Vehicle message analysis method and device, equipment and storage medium
By using preset filtering rules and deep learning models to identify packet structures and context correlation analysis in CAN bus message analysis, the problems of inefficiency and insufficient accuracy in the existing technology are solved, and efficient and accurate analysis of CAN bus messages is achieved.
Patent Information
- Application Number
- CN202510770296.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-10
- Publication Date
- 2025-07-22
AI Technical Summary
The existing CAN bus message analysis methods are inefficient and have insufficient accuracy, making it difficult to adapt to the changing communication environment and new message formats.
Filter the data of pending messages through preset filtering rules, use the target message analysis model to identify the packet structure and context association analysis, and combine deep learning and natural language processing technology to automatically analyze CAN bus messages.
It improves the efficiency and accuracy of CAN bus message resolution, can adapt to the new message format, and provides intelligent, flexible and secure resolution solutions.
Smart Images
Figure CN120358290A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of vehicles, and particularly to a method, device, equipment, and storage medium for vehicle message parsing. Background Technique
[0002] The Controller Area Network (CAN) was initially developed by the German company BOSCH and has now become an international standard (ISO 11898). It is one of the widely used fieldbuses. The CAN bus protocol was initially developed to reduce the complexity and cost of automotive wiring. Its features include high reliability, real-time performance, strong anti-interference ability, support for multi-master communication, simple wiring structure, and efficient error detection and handling mechanisms. These features make it particularly suitable for complex environments. The CAN bus protocol has the following characteristics: 1) High reliability: Through error detection and automatic retransmission mechanisms, it ensures the integrity and reliability of data; 2) Real-time performance: The priority mechanism enables high-priority messages to be transmitted in a timely manner, suitable for real-time control applications; 3) Multi-master support: Allows multiple nodes to send and receive data simultaneously, with strong flexibility; 4) Strong anti-interference ability: Has strong electromagnetic interference resistance and is suitable for complex environments; 5) Simple wiring: Uses twisted pair and terminal resistors, with simple wiring, reducing the complexity of physical connections; 6) Low cost: Compared with other communication protocols, the hardware and implementation costs of CAN are lower; 7) Scalability: Nodes can be added as needed, facilitating system expansion.
[0003] The CAN physical layer is divided into two forms: a closed-loop bus network and an open-loop bus network. The closed-loop bus network follows the ISO11898 standard and is a high-speed, short-distance CAN network with a maximum communication speed of 1 Mbps and a maximum bus length of 40 meters. The open-loop bus network follows the ISO11519-2 standard and is a low-speed, long-distance CAN network with a maximum communication rate of 125 kbit / s and a maximum bus length of 1000 meters. The data transmission of the CAN bus is carried out through five types of frames: data frames, remote frames, error frames, overload frames, and frame intervals. Data frames and remote frames have two formats: standard format and extended format. The standard format has an 11-bit identifier (ID), and the extended format has a 29-bit ID. A data frame consists of 7 segments, including frame start, arbitration segment, control segment, data segment, CRC segment, ACK segment, and frame end.
[0004] The widespread application of the CAN bus and the complexity of its message format make the parsing of CAN bus messages a technical challenge. Traditional parsing methods rely on manual configuration and hardware support, which are not only inefficient but also difficult to adapt to changing communication environments and message formats. Therefore, developing an intelligent CAN bus message parsing tool that can automatically identify and parse CAN bus messages is of great significance for improving parsing efficiency and accuracy. Summary of the Invention
[0005] The main objective of this application is to provide a vehicle message parsing method, device, equipment, and storage medium, aiming to solve the technical problems of low efficiency, insufficient accuracy, and difficulty in adapting to new message formats in existing CAN bus message parsing methods.
[0006] To achieve the above objective, this application proposes a vehicle message parsing method, which includes:
[0007] When receiving the message data to be processed sent by the target node, filter the message data to be processed through a preset filtering rule to obtain the message data to be parsed;
[0008] Input the preprocessed message data to be parsed into the target message parsing model for message structure recognition to obtain the key parameters of the message to be parsed and the key signals of the message to be parsed;
[0009] According to the key parameters of the message to be parsed, the key signals of the message to be parsed, and through the target message parsing model, perform context correlation analysis to determine the message dependency relationship of the message to be parsed;
[0010] Parse the message according to the key parameters of the message to be parsed, the key signals of the message to be parsed, and the message dependency relationship to obtain the target parsing result of the message to be parsed.
[0011] In one embodiment, before the step of inputting the preprocessed message data to be parsed into the target message parsing model for message structure recognition to obtain the key parameters of the message to be parsed and the key signals of the message to be parsed, it further includes:
[0012] Preprocess the message data to be processed to obtain the preprocessed message data to be parsed;
[0013] Train the initial message parsing model according to historical message data to obtain the target message parsing model.
[0014] In one embodiment, the step of preprocessing the message data to be parsed to obtain the preprocessed message data to be parsed includes:
[0015] Extract features from the message data to be parsed to obtain the target message features;
[0016] Perform standardization processing on the target message features to obtain the target processing features;
[0017] According to the preset message recombination strategy and the target processing features, obtain the message data to be parsed after preprocessing.
[0018] In one embodiment, before the step of inputting the preprocessed message data to be parsed into the target message parsing model to perform message structure recognition and obtain the message key parameters of the message to be parsed and the message key signals of the message to be parsed, it further includes:
[0019] Determine the corresponding message training set, message validation set, and message test set according to the historical message data;
[0020] Train the initial message parsing model according to the message training set to obtain the trained initial message parsing model;
[0021] According to the message validation set, the message test set, and the trained initial message parsing model, obtain the target message parsing model.
