Multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph

Abstract

The present invention discloses a multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph, including an intelligence data collection and cleaning module, an intelligence data security sharing module, an intelligence knowledge graph construction module and an intelligence data fusion display module, and the present invention relates to the field of information data processing technology. In the multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph, in the prior art, intelligence data is usually scattered in multiple isolated systems, which is difficult to share across institutions. The present invention utilizes the decentralized and distributed ledger characteristics of blockchain technology to build a unified intelligence data sharing platform. Through blockchain, intelligence data can be shared safely and reliably between multiple institutions, breaking the data island and improving the accessibility and circulation of data. The present invention ensures the integrity of the data by storing intelligence data on the blockchain and utilizing the tamper-proof nature of the blockchain.

Description

Technical Field

[0001] The present invention relates to the technical field of information data processing, and specifically to a multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph. Background Art

[0002] Existing intelligence data fusion technology faces challenges such as data heterogeneity, data incompleteness, data redundancy and data conflict when processing multi-source heterogeneous data. There are also security risks such as data leakage, data tampering and data destruction in the data fusion process, which leads to data silos, data tampering risks and poor data correlation among security intelligence data of different institutions. Existing solutions use machine learning, distributed computing, knowledge graphs, federated learning and other technologies to achieve multi-source heterogeneous data fusion. However, the use of a single technology cannot effectively solve the problems of data correlation, data security and other issues in the data fusion process. This patent uses blockchain and knowledge graph technology to solve the problems of data security sharing and data correlation extraction in the process of multi-source heterogeneous data fusion. Blockchain has the characteristics of decentralization, immutability and traceability, while knowledge graphs can effectively represent and manage the complex relationships between data. Combining the two can effectively solve the defects in existing technologies. Summary of the invention

[0003] 1. Technical issues to be solved

[0004] In view of the shortcomings of the existing technology, the present invention provides a multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph to solve the problems of data silos, data tampering risks and poor data correlation in the existing technology.

[0005] (II) Technical solution

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph, including an intelligence data collection and cleaning module, an intelligence data security sharing module, an intelligence knowledge graph construction module and an intelligence data fusion display module;

[0007] The intelligence data collection and cleaning module is used to collect intelligence data from multiple heterogeneous data sources and clean irrelevant data;

[0008] The intelligence data security sharing module uses blockchain technology to store and verify the collected intelligence data to ensure the integrity and non-tamperability of the data;

[0009] The intelligence knowledge graph construction module is used to construct a knowledge graph based on intelligence data to represent the relationship between data;

[0010] The intelligence data fusion and display module is used to fuse and analyze multi-source heterogeneous data based on the knowledge graph, and is also used to display the fused intelligence data in a visual manner.

[0011] Preferably, the intelligence data collection and cleaning module includes a plurality of data collection interfaces for connecting different types of data sources, and the data collected by the intelligence data collection and cleaning module are formatted and standardized through data preprocessing.

[0012] Preferably, the data collected by the intelligence data collection and cleaning module is formatted and standardized through data preprocessing, specifically including deleting noise data, correcting errors and unifying data formats.

[0013] Preferably, considering the problem of impure data in the process of collecting security intelligence data, it is necessary to perform data cleaning operations before using blockchain technology to store data. The TextCNN model is used to segment text data, and the embedded representation of each text segmentation word is generated based on the trained word vector model. After integration, the word vector matrix is ​​formed as input data, and the convolutional network is used to capture the important features of document type data, classify the collected security intelligence data, and clean up the data that is not related to the security intelligence data, thereby reducing the required data storage and improving the quality of the data.

[0014] Preferably, the intelligence data security sharing module adopts distributed ledger technology to store the collected data, and each data entry is encrypted and recorded in the blockchain to ensure that the data cannot be tampered with and is traceable. Blockchain technology builds a bridge for transferring, transmitting and exchanging intelligence between different institutions, and optimizes the operation process of the intelligence link. The blockchain module is responsible for managing and maintaining data sharing and access.

