Vehicle data wireless interaction system

Abstract

The invention discloses a vehicle data wireless interaction system, and particularly relates to the technical field of wireless interaction, and the system comprises a node relation model building module which is used for building a node model through analyzing the data flow and logic relation among a vehicle terminal, a network side node, a cloud end and a data server end; the multi-source data collection module is used for collecting data from each node to form a multi-source data set and cleaning the multi-source data set; the initial abnormal node extraction module is used for screening out abnormal nodes by monitoring key indexes and calculating node abnormal indexes; the abnormity diagnosis module is used for positioning a fault reason by analyzing the abnormity characteristic incidence matrix; the system further comprises a diffusion risk assessment module which is used for providing decision support for network management by analyzing risk factors and propagation paths of nodes, calculating abnormal diffusion risk coefficients and generating a network risk report, has a self-adaptive optimization mechanism, continuously optimizes risk assessment and a decision tree model according to a disposal effect, and improves the reliability and safety of the system.

Description

Technical Field

[0001] The present invention relates to the field of wireless interaction technology, and more particularly to a vehicle data wireless interaction system. Background Art

[0002] With the popularization of Internet of Vehicles technology and the continuous improvement of autonomous driving functions, vehicles need to interact with the external environment (including other vehicles, roadside units, and cloud platforms) in a large amount of data during driving. These interactive data not only cover the vehicle's own operating parameters (such as speed, steering angle, battery status, etc.) and environmental perception information (such as radar and camera detection results), but also include secure communication data and real-time collaborative instructions between the vehicle and the cloud. The on-board terminal and the cloud achieve multi-directional transmission and fusion analysis through wireless networks, aiming to improve the vehicle's driving safety and collaborative decision-making efficiency. However, in the face of the dynamic characteristics of the Internet of Vehicles system and massive real-time data streams, how to ensure that the information interaction between nodes is accurate, efficient and traceable has become an important research topic in the field of intelligent transportation.

[0003] In the process of wireless data interaction between vehicles, existing technologies often only perform simple threshold monitoring on single nodes or local links, and lack comprehensive consideration of multi-node and multi-process correlations and potential risk propagation mechanisms. For example, when an abnormality occurs in the vehicle terminal encryption module or cloud parsing service, it is difficult to determine in time whether it will have a chain effect on subsequent links (such as fleet scheduling modules or assisted driving decision systems). In addition, there are differences in data formats and time bases between different nodes, resulting in the inability to achieve high-precision alignment of data across nodes; when performing anomaly detection or troubleshooting, it is often necessary to rely on manual analysis or distributed logs, making it difficult to form adaptive and scalable linkage warning and closed-loop disposal capabilities. Summary of the invention

[0004] In order to overcome the above defects of the prior art, the present invention provides a vehicle data wireless interaction system to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a vehicle data wireless interaction system, comprising: The node relationship model building module is used to build a node relationship model for vehicle data interaction. The node types include vehicle terminals, network-side nodes, cloud and data servers. Each node of vehicle data interaction is modeled, and the functions and data interaction modes of vehicle terminals, roadside units, cloud and data servers are clarified. The node relationship model is constructed by analyzing the data flow and logical relationship between each node. The multi-source data collection module collects data from each node and forms a multi-source data set, extracts the collected data to obtain the key indicators of each node; Initial abnormal node extraction module: monitors the key indicators of each node, inputs the node abnormality measurement function to calculate the node abnormality index of each node, determines whether the node abnormality index meets the threshold requirement, and screens to obtain the initial abnormal node set; The abnormality diagnosis module extracts the initial abnormal node set to obtain an abnormal feature association matrix, wherein the abnormal feature association matrix includes the time features, spatial location features, and upstream and downstream dependency features of the initial abnormal nodes; performs fault diagnosis based on the abnormal feature association matrix; and takes measures based on the fault diagnosis results.

[0006] Preferably, the key indicators include public indicators and node function indicators, and the public indicators include at least: data throughput, processing delay, resource occupancy rate, and log anomaly rate; the node function indicators reflect the performance of the node category, and the node function indicators of the vehicle terminal node include at least: data packaging accuracy, sensor data accuracy, sensor data integrity rate, and encryption success rate; the node function indicators of the network side node include at least: communication delay, packet loss rate, and encryption / decryption pass rate; the node function indicators of the cloud node include at least: decapsulation accuracy, parsing time, data warehousing delay, and response time; the node function indicators of the data service node include at least: business processing accuracy, interface call success rate, and anomaly detection coverage.

