A network asset monitoring method, device, equipment and storage medium

By scanning and log analysis of network assets, a knowledge base of asset attributes and data ties are constructed, and a security knowledge graph is generated by embedding algorithms in combination with the graph, the problem of network asset monitoring is solved, visual monitoring and security management of network assets is realized, and the network is enhanced Safety.

CN118740654BActive Publication Date: 2024-11-22TONGLU COUNTY POWER SUPPLY CO OF STATE GRID ZHEJIANG ELECTRIC POWER CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411217145.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-02
Publication Date
2024-11-22
Estimated Expiration
2044-09-02

AI Technical Summary

Technical Problem

The existing technology is difficult to effectively monitor and identify network assets and data flow information in the cyberspace, resulting in network security risks and lack of comprehensive monitoring methods.

Method used

By scanning and log analysis of the target network, an asset attribute knowledge base and data ties map are built, and a graph embedding algorithm is combined to generate a network asset security knowledge map, and visually display it, using threat intelligence information to enhance the security of the map.

Benefits of technology

It realizes accurate identification and positioning of network assets, provides visual monitoring of network assets, enhances the basis of network security management, and improves the ability to identify and respond to cyberspace threats.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118740654B_ABST
    Figure CN118740654B_ABST
Patent Text Reader

Abstract

The present invention discloses a network asset monitoring method, device, equipment and storage medium, which belongs to the field of network technology, including scanning and log analysis of a target network to obtain network asset information of the target network; constructing an asset attribute knowledge base based on the network asset information; obtaining data flow information of network assets, and constructing a data lineage map based on the data flow information; constructing a network asset security knowledge map based on the asset attribute knowledge base and the data lineage map; and using a graph embedding algorithm to visualize the network asset security knowledge map. The embodiments of the present invention can accurately identify and locate various network assets and their data flow information in the network space, and finally realize the visualization of network assets, laying a foundation for maintaining network security.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of network technology, and in particular to a network asset monitoring method, device, equipment and storage medium. Background Art

[0002] With the continuous development and popularization of the Internet, people's lives have become more digital. With the continuous development of network technology, cyber attacks and digital crimes have become more complex and unpredictable. Cybersecurity has become an urgent problem to be solved in today's digital world.

[0003] In cyberspace, there are a large number of network assets related to national economy and people's livelihood, which are often easy to become the target of various network attacks. However, due to the huge number of network assets and the fact that some network assets are relatively hidden, there is currently a lack of effective methods to comprehensively monitor various network assets, and the "invisibility" of network assets has buried huge security risks for network security. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a network asset monitoring method, device, equipment and storage medium, which can accurately identify and locate various network assets and their data flow information in the network space, and ultimately realize the visualization of network assets, thereby laying the foundation for maintaining network security.

[0005] To achieve the above object, an embodiment of the present invention provides a network asset monitoring method, comprising:

[0006] Scan and analyze the target network logs to obtain the target network's network asset information;

[0007] Building an asset attribute knowledge base based on the network asset information;

[0008] Obtaining data flow information of network assets, and constructing a data lineage map based on the data flow information;

[0009] Constructing a network asset security knowledge graph based on the asset attribute knowledge base and the data lineage graph;

[0010] A graph embedding algorithm is used to visualize the network asset security knowledge graph.

[0011] As an improvement of the above solution, the network asset information includes asset attribute data, and then, constructing an asset attribute knowledge base according to the network asset information includes:

[0012] Performing data cleaning on the asset attribute data;

[0013] Using natural language processing technology, semantic analysis and keyword extraction are performed on the asset attribute data after data cleaning to obtain the attributes of the asset; wherein the attributes of the asset include at least one of device type, service type, operating system, open port and hardware configuration;

[0014] According to the attributes of the assets, an asset attribute knowledge base is constructed using knowledge graph technology; wherein the asset attribute knowledge base includes semantic associations between network assets and attributes.

[0015] As an improvement of the above solution, the step of obtaining data flow information of network assets and constructing a data lineage map according to the data flow information includes:

[0016] Constructing a graph model based on predefined entity types and relationship types; wherein the entity types include data processing operations and data storage locations, and the relationship types include data input, data output, and data conversion;

[0017] Use data flow tracking technology to extract data flow information at all stages of the entire life cycle;

[0018] A data lineage graph is constructed based on the flow information and the graph model.

