Intelligent cabin log processing method, system and equipment

Abstract

The embodiment of the invention relates to the technical field of data processing, and discloses an intelligent cabin log processing method, system and equipment, and the method comprises the steps: obtaining log data of each subsystem of an intelligent cabin, and processing the log data to obtain a standard data set; and performing deep analysis on the standard data set through machine learning and deep learning algorithms to obtain user preference archives, personalized recommendations, real-time performance indexes, fault related information and environment optimization suggestions corresponding to the environment optimization instructions, and displaying analysis results in partitions. According to the method provided by the invention, all-terminal subsystem data acquisition is realized, a data blind area is eliminated, a user behavior mode is automatically identified through an output standard data set, personalized recommendation is generated, the problem that thousands of persons in a traditional cabin are available is solved, the user satisfaction degree is improved, the system performance is evaluated in real time, faults are predicted, the fault response time is optimized, and the user experience is improved. The environment setting is dynamically optimized, the comfort level score is improved, the analysis result is displayed in a partitioned mode, and the result availability is improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method, system, and device for processing intelligent cockpit logs. Background Technology

[0002] As the penetration rate of automotive intelligence increases, intelligent cockpits have expanded from a single infotainment function to a multi-domain collaborative system that integrates infotainment, driver assistance systems (ADAS), environmental control (temperature / light), and biological sensing (DMS / OMS).

[0003] The system generates massive amounts of log data during operation, mainly including user interaction data, system status data, and environmental and biological data. Among them, user interaction data includes voice commands, touch screen operations, and gesture control records; system status data includes operating parameters, error codes, and response latency of various cockpit subsystems; and environmental and biological data includes cockpit temperature, humidity, and pilot heart rate / fatigue status.

[0004] These log data are the core basis for optimizing user experience, ensuring system reliability, and iterating cockpit functions. However, the existing technology system remains at the stage of simple recording and manual analysis, which cannot release the value of the data. Specifically, it is reflected in the inefficiency and passivity of the entire chain of collection, analysis, application, and storage, making it difficult to adapt to the complex needs of intelligent cockpits.

[0005] Existing log collection systems focus only on infotainment systems, neglecting data from driver assistance and biometric sensing subsystems. This results in missing data dimensions and an inability to support multi-scenario correlation analysis, such as user fatigue and excessive cabin temperature. The intelligent cockpit subsystem uses multiple automotive communication protocols, but most existing log collection modules only support a single protocol. Automakers need to develop dedicated modules for different models, leading to low adaptation efficiency and high costs. Furthermore, logs from different subsystems have inconsistent formats and are stored directly without being organized, requiring additional time to process format issues during subsequent analysis.

[0006] Existing log analysis tools require manual data screening and setting of analysis dimensions, and cannot automatically identify hidden patterns, resulting in low efficiency. Existing analyses are mostly offline batch processing, which cannot respond to cockpit anomalies in real time, missing the best opportunity for fault warnings and real-time optimization.

[0007] Existing systems mostly display results in text logs or simple tables, which are difficult for non-technical personnel to understand; and they only support local viewing on PCs, which cannot meet the needs of scenarios such as remote monitoring of fleets and viewing on users' mobile phones, and the AI ​​analysis results cannot quickly reach the target users. Summary of the Invention

[0008] To address the problems of incomplete data coverage, protocol incompatibility, reliance on manual intervention, poor real-time performance, unintuitive result display, and poor scenario adaptability in existing log collection and analysis systems, this invention provides a smart cockpit log processing method, system, and device.

[0009] According to an embodiment of the present invention, a method for processing intelligent cockpit logs is provided, comprising the following steps: Acquire log data from each subsystem of the intelligent cockpit, and process the acquired log data to obtain a standard dataset with a unified format and standardized type. Deep analysis is performed on the standardized data related to user operations in the standard dataset to automatically identify user behavior patterns, and user preference profiles and personalized recommendations are generated and output based on the identified user behavior patterns; A deep analysis is performed on the standardized data related to system operation in the standard dataset to obtain the real-time performance indicators and fault-related information of the intelligent cockpit, and the real-time performance indicators and fault-related information are output. Deep analysis is performed on the standardized data related to environmental perception in the standard dataset to obtain environmental optimization strategies, and corresponding environmental optimization instructions are output based on the environmental optimization strategies. The user preference profile and personalized recommendations, the real-time performance metrics and fault-related information, and the environmental optimization suggestions corresponding to the environmental optimization instructions are displayed in separate sections.

[0010] In some alternative implementations, the subsystems of a smart cockpit include at least an infotainment system, a driver assistance system, an environmental control system, and a biosensing system; Standard automotive communication protocols include at least: CAN bus, LIN bus, and MOST bus; Obtain log data from each subsystem of the intelligent cockpit, specifically including: The user operation records and system response data of the infotainment system are acquired via the MOST bus. The sensor operation data, function activation and operation data, and fault and warning data of the driver assistance system are acquired via the CAN bus. The cabin environment perception data and control equipment operation data of the environmental control system are acquired through the CAN bus and / or LIN bus. Driver and passenger monitoring data from the biosensing system are acquired via the LIN bus.

[0011] In some optional implementations, the acquired log data is processed, specifically including: The acquired log data is initially formatted and stored. The log data that has undergone preliminary formatting is cleaned by removing noise and abnormal data. The cleaned log data is converted into a standardized format according to preset rules, and the data type is converted into a standard type to achieve data conversion. The log data that has undergone data transformation is processed by timestamp synchronization and alignment, scenario-based association and integration, and redundant data removal to achieve data fusion.

[0012] In some optional implementations, deep analysis is performed on standardized data related to user actions in the standard dataset to automatically identify user behavior patterns. Based on these identified patterns, user preference profiles and personalized recommendations are generated and output. Specifically, this includes: In-depth analysis of standardized data related to user operations in the standard dataset is performed using the K-means clustering model to obtain user behavior patterns. By associating user operation records with environmental parameters through a decision tree model, user preference parameters are extracted based on the user behavior patterns to generate user preference profiles. Personalized recommendations are extracted from the user's preference profile based on the current driving scenario, and then converted into corresponding instructions and output. A deep analysis is performed on the standardized data related to system operation in the standard dataset to obtain real-time performance indicators and fault-related information of the intelligent cockpit, and the real-time performance indicators and fault-related information are output, specifically including: The standardized data related to system operation in the standard dataset are analyzed in depth using an LSTM deep learning model to obtain real-time performance indicators and performance prediction data for a preset time period for the intelligent cockpit. The performance prediction data is analyzed to obtain fault warning information; The fault warning information is analyzed using a decision tree model to obtain the fault type and root cause, and maintenance suggestions are generated. Deep analysis is performed on the standardized data related to environmental perception in the standard dataset to obtain environmental optimization strategies, and corresponding environmental optimization instructions are output based on the environmental optimization strategies, specifically including: A comfort model is established by performing in-depth analysis of standardized data related to environmental perception in the standard dataset using a reinforcement learning model. Based on the user preference profile, an environmental optimization strategy is obtained using the aforementioned comfort model. Based on the environmental optimization strategy, corresponding environmental optimization instructions are output, and the comfort model is updated in real time using the environmental optimization instructions.