[0007] Preferably, the node anomaly measurement function satisfies the following formula: ; ; ; Among them, m represents the total number of key indicators of the node, s represents the sequence number of the key indicators; x s Indicates the actual value of the key indicator s; gw s Indicates the weight of key indicator s; Used to quantify key indicators x s Relative to threshold The abnormal degree of , α represents the adjustment coefficient; Represents the abnormal deviation function, indicating the current value x s With the average value μ s The degree of deviation, Indicates the coefficient of volatility of the key indicator s.

[0008] Preferably, the abnormal feature association matrix includes time features, spatial location features, and upstream and downstream dependency features of the initial abnormal node; The time feature is obtained by: collecting the timestamp information of the initial abnormal node, including the time when the abnormality first occurred, the duration, and the frequency of the abnormality; The spatial location feature is obtained by: obtaining it according to the node relationship model; if it is a physical node, the spatial and temporal location information of the node is obtained by using geographic coordinates and location sensor data; if it is a data node, the virtual space positioning is performed according to the server where the node is located and the network partition information; the upstream and downstream dependency features include: data flow features, business process features and interface call dependency features; The data flow features are obtained by: starting from the initial abnormal node, tracing its data flow to the connected downstream nodes, and collecting abnormal conditions of key indicators of the downstream nodes; or tracing the dependent source nodes of the initial abnormal node, and evaluating the impact of the upstream abnormality on the current abnormality; The business process characteristics are obtained by: starting from the initial abnormal node, determining the position in the business process, and the impact on its upstream and downstream steps; The interface call dependency feature is obtained by recording the interface call behavior of the initial abnormal node and evaluating the impact of the initial abnormal node on the interface.

[0009] Preferably, the fault diagnosis refers to establishing a mapping relationship between abnormal node types and abnormal feature association matrices based on a decision tree algorithm, constructing a decision tree model by summarizing the time characteristics, spatial location characteristics, and upstream and downstream dependency characteristics of abnormal nodes in historical data or simulation annotation samples, and identifying the abnormal type and locating the root cause of the fault through the decision tree model.

[0010] Preferably, the system further comprises: The diffusion risk assessment module performs correlation analysis on the propagation path of the initial abnormal node in the node relationship model and outputs the abnormal diffusion path and abnormal diffusion risk coefficient; The diffusion risk judgment management module triggers linkage warning and protection actions based on the pre-defined linkage strategy if the abnormal diffusion risk coefficient exceeds the threshold, indicating that there is a high probability of chain abnormalities, including switching backup communication channels, enabling redundant analysis modules, and notifying the scheduling platform to pay attention to potential risks.

[0011] Preferably, the abnormal diffusion path is obtained by: The initial abnormal node is used as the starting point of the path, and the breadth-first search algorithm is used to traverse the node relationship model. Starting from the starting point, the neighbor nodes that meet the upstream and downstream logical relationships are visited layer by layer. During each traversal, it is determined whether the new node meets the propagation probability threshold. If the requirement is met, the new node is added to the diffusion path and the traversal continues to the next layer. When the set number of traversals is reached, the abnormal diffusion path is output.

[0012] Preferably, the abnormal diffusion risk coefficient is obtained in the following manner: Calculate the initial risk index: analyze the initial abnormal node set and obtain the risk factor of each initial abnormal node, the risk factor includes at least: information entropy of node abnormal feature association matrix, node vehicle impact ratio, node traffic impact ratio, node hardware failure rate, node software failure rate, node protection level; perform weighted summation on the quantified risk factors and corresponding weights, and output the initial risk index of each initial abnormal node; The probability product of all connected nodes is recorded as the propagation probability of the abnormal diffusion path; Set channel weights for each abnormal diffusion path based on data transmission frequency and security protection level; The propagation probability and channel weight are jointly analyzed to calculate the path risk index of each abnormal diffusion path; The initial risk indexes of all initial abnormal nodes are added together to obtain the sum of node risks; the path risk indexes of all abnormal diffusion paths are added together to obtain the sum of path risks; the node risk sum and path risk are weighted and summed to calculate the abnormal diffusion risk coefficient; Conduct a hierarchical assessment of the overall network risk level based on the abnormal diffusion risk coefficient and generate a network risk report; The network risk report includes: risk level defined according to the abnormal diffusion risk coefficient; key information of the abnormal diffusion path, abnormal diffusion path length and propagation probability.