[0019] As an improvement of the above solution, the network asset security knowledge graph is constructed according to the asset attribute knowledge base and the data lineage graph, including:

[0020] Using graph isomorphism technology to identify common entities and associations between the asset attribute knowledge base and the data lineage graph;

[0021] According to the common entity and the association relationship, the asset attribute knowledge base and the data lineage graph are node-aligned and edge-aligned, and semantic links are constructed to obtain a network asset security knowledge graph.

[0022] As an improvement of the above solution, after visually displaying the network asset security knowledge graph, the method further includes:

[0023] Acquire threat intelligence information from a threat intelligence platform; wherein the threat intelligence information includes at least one of vulnerability information, attack method description, and malicious code characteristics;

[0024] Extracting threat intelligence entities from the threat intelligence information using named entity recognition technology;

[0025] Map the threat intelligence entity to the corresponding entity node in the asset security knowledge graph.

[0026] As an improvement of the above solution, mapping the threat intelligence entity to a corresponding entity node in the asset security knowledge graph includes:

[0027] According to the co-occurrence frequency and dependency relationship of each of the threat intelligence entities, the relationship type and relationship strength of each of the threat intelligence entities are obtained, and a relationship set is constructed;

[0028] According to the relationship set and entity set, the TransE algorithm is used to perform embedding representation learning on the entities and relationships to obtain a threat intelligence entity vector;

[0029] Constructing a node feature vector according to the attribute characteristics and structural characteristics of each node in the asset security knowledge graph;

[0030] Calculating the Euclidean distance between the threat intelligence entity vector and the node feature vector;

[0031] When the Euclidean distance is less than a preset mapping threshold, new nodes and edges are added to the asset security knowledge graph according to the threat intelligence entity.

[0032] As an improvement of the above solution, the graph embedding algorithm is the DeepWalk algorithm or the GraphSAGE algorithm.

[0033] To achieve the above object, an embodiment of the present invention further provides a network asset monitoring device, comprising:

[0034] The network asset positioning module is used to scan and analyze the target network logs to obtain the network asset information of the target network;

[0035] An asset attribute knowledge base construction module, used to construct an asset attribute knowledge base based on the network asset information;

[0036] A data lineage map construction module is used to obtain data flow information of network assets and construct a data lineage map based on the data flow information;

[0037] A network asset security knowledge graph construction module, used to construct a network asset security knowledge graph based on the asset attribute knowledge base and the data lineage graph;

[0038] The visualization display module is used to use a graph embedding algorithm to visualize the network asset security knowledge graph.

[0039] To achieve the above objectives, an embodiment of the present invention also provides a network asset monitoring device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the network asset monitoring method described in any of the above embodiments.

[0040] To achieve the above objectives, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the network asset monitoring method as described in any of the above embodiments.

[0041] Compared with the prior art, the network asset monitoring method, device, equipment and storage medium provided by the embodiments of the present invention scan and analyze the logs of the target network to obtain the network asset information of the target network; construct an asset attribute knowledge base based on the network asset information; obtain the data flow information of the network assets, and construct a data lineage map based on the data flow information; construct a network asset security knowledge map based on the asset attribute knowledge base and the data lineage map; and use a graph embedding algorithm to visualize the network asset security knowledge map. The embodiments of the present invention can accurately identify and locate various network assets and their data flow information in the cyberspace, and ultimately realize the visualization of network assets, laying a foundation for maintaining network security. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of a network asset monitoring method provided by an embodiment of the present invention;

[0043] Figure 2 It is a structural schematic diagram of a network asset monitoring device provided by an embodiment of the present invention;

[0044] Figure 3 It is a structural diagram of a network asset monitoring device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] See also Figure 1 , is a flow chart of a network asset monitoring method provided by an embodiment of the present invention, comprising steps S1 to S5:

[0047] S1. Scan and analyze the target network logs to obtain the network asset information of the target network;

[0048] S2. constructing an asset attribute knowledge base based on the network asset information;

[0049] S3, obtaining data flow information of network assets, and constructing a data lineage map based on the data flow information;

[0050] S4. Constructing a network asset security knowledge graph based on the asset attribute knowledge base and the data lineage graph;

[0051] S5. Use a graph embedding algorithm to visualize the network asset security knowledge graph.