[0013] Some alternative implementations also include: K-means clustering model, LSTM deep learning model and reinforcement learning model are trained using historical log data from the various subsystems of the stored smart cockpit. The system receives user preference profiles and personalized recommendations in real time, and optimizes the trained K-means clustering model using these profiles and recommendations. The system receives real-time performance metrics and fault-related information of the intelligent cockpit in real time, and optimizes the LSTM deep learning model based on these metrics and information. The environment optimization strategy is received in real time, and the reinforcement learning model is optimized using the environment optimization strategy.

[0014] In some optional implementations, the user preference profile and personalized recommendations, the real-time performance metrics and fault-related information, and the environment optimization suggestions corresponding to the environment optimization instructions are displayed in separate partitions, specifically including: The stand-alone interface is divided into areas, including at least a cockpit status monitoring area, a personalized recommendation area, an environment setting control area, and a historical data query area. The cockpit status monitoring area is used to display a performance trend chart generated in real time based on the real-time performance indicators and fault-related information. The personalized recommendation area is used to display personalized suggestions generated through the user preference profile and personalized recommendations, and to recommend them to various subsystems of the smart cockpit; The environment settings control area is used to display the environment optimization suggestions; The historical log data, user preference profiles and personalized recommendations, real-time performance metrics, fault-related information, and environmental optimization suggestions corresponding to the environmental optimization instructions are read from the historical data query area. The AI ​​analysis results are displayed through a web interface, specifically including: The web interface is divided into areas, including at least a vehicle selection and management area, a performance indicator and fault warning area, a data analysis and reporting area, and a user management and permission settings area. The vehicle selection and management area is used to filter different vehicles based on their basic information and to query and manage the selected vehicles. The performance indicators and fault warning areas are used to display a multi-vehicle performance comparison line chart generated based on the real-time performance indicators and fault-related information. The data analysis and reporting area is used to display the environmental comfort change curve generated by the environmental optimization instructions; User authentication and permission management are performed through the user management and permission settings area.

[0015] According to another objective of embodiments of the present invention, an intelligent cockpit log processing system is provided, comprising: The data acquisition module is used to acquire log data from various subsystems of the intelligent cockpit; The data preprocessing module is used to process the acquired log data to obtain a standard dataset with a unified format and standardized type. The AI ​​analysis module is used to perform in-depth analysis on standardized data related to user operations in the standard dataset to automatically identify user behavior patterns, generate user preference profiles and personalized recommendations based on the identified user behavior patterns, and output them; to perform in-depth analysis on standardized data related to system operation in the standard dataset to obtain real-time performance indicators and fault-related information of the intelligent cockpit, and output the real-time performance indicators and fault-related information; and to perform in-depth analysis on standardized data related to environmental perception in the standard dataset to obtain environmental optimization strategies, and output corresponding environmental optimization instructions based on the environmental optimization strategies. The visualization module is used to display the user preference profiles and personalized recommendations output by the AI ​​analysis module, the real-time performance indicators and fault-related information, and the environmental optimization suggestions corresponding to the environmental optimization instructions in designated areas; and The storage management module is used to store the log data of each subsystem of the intelligent cockpit acquired by the data acquisition module, as well as the user preference profile and personalized recommendations output by the AI ​​analysis module, the real-time performance indicators and the fault-related information, and the environmental optimization suggestions corresponding to the environmental optimization instructions. The intelligent cockpit subsystems include at least an infotainment system, a driver assistance system, an environmental control system, and a biosensing system. Standard automotive communication protocols include at least the following: CAN bus, LIN bus, and MOST bus.

[0016] In some optional implementations, the AI ​​analysis module includes a user behavior analysis submodule, a system performance evaluation submodule, an environmental comfort optimization submodule, and a model training and prediction unit; The user behavior analysis submodule is used to perform in-depth analysis of standardized data related to user operations in the standard dataset using a K-means clustering model to obtain user behavior patterns; to associate user operation records with environmental parameters using a decision tree model, to extract user preference parameters based on the user behavior patterns, and to generate user preference profiles; and to extract personalized recommendations from the user preference profiles according to the current driving scenario, and to convert them into corresponding instructions and output them. The system performance evaluation submodule is used to perform in-depth analysis on the standardized data related to system operation in the standard dataset using an LSTM deep learning model to obtain real-time performance indicators of the intelligent cockpit and performance prediction data within a preset time period; analyze the performance prediction data to obtain fault warning information; analyze the fault warning information using a decision tree model to obtain the fault type and root cause of the fault, and generate maintenance suggestions. The environmental comfort optimization submodule is used to perform in-depth analysis of standardized data related to environmental perception in the standard dataset using a reinforcement learning model to establish a comfort model; obtain an environmental optimization strategy based on the user preference profile using the comfort model; output corresponding environmental optimization instructions according to the environmental optimization strategy; and update the comfort model in real time using the environmental optimization instructions. The prediction model training module is used to train a K-means clustering model, an LSTM deep learning model, and a reinforcement learning model using historical log data from the stored subsystems of the smart cockpit; to receive user preference profiles and personalized recommendations in real time, and to optimize the trained K-means clustering model using these profiles and recommendations; to receive real-time performance metrics and fault-related information of the smart cockpit in real time, and to optimize the LSTM deep learning model using these metrics and information; and to receive environmental optimization strategies in real time, and to optimize the reinforcement learning model using these strategies.

[0017] In some optional implementations, the visualization module includes a standalone interface and / or a web interface; The stand-alone interface is at least divided into a cockpit status monitoring area, a personalized recommendation area, an environment setting control area, and a historical data query area. The web interface is at least divided into a vehicle selection and management area, a performance indicator and fault warning area, a data analysis and reporting area, and a user management and permission settings area. The cockpit status monitoring area is used to display a performance trend chart generated in real time based on the real-time performance indicators and fault-related information. The personalized recommendation area is used to display personalized suggestions generated through the user preference profile and personalized recommendations, and to recommend them to various subsystems of the smart cockpit; The environment settings control area is used to display the environment optimization suggestions; The historical log data, user preference profiles and personalized recommendations, real-time performance metrics, fault-related information, and environmental optimization suggestions corresponding to the environmental optimization instructions are read from the historical data query area. The vehicle selection and management area is used to filter different vehicles based on their basic information and to query and manage the selected vehicles. The performance indicators and fault warning areas are used to display a multi-vehicle performance comparison line chart generated based on the real-time performance indicators and fault-related information. The data analysis and reporting area is used to display the environmental comfort change curve generated by the environmental optimization instructions; User authentication and permission management are performed through the user management and permission settings area.