[0022] In one embodiment, the step of obtaining the target message parsing model according to the message validation set, the message test set, and the trained initial message parsing model includes:
[0023] Evaluate the trained initial message parsing model according to the message validation set to obtain the target model evaluation result;
[0024] Adjust the model hyperparameters corresponding to the trained initial message parsing model according to the target model evaluation result to obtain the adjusted message parsing model;
[0025] Test the adjusted message parsing model according to the message test set to obtain the target model test result;
[0026] When the target model test result is a model test pass result, determine the adjusted message parsing model as the target message parsing model.
[0027] In one embodiment, after the step of performing message parsing according to the message key parameters, message key signals, and the message dependency relationship of the message to be parsed to obtain the target parsing result of the message to be parsed, it further includes:
[0028] Perform data analysis according to the target message parsing model to obtain the target data analysis result;
[0029] Generate and display a corresponding message data chart based on the analysis result of the target data.
[0030] In one embodiment, after the step of parsing the message to be parsed according to the key parameters of the message, the key signals of the message, and the message dependency relationship to obtain the target parsing result of the message to be parsed, the method further includes:
[0031] Evaluate the target message parsing result according to a preset result evaluation strategy to obtain a target parsing evaluation result;
[0032] Update the target message parsing model according to the user feedback information and the target parsing evaluation result to obtain an updated message parsing model.
[0033] In addition, to achieve the above object, the present application further provides a vehicle message parsing device, where the vehicle message parsing device includes:
[0034] A processing module, configured to filter the to-be-processed message data through a preset filtering rule when receiving the to-be-processed message data sent by a target node, to obtain to-be-parsed message data;
[0035] The processing module is further configured to input the preprocessed to-be-parsed message data into a target message parsing model for message structure recognition, to obtain the key parameters of the to-be-parsed message and the key signals of the to-be-parsed message;
[0036] The processing module is further configured to perform context correlation analysis through the target message parsing model according to the key parameters of the to-be-parsed message and the key signals of the to-be-parsed message, to determine the message dependency relationship of the to-be-parsed message;
[0037] A parsing module, configured to parse the message according to the key parameters of the to-be-parsed message, the key signals of the to-be-parsed message, and the message dependency relationship, to obtain the target parsing result of the to-be-parsed message.
[0038] In addition, to achieve the above object, the present application further provides a vehicle message parsing device, where the device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the vehicle message parsing method as described above.
[0039] In addition, to achieve the above object, the present application further provides a storage medium, where the storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the vehicle message parsing method as described above are implemented.
[0040] In addition, to achieve the above object, the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the vehicle message parsing method described above.
[0041] When the present application receives the message data to be processed sent by a target node, it filters the message data to be processed through a preset filtering rule to obtain the message data to be parsed; inputs the preprocessed message data to be parsed into a target message parsing model for message structure recognition to obtain the key parameters of the message to be parsed and the key signals of the message to be parsed; performs context correlation analysis through the target message parsing model according to the key parameters of the message to be parsed and the key signals of the message to be parsed to determine the message dependency relationship of the message to be parsed; and parses the message according to the key parameters of the message to be parsed, the key signals of the message, and the message dependency relationship to obtain the target parsing result of the message to be parsed. By training the message parsing model, the trained message parsing model is obtained, and then the preprocessed message data is parsed according to the trained message parsing model to obtain the message parsing result, that is, by using the deep learning and natural language processing capabilities of the large model, the messages transmitted on the CAN bus are parsed in an automated and intelligent manner. This improves the efficiency and accuracy of CAN bus message parsing and solves the problem that CAN bus message parsing is difficult to adapt to new message formats. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.
[0043] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0044] Figure 1 It is a schematic flowchart provided for Embodiment 1 of the vehicle message parsing method of the present application;
[0045] Figure 2 It is a schematic flowchart provided for Embodiment 2 of the vehicle message parsing method of the present application;
[0046] Figure 3 It is a schematic flowchart of the vehicle message parsing method provided for Embodiment 1 of the present application;
[0047] Figure 4 It is a schematic block diagram of the module structure of the vehicle message parsing device according to the embodiment of the present application;
[0048] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the vehicle message parsing method in the embodiments of the present application.
[0049] The realization of the purpose, functional features and advantages of the present application will be further described with reference to the accompanying drawings in combination with the embodiments. Detailed implementation manners
[0050] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0051] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the accompanying drawings of the specification and specific implementation manners.
[0052] The main solution of the embodiments of the present application is: input the preprocessed message data to be parsed into the target message parsing model to obtain message key parameters and message output signals; parse the message output signals to obtain message parsing parameters; and obtain the target message parsing result according to the message key parameters and the message parsing parameters.
[0053] The wide application of the CAN bus and the complexity of its message format make the parsing of CAN bus messages a technical challenge. Traditional parsing methods rely on manual configuration and hardware support, which are not only inefficient but also difficult to adapt to changing communication environments and message formats. Therefore, developing an intelligent CAN bus message parsing tool that can automatically identify and parse CAN bus messages is of great significance for improving parsing efficiency and accuracy.