[0052] It is worth mentioning that network assets can be understood as various devices used in computer networks, including servers, workstations, routers, switches, printers, etc.

[0053] In step S1, by using network scanning technology and log analysis technology to identify and classify the devices, services and applications in the target network, it is possible to obtain basic information about the network assets in the target network, including device types, operating systems and open ports. Exemplarily, the network scanning tool Nmap (Network Mapper) can be used to scan the target network. Specifically, when using the network scanning tool Nmap to scan the target network, it is also necessary to set parameters such as scanning frequency, scanning port and scanning depth. Exemplarily, the scanning frequency can be set to once per minute, the scanning depth to 3, and the scanner port range to 1-65535. Finally, network asset information such as device type, operating system and open port is extracted from the Nmap scanning results. For example, more complex scanning techniques such as SYN scanning (half-open scanning), UDP (User Datagram Protocol) scanning, and SCTP (Stream Control Transmission Protocol) scanning can also be used to detect open ports and services; then specific data packet response patterns and behaviors are used to analyze and confirm the operating system type and version of the device; finally, decision tree algorithms and neural network algorithms are used to further process the scanned and parsed network asset information to obtain the final network asset information. Furthermore, the log analysis tool Splunk can be used to deeply analyze network traffic. The log analysis time can be set to the past week. By performing log analysis on the target network, service and application information in the target network can be obtained.

[0054] In step S2, an asset attribute knowledge base is established based on the network asset information identified and located in step S1; further, in step S3, data flow information of network assets is obtained and a data lineage map is constructed; in step S4, a network asset security knowledge map is constructed based on the asset attribute knowledge base and the data lineage map. The embodiment of the present invention not only establishes an asset attribute knowledge base based on network asset information, but also tracks the data flow information of network assets and constructs a data lineage map, so that network asset security can be monitored from the source and a more global network asset security knowledge map can be constructed.

[0055] Furthermore, in step S5, the network asset security knowledge graph is visualized so that security managers can more intuitively understand the distribution and security status of network assets. Furthermore, more features that can characterize the characteristics of network assets can be extracted from the original network asset information through intelligent management tools, such as the asset management system CMDB (Configuration Management Database), such as the statistical features of port opening (total number, common port opening frequency, etc.), and visualized using the visualization tool D3.js.

[0056] Compared with the prior art, the network asset monitoring method provided by the embodiment of the present invention can build an asset attribute knowledge base based on network asset information, build a data lineage map based on data flow information, and integrate the asset attribute knowledge base and the data lineage map into an asset security knowledge map for visual display, thereby realizing the global display of network asset information and laying the foundation for network security.

[0057] As an optional implementation manner, the network asset information includes asset attribute data, and then, constructing an asset attribute knowledge base according to the network asset information includes:

[0058] Performing data cleaning on the asset attribute data;

[0059] Using natural language processing technology, semantic analysis and keyword extraction are performed on the asset attribute data after data cleaning to obtain the attributes of the asset; wherein the attributes of the asset include at least one of device type, service type, operating system, open port and hardware configuration;

[0060] According to the attributes of the assets, an asset attribute knowledge base is constructed using knowledge graph technology; wherein the asset attribute knowledge base includes semantic associations between network assets and attributes.

[0061] Exemplarily, data cleaning may include removing fields with more than 30% missing values, and filling the remaining missing values ​​using a KNN (k-Nearest Neighbor) algorithm.

[0062] For example, the Neo4j graph database can be used to build an asset attribute knowledge base, and the asset attribute data can be imported into Neo4j to form asset attribute nodes; through the Cypher query language, based on the attribute information of the asset attribute nodes, the semantic association relationship between assets can be mined and the association relationship can be created in Neo4j. If the asset attribute data has a hierarchical structure, an asset classification tree is constructed in Neo4j, and asset nodes of different levels are connected through parent-child relationships to realize asset classification retrieval.

[0063] As an optional implementation manner, the acquiring of data flow information of network assets and constructing a data lineage map according to the data flow information includes:

[0064] Constructing a graph model based on predefined entity types and relationship types; wherein the entity types include data processing operations and data storage locations, and the relationship types include data input, data output, and data conversion;

[0065] Use data flow tracking technology to extract data flow information at all stages of the entire life cycle;

[0066] A data lineage graph is constructed based on the flow information and the graph model.

