Vehicle-road cloud integrated multi-network integration system data classification and grading method

Abstract

The invention provides a vehicle-road cloud integrated multi-network integration system data classification and grading method, which realizes automatic data screening and marking through construction of a multi-scene data identification rule base and business process feature analysis, and solves the problem of standardized identification caused by lack of a unified classification framework of multi-source data. Semantic relation systematic modeling is achieved by means of a multi-layer architecture model and multi-layer model construction, and the problems of insufficient vehicle and road cloud cross-domain entity semantic abstraction and model fragmentation are solved; according to the method, quantitative evaluation of importance and sensitivity is achieved in combination with regulation requirements and modeled data, the problems that data classification and grading standards are missing and a safety evaluation system is imperfect are solved, a closed-loop process of data recognition, semantic modeling, model mapping and grading evaluation is formed, and the problems that in the prior art, a static rule is relied on, and safety evaluation is poor are solved. And changes of data types, interaction types and security requirements in a multi-network fusion scene cannot be dynamically adapted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle-road-cloud data classification and grading, and particularly relates to a vehicle-road-cloud integrated multi-network fusion system data classification and grading method. BACKGROUND

[0002] With the in-depth development of vehicle-road-cloud integration technology, the dynamic security management needs of multi-network fusion data in typical scenarios such as identity authentication and vehicle-road interaction are increasingly prominent.

[0003] In the prior art, a data classification and grading system is constructed by relying on static rules, which is difficult to adapt to the real-time changes of data types, interaction paths and security needs in the multi-network fusion scenario.

[0004] Among them, in the identity authentication scenario, the static rules cannot update the identification rules of vehicle identification data with new authentication protocols, resulting in confusion in the management of sensitive authentication information and ordinary data; in the vehicle-road interaction scenario, the traditional technology uses a fixed semantic analysis template to process unstructured data such as radar point cloud, and when new types of roadside sensors are added, entity features cannot be dynamically extracted, resulting in lagging of automatic driving decision data grading; in the vehicle-pile interaction scenario, the static grading model does not include real-time interaction features of charging data, and when the charging protocol version is iterated, the billing data privacy protection strategy cannot be updated synchronously; in the vehicle-cloud interaction scenario, the grading standard of cloud service data relies on artificial preset thresholds, and when the precision of high-precision map slices is upgraded or new traffic event data is accessed, the matching efficiency of security strategies across domains is low.

[0005] In addition, in key business scenarios such as automatic driving, the static risk assessment mechanism lacks real-time analysis capability for the correlation of multi-source data, and it is difficult to dynamically calibrate the importance level of data according to the business process, resulting in disconnection between data security protection and business needs. SUMMARY

[0006] The present application provides a vehicle-road-cloud integrated multi-network fusion system data classification and grading method to solve the problem that the prior art relies on static rules and cannot dynamically adapt to changes in data types, interaction types and security needs in the multi-network fusion scenario.

[0007] In one aspect, the present application provides a vehicle-road-cloud integrated multi-network fusion system data classification and grading method, comprising: Obtaining multi-source data of a vehicle-road-cloud interaction scenario, and extracting data interaction features of the multi-source data by analyzing business process logic; Based on the data interaction features, a multi-scenario data recognition rule library is constructed, the multi-source data is filtered and labeled, and standardized recognition data is outputted; Input the standardized identification data into a multi-layer architecture model, and output a named entity recognition result through word vector training, bidirectional encoding representation converter semantic extraction, bidirectional long short-term memory network sequence modeling, and conditional random field entity boundary optimization. Associate the named entity recognition result with scene semantics, construct a vehicle-road cloud multi-network fusion scene corpus, and form structured semantic data containing entity types and semantic relationships. Input the structured semantic data into a multi-level model, and output a modeled data set; the multi-level model includes a concept model formed by abstracting the business logic of vehicle-road cloud cross-domain entity objects, a logic model formed by mapping business rules, and a physical model formed by combining data storage and interaction requirements. Evaluate the importance, sensitivity, and leakage impact of the data in combination with the modeled data set and regulatory requirements, and develop multi-network fusion data classification and grading standards.

[0008] Optionally, the multi-source data of the vehicle-road cloud interaction scene is obtained by analyzing the business process logic to extract data interaction features of the multi-source data, including: Collecting raw data from vehicle-side interfaces, roadside-side interfaces, and cloud-side interfaces; Analyzing the business process of the vehicle-road cloud interaction scene to generate multi-source data; Extracting interaction features related to time dimension, space dimension, data structure, and transmission protocol from the multi-source data.

[0009] Optionally, based on the data interaction features, a multi-scene data recognition rule library is constructed to filter and label the multi-source data, and standardized identification data is output, including: Based on the interaction features, a multi-scene data recognition rule library containing scene classification rules, data format verification rules, and security level pre-judgment rules is established; Using the multi-scene data recognition rule library to perform legality verification on the raw data, and eliminating invalid data, adding scene labels, format labels, and security level preliminary labels to the raw data that passes the verification; Converting the labeled raw data into a predetermined data format; Structuring the raw data to generate standardized identification data containing data identification, scene attributes, security attributes, and raw data content.

[0010] Optionally, based on the interaction features, a multi-scene data recognition rule library containing scene classification rules and security level pre-judgment rules is established, further including: Formulating data time effectiveness rules through time dimension features in the interaction features; Generating data source verification rules through space dimension features in the interaction features; establishing a data format verification rule through a data structure in the interaction feature; generating a data interaction security rule through a transmission protocol feature in the interaction feature.

[0011] Optionally, the standardized recognition data is input into a multi-layer architecture model, and a named entity recognition result is output through word vector training, bidirectional encoding representation converter semantic extraction, bidirectional long short-term memory network sequence modeling, and conditional random field entity boundary optimization, including: The standardized recognition data is subjected to sub-word segmentation and vector mapping to generate an initial word vector matrix; The initial word vector matrix is input into a pre-trained bidirectional encoding representation converter to extract context-enhanced semantic representation vectors, and a feature vector is output after multi-layer weighted fusion; The feature vector is input into a bidirectional long short-term memory network to capture bidirectional dependency relationships of data sequences, and an intermediate vector containing timing features is generated; The intermediate vector is subjected to global optimal decoding through a conditional random field layer, and a named entity recognition result containing entity types and position indexes is output.

