every hour, every half hour, or when a specific event occurs. The selection of time points should take into account the frequency of vehicle use and driving habits. For each selected time point, extract relevant features from the time series state parameters, such as average speed, average acceleration, throttle and brake usage rate. The average speed is calculated as: average speed = ∑ speed / N, where N is the number of samples within the time point. Store the generated vehicle operation state features at multiple time points in the database to support subsequent analysis and modeling. Design the corresponding data table structure to ensure the traceability and consistency of feature data. Clarify the different operation scenarios of the vehicle, such as urban driving, high-speed driving, sudden braking, and sudden acceleration. Each scenario should have a specific feature description. Select a suitable matching algorithm (such as KNN, support vector machine) to perform scene matching on the state features of multiple time points. The training model uses the labeled scene data for learning. After scene matching on the state features of each time point, analyze its state changes. For example, observe the change from the urban scene to the high-speed scene, and calculate the change amplitude of parameters such as speed and acceleration. Generate a state change trend chart for each scene, and record the amplitude and frequency of state changes. The mined state change trend data is stored in the database, and a visualization chart is generated to facilitate subsequent analysis and management. Visualization tools can use Matplotlib or Tableau for data display. Scenario definition examples: city driving, high-speed driving, emergency braking. State change record example: {"scene": "city", "avg_speed_change": 10, "acceleration_change": -2}. According to the personalized driving behavior characteristics of the car owner, build driving behavior models suitable for different scenarios. These models should consider driving habits, scene characteristics and corresponding operating states. Set simulation parameters for each scenario, such as speed range, acceleration range, steering angle, etc. Ensure that the simulation parameters can truly reflect the operating state of the vehicle in the scenario. Use simulation tools (such as MATLAB Simulink, CarSim) to run simulations for each scenario. Generate vehicle state change data based on the set driving behavior model and scenario parameters. Analyze the simulation results to evaluate the vehicle performance in different scenarios. Adjust the driving behavior model based on the analysis results to improve the accuracy and practicality of the simulation. Record the simulation results of each scenario, and conduct comparative analysis to find optimization points.

[0181] In this embodiment, the specific steps of step S22 are:

[0182] Identify key time points of vehicle timing state parameters and mark multiple key time points of vehicle operation;

[0183] Calculate the engine speed based on multiple key time points of vehicle operation to obtain the engine speed characteristics at each time point;

[0184] Perform engine temperature time series variation analysis on vehicle time series state parameters to generate engine temperature variation characteristics;

[0185] Perform discrete fitting of temperature fluctuations on the engine temperature variation characteristics and construct the engine temperature variation curve;

[0186] Perform real-time tire pressure situation analysis on vehicle time sequence state parameters to generate vehicle tire pressure situation characteristics;

[0187] Calculating the vehicle speeds at the plurality of key time points of vehicle operation;

[0188] A multi-time point vehicle operation state analysis is performed on the vehicle speed, engine temperature curve, vehicle tire pressure situation characteristics and engine speed characteristics at each time point to generate vehicle operation state characteristics at multiple time points.

[0189] In this embodiment, determine what kind of events or conditions constitute critical time points, such as acceleration, deceleration, steering, sudden braking, engine start or shut down, etc. These time points will help understand the dynamic behavior of the vehicle. Select appropriate data analysis tools, such as the Pandas library in Python, to process and analyze the vehicle time series state data. Ensure that the data is sorted by timestamp. Implement an event detection algorithm, such as using a threshold method to identify critical time points. It can be set to mark a critical time point when the speed change exceeds a certain value (such as 10 km / h) or the accelerator pedal position changes by more than a certain percentage (such as 20%). If the speed suddenly rises from 40 km / h to 60 km / h within a certain period of time, the time can be marked as a critical time point. Manually verify the identified key time points to ensure the accuracy of the algorithm. A time series graph can be drawn through a visualization tool (such as Matplotlib) to check the rationality of the key time point marking. Ensure that the vehicle time series state parameters contain relevant data on the engine speed, usually expressed in RPM (revolutions per minute). For each critical time point, extract the corresponding engine speed value from the time series state data. Ensure that the timestamps are matched accurately. Calculate and store the engine speed characteristics at each key time point. Ensure that the time series status data contains engine temperature information, usually expressed in degrees Celsius. Perform time series analysis on the engine temperature data and calculate the average, maximum, and minimum values ​​of the temperature to capture the overall trend of temperature changes. Plot the temperature change curve with time as the x-axis and temperature as the y-axis to identify temperature fluctuations. Preprocess the collected temperature change data, including removing outliers and filling missing values, to ensure the integrity and accuracy of the data. Select an appropriate discrete fitting method, such as polynomial fitting, spline interpolation, etc., to model temperature changes. Determine the order and parameters of the fit. Use data analysis tools (such as NumPy and SciPy libraries in Python) to perform discrete fitting of temperature data. Generate a fitting curve to describe the temperature change trend. from scipy.interpolate import UnivariateSpline