[0054] When this application receives the to-be-processed message data sent by the target node, it filters the to-be-processed message data through a preset filtering rule to obtain the to-be-parsed message data; inputs the preprocessed to-be-parsed message data into the target message parsing model for message structure recognition to obtain the key parameters of the to-be-parsed message and the key signals of the to-be-parsed message; performs context correlation analysis through the target message parsing model according to the key parameters of the to-be-parsed message and the key signals of the to-be-parsed message to determine the message dependency relationship of the to-be-parsed message; and performs message parsing according to the key parameters of the to-be-parsed message, the key signals, and the message dependency relationship to obtain the target parsing result of the to-be-parsed message. The trained message parsing model is obtained by training the message parsing model, and then the preprocessed message data is parsed according to the trained message parsing model to obtain the message parsing result, that is, the deep learning and natural language processing capabilities of the large model are utilized to parse the messages transmitted on the CAN (Controller Area Network) bus in an automated and intelligent manner. The efficiency and accuracy of CAN bus message parsing are improved, and the problem that CAN bus message parsing is difficult to adapt to new message formats is solved.
[0055] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a vehicle message parsing device that can implement the above functions. Hereinafter, taking the vehicle message parsing device as the execution subject as an example, this embodiment and the following embodiments will be described.
[0056] Based on this, an embodiment of this application provides a vehicle message parsing method, referring to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the vehicle message parsing method of this application.
[0057] In this embodiment, the vehicle message parsing method includes steps S10 to S30:
[0058] Step S10, when receiving the to-be-processed message data sent by the target node, filtering the to-be-processed message data through a preset filtering rule to obtain the to-be-parsed message data;
[0059] It should be noted that this embodiment utilizes the deep learning and natural language processing capabilities of the large model to parse the messages transmitted on the CAN (Controller Area Network) bus in an automated and intelligent manner. To solve the problems of low efficiency, insufficient accuracy, and difficulty in adapting to new message formats existing in the existing CAN bus message parsing methods. Furthermore, a more intelligent, flexible, and secure CAN bus message parsing solution is provided for users.
[0060] It is understandable that the data of the message to be parsed refers to the data packet transmitted through the CAN network to be parsed, and the preset filtering rule refers to the rule for filtering irrelevant CAN bus messages set in advance.
[0061] In a specific implementation, when receiving a data packet transmitted through the CAN network to be parsed sent by any node, by introducing an intelligent filtering algorithm, it is possible to automatically identify and filter irrelevant CAN bus messages according to the rules defined by the user or based on a machine learning model, reduce the load of data processing, and improve the parsing efficiency.
[0062] In a feasible implementation manner, step S10 may include steps A11 to A12:
[0063] Step A11, preprocess the data of the message to be parsed to obtain the preprocessed data of the message to be parsed;
[0064] In a specific implementation, to improve the accuracy of message parsing, preprocess the data packet transmitted through the CAN network to be parsed, that is, feature extraction, data standardization, and message recombination, etc., and then obtain the preprocessed data of the message to be parsed.
[0065] It should be noted that in this implementation, a CAN device is used to receive continuously transmitted CAN messages and transmit the messages to the loop processing flow. Specifically: 1) Intelligent filtering mechanism. By introducing an intelligent filtering algorithm, it is possible to automatically identify and filter irrelevant CAN bus messages according to the rules defined by the user or based on a machine learning model, reduce the load of data processing, and improve the parsing efficiency; 2) Dynamic bandwidth allocation. Implement a dynamic bandwidth allocation mechanism to dynamically adjust the bandwidth of each node according to the real-time traffic and message priority on the CAN bus, and optimize the use of network resources; 3) Wireless CAN interface. Develop a wireless CAN interface module to allow CAN devices to communicate without physical connection, expand the application range of the CAN network, and improve the flexibility of the system; 4) Introduction of an event trigger mechanism. Implement an event trigger mechanism to automatically trigger an alarm or diagnostic program when detecting a specific pattern or abnormal message, providing support for real-time monitoring and fault response.
[0066] In a feasible implementation manner, step A11 may include steps B11 to B13:
[0067] Step B11, extract features from the data of the message to be parsed to obtain the target message features;
[0068] It should be noted that the target message features refer to the features extracted based on the data of the message to be parsed.
[0069] In a specific implementation, feature extraction is performed on the received CAN message to obtain features extracted from the data of the message to be parsed, such as frame ID, timestamp, period, payload data, etc.
[0070] Step B12, perform normalization processing on the target message features to obtain target processed features;
[0071] It can be understood that the target processed features refer to the message features after normalization processing.
[0072] In a specific implementation, data normalization processing is performed on the features extracted from the data of the message to be parsed to eliminate the influence of different dimensions and magnitudes on subsequent model training, and then the message features after normalization processing, that is, the target processed features, are obtained.
[0073] Step B13, according to the preset message recombination strategy and the target processed features, obtain the data of the message to be parsed after preprocessing.
[0074] It can be understood that the preset message recombination strategy refers to a preset intelligent algorithm for message recombination.
[0075] In a specific implementation, the message features after normalization processing are recombined through a preset intelligent algorithm for message recombination to obtain the data of the message to be parsed after preprocessing, so as to ensure the integrity and accuracy of the data.
[0076] It should be noted that in this embodiment, a preliminary data preprocessing function, such as CRC check, signal shaping, etc., is integrated in the frame information preprocessing module to reduce the complexity of subsequent processing steps, as follows: 1). Feature extraction is performed on the received CAN message, including frame ID, timestamp, period, payload data, etc. According to the characteristics of the CAN message, the payload is divided into 8 feature bits (byte0, byte1, byte2, byte3, byte4, byte5, byte6, byte7), and all these feature bits are distributed between 0 and 255; 2). Data normalization processing, data normalization processing is performed on the extracted features to eliminate the influence of different dimensions and magnitudes on subsequent model training. This step ensures that the data is compared and processed under the same standard, improving the accuracy of subsequent analysis; 3). Introduce an intelligent algorithm for message recombination, which is used to process the message fragments scattered due to network delay or interference to ensure the integrity and accuracy of the data.