[0018] According to another objective of the present invention, a computer device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction that causes the processor to perform operations as described in any of the preceding descriptions of a smart cockpit log processing method.

[0019] Compared with the prior art, the present invention has the following advantages: This invention provides an intelligent cockpit log processing method that achieves full-system data collection, eliminates data blind spots, and outputs a standard dataset that provides high-quality input for subsequent AI deep analysis. This is a core prerequisite for ensuring the accuracy and reliability of AI analysis results. It automatically identifies user behavior patterns to provide a basis for personalized services, solving the problem of a one-size-fits-all approach in traditional cockpits. It evaluates cockpit system performance to monitor the performance indicators of each subsystem, predicts potential faults, and locates the root causes of faults, reducing maintenance costs and downtime. It also optimizes cockpit environment settings to improve driving comfort and user satisfaction. Through standalone and / or web interfaces, the AI ​​analysis results are displayed in visualized reports in sections to adapt to multiple scenarios and users, enabling non-technical personnel to quickly obtain key information, improving the efficiency of result understanding, and facilitating subsequent reporting and archiving.

[0020] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0021] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 The diagram shows a flowchart of a smart cockpit log processing method provided by an embodiment of the present invention.

[0022] Figure 2 This diagram illustrates the implementation flow of step S10, which involves processing the acquired log data, in an intelligent cockpit log processing method according to an embodiment of the present invention.

[0023] Figure 3 This diagram illustrates the process of obtaining user preference profiles and personalized recommendations in step S20 of a smart cockpit log processing method provided in an embodiment of the present invention.

[0024] Figure 4 This diagram illustrates the process of obtaining the environmental optimization strategy in step S20 of a smart cockpit log processing method provided by an embodiment of the present invention.

[0025] Figure 5 This diagram illustrates the process of acquiring real-time performance indicators and fault-related information in step S20 of a smart cockpit log processing method provided by an embodiment of the present invention.

[0026] Figure 6 The diagram shows a structural block diagram of an intelligent cockpit log processing system provided by an embodiment of the present invention.

[0027] Figure 7 A structural block diagram of a computer device provided by an embodiment of the present invention is shown. Detailed Implementation

[0028] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0029] This embodiment addresses the problems of incomplete data coverage, protocol incompatibility, reliance on manual intervention, poor real-time performance, unintuitive result display, and poor scenario adaptability in existing log collection and analysis systems, and provides an intelligent cockpit log processing method.

[0030] This invention provides a method for processing intelligent cockpit logs, such as... Figure 1 As shown, it includes the following steps: S10. Obtain log data from each subsystem of the intelligent cockpit, and process the obtained log data to obtain a standard dataset with a unified format and standardized type.

[0031] In this step, the subsystems of the intelligent cockpit include at least an infotainment system, a driver assistance system, an environmental control system, and a biosensing system.

[0032] Standard automotive communication protocols include at least the following: CAN bus, LIN bus, and MOST bus.

[0033] Therefore, the acquisition of log data from each subsystem of the intelligent cockpit in this step specifically includes: User operation records and system response data of the infotainment system are acquired through the MOST bus.

[0034] The user operation log includes log data such as touch screen clicks, voice commands, and gesture control trigger times, operation types, and execution results during interactive operations.

[0035] System response data includes performance parameters such as application startup latency, interface switching smoothness, and voice recognition response time, as well as error log data such as application crash error codes, voice recognition failure reasons, and abnormal audio and video playback records.

[0036] The system acquires sensor operation data, function activation and operation data, and fault and warning data of the driver assistance system via the CAN bus.

[0037] The sensor operation data includes core sensor parameters such as real-time values ​​of millimeter-wave radar, cameras, and lidar, as well as sensor collaborative data such as multi-sensor data synchronization status and sensor calibration results.

[0038] Function activation and operation data include the activation status and operation parameters of functions such as ACC adaptive cruise control, lane keeping assist, and automatic emergency braking, as well as environmental perception results such as distance to vehicles ahead, pedestrian recognition results, traffic sign recognition results, and confidence levels.

[0039] Fault and warning data include sensor fault codes and records of functional abnormalities.

[0040] The cabin environment perception data and control equipment operation data of the environmental control system are acquired via CAN bus and / or LIN bus.

[0041] The cabin environment perception data includes core environmental parameters such as real-time monitoring values ​​of cabin temperature, air quality, and light intensity, as well as external environmental data such as outside temperature and rain / snow weather recognition results.

[0042] The control equipment operation data includes the set values ​​and actual operating status of equipment such as air conditioners, seats, and ambient lights, as well as adjustment records such as the operation time of users manually adjusting environmental settings, parameters before and after adjustment, and equipment response time.

[0043] Driver and passenger monitoring data from the biosensing system are acquired via the LIN bus.

[0044] The driver monitoring data includes biometrics such as heart rate, blood oxygen saturation, facial features, and facial orientation, as well as behavioral status such as blinking frequency, whether making or receiving phone calls, whether wearing a seatbelt, and duration of continuous driving.

[0045] Passenger monitoring data includes passenger numbers, passenger posture, whether there are children, and other passenger status information, as well as passenger interaction behaviors such as operation of the rear entertainment screen and adjustment records of the rear air conditioning / seats.

[0046] The log data collected in this step covers all dimensions of the smart cockpit users, system, and environment, encompassing four core domains: infotainment, driver assistance, environmental control, and biosensing. No additional protocol conversion module is required, and data collection is comprehensive.

[0047] The data types include text, numerical, status, and fault types, providing a comprehensive and timely basic data source for subsequent data preprocessing and AI analysis, fully matching the design goals that cover all aspects of cockpit operation.

[0048] Match the optimal protocol to the data requirements of different subsystems to avoid performance bottlenecks caused by transmitting large amounts of data using low-bandwidth protocols, and ensure the real-time performance and stability of data acquisition.

[0049] In this step, the acquired log data is processed, including: The acquired log data undergoes preliminary formatting. The log data that has undergone preliminary formatting is then subjected to data cleaning, data transformation, and data fusion processes to obtain a standard dataset with a unified format and standardized type.