[0190] import numpy as np

[0191] timestamps = [ / * timestamp data* / ]

[0192] temperatures = [ / * temperature data* / ]

[0193] spline = UnivariateSpline(timestamps, temperatures) Store the fitted temperature curve data in the database and draw a curve graph to show the law and trend of temperature change. Analyze the characteristics of the temperature curve, such as the fluctuation range, rising and falling slopes, to understand the thermal management performance of the engine. Ensure that the vehicle timing status data contains tire pressure information, usually in psi (pounds per square inch). Monitor the collected tire pressure data in real time and calculate the tire pressure changes at each time point. Set the normal tire pressure range (for example, 32-35 psi) as a benchmark. [

[0194] {"timestamp": "2024-01-15T08:00:00", "tire_pressure": 34},

[0195] {"timestamp": "2024-01-15T08:05:00", "tire_pressure": 30, "status":"low"}

[0196] ] Store tire pressure status characteristics in a database and set an alarm mechanism to automatically notify the driver when the tire pressure is below the normal range. Use visualization tools to display tire pressure change trends to help drivers understand tire pressure conditions in a timely manner. Ensure that the time series status data contains vehicle speed information, usually expressed in km / h. For each key time point, extract the corresponding speed value from the time series status data. Record the vehicle speed at each key time point and store the calculated speed characteristics in the database for subsequent analysis. Integrate each feature data (speed, engine speed, temperature curve, tire pressure characteristics) into a unified data structure for comprehensive analysis. Select appropriate analysis methods (such as multivariate linear regression, time series analysis) to analyze the integrated data and understand the relationship between each feature. [

[0197] {"timestamp": "2024-01-15T08:00:00", "speed": 60, "engine_rpm":2000, "temperature": 90, "tire_pressure": 34},

[0198] {"timestamp": "2024-01-15T08:05:00", "speed": 65, "engine_rpm":2500, "temperature": 95, "tire_pressure": 30}

[0199] ] The generated vehicle operating status characteristics are stored in a database, and data analysis is performed to extract valuable information.

[0200] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0201] Step S31: Perform rolling prediction of vehicle status in future time periods on the vehicle status operation simulation data of each scenario to generate vehicle status characteristics in future time periods;

[0202] Step S32: predicting potential abnormal faults based on vehicle state characteristics in a future time period, thereby obtaining potential abnormal faults of the vehicle state;

[0203] Step S33: locating the fault part of the potential abnormal fault of the vehicle state, and marking the location point of the abnormal fault part of the vehicle;

[0204] Step S34: Calculate the failure time window probability of the potential abnormal failure of the vehicle state, so as to obtain a failure time window probability curve.