[0077] Step A12, train the initial message parsing model according to the historical message data to obtain the target message parsing model.
[0078] It can be understood that the historical message data includes historical vehicle messages and historical parsing data, and the initial message parsing model refers to an untrained deep learning model, including a convolutional neural network and a recurrent neural network.
[0079] In a specific implementation, the untrained deep learning model is trained according to the historical vehicle messages and historical parsing data, and the backpropagation algorithm is used to optimize the model parameters to minimize the prediction error, so as to obtain a deep learning model for CAN message parsing, that is, the target message parsing model.
[0080] Step S20: Input the preprocessed message data to be parsed into the target message parsing model for message structure recognition, and obtain the message key parameters and message key signals of the message to be parsed.
[0081] It can be understood that the target message parsing model refers to a deep learning model for CAN message parsing. The message key parameters refer to the key parameters in the message, including frame ID recognition and the frame ID of the recognized message, etc. The message output signal refers to the key signal in the message.
[0082] In a specific implementation, the model can automatically identify the key parameters and signals in the message by learning the structure and content of the CAN message, that is, input the preprocessed message data into the deep learning model for CAN message parsing, and then obtain the key parameters and signals in the message, that is, the message key parameters and message output signals.
[0083] Step S30: Perform context correlation analysis through the target message parsing model according to the message key parameters and message key signals of the message to be parsed, and determine the message dependency relationship of the message to be parsed.
[0084] It can be understood that the message dependency relationship refers to the context relationship between messages.
[0085] In a specific implementation, the intelligent parsing module in this embodiment not only identifies the content of a single message, but also can understand the context relationship between messages. This enables the model to parse signals with dependency relationships. For example, the value of some signals may depend on the state of other signals. At the same time, this module also integrates an anomaly detection mechanism, which can identify abnormal or error signals in the message, which is crucial for fault diagnosis and system monitoring.
[0086] Step S40: Perform message parsing according to the message key parameters, message key signals and message dependency relationship of the message to be parsed, and obtain the target parsing result of the message to be parsed.
[0087] In a specific implementation, the intelligent parsing module in this embodiment can process the messages on the CAN bus in real time and quickly provide parsing results. At the same time, the module can self-adjust and optimize according to the user's feedback and the accuracy of the parsing results.
[0088] It should be noted that this embodiment is based on a trained large model to intelligently parse the preprocessed CAN message data and automatically identify key parameters and signals. Specifically, it includes the following aspects: 1) Model input and preprocessing. The intelligent parsing module receives the preprocessed CAN message data, which has been standardized and cleaned by the frame information preprocessing module. The preprocessing steps ensure the quality of the input data and provide consistent and reliable input for the model; 2) Signal and parameter identification. The model can automatically identify the key parameters and signals in the message by learning the structure and content of the CAN message. It mainly includes the following contents: Frame ID identification, identifying the frame ID of the message, which is the key information to distinguish different messages; Signal extraction, extracting specific signal values from the data field of the message; Signal decoding, converting the extracted signal values into actual physical quantities, such as speed, temperature, pressure, etc.; Result output, including the detailed information of the message and the parsed parameter values; 3) Context understanding and anomaly detection. The intelligent parsing module not only identifies the content of a single message but also can understand the context relationship between messages. This enables the model to parse signals with dependencies. For example, the value of some signals may depend on the state of other signals. At the same time, the module also integrates an anomaly detection mechanism to identify abnormal or incorrect signals in the message, which is crucial for fault diagnosis and system monitoring; 4) Real-time parsing and feedback. The intelligent parsing module can process the messages on the CAN bus in real time and quickly provide parsing results. At the same time, the module can self-adjust and optimize according to the user's feedback and the accuracy of the parsing results.
[0089] In a feasible implementation manner, after step S40, steps C11 to C12 may further be included:
[0090] Step C11, performing data analysis according to the target message parsing model to obtain a target data analysis result;
[0091] It can be understood that the target data analysis result refers to the analysis result of the parsed signal values, units, and status information.
[0092] In a specific implementation, for visual display through a graphical user interface (GUI) to help users intuitively understand the message content, and then perform data analysis on the parsed signal values, units, and status information to determine the target data analysis result.
[0093] Step C12, generating a corresponding message data chart according to the target data analysis result and displaying it.
[0094] In a specific implementation, the message data chart includes a signal line chart, a line chart of the relationship between vehicle speed and time, etc. The corresponding signal line chart, line chart of the relationship between vehicle speed and time, etc. are generated according to the analysis results of the parsed signal values, units, and status information. That is, the message data chart.