[0013] Preferably, the initial risk index is obtained in the following manner: Assume there are Q risk factors, use p to represent the order of the risk factors, and record the value of the pth risk factor as f p ; The initial risk index Cf is calculated by the following formula: The initial risk index is calculated by the following formula: ; in, represents the weight of the pth risk factor, which is set based on experience; Assume that the starting point of each abnormal diffusion path is node i and the end point is node j; the channel weight is obtained as follows:

[0014] Among them, w ij Represents a slave node arrive The channel risk weight, F ij Representation Node arrive Data transmission frequency, ranging from 0 to 1, the larger the value, the more frequent the data interaction; S ij Represents a slave node arrive The average security protection level of the system is in the range of [0, 1]. The larger the value, the higher the security protection capability.

[0015] Preferably, the system further comprises: The disposal effect adaptive optimization module tracks the effects of the linkage warning and protection actions triggered by the diffusion risk assessment module, and continuously tracks the operating status and alarm indicators of the initial abnormal node; if the abnormality is alleviated or gradually disappears, the abnormality and disposal process will be recorded in the case library to improve the risk model and strategy threshold; if the disposal effect is not up to standard or new risks are derived, the latest initial abnormal node will be re-included in the abnormal diagnosis module, so as to continuously iterate and optimize the decision tree algorithm through the adaptive correction mechanism to ensure the reliability and security of the vehicle data wireless interaction process.

[0016] Technical effects and advantages of the present invention: 1. The vehicle data wireless interaction system provided by the present invention realizes efficient data interaction and fault diagnosis between the vehicle and the cloud, network side and data service side by constructing a node relationship model for vehicle data interaction and adopting multi-source data collection and abnormal node extraction technology. The key indicator monitoring of the receiving node and the calculation of the abnormal measurement function can identify potential abnormal nodes in the system in real time, and perform fault diagnosis through the abnormal feature association matrix, solving the problem that the root cause of the fault cannot be accurately located in the traditional vehicle data management system. The system effectively improves the stability and reliability of vehicle data interaction and ensures the car owner's car experience in various complex environments.

[0017] 2. The vehicle data wireless interaction system of the present invention, by introducing a diffusion risk assessment and management module, realizes comprehensive early warning and protection of system anomalies based on the quantitative analysis of abnormal diffusion paths and risk coefficients. The system can warn of possible chain failures based on the node risk characteristics and the propagation probability of abnormal diffusion paths, and trigger redundant modules and backup communication paths through linkage strategies to ensure that the vehicle data interaction system can continue to operate stably in the event of a failure. This technology effectively solves the problem that traditional systems lack the ability to predict and deal with emergencies in the face of abnormal propagation, and greatly improves the system's fault tolerance and emergency response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a structural block diagram of the vehicle data wireless interaction system of the present invention.

[0019] Figure 2 The present invention provides a structural block diagram for obtaining the abnormal diffusion risk coefficient. DETAILED DESCRIPTION

[0020] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0021] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0022] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0023] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0024] Background technology: In the embodiments of the present invention, a node can be understood as a functional entity or module divided by logical function or physical deployment in the process of data collection, transmission, processing, storage, analysis, etc.; a node refers to an entity or functional module that undertakes different functions and performs different operations in the whole process of data interaction; each node can be a physical device or a software / service process, as long as it plays an independent and identifiable functional role in the data link, it can be regarded as a node; common node types and typical functions are as follows: Vehicle terminal (vehicle side): Function examples: data collection, preprocessing, packaging, encryption, etc.; Data types: vehicle sensor output (such as speed, location, fuel consumption, vehicle status information, etc.), packaged logs, encrypted operation logs.

[0025] Roadside unit: Functional example: short-range wireless communication with vehicle terminals (such as V2X communication) to assist in data relay or preliminary processing; Data type: relay communication log, forwarding status information, network connection or fault information, etc.

[0026] Network-side nodes: Functional examples: Intermediate nodes (such as base stations, gateways, encryption / decryption units) when data is transmitted in the public / private network, performing encryption, routing or forwarding functions; Data types: encryption / decryption success rate, communication delay, packet loss information, network load, etc.