[0205] In this embodiment, the vehicle status operation simulation data of each scene is collected and sorted, including speed, engine speed, temperature, tire pressure and other parameters to ensure data integrity and accuracy, and select a suitable time series prediction model, such as ARIMA (autoregressive integrated moving average model), LSTM (long short-term memory network), etc. These models can process time series data and make effective predictions. The selected prediction model is trained using historical vehicle status data. During the training process, the data needs to be standardized to improve the convergence speed and prediction accuracy of the model. The trained model is applied to the vehicle status data to make rolling predictions for future time periods. According to the current state, the state characteristics of the next time point are predicted, and the prediction results are used as the input of the next time point. This process is repeated to generate state characteristics of multiple future time points, and a suitable anomaly detection algorithm is selected, such as Isolation Forest, One-Class SVM or deep learning-based autoencoders, etc. These models can effectively identify data points that are significantly different from the normal state, extract key features from the vehicle state characteristics in the future time period, such as a sharp change in speed, an abnormal increase in engine temperature, a significant drop in tire pressure, etc., as input data, use the normal state and fault state marked in the historical data for model training to ensure that the model can learn the characteristics of the normal operating state and identify abnormal patterns that are different from it, apply the trained model to future state feature data, identify potential abnormal faults, mark the time points identified as abnormal by the model, and record the relevant state characteristics, record the predicted potential abnormal faults, and analyze them to evaluate the severity and possible impact of the faults, conduct in-depth analysis of the identified potential abnormal faults, identify the key state parameters when the fault occurs, such as the changing trends of temperature, speed and tire pressure, and establish fault characteristics and potential fault locations based on the structure and working principle of the vehicle The mapping relationship between them, for example, abnormal engine temperature may point to a cooling system failure. Combined with professional vehicle maintenance knowledge, confirm the correlation between fault characteristics and fault locations. Consult a professional technician or refer to the maintenance manual to ensure accuracy. Record the fault location and its corresponding state characteristics to form fault location data, including the fault location, state parameters and timestamp. Determine the concept of the fault time window, that is, the possibility of a fault occurring within a certain time period. This window is usually set around the identified potential fault time point. Collect and analyze historical fault data, and statistically analyze the time distribution and frequency of fault occurrence to determine the probability of fault occurrence in different time periods. Select a suitable probability model (such as Poisson distribution or normal distribution) to fit the fault time distribution data. These models can effectively describe the time characteristics of fault occurrence. Based on the selected probability model, perform probability calculations on the time window of potential faults, generate a fault time window probability curve, and record the probability of fault occurrence within a specific time range.The calculated probability curve is visualized to help managers understand the failure risk and formulate corresponding maintenance strategies.

[0206] In this embodiment, step S4 includes the following steps:

[0207] Step S41: performing fault attribution diagnosis analysis on the abnormal fault location points of the vehicle, thereby generating abnormal fault diagnosis data;

[0208] Step S42: performing vehicle fault decision on the abnormal fault diagnosis data, thereby generating vehicle fault diagnosis decision data;

[0209] Step S43: mining diagnostic equipment update requirements based on vehicle fault diagnosis decision data to generate diagnostic equipment update requirement data;

[0210] Step S44: Synchronize the latest update data on the cloud based on the diagnostic device update requirement data to generate fault diagnosis requirement update data.

[0211] In this embodiment, characteristic data related to abnormal faults are collected, including state parameters of the faulty parts (such as temperature, pressure, speed, etc.), and the integrity and accuracy of the data are ensured for subsequent analysis. A suitable fault attribution analysis method is selected, such as causal analysis, decision tree analysis, or fault tree analysis (FTA). These methods can help identify the root cause of the fault. The collected fault characteristic data are organized into a structured format and input into the selected analysis model. A correlation matrix is ​​constructed according to the data characteristics to identify the relationship between each characteristic and the fault. The attribution analysis model is run to identify the main factors and potential causes of the fault. For example, if the abnormal engine temperature is related to insufficient coolant, the factor can be marked as the cause of the fault. The standards for vehicle fault decision-making are determined, including fault severity, impact scope, and repair priority. These standards will be used to evaluate the handling strategy for each fault. The diagnostic data from the fault attribution analysis is integrated to ensure that all relevant information (such as fault type, severity, and recommended solutions) are summarized into one data set. A suitable decision model is selected, such as multi-attribute decision analysis (MADA) or a priority ranking model, to help evaluate the handling solutions for different faults. The decision model is run to handle each fault. Evaluate the treatment plan and generate corresponding decision results. For example, if the repair cost of a certain fault is low and the impact is significant, it will be handled first. Record the generated fault decision results, including the decision basis, recommended treatment measures and execution schedule, to provide guidance for subsequent execution. Establish an equipment update demand analysis framework to clarify the necessity of updating equipment, the performance bottleneck of current equipment and the impact of related fault data. Integrate fault decision data with the performance data of existing diagnostic equipment to evaluate the effectiveness of current equipment in fault detection and diagnosis. Select appropriate data mining techniques, such as association rule mining, cluster analysis or regression analysis, to identify potential needs for equipment updates. Run the selected data mining model to identify the need for equipment updates based on fault type and frequency. For example, if cooling system failures occur frequently, it may be necessary to update related detection equipment. Establish a cloud data management platform to ensure that all equipment update requirements and fault diagnosis data can be centrally stored and managed. Unify the data format to ensure that the update requirement data is consistent with the data structure in the cloud database for smooth data synchronization. Design a data synchronization mechanism to ensure that each update requirement can be updated to the cloud platform in real time after it is generated. REST can be used Technologies such as API or WebSocket are used to achieve real-time data transmission, and the generated diagnostic equipment update requirement data is uploaded to the cloud to ensure the timeliness and accuracy of the information. At the same time, a data backup mechanism is set up to prevent data loss, verify the accuracy and completeness of cloud updates, and ensure that all relevant personnel can obtain the latest diagnostic requirement information in a timely manner and optimize based on feedback.