[0067] For example, during the data flow process, the distributed link tracking system Zipkin can be used to generate a globally unique ID (IdentityDocument, ID card identification number) for each data processing job, and the ID is attached to the data during data transmission to form a data traceability link.

[0068] Furthermore, you can also develop a graph application layer based on the SpringBoot framework, provide flexible query functions based on Cypher, and use D3.js to visualize blood relationships, support users to interactively explore data traceability paths and data impact ranges, etc., to help data governance and data value mining.

[0069] As an optional implementation manner, the constructing of a network asset security knowledge graph based on the asset attribute knowledge base and the data lineage graph includes:

[0070] Using graph isomorphism technology to identify common entities and associations between the asset attribute knowledge base and the data lineage graph;

[0071] According to the common entity and the association relationship, the asset attribute knowledge base and the data lineage graph are node-aligned and edge-aligned, and semantic links are constructed to obtain a network asset security knowledge graph.

[0072] Exemplarily, by defining cross-domain semantic mapping rules such as asset type matching and asset name similarity, common entities and association relationships in the asset attribute knowledge base and the data lineage graph are identified, and node alignment and edge alignment are achieved. For example, the "Server A" node in the asset attribute knowledge base is aligned with the "Server A" node in the data lineage graph, and the "Server A contains database B" relationship in the two knowledge bases and graphs is aligned.

[0073] As an optional implementation manner, after visually displaying the network asset security knowledge graph, the method further includes:

[0074] Acquire threat intelligence information from a threat intelligence platform; wherein the threat intelligence information includes at least one of vulnerability information, attack method description, and malicious code characteristics;

[0075] Extracting threat intelligence entities from the threat intelligence information using named entity recognition technology;

[0076] Map the threat intelligence entity to the corresponding entity node in the asset security knowledge graph.

[0077] For example, a crawler program can be written using the Scrapy framework of the Python programming language, and the target website to be crawled can be set to mainstream threat intelligence platforms such as CNNVD (China National Vulnerability Database of Information) and CNVD (China National Vulnerability Database), and the crawling time range can be set to the most recent week. Fields such as vulnerability name, CVE (Common Vulnerabilities & Exposures) number, threat level, attack method, and malicious code characteristics can be extracted through XPath parsing.

[0078] As an optional implementation manner, mapping the threat intelligence entity to a corresponding entity node in the asset security knowledge graph includes:

[0079] According to the co-occurrence frequency and dependency relationship of each of the threat intelligence entities, the relationship type and relationship strength of each of the threat intelligence entities are obtained, and a relationship set is constructed;

[0080] According to the relationship set and entity set, the TransE algorithm is used to perform embedding representation learning on the entities and relationships to obtain a threat intelligence entity vector;

[0081] Constructing a node feature vector according to the attribute characteristics and structural characteristics of each node in the asset security knowledge graph;

[0082] Calculating the Euclidean distance between the threat intelligence entity vector and the node feature vector;

[0083] When the Euclidean distance is less than a preset mapping threshold, new nodes and edges are added to the asset security knowledge graph according to the threat intelligence entity.

[0084] Exemplarily, entity sets and relationship sets are constructed based on threat intelligence information, for example, entities such as malware, attackers and victims, and the associations between them are extracted from threat intelligence information, such as "malware A infected victim B", "attacker C used malware A", etc. By analyzing the co-occurrence frequency and dependency relationship between entities, the relationship strength between entities can be calculated. The TransE (Translating Embedding, knowledge graph embedding) algorithm is used to embed representation learning of entities and relationships, and they are mapped into a 100-dimensional vector space, so that semantically similar entities and relationships are closer in the vector space. For each node in the asset security knowledge graph, its attribute features, such as node type and node name, and structural features, such as node degree and clustering coefficient, are extracted to construct a 200-dimensional node feature vector. The Euclidean distance between the threat intelligence entity vector and the node feature vector is calculated, and the mapping threshold is set to 8. If the distance is less than the threshold, it is considered that the two nodes can establish a mapping relationship, and the mapped threat intelligence entity is integrated into the asset security knowledge graph, new nodes and edges are added, and the structure and attribute information of the asset security knowledge graph is updated.

[0085] Exemplarily, the open source vulnerability scanning tool Nessus may be used to periodically scan network assets for vulnerabilities. Specifically, the scanning frequency may be set to once a day, the scanning depth may be set to 5, and the scanner port range may be set to 1-65535.