[0095] It should be noted that after the parsing is completed in this embodiment, the module outputs the results in a structured manner, including the parsed signal values, units, and status information. The results can be visually displayed through a graphical user interface (GUI) to help users intuitively understand the message content. Specifically, it includes the following contents: 1) Real-time data visualization: Use a Python script to receive CAN messages and visualize the signal values in real time. By using the pyqt library (a Python binding library for creating graphical user interfaces), a graphical interface can be created to display the charts of CAN data in real time. For example, the change curves of specific signals (such as temperature, speed, etc.) over time can be displayed to provide users with intuitive data analysis. 2) Data parsing and plotting: Parse the CAN bus messages and generate curves for data analysis, positioning, and comparison. Parse the CAN messages based on Python tools and finally draw a signal line chart. Through the matplotlib library (used to generate static, dynamic, and interactive charts, histograms, power spectra, bar charts, error charts, scatter plots, etc.), a line chart of the relationship between vehicle speed and time can be generated to help users understand the data change trend. 3) Network structure visualization: In order to check whether the design of the network structure is reasonable and at the same time observe whether the change rules of the input data in the network meet the expectations, various network visualization methods can be adopted. For example, use torchsummary (a helper tool for the PyTorch framework) to output information such as the layer structure, layer parameters, and total parameters of the network model; use graphviz (automatically generate a graphical structure according to a descriptive language) and torchviz (used to visualize the PyTorch computational graph through Graphviz) to output the network structure diagram to help users understand the internal details of the model. 4) Interactive user interface: Design an interactive user interface that allows users to interact with the analysis results of the model and deeply explore different requirements and problems. Users can select different signals or parameters through the interface to view the detailed parsing results and charts. 5) Multi-dimensional data display: In order to more comprehensively display the parsing results, multi-dimensional data display technologies such as three-dimensional charts, scatter plots, bar charts, etc. can be adopted to meet the display requirements of different types of data. Through the above technologies, the result output and visualization module can not only provide basic data display functions, but also provide advanced data visualization, interactive operations, and multi-dimensional analysis, greatly improving the user experience and the depth of data analysis.
[0096] In a feasible implementation, after step S40, steps D11 to D12 may further be included:
[0097] Step D11: Evaluate the target message parsing result according to a preset result evaluation strategy to obtain a target parsing evaluation result;
[0098] It can be understood that the preset result evaluation strategy refers to a strategy for presetting the evaluation of the parsing result quality, and the target parsing evaluation result refers to the quality evaluation result of the message parsing result.
[0099] In a specific implementation, the quality of the target message parsing result is evaluated according to the preset strategy for evaluating the parsing result quality, that is, the performance of the model is evaluated through indicators such as precision and recall, and then the quality evaluation result of the message parsing result, that is, the target parsing evaluation result, is determined.
[0100] Step D12: Update the target message parsing model according to the user feedback information and the target parsing evaluation result to obtain an updated message parsing model.
[0101] It can be understood that the user feedback information refers to the information of the message parsing result feedback by the user, and the updated message parsing model refers to the message parsing model after the model parameters are updated.
[0102] In a specific implementation, the parameters of the deep learning model for CAN message parsing are dynamically updated according to the information of the message parsing result feedback by the user and the quality evaluation result of the message parsing result, and then the message parsing model after the model parameters are updated, that is, the updated message parsing model, is obtained.
[0103] It should be noted that in this embodiment, the large model is continuously adjusted and optimized through user feedback and the accuracy of the parsing results to improve the accuracy and robustness of the parsing. It includes the following contents: 1) User feedback collection: This module collects user feedback on the parsing results through the user interface. Users can provide evaluations and suggestions on the accuracy, integrity, and usability of the parsing. This feedback information will be used for further training and optimization of the model. 2) Analysis result evaluation: The feedback loop module contains an evaluation mechanism for quantitatively analyzing the quality of the parsing results. Through indicators such as precision and recall, the performance of the model is evaluated and combined with user feedback to determine the direction of model optimization. 3) Model online learning: Based on user feedback and the evaluation of the parsing results, the module adopts an online learning strategy to dynamically update the model's parameters. This strategy enables the model to maintain the latest state in the continuously changing data stream and improve the accuracy of the parsing. 4) Iterative optimization: The feedback loop module supports the iterative optimization process. Each iteration includes model training, evaluation, and update until the model performance reaches a satisfactory level. This process can be automated or triggered according to the performance threshold set by the user. 5) Real-time monitoring and adjustment: The module provides a real-time monitoring function to monitor the parsing process and results of CAN bus messages. Once a parsing deviation or anomaly is detected, the system will automatically adjust the parsing strategy to ensure the stability and reliability of the parsing results. 6) Storage and management of feedback data: All user feedback and parsing result evaluation data are stored in the central database for historical analysis and future model training. Data management includes data security, privacy protection, and access control. 7) Intelligent alarm and notification: When there are serious deviations in the parsing results or the system performance degrades, the module will trigger the intelligent alarm mechanism and notify relevant personnel via email, text message, or system notification, etc., so that timely measures can be taken. Through these mechanisms, the feedback loop module not only improves the accuracy and efficiency of CAN bus message parsing, but also enhances the adaptive ability and user participation of the system, ensuring the long-term stability and reliability of the system.
[0104] In this embodiment, when receiving the to-be-processed message data sent by the target node, the to-be-processed message data is filtered through a preset filtering rule to obtain the to-be-parsed message data; the preprocessed to-be-parsed message data is input into the target message parsing model for message structure recognition to obtain the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message; according to the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message, context correlation analysis is performed through the target message parsing model to determine the message dependency relationship of the to-be-parsed message; message parsing is performed according to the message key parameters, message key signals, and the message dependency relationship of the to-be-parsed message to obtain the target parsing result of the to-be-parsed message. The trained message parsing model is obtained by training the message parsing model, and then the preprocessed message data is parsed according to the trained message parsing model to obtain the message parsing result, that is, the deep learning and natural language processing capabilities of the large model are utilized to parse the messages transmitted on the CAN bus in an automated and intelligent manner. The efficiency and accuracy of CAN bus message parsing are improved, and the problem that CAN bus message parsing is difficult to adapt to new message formats is solved.