[0212] In this embodiment, the specific steps of step S5 are:

[0213] Step S51: predicting the idle time of the vehicle based on the driving behavior model of the vehicle owner in different scenarios, and generating the predicted idle time of the vehicle;

[0214] Step S52: performing idle time distribution analysis on the predicted idle time of the vehicle and constructing a vehicle idle time distribution map;

[0215] Step S53: Calculate the optimal demand update time for the vehicle idle time distribution diagram according to the failure time window probability curve, and extract the optimal diagnostic equipment update time point.

[0216] In this embodiment, the driving data of the car owner is collected, including driving time, driving mode (such as city, rural, highway), daily travel habits, etc. This data can be obtained through the vehicle's driving recorder or smartphone application to ensure the integrity of the data. The recording format should be structured data, including timestamp, driving behavior type and mileage. Based on the collected data, driving behavior models in different scenarios are constructed. Clustering algorithms (such as K-means) can be used to classify driving behaviors and identify different driving modes. For example, city driving may show frequent stops and accelerations, while highway driving shows longer continuous driving time. The established driving behavior model is combined with historical data to predict the idle time of the vehicle, which can be used to predict the idle time of the vehicle. Time series analysis methods (such as ARIMA model) are used to predict future idle time. By analyzing daily driving patterns, the idle time in each scenario is calculated and a prediction result is generated. For example, if a car owner's average driving time on weekdays is 4 hours, the idle time is 20 hours. The predicted idle time is organized into structured data, and the idle prediction time for each time period is recorded. These data should include the time period, the predicted idle time and the corresponding driving scenario. The vehicle idle prediction time data is extracted to ensure the accuracy and completeness of the data. The data should include the predicted idle time and timestamp. The idle time distribution in different time periods is counted. By calculating the idle time frequency in each time period, the peak and trough periods of vehicle idleness can be identified. For example, For example, analyze the difference in idle time between a car owner on weekends and weekdays to determine which time periods the vehicle is most likely to be idle. Use data visualization tools (such as Matplotlib or Seaborn) to build an idle time distribution chart. The chart should show the idle time frequency in different time periods to help identify the best time to manage the vehicle. Make sure the chart contains clear labels and legends for easy understanding and sharing. Store the analysis results and distribution chart in the database and generate a report to record relevant statistics and charts of idle time. These data will be used for subsequent optimization decisions. Collect vehicle failure history data, including failure time, failure type, and maintenance records. Ensure the accuracy of these data for subsequent analysis. According to historical failure data, classify Analyze the time window of fault occurrence and construct the fault probability curve. Statistical methods (such as normal distribution or Poisson distribution) can be used to describe the probability of fault occurrence. If a certain vehicle model has a high fault incidence rate in a specific time period, then this time period can be regarded as a window with a higher fault risk. The fault time window probability curve is combined with the vehicle idle time distribution map to identify the intersection area of ​​idle time and fault risk, and calculate the optimal time to update equipment in these time periods. If the idle time in a certain time period is long and the probability of fault occurrence is high, it is recommended to update the equipment during this period. According to the analysis results, the optimal diagnostic equipment update time point is extracted, and the corresponding timestamps and update suggestions are recorded. These time points should have higher idle time and lower risk.