[0050] In this step, the acquired log data undergoes preliminary formatting followed by data cleaning to remove noise and abnormal data, ensuring data accuracy and addressing the issues of high data noise and low accuracy, thus laying the foundation for subsequent data processing.

[0051] The cleaned log data is transformed into a structured format that can be directly read in step S20, which solves the problem of incompatibility between data formats of different subsystems and eliminates format barriers.

[0052] The log data that has undergone data transformation is subjected to data fusion processing to integrate structured data from different subsystems according to scenarios, forming a complete data link. This provides a multi-dimensional, full-scenario analysis basis for step S20, thereby solving the problem of data silos.

[0053] S20. Perform in-depth analysis on standardized data related to user operations in the standard dataset to automatically identify user behavior patterns, generate user preference profiles and personalized recommendations based on the identified user behavior patterns, and output them. A deep analysis is performed on the standardized data related to system operation in the standard dataset to obtain the real-time performance indicators and fault-related information of the intelligent cockpit, and the real-time performance indicators and fault-related information are output. Deep analysis is performed on the standardized data related to environmental perception in the standard dataset to obtain environmental optimization strategies, and corresponding environmental optimization instructions are output based on the environmental optimization strategies. In this step, by analyzing user operation log data in the smart cockpit, user behavior patterns and preference settings are identified, user preference profiles and personalized recommendations are generated, solving the problem of the uniformity of traditional cockpits and providing a basis for decision-making for personalized experiences.

[0054] By analyzing the operation log data of each subsystem, real-time performance indicators and fault-related information of the intelligent cockpit can be obtained to assess the health status of the system in real time, solve the problem of low efficiency of traditional post-maintenance, and ensure the reliability of the cockpit.

[0055] By analyzing standardized data related to environmental perception, combining environmental sensor data and user feedback, and optimizing cabin environment settings through algorithms, an adaptive comfort cabin environmental optimization strategy is achieved, solving the problem of cumbersome traditional manual adjustments.

[0056] S30. Display user preference profiles and personalized recommendations, real-time performance metrics and fault-related information, and environmental optimization suggestions corresponding to environmental optimization commands in separate sections.

[0057] In this step, the analysis results of step S20 are displayed in sections through a standalone or web interface.

[0058] The standalone version is designed to run on a PC, allowing users to view analysis results locally without relying on a network connection. This standalone version facilitates in-depth data analysis and system debugging during the development phase.

[0059] The web version provides services through a cloud server, allowing users to access the system via a browser and conveniently view data and analysis reports anytime, anywhere on different devices. It is suitable for fleet managers and remote monitoring scenarios.

[0060] This step supports both standalone and web-based versions of the display page, meeting the usage needs of different users in various scenarios and improving the system's applicability and flexibility.

[0061] This embodiment provides an intelligent cockpit log processing method that achieves full-system data collection, eliminates data blind spots, and outputs a standard dataset that provides high-quality input for subsequent AI deep analysis. This is a core prerequisite for ensuring the accuracy and reliability of AI analysis results. It automatically identifies user behavior patterns to provide a basis for personalized services, addressing the problem of a one-size-fits-all approach in traditional cockpits. It evaluates cockpit system performance to monitor the performance indicators of each subsystem, predicts potential faults, locates the root causes of faults, reduces maintenance costs and downtime, and optimizes cockpit environment settings to improve driving comfort and user satisfaction. The AI ​​analysis results are displayed in visualized reports through standalone and / or web interfaces, adapting to multiple scenarios and users. This allows non-technical personnel to quickly obtain key information, improves the efficiency of understanding results, and facilitates subsequent reporting and archiving.

[0062] This embodiment is a preferred embodiment, and the specific implementation process of processing the obtained log data provided in step S10 has been optimized.

[0063] In this embodiment, as Figure 2 As shown, the acquired log data is processed, specifically including: S101. Perform preliminary formatting and storage on the acquired log data.

[0064] S102. Perform noise and abnormal data removal on the log data that has completed the initial formatting process to achieve data cleaning.

[0065] This step specifically involves using statistical thresholding and / or rule matching to identify noise in the log data that has undergone preliminary formatting and then removing it.

[0066] For example, outliers in environmental sensor data are removed using the 3σ principle.

[0067] Abnormal data in the log data that has undergone preliminary formatting is identified by comparing historical data and / or using linear interpolation, and then removed or repaired.

[0068] For example, user operation records can be used to remove duplicate records caused by accidental touches on the vehicle's touchscreen through rule matching.

[0069] S103. Convert the cleaned log data into a standardized format according to preset rules, and convert the data type to a standard type to achieve data conversion.

[0070] This step specifically involves converting heterogeneous data formats output by different subsystems into a standardized format according to preset rules, achieving unified format conversion. This standardizes field data types to avoid errors caused by type mismatches during AI analysis, thus achieving data type standardization.

[0071] For example, for JSON format data from infotainment systems, key fields can be directly extracted while retaining structured information; The binary format data of the ADAS system is converted into readable numerical values ​​using binary and decimal parsing scripts. For XML format data of the environmental control system, the tag content is extracted using an XML parser; Finally, all data is converted to Parquet or CSV format to ensure consistent field structure.

[0072] Data type standardization mainly achieves the unification of timestamps, numerical data, and text data.

[0073] S104. Perform timestamp synchronization and alignment, scenario-based association and integration, and redundant data removal on the log data after data transformation to achieve data fusion.

[0074] This step specifically involves calibrating the timestamps of log data from different subsystems based on the vehicle clock to optimize the time deviation of related data.

[0075] Based on the subsystem correlation rules, related log data under the same time dimension are integrated into a scenario dataset.

[0076] After integration, duplicate association information is removed, and only one valid log data is retained, reducing the size of the scenario dataset.

[0077] After processing the log data in this step, a standardized dataset that is time-aligned, complete in terms of scenario, and free of redundancy is output. This dataset is then directly transmitted to step S20 for in-depth analysis and simultaneously backed up to the storage management module for storage.

[0078] This embodiment is a preferred embodiment, and the specific implementation process of performing in-depth analysis of the standard dataset using machine learning and deep learning algorithms provided in step S20 has been optimized.

[0079] In this embodiment, step S20 involves performing in-depth analysis on the standardized data related to user operations in the standard dataset to automatically identify user behavior patterns, and generating and outputting user preference profiles and personalized recommendations based on the identified user behavior patterns. Specifically, this includes: S201. Perform in-depth analysis on the standardized data related to user operations in the standard dataset using the K-means clustering model to obtain user behavior patterns.