[0086] Furthermore, CVSS (Common Vulnerability Scoring System) can be used to conduct risk assessment on the scanned vulnerabilities to determine the severity and impact of the risk. Furthermore, corresponding defense strategies can be formulated based on the risk assessment results, such as using firewalls and intrusion detection systems, to improve the security of cyberspace. Furthermore, defense strategies can also be implemented by writing scripts using the Python programming language.

[0087] As an optional implementation manner, the graph embedding algorithm is a DeepWalk algorithm or a GraphSAGE algorithm.

[0088] Compared with the prior art, the network asset monitoring method provided by the embodiment of the present invention scans and analyzes the logs of the target network to obtain the network asset information of the target network; constructs an asset attribute knowledge base based on the network asset information; obtains the data flow information of the network assets, and constructs a data lineage graph based on the data flow information; constructs a network asset security knowledge graph based on the asset attribute knowledge base and the data lineage graph; and uses a graph embedding algorithm to visualize the network asset security knowledge graph. The embodiment of the present invention can accurately identify and locate various network assets and their data flow information in the cyberspace, and ultimately realize the visualization of network assets, laying a foundation for maintaining network security.

[0089] See also Figure 2 As shown, the embodiment of the present invention further provides a network asset monitoring device 10, comprising:

[0090] The network asset positioning module 11 is used to scan and analyze the logs of the target network to obtain the network asset information of the target network;

[0091] An asset attribute knowledge base construction module 12 is used to construct an asset attribute knowledge base based on the network asset information;

[0092] A data lineage map construction module 13 is used to obtain data flow information of network assets and construct a data lineage map based on the data flow information;

[0093] A network asset security knowledge graph construction module 14, used to construct a network asset security knowledge graph based on the asset attribute knowledge base and the data lineage graph;

[0094] The visualization display module 15 is used to use a graph embedding algorithm to visualize the network asset security knowledge graph.

[0095] It is worth noting that the network asset monitoring device provided in the embodiment of the present invention can implement all the process steps of the network asset monitoring method described in the above embodiment. The functions of each module and unit in the device and the technical effects achieved are respectively the same as the functions and technical effects achieved by the network asset monitoring method described in the above embodiment. The specific implementation method will not be repeated here.

[0096] See also Figure 3The embodiment of the present invention further provides a network asset monitoring device 20, comprising a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned network asset monitoring method embodiment are implemented, for example Figure 1 or, the processor implements the functions of each module in the above-mentioned device embodiments when executing the computer program.

[0097] The network asset monitoring device 20 may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The network asset monitoring device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art may understand that the schematic diagram is only an example of a network asset monitoring device and does not constitute a limitation on the network asset monitoring device. The network asset monitoring device 20 may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the network asset monitoring device 20 may also include input and output devices, network access devices, buses, etc.

[0098] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the network asset monitoring device 20, and uses various interfaces and lines to connect various parts of the entire network asset monitoring device 20.

[0099] The memory 22 can be used to store the computer program and / or module. The processor 21 implements various functions of the network asset monitoring device 20 by running or executing the computer program and / or module stored in the memory 21 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc.; the data storage area can store data created according to the use of the controller, etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0100] Wherein, if the module integrated in the network asset monitoring device 20 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0101] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A network asset monitoring method, characterized in that: include: Scan and analyze the target network logs to obtain the target network's network asset information; Building an asset attribute knowledge base based on the network asset information; Obtaining data flow information of network assets, and constructing a data lineage map based on the data flow information; Constructing a network asset security knowledge graph based on the asset attribute knowledge base and the data lineage graph; Using a graph embedding algorithm, the network asset security knowledge graph is visualized; The obtaining of data flow information of network assets and constructing a data lineage map according to the data flow information includes: Constructing a graph model based on predefined entity types and relationship types; wherein the entity types include data processing operations and data storage locations, and the relationship types include data input, data output, and data conversion; Use data flow tracking technology to extract data flow information at all stages of the entire life cycle; Constructing a data lineage graph according to the flow information and the graph model; After visually displaying the network asset security knowledge graph, the method further includes: Acquire threat intelligence information from a threat intelligence platform; wherein the threat intelligence information includes at least one of vulnerability information, attack method description, and malicious code characteristics; Extracting threat intelligence entities from the threat intelligence information using named entity recognition technology; Mapping the threat intelligence entity to a corresponding entity node in the asset security knowledge graph; Mapping the threat intelligence entity to a corresponding entity node in the asset security knowledge graph includes: According to the co-occurrence frequency and dependency relationship of each of the threat intelligence entities, the relationship type and relationship strength of each of the threat intelligence entities are obtained, and a relationship set is constructed; According to the relationship set and entity set, the TransE algorithm is used to perform embedding representation learning on the entities and relationships to obtain a threat intelligence entity vector; Constructing a node feature vector according to the attribute characteristics and structural characteristics of each node in the asset security knowledge graph; Calculating the Euclidean distance between the threat intelligence entity vector and the node feature vector; When the Euclidean distance is less than a preset mapping threshold, new nodes and edges are added to the asset security knowledge graph according to the threat intelligence entity.