[0012] Optionally, the training process of the multi-layer architecture model includes: The weighted sum of the cross-entropy loss function and the conditional random field potential function is used as the total loss function; The model parameters are iteratively updated through the back propagation algorithm and the stochastic gradient descent optimizer until the validation set loss converges; During the training process, a dynamic learning rate adjustment strategy and Dropout regularization are used to prevent model overfitting.

[0013] Optionally, the named entity recognition result is associated with the scene semantics to construct a vehicle-road cloud multi-network fusion scene corpus to form structured semantic data containing entity types and semantic relationships, including: The entity types in the named entity recognition result are matched with the semantic features of the corresponding scene to generate a scene-entity association matrix; Based on the business process logic, the interaction relationships between entities are extracted to construct a semantic relationship graph; The entity types, scene semantic information, and the semantic relationship graph are subjected to structured processing and stored in the corpus according to the preset data format to form structured semantic data containing entity types, semantic relationships, and scene attributes; the structured semantic data contains data identifiers, entity content, entity types, belonging scenes, associated entities, and interaction action fields.

[0014] Optionally, input the structured semantic data into a multi-level model to output a modeled data set; the multi-level model includes a concept model formed by abstracting the business logic of the vehicle-road cloud cross-domain entity object, a logic model formed by mapping business rules, and a physical model formed by combining data storage and interaction requirements, including: abstracting and classifying the vehicle-road cloud cross-domain entity object in the structured semantic data, defining an entity set and attributes, establishing a logical relationship graph between entities, and forming the concept model; mapping the logical relationship in the concept model into data processing rules and interaction protocols, defining data lifecycle management rules, and generating a logic model; According to the requirements of the logic model, design the data storage structure and interaction interface, establish the index optimization and data sharding strategy, output the physical model containing the storage scheme, interface definition and performance optimization rules; Integrate the output results of the concept model, the logic model and the physical model to form a modeled data set containing entity definition, rule constraint and storage interaction specification.

[0015] Optionally, the combination of the modeled data set and the regulation requirement evaluates the importance, sensitivity and leakage impact of the data, and formulates a multi-network fusion data classification and grading standard, including: Based on the entity attributes, relationship structure and interaction rules of the modeled data set, identify the functional positioning of the data in the vehicle-road cloud business process, and extract the data criticality index; Match the data attributes with the regulations clauses according to the national data security regulations and industry standards, and determine the sensitive types involved in the data; Build a data leakage impact evaluation model to score the risk of personal privacy leakage, the risk of commercial value loss and the risk of national security threat, and output the data leakage impact score; According to the criticality index, the sensitive type and the data leakage impact score, generate a multi-network fusion data classification and grading standard.

[0016] Optionally, it also includes: According to the multi-network fusion data classification and grading standard, divide the original data into public data, sensitive data and important data, and match the differentiated security strategy; According to the data interaction characteristics, the business process logic and the changes of the national data security regulations, automatically update the multi-network fusion data classification and grading standard and the differentiated security strategy; The differentiated security strategy includes: If the original data is public data, open the access mechanism and implement basic encryption protection; If the original data is sensitive data, desensitization processing is performed and fine-grained access control is applied. If the original data is important data, encrypted transmission, blockchain storage, and a cross-network transmission approval mechanism are implemented.

[0017] In another aspect, the present application also provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the vehicle-road-cloud integrated multi-network fusion system data classification and grading method according to any one of the above.

[0018] In another aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the vehicle-road-cloud integrated multi-network fusion system data classification and grading method according to any one of the above.

[0019] In another aspect, the present application also provides a computer program product comprising a computer program, wherein the computer program is executable by a processor to implement the vehicle-road-cloud integrated multi-network fusion system data classification and grading method according to any one of the above.

[0020] The present application provides a vehicle-road-cloud integrated multi-network fusion system data classification and grading method, which realizes automatic data screening and marking by constructing a multi-scene data recognition rule library and analyzing business process characteristics, solves the problem of standardized recognition caused by the lack of a unified classification framework for multi-source data, realizes semantic relationship system modeling by means of a multi-layer architecture model and a multi-level model, solves the problems of insufficient semantic abstraction of cross-domain entities and model fragmentation in vehicle-road-cloud, and realizes quantitative evaluation of importance and sensitivity by combining regulatory requirements and modeled data, solves the problems of missing data classification and grading standards and imperfect security evaluation system, and the method provided by the present application forms a closed-loop process of data recognition, semantic modeling, model mapping, and grading evaluation, and solves the problem that the prior art relies on static rules and cannot dynamically adapt to changes in data types, interaction types, and security requirements in a multi-network fusion scenario. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0022] Figure 1 Fig. 1 is one of the flowcharts of the vehicle-road-cloud integrated multi-network fusion system data classification and grading method provided by the embodiments of the present application; Figure 2Figure 2 is a flowchart of a data classification method of a vehicle-road-cloud integrated multi-network fusion system according to an embodiment of the present application; Figure 3 Figure 3 is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be described below in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0024] Figure 1 Figure 1 is a flowchart of a data classification method of a vehicle-road-cloud integrated multi-network fusion system according to an embodiment of the present application.

[0025] As shown in Figure 2, the data classification method of the vehicle-road-cloud integrated multi-network fusion system according to an embodiment of the present application mainly includes the following steps. Figure 1 101, obtaining multi-source data of a vehicle-road-cloud interaction scene, and extracting data interaction features of the multi-source data by analyzing business process logic.

[0026] The multi-source data is from data of a vehicle end, a road end, and a cloud server. After obtaining the multi-source data, the interaction features between the multi-source data are extracted by analyzing the business process logic. Specifically, the step of obtaining multi-source data of a vehicle-road-cloud interaction scene and extracting data interaction features of the multi-source data by analyzing business process logic includes: collecting original data from a vehicle end interface, a road side end interface, and a cloud end interface.

[0027] analyzing a business process of the vehicle-road-cloud interaction scene to generate multi-source data.

[0028] extracting interaction features of time dimension, space dimension, data structure, and transmission protocol in the multi-source data.