[0015] Preferably, the intelligence knowledge graph construction module integrates security intelligence data into a unified knowledge base through entity alignment, relationship extraction and graph fusion. The module performs semantic analysis on the collected data, extracts entities and relationships in the data, and constructs a knowledge graph. The knowledge graph is stored in a graph database and supports complex queries and reasoning operations. The knowledge graph cleans up a large amount of low-density information, processes knowledge in a strong semantic environment, and improves the value and availability of data through knowledge reasoning, visualization, and data mining methods.

[0016] Preferably, the knowledge graph construction method in the intelligence knowledge graph construction module specifically includes the following steps:

[0017] S1. Data extraction: Extract security intelligence data from the blockchain system, segment and annotate the acquired data, and map it to the existing domain ontology model, using rule mapping and semantic analysis technology to extract useful information;

[0018] S2. Entity alignment: In the fusion process, Word2Vec technology is used to determine the similarity between entities, thereby solving the entity alignment problem. Entity alignment is an important part of knowledge graph construction, which involves matching and associating the same entities in different knowledge sources;

[0019] S3. Topological structure of knowledge graph: The system constructs the topological structure of knowledge graph by extracting features from multi-source heterogeneous data and analyzing the relationship between attribute sets. This structure is used to represent and manage the association between different data nodes, which helps to better understand and utilize multi-source heterogeneous data;

[0020] S4. Knowledge storage: The system uses Neo4j graph database to store knowledge graphs to ensure efficient storage and retrieval of data. Data is stored in the form of nodes and edges to form a complex relationship network.

[0021] S5. Knowledge evaluation and verification: In order to ensure the reliability and accuracy of knowledge, the system will evaluate and verify the data in the knowledge graph. The evaluation and verification methods are based on Bayesian models, DS evidence theory or fuzzy set theory. These methods can effectively solve the conflict problems between multi-source heterogeneous data and improve the confidence of knowledge.

[0022] Preferably, the intelligence data fusion and display module associates and fuses multi-source data based on the knowledge graph, uses machine learning algorithms to perform data analysis and pattern recognition, and generates a comprehensive intelligence report. In addition, it provides a user interface to support visual display of data. Users view the fused intelligence data in the form of charts or network diagrams, and display the knowledge graph through a graphical interface to help users intuitively understand the associations between data.

[0023] (III) Beneficial effects

[0024] The present invention provides a multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph. Compared with the prior art, it has the following beneficial effects:

[0025] (1) The multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph. In the prior art, intelligence data is usually scattered in multiple isolated systems, making it difficult to share across institutions. The present invention utilizes the decentralized and distributed ledger characteristics of blockchain technology to build a unified intelligence data sharing platform. Through blockchain, multiple institutions can share intelligence data securely and reliably, breaking down data silos and improving data accessibility and liquidity.

[0026] (2) The multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph. In the traditional intelligence sharing system, data is easily tampered with, which affects the credibility of intelligence. The present invention ensures the integrity of data by storing intelligence data on the blockchain and utilizing the immutability of the blockchain. Each piece of data is encrypted and recorded in the blockchain, so that any tampering of the data will be recorded and tracked, increasing the security of the data.

[0027] (3) The multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph. In the prior art, intelligence data from different sources are often difficult to correlate and analyze due to different formats and standards. The present invention uses an intelligence knowledge graph construction module to perform semantic analysis and entity alignment on the collected multi-source heterogeneous data and integrate them into a unified knowledge base. This method not only improves the relevance of the data, but also supports complex query and reasoning operations through the graph database, so that users can better understand and use the data.

[0028] (4) This multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph utilizes the anonymity and one-way encryption function of blockchain. The present invention is outstanding in protecting the privacy of intelligence data. Through the hybrid storage method of storing public intelligence on the chain and sensitive data off the chain, the security of the data is further enhanced to prevent the leakage of sensitive information. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 Schematic diagram of the structure of the system of the present invention. DETAILED DESCRIPTION

[0030] 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.