[0217] In this embodiment, the specific steps of step S6 are:

[0218] Step S61: performing differential adaptation optimization of the current vehicle configuration according to the fault diagnosis requirement update data, and generating differential adaptation optimization update data;

[0219] Step S62: Identify independently executable data blocks for the differentiated adaptation optimization update data, and mark multiple independently executable data blocks;

[0220] Step S63: performing data segmentation processing based on the multiple independently executable data blocks to generate multiple segment update data packets;

[0221] Step S64: performing instant remote update processing on multiple segment update data packets based on the optimal diagnostic device update time point, thereby completing the data update operation of the automobile diagnostic device.

[0222] In this embodiment, relevant information is extracted from the fault diagnosis demand update data to ensure the integrity and accuracy of the data, including equipment model, fault type, historical maintenance records, etc. According to the vehicle configuration and fault diagnosis requirements, the difference between the current vehicle configuration and the optimal configuration is analyzed. This can be achieved through a comparison algorithm to evaluate the effectiveness and applicability of each configuration option. For example, the difference in the demand for fault diagnosis equipment for a certain model of vehicle in different environments (such as cities and highways) is analyzed, mismatched configurations are identified, and adaptation optimization strategies are formulated, including necessary equipment updates, software upgrades or configuration adjustments. The decision tree algorithm can be used to determine the optimal configuration option to ensure that each suggestion has a corresponding basis, and the above analysis and optimization strategies are organized into a structured Data, record optimization suggestions, devices and software versions that need to be updated, etc. These data will serve as the basis for subsequent updates. Extract relevant fields from the differentiated adaptation optimization update data to ensure the structure and operability of the data. These fields should include device name, update content, dependencies, etc. Evaluate the independent executable nature of each update item and identify independent data blocks that do not depend on other update items. This can be achieved by analyzing the dependency graph of each update to ensure that each data block can be executed independently without affecting other parts. Mark and classify independently executable data blocks and record their feature information. These marks will be used for subsequent data processing and update operations. Store the identified independently executable data blocks in the database to ensure subsequent It can be quickly accessed and referenced during operation, and valid information is extracted from independently executable data blocks to ensure that the content and structure of each data block are clear. The information should include the update content, version number, required time, etc. A segmented processing strategy is formulated to determine how to combine multiple independently executable data blocks into update data packets. You can consider grouping by functional modules or device types to facilitate subsequent updates and maintenance. According to the formulated strategy, independently executable data blocks are combined into multiple segmented update data packets. Each data packet should contain necessary metadata for identification and processing during updates. The generated segmented update data packets are verified to ensure the integrity and validity of each data packet. The verified data packets are stored in the database for subsequent updates. New operation, record the detailed information of each segment update data packet, including the size of the packet, the number of data blocks contained, etc. This information will be used for subsequent update scheduling and management, extract the optimal diagnostic equipment update time point, ensure the accuracy and applicability of the data, these time points will be used to schedule update operations, according to the optimal update time point, formulate an update scheduling plan, determine the specific update time of each segment update data packet, consider the idle time and failure probability of the device, ensure that the update operation is performed at the best time, use remote update tools (such as OTA update system) to process each segment update data packet in real time, ensure the data transmission is safe and reliable during the update process, avoid update failure due to network problems, and monitor the update status in real time during the update process.Record the update results of each data packet, and if any abnormal situation occurs, conduct troubleshooting and repair in time.