[0029] The original data is collected from a vehicle end interface, a road side end interface, and a cloud end interface. For example, the vehicle end interface can collect basic data, perception data, decision data, running data, and vehicle control data of a vehicle; the road side end interface can collect traffic data, application range data, running state, and map data; and the cloud end interface can collect control data, life service data, network monitoring data, vehicle service data, and user profile data. The original data collectively constitutes a multi-source data basis of the vehicle-road-cloud interaction scene.

[0030] ​In the process of analyzing raw data, it is necessary to deeply understand each link and process of vehicle-road cloud interaction, such as the communication process of vehicle and roadside device, the interaction process of vehicle and cloud, etc. Through the analysis of business processes, raw data can be converted into multi-source data with clear business meaning. For example, in vehicle-road interaction, raw data can obtain road change data, RSU number data, radar data, target identification, etc. In vehicle-cloud interaction, raw data can obtain map message, traffic flow, ETC (Electronic Toll Collection) billing, weather service, etc.

[0031] In addition, through vehicle interaction, data such as vehicle-pole positioning, charging billing, current voltage, and battery status can also be obtained.

[0032] Then, the interaction characteristics of time dimension, space dimension, data structure and transmission protocol in multi-source data are extracted. In the time dimension, the collection time and update time of the data can be extracted; in the space dimension, the geographical location and coverage range of the data can be extracted; in the data structure, the field type and field length of the data can be analyzed; in the transmission protocol, the transmission method and encryption method of the data can be parsed. These interaction characteristics together constitute the basis of the correlation and interaction between multi-source data.

[0033] Through the implementation of the above steps, comprehensive acquisition and in-depth analysis of multi-source data in vehicle-road cloud interaction scenarios can be realized, providing strong support for subsequent data classification, grading and efficient management.

[0034] 102、Based on the data interaction characteristics, a multi-scenario data recognition rule library is constructed to filter and label the multi-source data, and output standardized recognition data.

[0035] Among them, the scene data recognition rule library covers different types of vehicle-road cloud interaction scenarios, such as expressways, urban roads, parking lots, etc., ensuring accurate identification of data in various scenarios. Through the filtering and labeling steps, redundant and invalid data can be effectively removed, improving the quality and usability of the data. The output of standardized recognition data helps to achieve efficient management and optimization of the vehicle-road integrated multi-network fusion system.

[0036] Specifically, based on the data interaction characteristics, a multi-scenario data recognition rule library is constructed to filter and label the multi-source data, and output standardized recognition data, which specifically includes: 201、Based on the interaction characteristics, a multi-scenario data recognition rule library is established, which includes scene classification rules, data format verification rules and security level prediction rules.

[0037] 202. The original data is checked for legality using the multi-scenario data identification rule library, invalid data is removed, and the original data that passes the check is added with a scenario label, a format label, and a preliminary security level marker.

[0038] 203. The marked original data is uniformly converted into a preset data format.

[0039] 204. The original data is structured and processed to generate standardized identification data containing data identification, scenario attributes, security attributes, and original data content.

[0040] When building the multi-scenario data identification rule library, the scenario classification rule is used to distinguish data in different scenarios and ensure accurate classification of data. The data format verification rule is used to verify whether the data format meets expectations, avoiding problems caused by data format errors. The security level pre-judgment rule preliminarily judges the security level of data based on factors such as data source and content, providing a reference for subsequent data processing. By setting the multi-scenario data identification rule library, fine management of multi-source data is achieved.

[0041] When using the multi-scenario data identification rule library to check the legality of the original data, the characteristics of the data are checked to ensure the authenticity and validity of the data. Invalid data that cannot pass the check is removed to avoid interference with subsequent data processing. Adding scenario labels, format labels, and security level preliminary markers to the original data that passes the check helps to quickly identify and classify the original data.

[0042] In addition, the marked original data is uniformly converted into a preset data format to ensure data consistency and readability. Structuring the original data and generating standardized identification data containing data identification, scenario attributes, security attributes, and original data content helps to achieve comprehensive management and efficient use of data, providing support for efficient operation of the vehicle-road-cloud integrated multi-network fusion system.

[0043] For example, vehicle dynamics data such as vehicle speed and acceleration are collected from the vehicle CAN (Controller Area Network) bus interface, BSM (Basic Safety Message) messages are received through the LTE-V2X module of the roadside unit, charging power and SOC (State of Charge) status are obtained from the OCPP (Open Charge Point Protocol) protocol interface of the charging pile, and high-precision maps and traffic flow data are pulled through the cloud RESTful API.

[0044] Taking the vehicle-pile interaction scenario as an example, the state conversion logic of charging request→authentication and certification→charging execution→settlement notification is analyzed, and the data interaction types of each node are extracted, such as the association data of vehicle VIN (Vehicle Identification Number) code and charging pile ID required in the authentication stage, to form the business process state.

[0045] In some embodiments, based on the interaction features, a multi-scene data recognition rule library containing scene classification rules and security level pre-determination rules is established, which also includes: A data timeliness rule is formulated through the time dimension feature in the interaction feature.

[0046] A data source verification rule is generated through the spatial dimension feature in the interaction feature.

[0047] A data format verification rule is established through the data structure in the interaction feature.

[0048] A data interaction security rule is generated through the transmission protocol feature in the interaction feature.

[0049] Among them, by deeply analyzing the interaction features of data, including time dimension, spatial dimension, data structure and transmission protocol, key information that can accurately reflect the characteristics and source of data is extracted. Key information is the basis for building a multi-scene data recognition rule library.

[0050] Then, for the time dimension feature, a data timeliness rule is formulated. The data timeliness rule aims to ensure that the timeliness and update frequency of data meet the expectations, so that the latest and most accurate information can be obtained in the data processing and analysis process.

[0051] For the spatial dimension feature, a data source verification rule is generated. The data source verification rule verifies the reliability of the data source to enhance the credibility of the data. For example, data from authoritative institutions or certified data sources can be given higher trust, while data from unknown sources needs additional verification and audit.

[0052] In terms of data structure, a data format verification rule is established. The data format verification rule is used to verify whether the format of the data meets the expectations, so as to avoid problems caused by data format errors. For example, by defining a unified data format standard, the consistency and readability of data can be ensured, providing convenience for subsequent data processing.

[0053] In addition, for the transmission protocol feature, a data interaction security rule is generated. The interaction security rule focuses on the security of data in the transmission process, and through the use of encryption, signature and other technical means, it prevents data from being stolen or tampered with during transmission.