[0031] See also Figure 1 , the embodiment of the present invention provides two technical solutions: a multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph, including an intelligence data collection and cleaning module, an intelligence data security sharing module, an intelligence knowledge graph construction module and an intelligence data fusion display module;

[0032] Intelligence data collection and cleaning module, used to collect intelligence data from multiple heterogeneous data sources and clean irrelevant data;

[0033] Intelligence data security sharing module uses blockchain technology to store and verify collected intelligence data to ensure data integrity and non-tamperability;

[0034] Intelligence knowledge graph construction module, used to construct knowledge graphs based on intelligence data to represent the relationship between data;

[0035] The intelligence data fusion display module is used to fuse and analyze multi-source heterogeneous data based on the knowledge graph, and is also used to display the fused intelligence data in a visual way.

[0036] In an embodiment of the present invention, the intelligence data collection and cleaning module includes multiple data collection interfaces for connecting different types of data sources, such as databases, sensors, social media, and networks. The data collected by the intelligence data collection and cleaning module is formatted and standardized through data preprocessing. The data collected by the intelligence data collection and cleaning module is formatted and standardized through data preprocessing, which specifically includes deleting noise data, correcting errors, and unifying data formats. Considering the problem of impurity data in the process of security intelligence data collection, it is necessary to perform data cleaning operations before using blockchain technology to store data. The TextCNN model is used to perform word segmentation on text data, and an embedded representation is generated for each text segmentation word based on a trained word vector model. After integration, a word vector matrix is ​​formed as input data, and a convolutional network is used to capture important features of document type data, classify the collected security intelligence data, and clean up data that is not related to security intelligence data, thereby reducing the required data storage and improving the quality of the data.

[0037] In the embodiment of the present invention, the intelligence data security sharing module adopts distributed ledger technology to store the collected data. Each data entry is encrypted and recorded in the blockchain to ensure that the data cannot be tampered with and is traceable. The blockchain technology builds a bridge for transferring, transmitting and exchanging intelligence between different institutions and optimizes the operation process of the intelligence link. The blockchain module is responsible for managing and maintaining data sharing and access:

[0038] Smart contract design: including intelligence sharing contracts, intelligence response contracts and operation record contracts. These contracts are responsible for managing and recording the upload, sharing and query of intelligence, ensuring the transparency and non-tamperability of the entire intelligence sharing process.

[0039] Privacy protection design: The anonymity and immutability of blockchain are used to protect the privacy of intelligence sharers and users, while sensitive information in the intelligence is protected through a one-way encryption function.

[0040] Node function design: In order to ensure the consistency and efficient use of intelligence data, intelligence metadata extraction nodes, intelligence standardization nodes and intelligence value assessment nodes are designed, which are responsible for extracting metadata of original intelligence, performing standardized conversion of intelligence data, and evaluating the value of intelligence.

[0041] In addition, in order to further ensure data security and privacy, security intelligence data can be stored off-chain to protect sensitive data. This method effectively reduces the storage pressure of the blockchain and improves the security of intelligence storage.

[0042] In the embodiment of the present invention, the intelligence knowledge graph construction module integrates security intelligence data into a unified knowledge base through entity alignment, relationship extraction and graph fusion. The module performs semantic analysis on the collected data, extracts entities and relationships in the data, and constructs a knowledge graph. The knowledge graph is stored in a graph database and supports complex queries and reasoning operations. The knowledge graph cleans up a large amount of low-density information and processes knowledge in a strong semantic environment. The value and availability of data are improved through knowledge reasoning, visualization, and data mining methods. The knowledge graph construction method in the intelligence knowledge graph construction module specifically includes the following steps:

[0043] S1. Data extraction: Extract security intelligence data from the blockchain system, segment and annotate the acquired data, and map it to the existing domain ontology model, using rule mapping and semantic analysis technology to extract useful information;

[0044] S2. Entity alignment: In the fusion process, Word2Vec technology is used to determine the similarity between entities, thereby solving the entity alignment problem. Entity alignment is an important part of knowledge graph construction, which involves matching and associating the same entities in different knowledge sources;

[0045] S3. Topological structure of knowledge graph: The system constructs the topological structure of knowledge graph by extracting features from multi-source heterogeneous data and analyzing the relationship between attribute sets. This structure is used to represent and manage the association between different data nodes, which helps to better understand and utilize multi-source heterogeneous data;

[0046] S4. Knowledge storage: The system uses Neo4j graph database to store knowledge graphs to ensure efficient storage and retrieval of data. Data is stored in the form of nodes and edges to form a complex relationship network.

[0047] S5. Knowledge evaluation and verification: In order to ensure the reliability and accuracy of knowledge, the system will evaluate and verify the data in the knowledge graph. The evaluation and verification methods are based on Bayesian models, DS evidence theory or fuzzy set theory. These methods can effectively solve the conflict problems between multi-source heterogeneous data and improve the confidence of knowledge.

[0048] Example 2: The technical solution of the embodiment of the present invention is different from that of Example 1 in that: the intelligence data fusion display module associates and fuses multi-source data based on the knowledge graph, uses machine learning algorithms to perform data analysis and pattern recognition, and generates a comprehensive intelligence report. In addition, it provides a user interface to support visual display of data. Users can view the fused intelligence data in the form of charts or network diagrams, and display the knowledge graph through a graphical interface to help users intuitively understand the association between data.

[0049] The present invention realizes the efficient integration and reliable management of multi-source heterogeneous intelligence data by combining blockchain and knowledge graph technology, and enhances the relevance and security of data. Blockchain technology builds a bridge for transferring, transmitting and exchanging intelligence between different blocks, optimizes the operation process of the intelligence link, and solves the pain point of intelligence sharing security. The intelligence data through the blockchain strengthens the reliability of its source, and further realizes the integration and top-level application of data through the knowledge graph. The knowledge graph cleans up a large amount of low-density information, processes knowledge in a strong semantic environment, and improves the value and availability of data through knowledge reasoning, visualization, and data mining methods.

[0050] In summary, the present invention improves the efficiency and reliability of intelligence sharing based on blockchain technology: blockchain technology optimizes the operation process of the intelligence link, improves the security and reliability of intelligence sharing, and through the application of blockchain technology, the present invention effectively improves the efficiency of intelligence sharing. The decentralized nature of blockchain and the automated execution capabilities of smart contracts make the uploading, verification and sharing of intelligence data more efficient and reliable, eliminating manual intervention and lag in traditional systems.

[0051] Enhance the value of intelligence data based on knowledge graph: Knowledge graph further enhances the value and availability of data through knowledge reasoning, visualization, data mining and other methods. Through the construction of intelligence knowledge graph, the present invention integrates multi-source heterogeneous data into a unified knowledge base, which not only improves the relevance of data, but also further enhances the value of data through knowledge reasoning, data mining and other methods.

[0052] Intelligence data cleaning and processing: In the data collection and cleaning module, the TextCNN model is used to perform word segmentation and feature extraction on text data, filter out irrelevant data, and improve data quality. This method ensures that the data entering the blockchain system is cleaned high-quality data, reducing the interference of irrelevant information.

[0053] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0054] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0055] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph, characterized by: It includes intelligence data collection and cleaning module, intelligence data security sharing module, intelligence knowledge graph construction module and intelligence data fusion display module; The intelligence data collection and cleaning module is used to collect intelligence data from multiple heterogeneous data sources and clean irrelevant data; The intelligence data security sharing module uses blockchain technology to store and verify the collected intelligence data to ensure the integrity and non-tamperability of the data; The intelligence knowledge graph construction module is used to construct a knowledge graph based on intelligence data to represent the relationship between data; The intelligence data fusion and display module is used to fuse and analyze multi-source heterogeneous data based on the knowledge graph, and is also used to display the fused intelligence data in a visual manner.