[0105] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as in the above-mentioned first embodiment can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 2 , and before step S10 in the vehicle message parsing method, steps S11 to S13 are further included:
[0106] Step S11, determining the corresponding message training set, message verification set, and message test set according to the historical message data;
[0107] It can be understood that the message training set refers to the message data set used for model training, the message verification set refers to the message data set used for model verification, and the message test set refers to the message data set used for model testing.
[0108] In specific implementation, the historical message data is divided to obtain the message data set for model training, the message data set for model verification, and the message data set for model testing, that is, the message training set, the message verification set, and the message test set.
[0109] Step S12, training the initial message parsing model according to the message training set to obtain the trained initial message parsing model;
[0110] It can be understood that the untrained message parsing model is trained according to the message data set for model training to obtain the trained message parsing model, that is, the trained initial message parsing model.
[0111] Step S13: Obtain a target message parsing model based on the message verification set, the message test set, and the trained initial message parsing model.
[0112] In a specific implementation, evaluate and test the trained initial message parsing model according to the message data set for model verification and the message data set for model testing, and finally obtain the target message parsing model.
[0113] In a feasible implementation manner, step S13 may include steps E11 to E14:
[0114] Step E11: Evaluate the trained initial message parsing model according to the message verification set to obtain a target model evaluation result;
[0115] It can be understood that the target model evaluation result refers to the evaluation result of the model performance.
[0116] In a specific implementation, evaluate the performance of the trained initial message parsing model according to the message data set for model verification, and then obtain the evaluation result of the model performance, that is, the target model evaluation result.
[0117] Step E12: Adjust the model hyperparameters corresponding to the trained initial message parsing model according to the target model evaluation result to obtain an adjusted message parsing model;
[0118] It can be understood that the model hyperparameters include the network structure and the learning rate, etc. The adjusted message parsing model refers to the message parsing model after hyperparameter adjustment.
[0119] In a specific implementation, adjust and optimize the trained initial message parsing model according to the evaluation result of the model performance, that is, adjust the network structure and the learning rate of the model, etc., and then obtain the message parsing model after hyperparameter adjustment, that is, the adjusted message parsing model.
[0120] Step E13: Test the adjusted message parsing model according to the message test set to obtain a target model test result;
[0121] It can be understood that the target model test result refers to the performance test result of the message parsing model after hyperparameter adjustment, including the model test pass result and the model test fail result.
[0122] In a specific implementation, after completing the hyperparameter adjustment of the model, perform a performance test on the message parsing model after hyperparameter adjustment according to the message data set for model testing, and then obtain the performance test result of the message parsing model after hyperparameter adjustment, that is, the target model test result.
[0123] Step E14, when the target model test result is a model test pass result, determine the adjusted message parsing model as the target message parsing model.
[0124] In specific implementation, when the target model test result is a model test pass result, it indicates that the performance of the model meets the requirements. Then, the message parsing model after hyperparameter adjustment is used as the target message parsing model.
[0125] It should be noted that in this implementation, a large model is trained using machine learning algorithms. This model can learn the parsing rules of CAN messages based on historical data. The CAN message data has been preliminarily preprocessed for standardization and feature extraction. Selecting appropriate features is crucial for the performance of the model. A fast search algorithm can be used to achieve fast access and retrieval of features through a hash table. Design a deep learning model architecture suitable for CAN message parsing. This architecture includes a convolutional neural network (CNN) to extract local features of the message and a recurrent neural network (RNN) to process the time series features of the message. Subsequently, the model is trained, and the divided training set, validation set, and test set are used to train and validate the model. During the model training process, the backpropagation algorithm is used to optimize the model parameters to minimize the prediction error. Anomaly detection is introduced and the analysis model is enhanced for robustness. Machine learning algorithms are used to identify network messages on the in-vehicle bus to achieve intrusion detection of known / unknown threats to the vehicle. The anomaly detection technology based on machine learning has strong universality and does not require customized development for the adapted vehicle models, and can be used in a platformized manner for multiple vehicle models with strong scalability. Finally, the model is evaluated, fed back, and optimized. The performance of the model is evaluated on the validation set, and the model is adjusted and optimized according to the evaluation results, including adjusting hyperparameters such as the network structure and learning rate. At the same time, the application of multi-threaded processing and caching mechanism is used to improve the data processing efficiency. By creating multiple threads, each thread processes a part of the data, and the received messages are processed in parallel using multi-threading. Tools such as functools.lru_cache can be used to cache the recently accessed data, store the frequently accessed data, reduce repeated calculations, and improve the response speed of the model.
[0126] In this embodiment, a corresponding message training set, message validation set, and message test set are determined according to historical message data; the initial message parsing model is trained according to the message training set to obtain the trained initial message parsing model; according to the message validation set, the message test set, and the trained initial message parsing model, the target message parsing model is obtained. The accuracy of message parsing is improved through the intelligent parsing of the large model, and human errors are reduced.