[0223] In this embodiment, an automobile diagnostic device is provided, which is used to execute the data updating method of the automobile diagnostic device as described above, including:

[0224] The multi-scenario driving behavior module is used to obtain the vehicle's historical operation logs; perform multi-point sampling of the owner's driving behavior in the vehicle's historical operation logs, and perform behavior feature evolution in different scenarios, thereby obtaining the owner's driving behavior model in different scenarios;

[0225] The multi-scenario operation simulation module is used to extract the vehicle time-series state parameters based on the vehicle's historical operation logs; perform multi-scenario operation simulation on the vehicle time-series state parameters according to the owner's different scenario driving behavior models, and generate vehicle state operation simulation data for each scenario;

[0226] The fault prediction module is used to perform rolling prediction of vehicle status in future periods and calculate the probability of fault time window for the vehicle status operation simulation data of each scenario, and obtain the location point of abnormal fault part of the vehicle and the probability curve of fault time window;

[0227] The demand update module is used to perform fault attribution diagnosis and analysis on the location points of abnormal faults in vehicles and to mine the demand for diagnostic equipment updates to generate fault diagnosis demand update data;

[0228] The idle time prediction module is used to predict the idle time of the vehicle based on the failure time window probability curve and the driving behavior model of the vehicle owner in different scenarios, calculate the optimal demand update time, and extract the optimal diagnostic equipment update time point;

[0229] The real-time remote update module is used to update data according to fault diagnosis requirements to perform differentiated adaptation and optimization of the current vehicle configuration, and to perform real-time remote update processing based on the optimal diagnostic equipment update time point, thereby completing the data update operation of the vehicle diagnostic equipment.

[0230] The present invention can comprehensively capture the driving behavior of the car owner in different scenarios (such as urban driving, high-speed driving, etc.) through multi-point sampling, which enables the system to accurately construct the driving behavior model of the car owner, ensuring that the actual driving style of the car owner is taken into account in the subsequent vehicle state simulation. In different driving scenarios, the behavioral differences of the car owner will affect the vehicle state. Through the evolution of behavioral characteristics, personalized driving behavior models can be generated for different driving scenarios, providing a more accurate basis for subsequent vehicle state simulation and fault prediction. Based on the multi-scenario driving behavior model, the time series state of the vehicle can be simulated more carefully to ensure that the simulation results are closer to the actual usage. These simulation data can reflect the different driving scenarios. The vehicle operation characteristics under different scenarios can help predict the vehicle's operating status and potential faults. By extracting the vehicle's timing state parameters, the various operating states of the vehicle (such as engine speed, temperature, speed, etc.) can be accurately identified. These data provide a basis for subsequent fault prediction, equipment updates, etc. Through rolling prediction, the future state of the vehicle can be predicted and possible anomalies can be discovered in a timely manner. The probability calculation of the fault time window can help identify which time periods have a higher risk of failure, and then take preventive measures in advance. Through the combination of vehicle state simulation and fault time window, the part where the failure may occur can be accurately located, which provides a direct basis for subsequent fault diagnosis and repair, and improves the diagnostic accuracy. The accuracy of diagnosis can be improved by analyzing the fault location point, accurately identifying the root cause of the problem, helping maintenance personnel understand the specific cause of the fault, and quickly taking repair measures. While determining the fault location, the update requirements can be excavated according to the vehicle status and fault type, providing accurate update direction and content for diagnostic equipment. This accurate demand analysis can improve the pertinence of equipment updates and avoid unnecessary updates or erroneous updates. By combining the owner's driving behavior model and the fault time window, the idle time prediction module can accurately identify the idle time of the vehicle. Equipment updates during these time periods can minimize interference to the owner. By combining the analysis of the owner's driving behavior and fault risk, it can provide each owner with a precise update direction and content. The optimal diagnostic equipment update time is tailored for each vehicle to ensure that the equipment update can be performed when the owner least needs to use the vehicle. Through instant remote updates, the vehicle does not need to go to the repair station or factory for equipment updates, which greatly improves the convenience and flexibility of the update. This provides car owners with a convenient seamless update experience. According to the different configurations and diagnostic needs of the vehicles, differentiated adaptation and optimization are performed to ensure that the update content meets the specific requirements of each vehicle, avoiding unnecessary update content and waste of resources. Through the optimal update time point and differentiated adaptation, the diagnostic equipment can be updated when the vehicle is idle without interfering with the normal use of the vehicle. Remote updates can be completed in real time during the use of the vehicle, improving the efficiency and accuracy of equipment updates.