[0054] 103. input the standardized recognition data into a multi-layer architecture model, and output the named entity recognition result through word vector training, bidirectional encoding representation converter semantic extraction, bidirectional long short-term memory network sequence modeling, and conditional random field entity boundary optimization.

[0055] The named entity recognition result can accurately label the key information in the text, such as location, name, organization name, etc., providing a basis for subsequent data processing and analysis. After obtaining the named entity recognition result, further classification and grading of the entity are performed according to the preset data classification and grading rules. The classification process aims to classify the entity into its corresponding data category, such as personal information, traffic information, environmental information, etc.; and the grading process assigns different security levels to different categories of data according to the sensitivity and importance of the entity.

[0056] Specifically, the standardized recognition data is input into a multi-layer architecture model, and the named entity recognition result is output through word vector training, bidirectional encoding representation converter semantic extraction, bidirectional long short-term memory network sequence modeling, and conditional random field entity boundary optimization. The specific steps are as follows: 301. perform sub-word segmentation and vector mapping on the standardized recognition data to generate an initial word vector matrix.

[0057] 302. input the initial word vector matrix into a pre-trained bidirectional encoding representation converter to extract context-enhanced semantic feature vectors, and output feature vectors after multi-layer weighted fusion.

[0058] 303. input the feature vectors into a bidirectional long short-term memory network to capture the bidirectional dependency of the data sequence and generate intermediate vectors containing time sequence features.

[0059] 304. perform global optimal decoding on the intermediate vectors through a conditional random field layer to output the named entity recognition result containing entity types and position indexes.

[0060] The standardized recognition data is subjected to sub-word segmentation and vector mapping to generate an initial word vector matrix, which can be subjected to special sub-word segmentation to contain vehicle information, road information, cloud data, etc. Then, the word embedding technology is used to map the sub-words to a high-dimensional vector space to form an initial word vector matrix. For example, taking the sentence "Vehicle A is driving on the highway, and the cloud receives its speed data" as an example, first perform sub-word segmentation to obtain "Vehicle / A / In / Highway / On / Drive / , / Cloud / Receive / Its / Speed / Data". Then, the word embedding technology is used to map the sub-words to vectors to form an initial word vector matrix.

[0061] The initial word vector matrix is input into the pre-trained bidirectional encoding converter to extract context-enhanced semantic representation vectors. The bidirectional encoding converter can deeply understand the context information in the text, especially for complex relationships in the vehicle-road cloud data, such as the relationship between the vehicle and the road, the relationship between the vehicle and the cloud data, etc., to generate more accurate semantic representations. After multi-layer weighted fusion, the feature vector is output. For example, continuing with the sentence "Vehicle A drives on the highway, and the cloud receives its speed data", the initial word vector matrix is input into the pre-trained bidirectional encoding converter. The bidirectional encoding converter can capture the association between "Vehicle A" and "highway", "cloud" and "speed data", and generate more accurate semantic representation vectors. After multi-layer weighted fusion, the feature vector is obtained.

[0062] Then, the feature vector is input into the bidirectional long short-term memory network to capture the bidirectional dependency of the data sequence and generate an intermediate vector containing timing features. The bidirectional long short-term memory network can consider both forward and backward information of the text, and for the timing relationship in the vehicle-road cloud data, such as the time sequence of vehicle travel and the time sequence of cloud data reception, it can generate more comprehensive feature representations. For example, taking the sentence "Vehicle A enters the highway entrance at 9 am, leaves the exit at 10 am, and the cloud records its full-speed data" as an example, the feature vector is input into the bidirectional long short-term memory network. The bidirectional long short-term memory network can capture the time sequence of "Vehicle A" from the entrance to the exit and the timing relationship of the cloud recording speed data, and generate an intermediate vector containing timing features.

[0063] Finally, the intermediate vector is globally optimally decoded by the conditional random field layer to output the named entity recognition result containing entity types and position indexes. The conditional random field layer can consider the constraint relationship between the labels to ensure that the output named entity recognition result meets the syntax and semantic rules of the vehicle-road cloud data. In particular, for the entity types in the vehicle-road cloud data, such as vehicle information, road information, and cloud data, the conditional random field layer can accurately label these key information. For example, continuing with the sentence "Vehicle A enters the highway entrance at 9 am, leaves the exit at 10 am, and the cloud records its full-speed data", the intermediate vector is input into the conditional random field layer for global optimal decoding. The conditional random field layer considers the constraint relationship between the labels such as "Vehicle A (vehicle information, position index: 0-4)", "highway entrance (road information, position index: 9-14)", and "cloud (cloud data, position index: 21-22)", and outputs the named entity recognition result containing entity types and position indexes.

[0064] In some embodiments, the training process of the multi-layer architecture model includes: The weighted sum of the cross-entropy loss function and the conditional random field potential function is used as the total loss function.

[0065] The model parameters are iteratively updated by a backpropagation algorithm and a stochastic gradient descent optimizer until the validation set loss converges.

[0066] A dynamic learning rate adjustment strategy and Dropout regularization are adopted during training to prevent model overfitting.

[0067] Specifically, the cross-entropy loss function is used to measure the difference between the predicted probability distribution of the model and the true label, while the conditional random field potential function is used to consider the constraint relationship between the labels to ensure that the output named entity recognition result is more accurate. During the training process, the gradient is calculated by the backpropagation algorithm, and the model parameters are iteratively updated by the stochastic gradient descent optimizer to gradually reduce the value of the total loss function. At the same time, a dynamic learning rate adjustment strategy is adopted to dynamically adjust the learning rate according to the loss change during the training process to improve the convergence speed and performance of the model. In addition, the Dropout regularization technique is also adopted to randomly discard the output of part of the neurons to reduce the overfitting of the model to the training data and improve the generalization ability of the model.

[0068] 104、The named entity recognition result is associated with the scene semantics to construct a vehicle-road-cloud multi-network fusion scene corpus to form structured semantic data containing entity types and semantic relationships.

[0069] The named entity recognition result is associated with the scene semantics to construct a vehicle-road-cloud multi-network fusion scene corpus to form structured semantic data containing entity types and semantic relationships.