[0027] End platform; Function examples: receiving data transmitted from the vehicle side or the network side, performing decapsulation, parsing, storage, analysis, etc.; providing interfaces for external services or data analysis modules; Data types: decapsulation and parsing results, parsing time, database write logs, and response logs.

[0028] Other data service modules: Functional examples: modules that provide higher-level data mining, visualization or external services outside or on the cloud platform; data types: business processing logs, data call interface logs, exception handling records, etc.

[0029] Example 1, see Figure 1 The vehicle data wireless interaction system structure block diagram is provided in the embodiment of the present invention. The vehicle data wireless interaction system includes: The node relationship model building module is used to build a node relationship model for vehicle data interaction. The node types include vehicle terminals, network side nodes (such as roadside units, transmission units), cloud and data servers. Model each node of vehicle data interaction, clarify the functions and data interaction modes of vehicle terminals, roadside units, cloud and data servers, and build a node relationship model by analyzing the data flow and logical relationship between each node. Explanation: The node relationship model includes: a node function identifier for describing the node function, wherein the node function includes at least vehicle terminal preprocessing, network encryption, and cloud decapsulation; a data interaction channel for recording the data transmission path and connection mode between nodes; an upstream and downstream logical relationship for describing the order and logical association of each node in the data interaction process; The multi-source data collection module collects data from each node and forms a multi-source data set, extracts the collected data to obtain the key indicators of each node; cleans and unifies the multi-source data set, including timestamp alignment, field formatting and missing data filling; according to the node relationship model, the node function identifier, data interaction channel and upstream and downstream logical relationship are added to the cleaned data, and stored as a searchable basic data set; The data collected from each node specifically includes: collecting sensor output data and packaging logs from the vehicle terminal, collecting encryption / transmission status information and communication logs from the network side, collecting decapsulation analysis results and response logs from the cloud; and collecting logs from the data server; Initial abnormal node extraction module: monitors the key indicators of each node, inputs the node abnormality measurement function to calculate the node abnormality index of each node, determines whether the node abnormality index meets the threshold requirement, and screens to obtain the initial abnormal node set; Explanation: The node anomaly measurement function focuses on the abnormal performance of a single node and outputs the node anomaly index of each node to identify the initial abnormal node; The abnormality diagnosis module extracts the initial abnormal node set to obtain an abnormal feature association matrix, wherein the abnormal feature association matrix includes the time features, spatial location features, and upstream and downstream dependency features of the initial abnormal nodes; performs fault diagnosis based on the abnormal feature association matrix; and takes measures based on the fault diagnosis results.

[0030] What needs to be further explained in the embodiments of the present invention is that the key indicators include public indicators and node function indicators, and the public indicators include at least: data throughput, processing delay, resource occupancy rate, and log exception rate; the node function indicators reflect the performance of the node category, and the node function indicators of the vehicle terminal node include at least: data packaging accuracy, sensor data accuracy, sensor data integrity rate, and encryption success rate; the node function indicators of the network side nodes (such as roadside units, transmission units) include at least: communication delay, packet loss rate, encryption / decryption pass rate; the node function indicators of the cloud node include at least: decapsulation accuracy, parsing time, data warehousing delay, and response time; the node function indicators of the data service node include at least: business processing accuracy, interface call success rate, and anomaly detection coverage.

[0031] It needs to be further explained in the embodiment of the present invention that the node anomaly metric function satisfies the following formula: ; ; ; Among them, m represents the total number of key indicators of the node, s represents the sequence number of the key indicators; x s Indicates the actual value of the key indicator s; gw s Indicates the weight of key indicators (assigned based on business importance or historical statistical data); Used to quantify key indicators x s Relative to threshold The abnormal degree of , α represents the adjustment coefficient; Represents the abnormal deviation function, indicating the current value x s With the average value μ s The degree of deviation, Indicates the coefficient of volatility of the key indicator s.