[0080] This step mainly achieves: The K-means clustering model is used to analyze user operation records, extract hidden patterns, and realize user behavior pattern recognition.

[0081] S202. By linking user operation records with environmental parameters through a decision tree model, user preference parameters are extracted based on user behavior patterns to generate user preference profiles.

[0082] This step mainly achieves: The decision tree model automatically counts users' frequently used cockpit settings to generate user preference profiles, including environmental and interaction preferences, thereby extracting preference parameters and generating user preference profiles.

[0083] S203. Extract personalized recommendations from the user's preference profile based on the current driving scenario, convert them into corresponding instructions, and output them.

[0084] This step mainly achieves: Personalized recommendations are transformed into executable recommendation instructions, which are then passed to the visualization module for display, thus enabling personalized recommendation output.

[0085] In this embodiment, step S20 involves performing in-depth analysis on standardized data related to system operation in the standard dataset to obtain real-time performance indicators and fault-related information of the intelligent cockpit, and then outputting the real-time performance indicators and fault-related information. Specifically, this includes: S204. By using an LSTM deep learning model to perform in-depth analysis on the standardized data related to system operation in the standard dataset, the real-time performance indicators of the intelligent cockpit and the performance prediction data within a preset time period are obtained.

[0086] S205. Analyze the performance prediction data to obtain fault warning information.

[0087] S206. Analyze the fault warning information using a decision tree model to obtain the fault type and root cause, and generate maintenance suggestions.

[0088] This step mainly achieves: The LSTM deep learning model is used to track the performance indicators of the subsystem, generate performance curves, and realize real-time performance monitoring.

[0089] Performance curves include: Infotainment system: vehicle system response latency, application launch time, voice recognition response speed; Driver assistance systems: radar frame rate, camera exposure parameters, sensor synchronization accuracy; Environmental control system: air conditioning cooling / heating rate, seat function response time.

[0090] By analyzing performance trends and error code correlations, fault types can be predicted, including hardware and software faults, thus enabling early warning of potential faults.

[0091] For a fault that has occurred, the system correlates logs from multiple subsystems to locate the root cause and outputs maintenance suggestions, thus achieving root cause localization.

[0092] In this embodiment, step S20 involves performing in-depth analysis on the standardized data related to environmental perception in the standard dataset to obtain an environmental optimization strategy, and outputting corresponding environmental optimization instructions based on the environmental optimization strategy. Specifically, this includes: S207. A comfort model is established by performing in-depth analysis on the standardized data related to environmental perception in the standard dataset using a reinforcement learning model.

[0093] This step mainly achieves: By using reinforcement learning algorithms to correlate environmental parameters, user actions, and feedback logs, a comfort model is established to achieve environmental data correlation analysis.

[0094] S208. Using a comfort model, an environmental optimization strategy is derived based on the user preference profile.

[0095] S209. Output corresponding environmental optimization instructions based on the environmental optimization strategy, and update the comfort model in real time through the environmental optimization instructions.

[0096] This step mainly achieves: It receives environmental data in real time and outputs environmental optimization commands based on user preference profiles to achieve dynamic parameter optimization.

[0097] Collect user feedback on optimization results and update the comfort model in real time to make environmental optimization strategies more aligned with user needs and achieve iterative improvements based on user feedback.

[0098] This embodiment, as a preferred embodiment, also includes: K-means clustering model, LSTM deep learning model, and reinforcement learning model are trained using historical log data from the various subsystems of the stored smart cockpit.

[0099] The system receives user preference profiles and personalized recommendations in real time, and optimizes the trained K-means clustering model based on these profiles and recommendations.

[0100] The system receives real-time performance metrics and fault-related information from the intelligent cockpit and optimizes the LSTM deep learning model based on these metrics.

[0101] The environment optimization strategy is received in real time, and the reinforcement learning model is optimized using the environment optimization strategy.

[0102] This embodiment, as a preferred embodiment, optimizes the specific implementation process of step S30, which involves displaying user preference profiles and personalized recommendations, real-time performance indicators and fault-related information, as well as environmental optimization suggestions corresponding to environmental optimization instructions in separate sections.

[0103] In this embodiment, step S30 involves displaying user preference profiles and personalized recommendations, real-time performance metrics and fault-related information, and environmental optimization suggestions corresponding to environmental optimization instructions in separate sections. Specifically, this includes: The standalone interface is divided into areas, at least including a cockpit status monitoring area, a personalized recommendation area, an environment setting control area, and a historical data query area.

[0104] The cockpit status monitoring area is used to display performance trend charts generated in real time based on real-time performance indicators and fault-related information.

[0105] The personalized recommendation area is used to display personalized suggestions generated from user preference profiles and personalized recommendations, and to recommend them to various subsystems of the smart cockpit.

[0106] The environment settings control area is used to display environment optimization suggestions.

[0107] The system retrieves historical log data, user preference profiles and personalized recommendations, real-time performance metrics and fault-related information, as well as environment optimization suggestions corresponding to environment optimization commands from the historical data query area.

[0108] The AI ​​analysis results are displayed through a web interface, specifically including: The web interface should be divided into at least the following areas: vehicle selection and management area, performance indicators and fault warning area, data analysis and reporting area, and user management and permission settings area.

[0109] The vehicle selection and management area is used to filter different vehicles based on their basic information and to query and manage the selected vehicles.

[0110] The performance metrics and fault warning areas are used to display a multi-vehicle performance comparison line chart generated based on real-time performance metrics and fault-related information.

[0111] The data analysis and reporting area is used to display graphs showing changes in environmental comfort generated through environmental optimization directives.

[0112] User authentication and permission management are performed through the user management and permission settings area.

[0113] In this embodiment, the standalone version uses the PC's local hard disk, SSD, and SQLite database to store the raw log data of each subsystem of the smart cockpit and the analysis results output in step S20.

[0114] The web version utilizes an HDFS distributed storage cluster and a MySQL / PostgreSQL database to store the raw log data of each subsystem of the smart cockpit, as well as the AI ​​analysis results output in step S20.

[0115] In some optional embodiments, the present invention also discloses an intelligent cockpit log processing system.

[0116] This embodiment discloses an intelligent cockpit log processing system, such as Figure 4 As shown, it includes: a data acquisition module 100, a data preprocessing module 200, an AI analysis module 300, a visualization display module 400, and a storage management module 500.

[0117] The data acquisition module 100 acquires log data from various subsystems of the smart cockpit via standard automotive communication protocols, performs preliminary formatting on the acquired log data, sends the raw log data to the storage management module 500 for storage, and sends the pre-formatted log data to the data preprocessing module 200. The subsystems of the smart cockpit include at least an infotainment system, a driver assistance system, an environmental control system, and a biosensing system; the standard automotive communication protocols include at least CAN bus, LIN bus, and MOST bus.