[0070] Specifically, named entity recognition is an important task in natural language processing, which can identify entities with specific meanings in text, such as names, place names, and organization names. In the method provided in the embodiments of the present application, named entity recognition is used to identify key entities in a vehicle-road-cloud integrated multi-network fusion system, such as vehicles, roads, and cloud services.

[0071] Then, the identified named entities are associated with the scene semantics. Scene semantics refers to the specific scene described in the text or data and its related context information. By associating named entities and scene semantics, the role and mutual relationship of entities in a specific scene can be further understood.

[0072] Finally, based on the above association information, a vehicle-road-cloud multi-network fusion scene corpus is constructed. The vehicle-road-cloud multi-network fusion scene corpus not only contains information about entity types, but also contains semantic relationships between entities, thereby forming structured semantic data.

[0073] In some embodiments, the named entity recognition results are associated with the scene semantics, a vehicle-road cloud multi-network fusion scene corpus is constructed, and structured semantic data containing entity types and semantic relationships are formed, including: 401. The entity types in the named entity recognition results are matched with the semantic features of the corresponding scene to generate a scene-entity association matrix.

[0074] 402. Based on the business process logic, the interaction relationships between entities are extracted, and a semantic relationship graph is constructed.

[0075] 403. The entity types, scene semantic information, and semantic relationship graph are structured and stored in the corpus according to a predetermined data format to form structured semantic data containing entity types, semantic relationships, and scene attributes.

[0076] Among them, the structured semantic data contains data identification, entity content, entity type, belonging scene, associated entity and interaction action field.

[0077] Specifically, the entity types in the named entity recognition results are matched with the semantic features of the corresponding scene to generate a scene-entity association matrix, which can be realized by natural language processing technology and algorithm, which can automatically identify the named entities in the text and compare and match them with the preset scene semantic features. For example, when identifying the text "Zhang San drives a vehicle on the highway", it can identify "Zhang San" as a personal name entity and "highway" as a place name entity, and associate the personal name entity and place name entity with scene semantic features such as "drive" and "travel" to form a scene-entity association matrix, providing a basis for subsequent analysis.

[0078] Secondly, based on the business process logic, the interaction relationships between entities are extracted, and a semantic relationship graph is constructed, which needs to combine the actual business process of the vehicle-road cloud integrated multi-network fusion system, analyze the interaction behavior and relationship between entities through algorithm, and construct an intuitive semantic relationship graph. For example, when identifying the text "the vehicle interacts with the cloud service for data when passing through the intersection", it can identify the interaction relationship between the vehicle and the cloud service, and display it in the semantic relationship graph to help users better understand the operation mechanism of the vehicle-road cloud integrated multi-network fusion system.

[0079] Finally, the entity type, scene semantic information and semantic relationship graph are structured and stored in the corpus according to the preset data format, forming structured semantic data containing entity type, semantic relationship and scene attribute. Storing data in the preset data format in the corpus requires appropriate data structure and storage format to ensure the accuracy and readability of the data. For example, when storing structured semantic data, JSON or XML format can be used to store entity type, scene semantic information, associated entities and interactive actions in the form of key-value pairs, facilitating subsequent data analysis and application.

[0080] In addition, the structured semantic data contains data identification, entity content, entity type, belonging scene, associated entity and interactive action fields. Data identification is used to uniquely identify each piece of structured semantic data, ensuring the uniqueness and traceability of the data; entity content records the identified named entity, which is the core part of the data; entity type classifies the entity, which helps users quickly understand the nature of the entity; the belonging scene describes the specific environment in which the entity is located, providing rich contextual information for data analysis; the associated entity and interactive action fields reveal the interaction and dynamic changes between entities, making it possible to explore the operation mechanism of the vehicle-road cloud integrated multi-network fusion system in depth.

[0081] 105. Input the structured semantic data into the multi-level model and output the modeled data set.

[0082] The multi-level model includes a concept model formed by abstracting the business logic of the vehicle-road cloud cross-domain entity object, a logic model formed by mapping business rules, and a physical model formed by combining data storage and interaction needs.

[0083] The multi-level model is a comprehensive data processing framework that covers three levels of concept model, logic model and physical model. The concept model is a result of summarizing and abstracting entities and relationships. The concept model refines various entities such as vehicles, roads, cloud services, and the interactions and relationships between entities to form a clear and concise framework.

[0084] The logic model further refines the business rules based on the concept model. The logic model maps the entities and relationships in the concept model to specific business scenarios, clearly defining the meaning, source and destination of the data. The logic model ensures the accuracy and consistency of the data.

[0085] The physical model is an optimization and adjustment of the logical model in combination with data storage and interaction requirements. The physical model takes into account the actual data storage environment, access speed, and security factors, and specifically implements the data structure and storage method in the logical model. The physical model improves the storage efficiency and access speed of data, so that data can be quickly read and processed.

[0086] Through the processing of structured semantic data by the multi-level model, the structured semantic data is transformed into a modeled data set. The modeled data set not only has a clear structure and explicit meaning, but also meets the subsequent data analysis and application requirements.

[0087] Specifically, the input structured semantic data is input into the multi-level model, and the output modeled data set includes: 501. Abstract and classify the vehicle-road-cloud cross-domain entity objects in the structured semantic data, define entity sets and attributes, establish a logical relationship graph between entities, and form a concept model.

[0088] 502. Map the logical relationships in the concept model to data processing rules and interaction protocols, define data lifecycle management rules, and generate a logical model.

[0089] 503. According to the requirements of the logical model, design data storage structure and interaction interface, establish index optimization and data sharding strategy, output physical model containing storage scheme, interface definition and performance optimization rules.

[0090] 504. Integrate the output results of the concept model, logical model and physical model to form a modeled data set containing entity definition, rule constraint and storage interaction specification.

[0091] Specifically, the structured semantic data is abstracted and classified into vehicle-road-cloud cross-domain entity objects. For example, vehicle entities are classified into the "transportation tool" category, and their attributes such as license plate number, vehicle type, speed, etc. are defined; road entities are classified into the "infrastructure" category, and their attributes such as road name, road segment length, road surface condition, etc. are defined; cloud service entities are classified into the "information technology service" category, and their attributes such as service type, response time, data capacity, etc. are defined. Then, a logical relationship graph between entities is established, such as the driving relationship between vehicles and roads, the data interaction relationship between vehicles and cloud services, etc., to form a concept model.