[0127] Exemplarily, to help understand the implementation process of the vehicle message parsing method obtained by combining the above Embodiment 1, please refer toFigure 3 , Figure 3 A brief process schematic diagram of a vehicle message parsing method is provided. Specifically: The CAN message information acquisition and reception module uses a CAN device to receive continuously transmitted CAN messages; The CAN message frame information preprocessing module integrates preliminary data preprocessing functions, such as CRC check, signal shaping, etc., in the frame information preprocessing module to reduce the complexity of subsequent processing steps; The large model training module uses machine learning algorithms to train a large model, which can learn the parsing rules of CAN messages based on historical data. The CAN bus message intelligent parsing module, based on the trained large model, intelligently parses the preprocessed CAN message data to automatically identify key parameters and signals; Analysis result visualization module: After the parsing is completed, the module outputs the results in a structured manner, including the parsed signal values, units, and status information. The results can be visually displayed through a graphical user interface (GUI) to help users intuitively understand the message content; Feedback loop module: This module continuously adjusts and optimizes the large model through user feedback and the accuracy of the parsing results to improve the accuracy and robustness of the parsing.
[0128] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the vehicle message parsing method of this application. Based on this technical concept, more forms of simple transformations are within the protection scope of this application.
[0129] This application also provides a vehicle message parsing device. Please refer to Figure 4 , the vehicle message parsing device includes:
[0130] Processing module 10, which is used to filter the to-be-processed message data received from the target node through a preset filtering rule to obtain the to-be-parsed message data;
[0131] The processing module 10 is also used to input the preprocessed to-be-parsed message data into the target message parsing model for message structure recognition to obtain the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message;
[0132] The processing module 10 is also used to perform context correlation analysis through the target message parsing model according to the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message to determine the message dependency relationship of the to-be-parsed message;
[0133] Parsing module 20, which is used to perform message parsing according to the message key parameters, message key signals, and the message dependency relationship of the to-be-parsed message to obtain the target parsing result of the to-be-parsed message.
[0134] Optionally, the processing module 10 is also used to:
[0135] Preprocess the data of the message to be parsed to obtain the preprocessed data of the message to be parsed;
[0136] Train the initial message parsing model according to the historical message data to obtain the target message parsing model.
[0137] Optionally, the processing module 10 is further configured to:
[0138] Extract features from the data of the message to be parsed to obtain the target message features;
[0139] Perform standardization processing on the target message features to obtain the target processed features;
[0140] According to the preset message recombination strategy and the target processed features, obtain the preprocessed data of the message to be parsed.
[0141] Optionally, the processing module 10 is further configured to:
[0142] Determine the corresponding message training set, message validation set, and message test set according to the historical message data;
[0143] Train the initial message parsing model according to the message training set to obtain the trained initial message parsing model;
[0144] According to the message validation set, the message test set, and the trained initial message parsing model, obtain the target message parsing model.
[0145] Optionally, the processing module 10 is further configured to:
[0146] Evaluate the trained initial message parsing model according to the message validation set to obtain the target model evaluation result;
[0147] Adjust the model hyperparameters corresponding to the trained initial message parsing model according to the target model evaluation result to obtain the adjusted message parsing model;
[0148] Test the adjusted message parsing model according to the message test set to obtain the target model test result;
[0149] When the target model test result is a model test pass result, determine the adjusted message parsing model as the target message parsing model.
[0150] Optionally, the parsing module 20 is further configured to:
[0151] Perform data analysis according to the target message parsing model to obtain the target data analysis result;
[0152] Generate and display a corresponding message data chart based on the analysis result of the target data.
[0153] Optionally, the parsing module 20 is further configured to:
[0154] Evaluate the target message parsing result according to a preset result evaluation strategy to obtain a target parsing evaluation result;
[0155] Update the target message parsing model according to the user feedback information and the target parsing evaluation result to obtain an updated message parsing model.
[0156] The vehicle message parsing device provided by the present application adopts the vehicle message parsing method in the above embodiment, and can solve the technical problems of low efficiency, insufficient accuracy and difficulty in adapting to new message formats existing in the existing CAN bus message parsing method. Compared with the prior art, the beneficial effects of the vehicle message parsing device provided by the present application are the same as those of the vehicle message parsing method provided by the above embodiment, and other technical features in the vehicle message parsing device are the same as those disclosed in the above embodiment method, which will not be elaborated here.
[0157] The present application provides a vehicle message parsing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle message parsing method in the first embodiment above.
[0158] Next, refer to Figure 5 , which shows a schematic structural diagram of a vehicle message parsing device suitable for implementing the embodiments of the present application. The vehicle message parsing device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The vehicle message parsing device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.
[0159] As Figure 5As shown, the vehicle message parsing device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the vehicle message parsing device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the vehicle message parsing device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a vehicle message parsing device having various systems, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be alternatively implemented or had.
[0160] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.
[0161] The vehicle message parsing device provided by the present application adopts the vehicle message parsing method in the above-mentioned embodiment, and can solve the technical problems of low efficiency, insufficient accuracy, and difficulty in adapting to new message formats existing in the existing CAN bus message parsing method. Compared with the prior art, the beneficial effects of the vehicle message parsing device provided by the present application are the same as those of the vehicle message parsing method provided by the above-mentioned embodiment, and other technical features in the vehicle message parsing device are the same as those disclosed in the method of the previous embodiment, and will not be elaborated here.
[0162] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.
[0163] As described above, the above are only specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all of them should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.
[0164] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle message parsing method in the above embodiments.
[0165] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or combined with an instruction execution system, device, or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0166] The above computer-readable storage medium can be included in the vehicle message parsing device; or it can exist separately without being assembled into the vehicle message parsing device.