2. According to claim 1, the multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph is characterized by: The intelligence data collection and cleaning module includes multiple data collection interfaces for connecting different types of data sources, and the data collected by the intelligence data collection and cleaning module are formatted and standardized through data preprocessing.

3. The multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph according to claim 2 is characterized by: The data collected by the intelligence data collection and cleaning module is formatted and standardized through data preprocessing, specifically including deleting noise data, correcting errors and unifying data formats.

4. The multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph according to claim 2 is characterized by: The TextCNN model is used to perform word segmentation on text data. The embedded representation of each text segmentation word is generated based on the trained word vector model. After integration, the word vector matrix is ​​formed as the input data. The convolutional network is used to capture the important features of document type data, classify the collected security intelligence data, and clean up the data that is not related to the security intelligence data, thereby reducing the required data storage and improving the data quality.

5. The multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph according to claim 1 is characterized by: The intelligence data security sharing module adopts distributed ledger technology to store the collected data. Each data entry is encrypted and recorded in the blockchain to ensure that the data cannot be tampered with and is traceable. Blockchain technology builds a bridge for transferring, transmitting and exchanging intelligence between different institutions, and optimizes the operation process of the intelligence link. The blockchain module is responsible for managing and maintaining data sharing and access.

6. The multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph according to claim 1 is characterized by: The intelligence knowledge graph construction module integrates security intelligence data into a unified knowledge base through entity alignment, relationship extraction and graph fusion. The module performs semantic analysis on the collected data, extracts entities and relationships in the data, and constructs a knowledge graph. The knowledge graph is stored in a graph database and supports complex queries and reasoning operations. The knowledge graph cleans up a large amount of low-density information and processes knowledge in a strong semantic environment. The value and availability of data are improved through knowledge reasoning, visualization, and data mining methods.

7. The multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph according to claim 6 is characterized by: The knowledge graph construction method in the intelligence knowledge graph construction module specifically includes the following steps: S1. Data extraction: Extract security intelligence data from the blockchain system, segment and annotate the acquired data, and map it to the existing domain ontology model, using rule mapping and semantic analysis technology to extract useful information; S2. Entity alignment: In the fusion process, Word2Vec technology is used to determine the similarity between entities, thereby solving the entity alignment problem. Entity alignment is an important part of knowledge graph construction, which involves matching and associating the same entities in different knowledge sources; S3. Topological structure of knowledge graph: The system constructs the topological structure of knowledge graph by extracting features from multi-source heterogeneous data and analyzing the relationship between attribute sets. This structure is used to represent and manage the association between different data nodes, which helps to better understand and utilize multi-source heterogeneous data; S4. Knowledge storage: The system uses Neo4j graph database to store knowledge graphs to ensure efficient storage and retrieval of data. Data is stored in the form of nodes and edges to form a complex relationship network. S5. Knowledge evaluation and verification: In order to ensure the reliability and accuracy of knowledge, the system will evaluate and verify the data in the knowledge graph. The evaluation and verification methods are based on the Bayesian model, DS evidence theory or fuzzy set theory.

8. The multi-source heterogeneous security intelligence data fusion system based on blockchain and knowledge graph according to claim 1 is characterized by: The intelligence data fusion display module associates and fuses multi-source data based on the knowledge graph, uses machine learning algorithms to perform data analysis and pattern recognition, and generates a comprehensive intelligence report. In addition, it provides a user interface and supports the visualization of data. Users can view the fused intelligence data in the form of charts or network diagrams, and display the knowledge graph through a graphical interface to help users intuitively understand the association between data.

Images