[0118] The data preprocessing module 200 is used to perform data cleaning, data transformation and data fusion processing on the log data that has completed the initial formatting process, so as to obtain a standard dataset with unified format and standard type, and send the obtained standard dataset to the AI ​​analysis module 300.

[0119] The AI ​​analysis module 300 is used to perform in-depth analysis of standard datasets using machine learning and deep learning algorithms. This allows for the automatic identification of user behavior patterns based on standardized data related to user operations, generating and outputting user preference profiles and personalized recommendations based on these patterns. It also obtains real-time performance metrics and fault-related information for the intelligent cockpit based on standardized data related to system operation, and outputs these metrics and information. Furthermore, it develops environmental optimization strategies based on standardized data related to environmental perception, and outputs corresponding environmental optimization instructions. The analysis results are then sent to the visualization module 400 for display and to the storage management module 500 for storage.

[0120] The visualization module 400 is used to display the user preference profiles and personalized recommendations, real-time performance indicators and fault-related information output by the AI ​​analysis module, as well as the environmental optimization suggestions corresponding to the environmental optimization commands, in separate sections.

[0121] The storage management module 500 is used to store the log data of each subsystem of the smart cockpit acquired by the data acquisition module 100 and the analysis results output by the AI ​​analysis module 300.

[0122] In this embodiment, the data acquisition module 100 includes a communication interface, a data collection driver, and a preliminary data processing unit.

[0123] The communication interface supports standard automotive communication protocols such as CAN bus, LIN bus, and MOST bus, and is compatible with the hardware interfaces of various subsystems of the smart cockpit. It can establish physical communication channels with different smart cockpit subsystems to ensure that data from different subsystems of the smart cockpit can be collected.

[0124] The data collection driver program is customized for different vehicle models and different subsystems of the smart cockpit, supporting millisecond-level real-time data capture and enabling precise extraction of log data from specific subsystems.

[0125] The preliminary data processing unit performs preliminary processing and formatting of the collected log data from various subsystems of the intelligent cockpit, ensuring the integrity and consistency of the log data to avoid low analysis efficiency caused by messy raw data.

[0126] In this embodiment, the data acquisition module 100 obtains log data from each subsystem of the smart cockpit through the standard automotive communication protocol, and performs preliminary formatting processing on the obtained log data. For the specific implementation process, please refer to step S10 in the above-mentioned smart cockpit log processing method, which will not be repeated in this embodiment.

[0127] In this embodiment, the data preprocessing module 200 performs data cleaning, data conversion, and data fusion processing on the log data that has completed the initial formatting process in sequence to obtain a standard dataset with a unified format and standard type. For the specific implementation process, please refer to step S10 in the above-mentioned intelligent cockpit log processing method, which will not be repeated in this embodiment.

[0128] This embodiment is a preferred embodiment. The AI ​​analysis module 300 includes a user behavior analysis submodule, a system performance evaluation submodule, an environmental comfort optimization submodule, and a model training and prediction unit.

[0129] The user behavior analysis submodule is used to perform in-depth analysis of standardized data related to user operations in the standard dataset using the K-means clustering model to obtain user behavior patterns; it uses a decision tree model to associate user operation records with environmental parameters, extracts user preference parameters based on user behavior patterns, and generates user preference profiles; it extracts personalized recommendations from user preference profiles based on the current driving scenario, converts them into corresponding instructions, and outputs them.

[0130] The system performance evaluation submodule is used to perform in-depth analysis of standardized data related to system operation in the standard dataset using an LSTM deep learning model to obtain real-time performance indicators of the smart cockpit and performance prediction data within a preset time period; analyze the performance prediction data to obtain fault warning information; analyze the fault warning information through a decision tree model to obtain the fault type and root cause of the fault, and generate maintenance suggestions.

[0131] The Environmental Comfort Optimization submodule is used to perform in-depth analysis of standardized data related to environmental perception in the standard dataset using a reinforcement learning model to establish a comfort model; based on the user preference profile, an environmental optimization strategy is obtained using the comfort model; corresponding environmental optimization instructions are output according to the environmental optimization strategy; and the comfort model is updated in real time using the environmental optimization instructions.

[0132] The prediction model training module is used to train K-means clustering models, LSTM deep learning models, and reinforcement learning models using historical log data from various subsystems of the smart cockpit; it receives user preference profiles and personalized recommendations in real time, and optimizes the trained K-means clustering model based on these profiles and recommendations; it receives real-time performance metrics and fault-related information from the smart cockpit in real time, and optimizes the LSTM deep learning model based on these metrics; and it receives environmental optimization strategies in real time, and optimizes the reinforcement learning model based on these strategies.

[0133] In this embodiment, the AI ​​analysis module 300 performs in-depth analysis of the standard dataset using machine learning and deep learning algorithms to obtain the specific implementation process of user preference profiles and personalized recommendations, real-time performance indicators and fault-related information, and environmental optimization suggestions corresponding to environmental optimization instructions. See step S20 in the above-mentioned intelligent cockpit log processing method, which will not be repeated in this embodiment.

[0134] This embodiment is a preferred embodiment, and the visualization module 400 includes a stand-alone interface and / or a web interface.

[0135] In this embodiment, the standalone interface is divided into at least a cockpit status monitoring area, a personalized recommendation area, an environment setting control area, and a historical data query area.

[0136] The cockpit status monitoring area is used to display performance trend charts generated in real time based on real-time performance indicators and fault-related information.

[0137] The personalized recommendation area is used to display personalized suggestions generated from user preference profiles and personalized recommendations, and to recommend them to various subsystems of the smart cockpit.

[0138] The environmental settings control area displays the adjustment interface and optimization suggestions based on optimized cockpit environmental settings.

[0139] The historical data query area is used by users to read stored historical log data, stored user preference profiles and personalized recommendations, real-time performance indicators and fault-related information, as well as AI analysis results such as environmental optimization suggestions corresponding to environmental optimization commands.

[0140] In this embodiment, the web interface is divided into at least a vehicle selection and management area, a performance indicator and fault warning area, a data analysis and reporting area, and a user management and permission settings area.

[0141] The vehicle selection and management area is used to filter different vehicles based on their basic information and to query and manage the selected vehicles.

[0142] The performance metrics and fault warning areas are used to display a multi-vehicle performance comparison line chart generated based on real-time performance metrics and fault-related information.

[0143] The data analysis and reporting area is used to display graphs showing changes in environmental comfort generated through environmental optimization directives.