[0032] It needs to be further explained in the embodiment of the present invention that the abnormal feature association matrix includes time features, spatial location features and upstream and downstream dependency features of the initial abnormal node; The time feature is obtained by: collecting the timestamp information of the initial abnormal node, including the time when the abnormality first occurred, the duration, and the frequency of the abnormality; The spatial location feature is obtained by: obtaining it according to the node relationship model; if it is a physical node, the spatial and temporal location information of the node is obtained by using geographic coordinates and location sensor data; if it is a data node, the virtual space positioning is performed according to the server where the node is located and the network partition information; the upstream and downstream dependency features include: data flow features, business process features and interface call dependency features; The data flow features are obtained by: starting from the initial abnormal node, tracing its data flow to the connected downstream nodes, and collecting abnormal conditions of key indicators of the downstream nodes; or tracing the dependent source nodes of the initial abnormal node, and evaluating the impact of the upstream abnormality on the current abnormality; The business process characteristics are obtained by: starting from the initial abnormal node, determining the position in the business process, and the impact on its upstream and downstream steps; The interface call dependency feature is obtained by recording the interface call behavior of the initial abnormal node and evaluating the impact of the initial abnormal node on the interface.

[0033] What needs to be further explained in the embodiments of the present invention is that the fault diagnosis refers to establishing a mapping relationship between abnormal node types and abnormal feature association matrices based on a decision tree algorithm, constructing a decision tree model by summarizing the time characteristics, spatial position characteristics and upstream and downstream dependency characteristics of abnormal nodes in historical data or simulation annotation samples, and identifying the abnormal type and locating the root cause of the fault through the decision tree model; for example, if the model determines that a positioning sensor fault exists in a vehicle terminal, the type of fault perceived by the vehicle terminal is output; if it is determined that a data packet is lost in the encryption / transmission module of a network side node, the cause of the failure of the network encryption module or the transmission module is output; if it is found during the diagnosis process that the rules or models deviate significantly from the actual situation, the decision tree model needs to be updated and improved, new abnormal samples need to be added, or feature annotations need to be corrected, so as to continuously improve the diagnostic accuracy of the abnormal diagnosis module.

[0034] Furthermore, the decision tree model calculates the gain value or information gain of the feature, selects the best split point for training, and evaluates the accuracy of the model through the cross-validation method; during the diagnosis process, if it is found that the rules or models deviate significantly from the actual situation, the decision tree model needs to be updated and improved, new abnormal samples are added or feature annotations are corrected, so as to improve the diagnostic accuracy.

[0035] It needs to be further explained in the embodiment of the present invention that taking measures based on the fault diagnosis result includes: Measures such as anomaly isolation, joint remediation, risk control, fault repair and recovery, as well as case recording and model optimization are taken. These measures can quickly locate anomalies, reduce the impact of faults, improve system stability, and achieve system intelligence and high reliability through continuous optimization.

[0036] Explanation: Abnormal isolation measures refer to the rapid isolation of abnormal nodes or paths based on the fault diagnosis results to prevent the fault from spreading to other nodes or modules. It includes node isolation and path isolation: Node isolation refers to the removal of the diagnosed abnormal nodes from the data interaction process, such as temporarily suspending their data transmission function and reconnecting them to the system after the problem is solved; Path isolation refers to adjusting the data flow direction to bypass the fault point through other paths if the diagnosis results show that a certain transmission path is abnormal; The linkage remedial measures refer to implementing remedial actions on abnormal nodes and related paths according to pre-defined linkage strategies to reduce the impact of abnormalities on the overall system; including enabling redundancy mechanisms, data rollback and retransmission, and dynamic adjustment of thresholds; The fault impact assessment and risk control refers to the assessment of the impact of the current fault on the overall system in combination with the fault diagnosis results, and the implementation of risk control measures; including impact assessment, early warning mechanism and risk level classification; risk level classification refers to the classification of the fault impact scope and potential consequences according to the severity of the diagnosis results, such as low risk, medium risk and high risk, and the implementation of graded control measures; Fault repair and recovery refers to taking repair and recovery actions based on the fault type and root cause in the diagnosis results, including software system updates, hardware repair or replacement, and automatic reset; Fault case recording and model optimization refers to recording the fault diagnosis process and measures taken into the system case library for optimizing anomaly detection and diagnosis models; it includes case library recording, model optimization and linkage strategy iteration.

[0037] Summary: By building a node relationship model, collecting and cleaning multi-source data, calculating node anomaly index, generating anomaly feature association matrix, and performing fault diagnosis based on decision tree algorithm, it is not only possible to quickly locate faulty nodes and anomaly types, but also to effectively prevent the spread of faults and reduce system risks through measures such as anomaly isolation, linkage remediation, risk control, fault repair and recovery. In addition, through case recording and model optimization, the system has adaptive learning capabilities and can continuously optimize fault diagnosis and response strategies, thereby improving the stability, reliability and intelligence level of system operation.