[0167] The above computer-readable storage medium carries one or more programs, which, when executed by a vehicle message parsing device, cause the vehicle message parsing device to: when receiving to-be-processed message data sent by a target node, filter the to-be-processed message data through a preset filtering rule to obtain to-be-parsed message data; input the preprocessed to-be-parsed message data into a target message parsing model for message structure recognition to obtain message key parameters of the to-be-parsed message and message key signals of the to-be-parsed message; perform context correlation analysis through the target message parsing model according to the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message to determine the message dependency relationship of the to-be-parsed message; perform message parsing according to the message key parameters, message key signals, and the message dependency relationship of the to-be-parsed message to obtain a target parsing result of the to-be-parsed message.
[0168] Computer program code for performing the operations of the present application may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partially on the user's computer, execute as a stand-alone software package, execute partially on the user's computer and partially on a remote computer, or execute entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).
[0169] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that, in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.
[0170] The modules described in the embodiments of the present application can be implemented in software or in hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.
[0171] The readable storage medium provided by the present application is a computer-readable storage medium, and the computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for executing the above vehicle message parsing method, which can solve the technical problems of low efficiency, insufficient accuracy, and difficulty in adapting to new message formats existing in the existing CAN bus message parsing method. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as those of the vehicle message parsing method provided by the above embodiments, and will not be elaborated here.
[0172] The present application also provides a computer program product, including a computer program, which when executed by a processor implements the steps of the vehicle message parsing method as described above.
[0173] The computer program product provided by the present application can solve the technical problems of low efficiency, insufficient accuracy, and difficulty in adapting to new message formats existing in the existing CAN bus message parsing method. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the vehicle message parsing method provided by the above embodiments, and will not be elaborated here.
[0174] The above are only some embodiments of the present application, and do not limit the patent scope of the present application. All equivalent structural transformations made under the technical concept of the present application by using the content of the specification and drawings of the present application, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present application.
Claims
1. A vehicle message parsing method, characterized in that, The vehicle message parsing method includes: When receiving the to-be-processed message data sent by a target node, filtering the to-be-processed message data through a preset filtering rule to obtain to-be-parsed message data; Inputting the preprocessed to-be-parsed message data into a target message parsing model for message structure recognition to obtain the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message; According to the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message, performing context correlation analysis through the target message parsing model to determine the message dependency relationship of the to-be-parsed message; Performing message parsing according to the message key parameters, message key signals and the message dependency relationship of the to-be-parsed message to obtain the target parsing result of the to-be-parsed message.
2. The method according to claim 1, characterized in that, Before the step of inputting the preprocessed to-be-parsed message data into a target message parsing model for message structure recognition to obtain the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message, it further includes: Preprocessing the to-be-processed message data to obtain preprocessed to-be-parsed message data; Training an initial message parsing model according to historical message data to obtain a target message parsing model.
3. The method according to claim 2, wherein The step of preprocessing the to-be-parsed message data to obtain preprocessed to-be-parsed message data includes: Performing feature extraction on the to-be-parsed message data to obtain target message features; Performing standardization processing on the target message features to obtain target processed features; According to a preset message recombination strategy and the target processed features, obtaining the preprocessed to-be-parsed message data.
4. The method according to claim 1, characterized in that, Before the step of inputting the preprocessed to-be-parsed message data into a target message parsing model for message structure recognition to obtain the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message, it further includes: Determining a corresponding message training set, message validation set and message test set according to historical message data; Training the initial message parsing model according to the message training set to obtain a trained initial message parsing model; According to the message validation set, the message test set and the trained initial message parsing model, obtaining a target message parsing model.
5. The method according to claim 4, characterized in that The step of obtaining a target message parsing model according to the message validation set, the message test set and the trained initial message parsing model includes: Evaluating the trained initial message parsing model according to the message validation set to obtain a target model evaluation result; Adjusting the model hyperparameters corresponding to the trained initial message parsing model according to the target model evaluation result to obtain an adjusted message parsing model; Testing the adjusted message parsing model according to the message test set to obtain a target model test result; When the target model test result is a model test pass result, determining the adjusted message parsing model as the target message parsing model.
6. The method according to any one of claims 1-5, characterized in that, After the step of performing message parsing according to the message key parameters, message key signals and the message dependency relationship of the to-be-parsed message to obtain the target parsing result of the to-be-parsed message, it further includes: Perform data analysis according to the target message parsing model to obtain the target data analysis result; Generate a corresponding message data chart according to the target data analysis result and display it.
7. The method according to any one of claims 1-5, characterized in that, After the step of parsing the message to be parsed according to the message key parameters, message key signals and the message dependency relationship of the message to be parsed to obtain the target parsing result of the message to be parsed, it further includes: Evaluate the target message parsing result according to a preset result evaluation strategy to obtain a target parsing evaluation result; Update the target message parsing model according to the user feedback information and the target parsing evaluation result to obtain an updated message parsing model.
8. A vehicle message parsing device, characterized in that, The device includes: A processing module, configured to filter the to-be-processed message data through a preset filtering rule when receiving the to-be-processed message data sent by a target node, to obtain to-be-parsed message data; The processing module is further configured to input the preprocessed to-be-parsed message data into a target message parsing model for message structure recognition, to obtain the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message; The processing module is further configured to perform context correlation analysis through the target message parsing model according to the message key parameters of the to-be-parsed message and the message key signals of the to-be-parsed message, to determine the message dependency relationship of the to-be-parsed message; A parsing module, configured to parse the message according to the message key parameters, message key signals and the message dependency relationship of the to-be-parsed message, to obtain the target parsing result of the to-be-parsed message.
9. A vehicle message parsing device, characterized in that, The device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the computer program is configured to implement the steps of the vehicle message parsing method according to any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the vehicle message parsing method according to any one of claims 1 to 7.