[0092] On the basis of the concept model, the logical relationships in the concept model are mapped to data processing rules and interaction protocols. For example, the collection frequency, transmission format and verification rules of vehicle driving data are defined; the request and response format, error handling mechanism and data update strategy of cloud service data are formulated, etc. At the same time, data lifecycle management rules such as data storage period, backup strategy and deletion conditions are defined, and a logical model is generated.

[0093] Based on the requirements of the logical model, the data storage structure and interaction interface are designed. For example, a time series database storage structure is designed for vehicle travel data to facilitate rapid chronological retrieval and analysis; a spatial database storage structure is designed for road status data to facilitate geographic query and display. Furthermore, index optimization strategies are established, such as indexing common query conditions to improve retrieval efficiency; and data sharding strategies are developed, such as sharding based on data generation time or geographic location to increase parallelism and scalability in data processing. Ultimately, a physical model is output, including storage solutions, interface definitions, and performance optimization rules.

[0094] Integrate the outputs of the conceptual model, logical model, and physical model to form a modeled dataset containing entity definitions, rule constraints, and storage interaction specifications. For example, the definitions and attributes of entities such as vehicles, roads, and cloud services can be integrated into a unified data dictionary; data processing rules, interaction protocols, and lifecycle management rules can be integrated into the data governance framework; and data storage structures, interaction interfaces, and performance optimization rules can be integrated into the data storage and access layer.

[0095] 106. Combine modeled data sets and regulatory requirements to assess data importance, sensitivity, and the impact of leakage, and develop classification and grading standards for multi-network integrated data.

[0096] Modeled datasets provide detailed descriptions of data entities, attributes, rules, and storage interaction specifications. Combining these with regulatory requirements allows for a more comprehensive data classification process, assessing data importance, sensitivity, and the impact of a breach. Regulations include data protection laws, industry standards, and internal enterprise data management systems. These regulations define specific requirements for data processing, storage, transmission, and access, providing clear guidance and constraints for data classification and grading.

[0097] Combining modeled datasets with regulatory assessments can lead to the development of a multi-network convergence data classification and grading standard. This standard categorizes data of varying importance into different levels and establishes corresponding protection measures and management requirements for each level. This helps ensure secure data storage and compliant use, while also improving the efficiency and accuracy of data management.

[0098] Specifically, we will assess the importance, sensitivity, and impact of data leakage by combining modeled data sets with regulatory requirements, and develop multi-network converged data classification and grading standards, including: 601. Based on the entity attributes, relationship structure and interaction rules of the modeled data set, identify the functional positioning of the data in the vehicle-road-cloud business process and extract data criticality indicators.

[0099] Among them, starting from the modeling data set, the entity attributes, relationship structure and interaction rules in the modeling data set are analyzed. By studying the entity attributes, relationship structure and interaction rules, the function and position of the data in the vehicle-road cloud business process are clarified. For example, if a certain data directly affects the automatic driving decision or plays a key role in vehicle-road cooperation scheduling, the data occupies an important functional position in the business process, and accordingly the corresponding data criticality index is extracted to measure its indispensability and importance to business operation.

[0100] According to the national data security regulations and industry standards, the data attributes are matched with the regulations to determine the sensitive types involved by the data.

[0101] Among them, the data attributes are matched one by one with the regulations. For example, if the data contains personal biological characteristics, track trajectory, etc., it is known from the regulations that it belongs to personal sensitive information; if it involves enterprise core technology, trade secrets, etc., it corresponds to the type of commercial sensitive data, and if it involves national security map information, it corresponds to the type of national security data. Through accurate matching, the sensitive types involved by the data are clearly defined.

[0102] 602, build a data leakage impact evaluation model, and give weighted scores in three dimensions of personal privacy leakage risk, commercial value loss risk and national security threat risk, and output a data leakage impact score.

[0103] Among them, an evaluation model is built around the three dimensions of personal privacy leakage risk, commercial value loss risk and national security threat risk. Each dimension is given a reasonable weight, and the score is calculated according to the actual data. For example, if the data leakage may lead to exposure of a large amount of personal identity information, a high score is given in the dimension of personal privacy leakage risk; if it involves enterprise core business secrets, the commercial value loss risk dimension scores higher. The scores of each dimension are multiplied by the corresponding weight and summed to output the data leakage impact score, which quantifies the harm degree that data leakage may cause.

[0104] 603, generate multi-network fusion data classification and grading standards according to the criticality index, sensitive type and data leakage impact score.

[0105] The multi-network fusion data is classified and graded by integrating the criticality index, sensitive type and data leakage impact score. Data with high criticality, high sensitivity and high leakage impact score is classified into the highest level and given the most stringent protection measures; on the contrary, data with low criticality, low sensitivity and small leakage impact is given a relatively relaxed management strategy, thus forming a complete set of multi-network fusion data classification and grading standards.

[0106] For example, vehicle sensor data contains real-time information such as vehicle speed, brake, steering, etc. In the automatic driving decision-making process, vehicle sensor data directly determines the driving state and safe operation of the vehicle, and is the core basis for the automatic driving system to make decisions such as acceleration, deceleration, and avoidance. In the vehicle-road cloud business process, the function positioning is more critical, and the data key degree index is high. According to the national data security regulations, vehicle sensor data does not involve personal biological characteristics, business secrets and other sensitive content, so it is determined as a non-sensitive data type.

[0107] Vehicle sensor data has a low score because it does not involve personal privacy information. Vehicle sensor data has a medium score because it has little impact on the business value of the enterprise after being disclosed. Vehicle sensor data generally does not pose a threat to national security, so it has a low score. After weighting, the data leakage impact score is low. Considering the high score of the data key degree index, the non-sensitive type, and the low data leakage impact score, vehicle sensor data is classified as medium level, and appropriate data protection measures such as regular access control and data backup are taken.

[0108] For another example, vehicle networking user registration information is used to identify user identity and associate user services. In the vehicle-road cloud business process, it is the basis for providing personalized services and management for users, but it does not directly affect the operation of core businesses. The data key degree index is medium. User registration information contains personal information such as name, ID number, and contact information, which is clearly a type of personal sensitive information according to regulations. User registration information leakage will seriously threaten user privacy security, scoring high; user registration information has little impact on the business value of the enterprise, scoring medium; user registration information usually does not threaten national security, scoring low. After weighting, the data leakage impact score is high. Combined with the medium data key degree index, the personal sensitive type, and the high data leakage impact score, vehicle networking user registration information is classified as high level, and strict data encryption, access permission strict control and other protection measures are implemented.