[0144] The user management and permission settings area is used for user authentication and permission management.

[0145] In this embodiment, the specific implementation process of the visualization module 400 displaying the AI ​​analysis results output by the AI ​​analysis module through a visualization report is described in step S30 of the above-mentioned intelligent cockpit log processing method, and will not be repeated in this embodiment.

[0146] This embodiment is a preferred embodiment, and the storage management module 500 is adapted to both standalone and web versions.

[0147] The standalone version utilizes the PC's local hard drive, SSD, and SQLite database to store the raw log data of each subsystem of the smart cockpit, as well as the AI ​​analysis results output by the AI ​​analysis module 300.

[0148] The web version utilizes an HDFS distributed storage cluster and a MySQL / PostgreSQL database to store the raw log data of each subsystem of the smart cockpit, as well as the AI ​​analysis results output by the AI ​​analysis module 300.

[0149] In some alternative embodiments, the present invention also discloses a computer device.

[0150] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention is shown.

[0151] like Figure 5 As shown, the computer device includes a processor 610, a memory 620, a communication interface 630, and a communication bus 640. The processor 610, the memory 620, and the communication interface 630 communicate with each other through the communication bus 640.

[0152] In this embodiment, the memory 620 stores at least one executable instruction, which causes the processor 620 to perform operations as described in any of the above embodiments of a smart cockpit log processing method; the communication interface 630 is used to communicate with other devices, such as clients or other server network elements. The processor 610 is used to execute program 650, specifically performing the relevant steps in the above embodiments of a smart cockpit log processing method.

[0153] Specifically, program 650 may include program code, which includes computer-executable instructions.

[0154] The processor 610 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computer device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0155] Memory 620 is used to store program 650. Memory 620 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0156] Specifically, program 650 can be called by processor 610 to cause the computer device to perform the operation of the intelligent cockpit log processing method described in any of the above embodiments.

[0157] In some optional embodiments, the present invention also discloses a computer-readable storage medium storing at least one executable instruction that, when executed on a computer device, causes the computer device to perform the steps of an intelligent cockpit log processing method in any of the above method embodiments.

[0158] The specific implementation process of the intelligent cockpit log processing method described in this embodiment can be found in any of the above method embodiments, and will not be repeated in this embodiment.

[0159] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. Similarly, for the sake of brevity and to aid in understanding one or more aspects of the invention, in the description of exemplary embodiments of the invention above, various features of the embodiments are sometimes grouped together in a single embodiment, figure, or description thereof. The claims, which follow the detailed description, are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0160] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components, except that at least some of such features and / or processes or units are mutually exclusive.

[0161] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for processing intelligent cockpit logs, characterized in that, Includes the following steps: Acquire log data from each subsystem of the intelligent cockpit, and process the acquired log data to obtain a standard dataset with a unified format and standardized type. Deep analysis is performed on the standardized data related to user operations in the standard dataset to automatically identify user behavior patterns, and user preference profiles and personalized recommendations are generated and output based on the identified user behavior patterns; A deep analysis is performed on the standardized data related to system operation in the standard dataset to obtain the real-time performance indicators and fault-related information of the intelligent cockpit, and the real-time performance indicators and fault-related information are output. Deep analysis is performed on the standardized data related to environmental perception in the standard dataset to obtain environmental optimization strategies, and corresponding environmental optimization instructions are output based on the environmental optimization strategies. The user preference profile and personalized recommendations, the real-time performance metrics and fault-related information, and the environmental optimization suggestions corresponding to the environmental optimization instructions are displayed in separate sections.

2. The intelligent cockpit log processing method according to claim 1, characterized in that, The subsystems of a smart cockpit include at least an infotainment system, a driver assistance system, an environmental control system, and a biosensing system; Standard automotive communication protocols include at least: CAN bus, LIN bus, and MOST bus; Obtain log data from each subsystem of the intelligent cockpit, specifically including: The user operation records and system response data of the infotainment system are acquired via the MOST bus. The sensor operation data, function activation and operation data, and fault and warning data of the driver assistance system are acquired via the CAN bus. The cabin environment perception data and control equipment operation data of the environmental control system are acquired through the CAN bus and / or LIN bus. Driver and passenger monitoring data from the biosensing system are acquired via the LIN bus.

3. The intelligent cockpit log processing method according to claim 1, characterized in that, The acquired log data is processed, specifically including: The acquired log data is initially formatted and stored. The log data that has undergone preliminary formatting is cleaned by removing noise and abnormal data. The cleaned log data is converted into a standardized format according to preset rules, and the data type is converted into a standard type to achieve data conversion. The log data that has undergone data transformation is processed by timestamp synchronization and alignment, scenario-based association and integration, and redundant data removal to achieve data fusion.

4. The intelligent cockpit log processing method according to claim 1, characterized in that, Deep analysis is performed on standardized data related to user operations in the standard dataset to automatically identify user behavior patterns. Based on the identified user behavior patterns, user preference profiles and personalized recommendations are generated and output. Specifically, this includes: In-depth analysis of standardized data related to user operations in the standard dataset is performed using the K-means clustering model to obtain user behavior patterns. By associating user operation records with environmental parameters through a decision tree model, user preference parameters are extracted based on the user behavior patterns to generate user preference profiles. Personalized recommendations are extracted from the user's preference profile based on the current driving scenario, and then converted into corresponding instructions and output. A deep analysis is performed on the standardized data related to system operation in the standard dataset to obtain real-time performance indicators and fault-related information of the intelligent cockpit, and the real-time performance indicators and fault-related information are output, specifically including: The standardized data related to system operation in the standard dataset are analyzed in depth using an LSTM deep learning model to obtain real-time performance indicators and performance prediction data for a preset time period for the intelligent cockpit. The performance prediction data is analyzed to obtain fault warning information; The fault warning information is analyzed using a decision tree model to obtain the fault type and root cause, and maintenance suggestions are generated. Deep analysis is performed on the standardized data related to environmental perception in the standard dataset to obtain environmental optimization strategies, and corresponding environmental optimization instructions are output based on the environmental optimization strategies, specifically including: A comfort model is established by performing in-depth analysis of standardized data related to environmental perception in the standard dataset using a reinforcement learning model. Based on the user preference profile, an environmental optimization strategy is obtained using the aforementioned comfort model. Based on the environmental optimization strategy, corresponding environmental optimization instructions are output, and the comfort model is updated in real time using the environmental optimization instructions.