[0038] Embodiment 2: The difference between the embodiment of the present invention and embodiment 1 is that the system further includes: The diffusion risk assessment module performs correlation analysis on the propagation path of the initial abnormal node in the node relationship model and outputs the abnormal diffusion path and abnormal diffusion risk coefficient; The diffusion risk judgment management module triggers linkage warning and protection actions based on the pre-defined linkage strategy if the abnormal diffusion risk coefficient exceeds the threshold, indicating that there is a high probability of chain abnormalities, including switching backup communication channels, enabling redundant analysis modules, and notifying the scheduling platform to pay attention to potential risks.

[0039] It needs to be further explained in the embodiment of the present invention that the abnormal diffusion path is obtained in the following manner: The initial abnormal node is used as the starting point of the path, and the breadth-first search algorithm is used to traverse the node relationship model. Starting from the starting point, the neighbor nodes that meet the upstream and downstream logical relationships are visited layer by layer. During each traversal, it is determined whether the new node meets the propagation probability threshold. If the requirement is met, the new node is added to the diffusion path and the traversal continues to the next layer. When the set diffusion threshold or traversal times is reached, the abnormal diffusion path is output.

[0040] In the embodiments of the present invention, it is necessary to further explain that Figure 2 The abnormal diffusion risk coefficient is obtained by: Calculate the initial risk index: analyze the initial abnormal node set and obtain the risk factor of each initial abnormal node, the risk factor includes at least: information entropy of node abnormal feature association matrix, node vehicle impact ratio, node traffic impact ratio (ratio of node data traffic to total data traffic), node hardware failure rate, node software failure rate, node protection level; perform weighted summation on the quantified risk factors and corresponding weights, and output the initial risk index of each initial abnormal node; The probability product of all connected nodes is recorded as the propagation probability of the abnormal diffusion path; Set channel weights for each abnormal diffusion path based on data transmission frequency and security protection level; The propagation probability and channel weight are jointly analyzed to calculate the path risk index of each abnormal diffusion path; The initial risk indexes of all initial abnormal nodes are added together to obtain the sum of node risks; the path risk indexes of all abnormal diffusion paths are added together to obtain the sum of path risks; the node risk sum and path risk are weighted and summed to calculate the abnormal diffusion risk coefficient; Conduct a hierarchical assessment of the overall network risk level based on the abnormal diffusion risk coefficient and generate a network risk report; It is explained that the network risk report includes: risk levels (low, medium, high, extremely high, etc.) defined according to the abnormal diffusion risk coefficient and a detailed description of the current risk level, indicating high-risk areas or nodes and their causes; key information on abnormal diffusion paths, such as path nodes, length and propagation probability, and indicating the risk contribution of each node and the most critical influencing nodes; clarifying the risk level and potential threat of the initial abnormal node; specific protection plans for high-risk paths and nodes; in a possible implementation example, the network risk report will also predict future diffusion trends, provide early warning information, and simulate potential abnormal propagation, using charts and path diagrams to intuitively display the risk diffusion process, providing a basis for the early deployment of preventive measures.

[0041] It needs to be further explained in the embodiment of the present invention that the initial risk index is obtained in the following manner: Assume there are Q risk factors, use p to represent the order of the risk factors, and record the value of the pth risk factor as f p ; The initial risk index Cf is calculated by the following formula: The initial risk index is calculated by the following formula: ; in, represents the weight of the pth risk factor, which is set based on experience; What needs to be further explained in the embodiment of the present invention is that, assuming that the starting point of each abnormal diffusion path is node i and the end point is node j; the channel weight is obtained in the following manner: ; Among them, w ij Represents a slave node arrive The channel risk weight, F ij Representation Node arrive Data transmission frequency, ranging from 0 to 1, the larger the value, the more frequent the data interaction; S ij Represents a slave node arrive The average security protection level of the system is in the range of [0, 1]. The larger the value, the higher the security protection capability.

[0042] It needs to be further explained in the embodiment of the present invention that the system further includes: The disposal effect adaptive optimization module tracks the effects of the linkage warning and protection actions triggered by the diffusion risk assessment module, and continuously tracks the operating status and alarm indicators of the initial abnormal node; if the abnormality is alleviated or gradually disappears, the abnormality and disposal process will be recorded in the case library to improve the risk model and strategy threshold; if the disposal effect is not up to standard or new risks are derived, the latest initial abnormal node will be re-included in the abnormal diagnosis module, so as to continuously iterate and optimize the decision tree algorithm through the adaptive correction mechanism to ensure the reliability and security of the vehicle data wireless interaction process.