[0109] For another example, the road traffic control core algorithm data is a key to realize efficient traffic scheduling and optimize road resource allocation, directly affects the road traffic control ability of the whole vehicle-road cloud integrated multi-network fusion system, and is extremely important in the function positioning of the business process, and the data criticality index is high. The road traffic control core algorithm data involves the key strategy of enterprise core technology and traffic management, and belongs to the business sensitive data type. The road traffic control core algorithm data does not involve personal privacy, and the score is low; the road traffic control core algorithm data will damage the core competitiveness of the enterprise once leaked, and the score is high; the road traffic control core algorithm data may affect the traffic order and even national security if maliciously used, and the score is higher. After weighting, the data leakage impact score is high. Since the data criticality index is high, the business sensitive type, and the data leakage impact score is high, the road traffic control core algorithm data is divided into the highest level, and the most strict data protection is implemented, including multiple encryption, isolated storage, special person management and other measures.

[0110] In some embodiments, as shown in FIG. 1 1, Figure 2 The vehicle-road cloud integrated multi-network fusion system data classification and grading method provided by the present application further comprises: 107. According to the multi-network fusion data classification and grading standard, the original data is divided into public data, sensitive data and important data, and the differentiated security strategy is matched.

[0111] 108. According to the data interaction characteristics, business process logic and changes in national data security regulations, automatically update the multi-network fusion data classification and grading standard and the differentiated security strategy.

[0112] The differentiated security strategy comprises: If the original data is public data, an open access mechanism is adopted, and basic encryption protection is implemented.

[0113] If the original data is sensitive data, desensitization processing is performed and fine-grained access control is applied.

[0114] If the original data is important data, encryption transmission, blockchain storage and cross-network transmission approval mechanism are forced to be implemented.

[0115] According to the multi-network fusion data classification and grading standard, the original data is divided into public data, sensitive data and important data, and the differentiated security strategy is matched.

[0116] Specifically, the public data does not involve sensitive information and key business elements, and the security requirement is relatively low. For public data, an open access mechanism is adopted, allowing qualified subjects to freely access data, while implementing basic encryption protection to prevent data from being illegally stolen or tampered with during transmission and storage, and ensuring the basic security of data in open use.

[0117] Sensitive data includes data containing sensitive information such as personal privacy and business secrets. In order to reduce the risk brought by data leakage, sensitive data is desensitized to remove or conceal sensitive information, such as shielding part of the characters of personal identity card number and bank card number. At the same time, fine-grained access control is applied to accurately control the access range and operation type of sensitive data according to the identity, role, operation permission and other factors of the user, and strictly limit the use scenarios of sensitive data.

[0118] Important data has a key influence on business operation, national security or core interests of enterprises. For important data, encryption transmission is compulsorily implemented to ensure that the data cannot be easily cracked even if it is intercepted during transmission in the network; the block chain storage technology is adopted to utilize the tamper-proof feature of the block chain to guarantee the integrity and authenticity of the data, facilitate data tracing and responsibility identification; a cross-network transmission approval mechanism is established, and any cross-network data transmission behavior needs to go through a strict approval process to ensure the security and compliance of data transmission.

[0119] The data classification and grading method of the vehicle-road-cloud integrated multi-network fusion system provided by the application also considers the dynamic changes of data interaction features, business process logic and national data security regulations, has automatic updating capability, and continuously monitors data interaction features such as data transmission frequency and interaction object changes; tracks the adjustment of business process logic such as the development of new business and the optimization of original business processes; real-time attention to the update of national data security regulations, timely acquisition of the latest regulatory requirements and standards. Once the data interaction features, business process logic or national data security regulations change, the update mechanism is automatically triggered. The change factors are analyzed by algorithm and model, and the influence degree of the change factors on the data classification and grading standard and the security policy is evaluated.

[0120] According to the analysis result, the multi-network fusion data classification and grading standard is revised, and the data categories or grading levels are re-divided. At the same time, the differential security policy is updated synchronously to ensure that the security policy matches the new classification and grading standard, so that the data security management always meets the actual demand and regulatory requirements.

[0121] Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the application.

[0122] As Figure 3As shown, the electronic device can include a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 complete mutual communication through the communications bus 340. The processor 310 can invoke a logical instruction in the memory 330 to execute the vehicle-road-cloud integrated multi-network fusion system data classification and grading method.

[0123] In addition, the logical instruction in the memory 330 described above can be realized in the form of a software function unit and sold or used as an independent product, and can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0124] On the other hand, the present application also provides a computer program product, which includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the vehicle-road-cloud integrated multi-network fusion system data classification and grading method provided by the above-mentioned methods.

[0125] In yet another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the vehicle-road-cloud integrated multi-network fusion system data classification and grading method provided by the above-mentioned methods.

[0126] The device embodiments described above are only schematic, wherein the units shown as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement without creative labor.

[0127] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0128] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data classification and grading method for a vehicle-road-cloud integrated multi-network fusion system, characterized in that: include: Acquire multi-source data of vehicle-road-cloud interaction scenarios, and extract data interaction features of the multi-source data by analyzing business process logic; Based on the data interaction characteristics, a multi-scenario data recognition rule library is constructed to filter and mark the multi-source data and output standardized recognition data; Input the standardized recognition data into the multi-layer architecture model, and output the named entity recognition results through word vector training, bidirectional encoding representation converter semantic extraction, bidirectional long short-term memory network sequence modeling and conditional random field entity boundary optimization; Associating the named entity recognition results with scene semantics to construct a vehicle-road-cloud multi-network fusion scene corpus to form structured semantic data containing entity types and semantic relationships; Input the structured semantic data into a multi-level model and output a modeled data set; the multi-level model includes a conceptual model formed by abstracting the business logic of cross-domain vehicle-road-cloud entity objects, a logical model formed by mapping business rules, and a physical model formed by combining data storage and interaction requirements; Combine modeled data sets and regulatory requirements to assess data importance, sensitivity and leakage impact, and develop multi-network integrated data classification and grading standards.