5. The intelligent cockpit log processing method according to claim 4, characterized in that, Also includes: K-means clustering model, LSTM deep learning model and reinforcement learning model are trained using historical log data from the various subsystems of the stored smart cockpit. The system receives user preference profiles and personalized recommendations in real time, and optimizes the trained K-means clustering model using these profiles and recommendations. The system receives real-time performance metrics and fault-related information of the intelligent cockpit in real time, and optimizes the LSTM deep learning model based on these metrics and information. The environment optimization strategy is received in real time, and the reinforcement learning model is optimized using the environment optimization strategy.

6. The intelligent cockpit log processing method according to claim 1, characterized in that, The user preference profile and personalized recommendations, the real-time performance metrics and fault-related information, and the environmental optimization suggestions corresponding to the environmental optimization instructions are displayed in separate sections, specifically including: The stand-alone interface is divided into areas, including at least a cockpit status monitoring area, a personalized recommendation area, an environment setting control area, and a historical data query area. The cockpit status monitoring area is used to display a performance trend chart generated in real time based on the real-time performance indicators and fault-related information. The personalized recommendation area is used to display personalized suggestions generated through the user preference profile and personalized recommendations, and to recommend them to various subsystems of the smart cockpit; The environment settings control area is used to display the environment optimization suggestions; The historical log data, user preference profiles and personalized recommendations, real-time performance metrics, fault-related information, and environmental optimization suggestions corresponding to the environmental optimization instructions are read from the historical data query area. The AI ​​analysis results are displayed through a web interface, specifically including: The web interface is divided into areas, including at least a vehicle selection and management area, a performance indicator and fault warning area, a data analysis and reporting area, and a user management and permission settings area. The vehicle selection and management area is used to filter different vehicles based on their basic information and to query and manage the selected vehicles. The performance indicators and fault warning areas are used to display a multi-vehicle performance comparison line chart generated based on the real-time performance indicators and fault-related information. The data analysis and reporting area is used to display the environmental comfort change curve generated by the environmental optimization instructions; User authentication and permission management are performed through the user management and permission settings area.

7. An intelligent cockpit log processing system, characterized in that, include: The data acquisition module is used to acquire log data from various subsystems of the intelligent cockpit; The data preprocessing module is used to process the acquired log data to obtain a standard dataset with a unified format and standardized type. The AI ​​analysis module is used to perform in-depth analysis on standardized data related to user operations in the standard dataset to automatically identify user behavior patterns, generate user preference profiles and personalized recommendations based on the identified user behavior patterns, and output them; to perform in-depth analysis on standardized data related to system operation in the standard dataset to obtain real-time performance indicators and fault-related information of the intelligent cockpit, and output the real-time performance indicators and fault-related information; and to perform in-depth analysis on standardized data related to environmental perception in the standard dataset to obtain environmental optimization strategies, and output corresponding environmental optimization instructions based on the environmental optimization strategies. The visualization module is used to display the user preference profile and personalized recommendations, the real-time performance indicators and fault-related information output by the AI ​​analysis module, as well as the environmental optimization suggestions corresponding to the environmental optimization instructions in the partitioned display. as well as The storage management module is used to store the log data of each subsystem of the intelligent cockpit acquired by the data acquisition module, as well as the user preference profile and personalized recommendations output by the AI ​​analysis module, the real-time performance indicators and the fault-related information, and the environmental optimization suggestions corresponding to the environmental optimization instructions. The intelligent cockpit subsystems include at least an infotainment system, a driver assistance system, an environmental control system, and a biosensing system. Standard automotive communication protocols include at least the following: CAN bus, LIN bus, and MOST bus.

8. The intelligent cockpit log processing system according to claim 7, characterized in that, The AI ​​analysis module includes a user behavior analysis submodule, a system performance evaluation submodule, an environmental comfort optimization submodule, and a model training and prediction unit. The user behavior analysis submodule is used to perform in-depth analysis of standardized data related to user operations in the standard dataset using a K-means clustering model in order to obtain user behavior patterns. By linking user operation records with environmental parameters through a decision tree model, user preference parameters are extracted based on the user behavior pattern to generate a user preference profile; personalized recommendations are extracted from the user preference profile according to the current driving scenario, and then converted into corresponding instructions and output. The system performance evaluation submodule is used to perform in-depth analysis on the standardized data related to system operation in the standard dataset using an LSTM deep learning model to obtain the real-time performance indicators of the smart cockpit and the performance prediction data within a preset time. The performance prediction data is analyzed to obtain fault warning information; The fault warning information is analyzed using a decision tree model to obtain the fault type and root cause, and maintenance suggestions are generated. The environmental comfort optimization submodule is used to perform in-depth analysis of standardized data related to environmental perception in the standard dataset using a reinforcement learning model to establish a comfort model; obtain an environmental optimization strategy based on the user preference profile using the comfort model; output corresponding environmental optimization instructions according to the environmental optimization strategy; and update the comfort model in real time using the environmental optimization instructions. The prediction model training module is used to train a K-means clustering model, an LSTM deep learning model, and a reinforcement learning model using historical log data from the stored subsystems of the smart cockpit; to receive user preference profiles and personalized recommendations in real time, and to optimize the trained K-means clustering model using these profiles and recommendations; to receive real-time performance metrics and fault-related information of the smart cockpit in real time, and to optimize the LSTM deep learning model using these metrics and information; and to receive environmental optimization strategies in real time, and to optimize the reinforcement learning model using these strategies.

9. The intelligent cockpit log processing system according to claim 7, characterized in that, The visualization module includes a standalone interface and / or a web interface; The stand-alone interface is at least divided into a cockpit status monitoring area, a personalized recommendation area, an environment setting control area, and a historical data query area. The web interface is at least divided into a vehicle selection and management area, a performance indicator and fault warning area, a data analysis and reporting area, and a user management and permission settings area. The cockpit status monitoring area is used to display a performance trend chart generated in real time based on the real-time performance indicators and fault-related information. The personalized recommendation area is used to display personalized suggestions generated through the user preference profile and personalized recommendations, and to recommend them to various subsystems of the smart cockpit; The environment settings control area is used to display the environment optimization suggestions; The historical data query area is used to read the stored historical log data, the stored user preference profiles and personalized recommendations, the real-time performance indicators and the fault-related information, as well as the environmental optimization suggestions corresponding to the environmental optimization instructions; The vehicle selection and management area is used to filter different vehicles based on their basic information and to query and manage the selected vehicles. The performance indicators and fault warning areas are used to display a multi-vehicle performance comparison line chart generated based on the real-time performance indicators and fault-related information. The data analysis and reporting area is used to display the environmental comfort change curve generated by the environmental optimization instructions; User authentication and permission management are performed through the user management and permission settings area.

10. A computer device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation of the intelligent cockpit log processing method as described in any one of claims 1-6.

Images