[0231] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0232] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A data updating method for automobile diagnostic equipment, characterized in that: The following steps are involved: Step S1: obtaining a vehicle historical operation log; performing multi-point sampling of the owner's driving behavior in the vehicle historical operation log, and performing behavior feature evolution in different scenarios, thereby obtaining a driving behavior model of the owner in different scenarios; Step S2: extracting vehicle time-series state parameters based on the vehicle historical operation log; performing multi-scenario operation simulation on the vehicle time-series state parameters according to the vehicle owner's driving behavior model in different scenarios, and generating vehicle state operation simulation data for each scenario; Step S3: Perform rolling prediction of vehicle status in future time periods and calculation of fault time window probability for the vehicle status operation simulation data of each scenario, and obtain the location point of abnormal fault part of the vehicle and the fault time window probability curve; Step S4: performing fault attribution diagnosis analysis on the location points of abnormal fault parts of the vehicle, and mining the diagnostic equipment update requirements to generate fault diagnosis requirement update data; Step S5: predicting the idle time of the vehicle based on the different driving behavior models of the vehicle owner according to the fault time window probability curve, calculating the optimal required update time, and extracting the optimal diagnostic equipment update time point; Step S6: updating the data according to the fault diagnosis requirements to perform differential adaptation optimization of the current vehicle configuration, and performing instant remote update processing based on the optimal diagnostic equipment update time point, thereby completing the data update operation of the automobile diagnostic equipment; The specific steps of step S1 are: Step S11: Obtain vehicle historical operation log; Step S12: Perform multi-point sampling of the vehicle owner's driving behavior in the vehicle's historical operation log to extract the vehicle owner's driving behavior data; Step S13: mining the personalized driving characteristics of the vehicle owner on the vehicle owner's driving behavior data to generate a representation of the vehicle owner's driving behavior; Step S14: performing vehicle operation multi-scenario identification based on the vehicle historical operation log, and extracting multiple vehicle operation scenarios; Step S15: Evolving the behavior characteristics of different scenarios for multiple vehicle operation scenarios according to the driving behavior representation of the vehicle owner, thereby obtaining the driving behavior models of the vehicle owner in different scenarios; the specific steps of step S14 are: Perform vehicle location tracking calculations based on the vehicle's historical operation logs to generate the vehicle's time-series location trajectory; Perform GPS map visualization based on the vehicle's time-series positioning trajectory to obtain a location trajectory visualization map; The vehicle time series positioning position trajectory is segmented into multiple time periods to obtain the position trajectory of different time periods; According to the location trajectories in different time periods, the location trajectory visualization map identifies the road section where the trajectory is located, and analyzes the road section status characteristics in each time period; Based on the road state characteristics of each time period, multiple vehicle operation scenarios are identified and multiple vehicle operation scenarios are extracted.

2. The data updating method of the automobile diagnostic equipment according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: extracting vehicle time sequence state parameters based on the vehicle historical operation log; Step S22: performing a multi-time point vehicle operation state analysis on the vehicle time sequence state parameters to generate vehicle operation state characteristics at multiple time points; Step S23: performing state scenario matching on vehicle operation state characteristics at multiple time points based on multiple vehicle operation scenarios, and performing scene state change mining to generate a vehicle state change trend for each operation scenario; Step S24: Perform multi-scenario operation simulation on the vehicle state change trend of each operation scenario according to the vehicle owner's driving behavior model in different scenarios, and generate vehicle state operation simulation data for each scenario.

3. The data updating method of the automobile diagnostic equipment according to claim 2, characterized in that: The specific steps of step S22 are: Identify key time points of vehicle timing state parameters and mark multiple key time points of vehicle operation; Calculate the engine speed based on multiple key time points of vehicle operation to obtain the engine speed characteristics at each time point; Perform engine temperature time series variation analysis on vehicle time series state parameters to generate engine temperature variation characteristics; Perform discrete fitting of temperature fluctuations on the engine temperature variation characteristics and construct the engine temperature variation curve; Perform real-time tire pressure situation analysis on vehicle time sequence state parameters to generate vehicle tire pressure situation characteristics; Calculating the vehicle speeds at the plurality of key time points of vehicle operation; A multi-time point vehicle operation state analysis is performed on the vehicle speed, engine temperature curve, vehicle tire pressure situation characteristics and engine speed characteristics at each time point to generate vehicle operation state characteristics at multiple time points.