[0043] Summary: The embodiment of the present invention can realize comprehensive analysis and dynamic management of abnormal diffusion paths and their risks by adding a diffusion risk assessment module and a diffusion risk judgment management module; obtain abnormal diffusion paths based on a breadth-first search algorithm, combine the initial risk index, propagation probability and channel weight, accurately calculate the abnormal diffusion risk coefficient, and generate a detailed network risk report. Through risk classification assessment and the formulation of protection plans, the system can timely identify high-risk areas and key nodes, provide predictive warnings and protection measures, and significantly improve the system's risk resistance, abnormal management efficiency and overall security in a complex network environment.

[0044] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Vehicle data wireless interaction system, characterized in that: include: The node relationship model building module is used to build a node relationship model for vehicle data interaction. The node types include vehicle terminals, network side nodes, cloud and data service terminals. Each node of vehicle data interaction is modeled, and the node relationship model is constructed by analyzing the data flow and logical relationship between each node. The multi-source data collection module collects data from each node and forms a multi-source data set, extracts the collected data to obtain the key indicators of each node; Initial abnormal node extraction module: monitors the key indicators of each node, inputs the node abnormality measurement function to calculate the node abnormality index of each node, determines whether the node abnormality index meets the threshold requirement, and screens to obtain the initial abnormal node set; The abnormal diagnosis module extracts the initial abnormal node set to obtain an abnormal feature association matrix, wherein the abnormal feature association matrix includes the time feature, spatial location feature and upstream and downstream dependency feature of the initial abnormal node; Perform fault diagnosis based on the abnormal feature association matrix; take measures based on the fault diagnosis results.

2. The vehicle data wireless interaction system according to claim 1, characterized in that: The key indicators include public indicators and node function indicators. The public indicators include at least: data throughput, processing delay, resource occupancy rate, and log anomaly rate; the node function indicators reflect the performance of the node category. The node function indicators of the vehicle terminal node include at least: data packaging accuracy, sensor data accuracy, sensor data integrity rate, and encryption success rate; the node function indicators of the network side node include at least: communication delay, packet loss rate, and encryption / decryption pass rate; the node function indicators of the cloud node include at least: decapsulation accuracy, parsing time, data warehousing delay, and response time; the node function indicators of the data service node include at least: business processing accuracy, interface call success rate, and anomaly detection coverage.

3. The vehicle data wireless interaction system according to claim 1, characterized in that: The node anomaly measurement function satisfies the following formula: ； ； ； Among them, m represents the total number of key indicators of the node, s represents the sequence number of the key indicators; x s Indicates the actual value of the key indicator s; gw s Indicates the weight of key indicator s; Used to quantify key indicators x s Relative to threshold The abnormal degree of , α represents the adjustment coefficient; Represents the abnormal deviation function, indicating the current value x s With the average value μ s The degree of deviation, Indicates the coefficient of volatility of the key indicator s.

4. The vehicle data wireless interaction system according to claim 1, characterized in that: The abnormal feature association matrix includes time features, spatial location features and upstream and downstream dependency features of the initial abnormal node; The time feature is obtained by: collecting the timestamp information of the initial abnormal node, including the time when the abnormality first occurred, the duration, and the frequency of the abnormality; The spatial location feature is obtained by: obtaining it according to the node relationship model; if it is a physical node, the spatial and temporal location information of the node is obtained by using geographic coordinates and location sensor data; If it is a data node, the virtual space positioning is performed according to the server where the node is located and the network partition information; the upstream and downstream dependency characteristics include: data flow characteristics, business process characteristics and interface call dependency characteristics; The data flow features are obtained by: starting from the initial abnormal node, tracing its data flow to the connected downstream nodes, and collecting abnormal conditions of key indicators of the downstream nodes; or tracing the dependent source nodes of the initial abnormal node, and evaluating the impact of the upstream abnormality on the current abnormality; The business process characteristics are obtained by: starting from the initial abnormal node, determining the position in the business process, and the impact on its upstream and downstream steps; The interface call dependency feature is obtained by recording the interface call behavior of the initial abnormal node and evaluating the impact of the initial abnormal node on the interface.