2. The data classification and grading method for the vehicle-road-cloud integrated multi-network fusion system according to claim 1 is characterized in that: The step of obtaining multi-source data of a vehicle-road-cloud interaction scenario and extracting data interaction features of the multi-source data by analyzing business process logic includes: Collect raw data from vehicle-side interfaces, roadside interfaces, and cloud interfaces; Analyze the business processes of vehicle-road-cloud interaction scenarios and generate multi-source data; Extract interactive features of the multi-source data regarding time dimension, space dimension, data structure and transmission protocol.

3. The data classification and grading method for the vehicle-road-cloud integrated multi-network fusion system according to claim 2 is characterized in that: The multi-scenario data recognition rule library is constructed based on the data interaction characteristics to filter and mark the multi-source data and output standardized recognition data, including: Based on the interaction features, a multi-scenario data recognition rule library is established, which includes scenario classification rules, data format verification rules, and security level prediction rules; Using the multi-scenario data recognition rule library to perform a validity check on the original data, remove invalid data, and add a scenario label, a format label, and a preliminary security level mark to the original data that passes the check; Converting the marked raw data into a preset data format; The original data is structured to generate standardized identification data including data identification, scene attributes, security attributes and original data content.

4. The data classification and grading method for the vehicle-road-cloud integrated multi-network fusion system according to claim 3 is characterized in that: The method of establishing a multi-scenario data recognition rule base including scenario classification rules and security level pre-determination rules based on the interaction features further includes: Formulate data timeliness rules based on the time dimension features in the interaction features; Generate data source verification rules through the spatial dimension features in the interaction features; Establishing data format verification rules through the data structure in the interactive feature; Data interaction security rules are generated through the transmission protocol features in the interaction features.

5. The data classification and grading method for the vehicle-road-cloud integrated multi-network fusion system according to claim 1 is characterized in that: The standardized recognition data is input into the multi-layer architecture model, and the named entity recognition results are output through word vector training, bidirectional encoding representation converter semantic extraction, bidirectional long short-term memory network sequence modeling and conditional random field entity boundary optimization, including: Perform subword segmentation and vector mapping on the standardized recognition data to generate an initial word vector matrix; Input the initial word vector matrix into a pre-trained bidirectional encoding representation converter to extract a context-enhanced semantic representation vector, and output a feature vector after multi-layer weighted fusion; Inputting the feature vector into a bidirectional long short-term memory network to capture the bidirectional dependency of the data sequence and generate an intermediate vector containing time series features; The intermediate vector is globally optimally decoded through a conditional random field layer, and a named entity recognition result including entity type and position index is output.

6. The data classification and grading method for the vehicle-road-cloud integrated multi-network fusion system according to claim 1 is characterized in that: The training process of the multi-layer architecture model includes: The weighted sum of the cross entropy loss function and the conditional random field potential energy function is used as the total loss function; Iteratively update the model parameters through the back-propagation algorithm and the stochastic gradient descent optimizer until the validation set loss converges; During the training process, a dynamic learning rate adjustment strategy and Dropout regularization are used to prevent the model from overfitting.

7. The data classification and grading method for the vehicle-road-cloud integrated multi-network fusion system according to any one of claims 3 to 5, characterized in that: The named entity recognition results are associated with scene semantics to construct a vehicle-road-cloud multi-network fusion scene corpus to form structured semantic data containing entity types and semantic relationships, including: Matching the entity type in the named entity recognition result with the semantic features of the corresponding scene to generate a scene-entity association matrix; Based on business process logic, extract the interaction relationship between entities and build a semantic relationship graph; The entity type, scene semantic information and the semantic relationship graph are structured and stored in the corpus according to the preset data format to form structured semantic data containing entity type, semantic relationship and scene attributes; the structured semantic data includes data identification, entity content, entity type, scene to which it belongs, related entity and interaction action fields.

8. The data classification and grading method for the vehicle-road-cloud integrated multi-network fusion system according to claim 1 is characterized in that: Input the structured semantic data into a multi-level model and output a modeled data set; the multi-level model includes a conceptual model formed by abstracting the business logic of cross-domain vehicle-road-cloud entity objects, a logical model formed by mapping business rules, and a physical model formed by combining data storage and interaction requirements, including: Abstractly classify the vehicle-road-cloud cross-domain entity objects in the structured semantic data, define entity sets and attributes, establish a logical relationship graph between entities, and form the conceptual model; Mapping the logical relationships in the conceptual model into data processing rules and interaction protocols, defining data lifecycle management rules, and generating a logical model; Design data storage structure and interactive interface according to the requirements of logical model, establish index optimization and data sharding strategy, and output physical model including storage solution, interface definition and performance optimization rules; The output results of the conceptual model, the logical model and the physical model are integrated to form a modeled data set including entity definitions, rule constraints and storage interaction specifications.

9. The data classification and grading method for the vehicle-road-cloud integrated multi-network fusion system according to claim 3 is characterized in that: The aforementioned assessment of data importance, sensitivity, and leakage impact is conducted by combining modeled data sets with regulatory requirements, and developing multi-network converged data classification and grading standards, including: Based on the entity attributes, relationship structure and interaction rules of the modeled data set, identify the functional positioning of the data in the vehicle-road-cloud business process and extract data criticality indicators; Compare data attributes with regulatory provisions against national data security regulations and industry standards to determine the sensitive types of data involved; Construct a data leakage impact assessment model, perform weighted scoring based on the three dimensions of personal privacy leakage risk, commercial value loss risk, and national security threat risk, and output the data leakage impact score; A multi-network fusion data classification and grading standard is generated based on the criticality index, the sensitivity type and the data leakage impact score.

10. The data classification and grading method for the vehicle-road-cloud integrated multi-network fusion system according to claim 9 is characterized in that: Also includes: Classify the original data into public data, sensitive data and important data according to the multi-network integration data classification and grading standard, and match differentiated security policies; Automatically update the multi-network convergence data classification and grading standards and the differentiated security strategy based on the data interaction characteristics, the business process logic, and changes in national data security regulations; The differentiated security strategy includes: If the original data is public data, an open access mechanism is implemented to implement basic encryption protection; If the original data is sensitive data, desensitization is performed and fine-grained access control is applied; If the original data is important data, encrypted transmission and blockchain evidence storage will be enforced, and a cross-network transmission approval mechanism will be established.

Images