4. The data updating method of the automobile diagnostic equipment according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: Perform rolling prediction of the vehicle state in the future time period on the vehicle state operation simulation data of each scenario to generate the vehicle state characteristics of the future time period; Step S32: predicting potential abnormal faults based on vehicle state characteristics in a future time period, thereby obtaining potential abnormal faults of the vehicle state; Step S33: locating the fault part of the potential abnormal fault of the vehicle state, and marking the location point of the abnormal fault part of the vehicle; Step S34: Calculate the failure time window probability of the potential abnormal failure of the vehicle state, so as to obtain a failure time window probability curve.

5. The data updating method of the automobile diagnostic equipment according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: performing fault attribution diagnosis analysis on the abnormal fault location points of the vehicle, thereby generating abnormal fault diagnosis data; Step S42: performing vehicle fault decision on the abnormal fault diagnosis data, thereby generating vehicle fault diagnosis decision data; Step S43: mining diagnostic equipment update requirements based on vehicle fault diagnosis decision data to generate diagnostic equipment update requirement data; Step S44: Synchronize the latest update data on the cloud based on the diagnostic device update requirement data to generate fault diagnosis requirement update data.

6. The data updating method of the automobile diagnostic equipment according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: predicting the idle time of the vehicle based on the driving behavior model of the vehicle owner in different scenarios, and generating the predicted idle time of the vehicle; Step S52: performing idle time distribution analysis on the predicted idle time of the vehicle and constructing a vehicle idle time distribution map; Step S53: Calculate the optimal demand update time for the vehicle idle time distribution diagram according to the failure time window probability curve, and extract the optimal diagnostic equipment update time point.

7. The data updating method of the automobile diagnostic equipment according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing differential adaptation optimization of the current vehicle configuration according to the fault diagnosis requirement update data, and generating differential adaptation optimization update data; Step S62: Identify independently executable data blocks for the differentiated adaptation optimization update data, and mark multiple independently executable data blocks; Step S63: performing data segmentation processing based on the multiple independently executable data blocks to generate multiple segment update data packets; Step S64: performing instant remote update processing on multiple segment update data packets based on the optimal diagnostic device update time point, thereby completing the data update operation of the automobile diagnostic device.

8. An automobile diagnostic device, characterized in that: The method for executing the data updating method of the automobile diagnostic device as claimed in claim 1 comprises: The multi-scenario driving behavior module is used to obtain the vehicle's historical operation logs; perform multi-point sampling of the owner's driving behavior in the vehicle's historical operation logs, and perform behavior feature evolution in different scenarios, thereby obtaining the owner's driving behavior model in different scenarios; The multi-scenario operation simulation module is used to extract the vehicle time-series state parameters based on the vehicle's historical operation logs; perform multi-scenario operation simulation on the vehicle time-series state parameters according to the owner's different scenario driving behavior models, and generate vehicle state operation simulation data for each scenario; The fault prediction module is used to perform rolling prediction of vehicle status in future periods and calculate the probability of fault time window for the vehicle status operation simulation data of each scenario, and obtain the location point of abnormal fault part of the vehicle and the probability curve of fault time window; The demand update module is used to perform fault attribution diagnosis and analysis on the location points of abnormal faults in vehicles and to mine the demand for diagnostic equipment updates to generate fault diagnosis demand update data; The idle time prediction module is used to predict the idle time of the vehicle based on the failure time window probability curve and the driving behavior model of the vehicle owner in different scenarios, calculate the optimal demand update time, and extract the optimal diagnostic equipment update time point; The real-time remote update module is used to update data according to fault diagnosis requirements to perform differentiated adaptation and optimization of the current vehicle configuration, and to perform real-time remote update processing based on the optimal diagnostic equipment update time point, thereby completing the data update operation of the vehicle diagnostic equipment.

Images