5. The vehicle data wireless interaction system according to claim 1, characterized in that: The fault diagnosis refers to establishing a mapping relationship between abnormal node types and abnormal feature association matrices based on a decision tree algorithm, building a decision tree model by summarizing the time characteristics, spatial location characteristics, and upstream and downstream dependency characteristics of abnormal nodes in historical data or simulation annotation samples, and identifying the abnormal type and locating the root cause of the fault through the decision tree model.

6. The vehicle data wireless interaction system according to claim 1, characterized in that: The system further comprises: The diffusion risk assessment module performs correlation analysis on the propagation path of the initial abnormal node in the node relationship model and outputs the abnormal diffusion path and abnormal diffusion risk coefficient; The diffusion risk judgment management module triggers linkage warning and protection actions based on the pre-defined linkage strategy if the abnormal diffusion risk coefficient exceeds the threshold, indicating that there is a high probability of chain abnormalities, including switching backup communication channels, enabling redundant analysis modules, and notifying the scheduling platform to pay attention to potential risks.

7. The vehicle data wireless interaction system according to claim 6, characterized in that: The abnormal diffusion path is obtained as follows: The initial abnormal node is used as the starting point of the path, and the breadth-first search algorithm is used to traverse the node relationship model. Starting from the starting point, the neighbor nodes that meet the upstream and downstream logical relationships are visited layer by layer. During each traversal, it is determined whether the new node meets the propagation probability threshold. If the requirement is met, the new node is added to the diffusion path and the traversal continues to the next layer. When the set number of traversals is reached, the abnormal diffusion path is output.

8. The vehicle data wireless interaction system according to claim 6, characterized in that: The abnormal diffusion risk coefficient is obtained as follows: Calculate the initial risk index: analyze the initial abnormal node set and obtain the risk factor of each initial abnormal node, the risk factor includes at least: information entropy of node abnormal feature association matrix, node vehicle impact ratio, node traffic impact ratio, node hardware failure rate, node software failure rate, node protection level; perform weighted summation on the quantified risk factors and corresponding weights, and output the initial risk index of each initial abnormal node; The probability product of all connected nodes is recorded as the propagation probability of the abnormal diffusion path; Set channel weights for each abnormal diffusion path based on data transmission frequency and security protection level; The propagation probability and channel weight are jointly analyzed to calculate the path risk index of each abnormal diffusion path; The initial risk indexes of all initial abnormal nodes are added together to obtain the sum of node risks; the path risk indexes of all abnormal diffusion paths are added together to obtain the sum of path risks; the node risk sum and path risk are weighted and summed to calculate the abnormal diffusion risk coefficient; Conduct a hierarchical assessment of the overall network risk level based on the abnormal diffusion risk coefficient and generate a network risk report; The network risk report includes: risk level defined according to the abnormal diffusion risk coefficient; key information of the abnormal diffusion path, abnormal diffusion path length and propagation probability.

9. The vehicle data wireless interaction system according to claim 8, characterized in that: The initial risk index is obtained as follows: Assume there are Q risk factors, use p to represent the order of the risk factors, and record the value of the pth risk factor as f p ; The initial risk index Cf is calculated by the following formula: The initial risk index is calculated by the following formula: ； in, represents the weight of the pth risk factor, which is set based on experience; Assume that the starting point of each abnormal diffusion path is node i and the end point is node j; the channel weight is obtained as follows: ； Among them, w ij Represents a slave node arrive The channel risk weight, F ij Representation Node arrive Data transmission frequency, ranging from 0 to 1, the larger the value, the more frequent the data interaction; S ij Represents a slave node arrive The average security protection level of the system is in the range of [0, 1]. The larger the value, the higher the security protection capability.

10. The vehicle data wireless interaction system according to claim 6, characterized in that: Also includes: The disposal effect adaptive optimization module tracks the effects of the linkage warning and protection actions triggered by the diffusion risk assessment module, and continuously tracks the operating status and alarm indicators of the initial abnormal node; if the abnormality is alleviated or gradually disappears, the abnormality and disposal process will be recorded in the case library to improve the risk model and strategy threshold; if the disposal effect is not up to standard or new risks are derived, the latest initial abnormal node will be re-included in the abnormal diagnosis module, so as to continuously iterate and optimize the decision tree algorithm through the adaptive correction mechanism to ensure the reliability and security of the vehicle data wireless interaction process.

Images