2. The network asset monitoring method according to claim 1, characterized in that: The network asset information includes asset attribute data, and then, constructing an asset attribute knowledge base according to the network asset information includes: Performing data cleaning on the asset attribute data; Using natural language processing technology, semantic analysis and keyword extraction are performed on the asset attribute data after data cleaning to obtain the attributes of the asset; wherein the attributes of the asset include at least one of device type, service type, operating system, open port and hardware configuration; According to the attributes of the assets, an asset attribute knowledge base is constructed using knowledge graph technology; wherein the asset attribute knowledge base includes semantic associations between network assets and attributes.

3. The network asset monitoring method according to claim 1, characterized in that: The step of constructing a network asset security knowledge graph based on the asset attribute knowledge base and the data lineage graph includes: Using graph isomorphism technology to identify common entities and associations between the asset attribute knowledge base and the data lineage graph; According to the common entity and the association relationship, the asset attribute knowledge base and the data lineage graph are node-aligned and edge-aligned, and semantic links are constructed to obtain a network asset security knowledge graph.

4. The network asset monitoring method according to claim 1, characterized in that: The graph embedding algorithm is the DeepWalk algorithm or the GraphSAGE algorithm.

5. A network asset monitoring device, characterized in that: include: The network asset positioning module is used to scan and analyze the target network logs to obtain the network asset information of the target network; An asset attribute knowledge base construction module, used to construct an asset attribute knowledge base based on the network asset information; A data lineage map construction module is used to obtain data flow information of network assets and construct a data lineage map based on the data flow information; A network asset security knowledge graph construction module, used to construct a network asset security knowledge graph based on the asset attribute knowledge base and the data lineage graph; A visualization display module, used to visualize the network asset security knowledge graph using a graph embedding algorithm; The obtaining of data flow information of network assets and constructing a data lineage map according to the data flow information includes: Constructing a graph model based on predefined entity types and relationship types; wherein the entity types include data processing operations and data storage locations, and the relationship types include data input, data output, and data conversion; Use data flow tracking technology to extract data flow information at all stages of the entire life cycle; Constructing a data lineage graph according to the flow information and the graph model; After visually displaying the network asset security knowledge graph, the method further includes: Acquire threat intelligence information from a threat intelligence platform; wherein the threat intelligence information includes at least one of vulnerability information, attack method description, and malicious code characteristics; Extracting threat intelligence entities from the threat intelligence information using named entity recognition technology; Mapping the threat intelligence entity to a corresponding entity node in the asset security knowledge graph; Mapping the threat intelligence entity to a corresponding entity node in the asset security knowledge graph includes: According to the co-occurrence frequency and dependency relationship of each of the threat intelligence entities, the relationship type and relationship strength of each of the threat intelligence entities are obtained, and a relationship set is constructed; According to the relationship set and entity set, the TransE algorithm is used to perform embedding representation learning on the entities and relationships to obtain a threat intelligence entity vector; Constructing a node feature vector according to the attribute characteristics and structural characteristics of each node in the asset security knowledge graph; Calculating the Euclidean distance between the threat intelligence entity vector and the node feature vector; When the Euclidean distance is less than a preset mapping threshold, new nodes and edges are added to the asset security knowledge graph according to the threat intelligence entity.

6. A network asset monitoring device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the network asset monitoring method according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the network asset monitoring method according to any one of claims 1 to 4.