CN114741526B - Knowledge graph cloud platform in network space safety field - Google Patents
Knowledge graph cloud platform in network space safety field Download PDFInfo
- Publication number
- CN114741526B CN114741526B CN202210287641.4A CN202210287641A CN114741526B CN 114741526 B CN114741526 B CN 114741526B CN 202210287641 A CN202210287641 A CN 202210287641A CN 114741526 B CN114741526 B CN 114741526B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- network
- field
- data set
- network space
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000605 extraction Methods 0.000 claims abstract description 31
- 230000006870 function Effects 0.000 claims description 24
- 238000002372 labelling Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 11
- 239000013598 vector Substances 0.000 claims description 10
- 238000013526 transfer learning Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 4
- 238000012827 research and development Methods 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 23
- 238000010586 diagram Methods 0.000 description 10
- 238000013523 data management Methods 0.000 description 8
- 238000013461 design Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 231100000279 safety data Toxicity 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/55—Detecting local intrusion or implementing counter-measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a knowledge graph cloud platform in the field of network space security, which relates to the technical field of knowledge graphs in the field of network space security, and is technically characterized in that: the system comprises an OpenStack cloud management system, an original data crawler module, a knowledge extraction module, a knowledge storage graph database and a knowledge graph application management service system; the OpenStack cloud management system adopts three-node deployment, has the same hardware distribution and logic distribution, and is divided into a control node, a computing node and a network node. The knowledge graph cloud platform in the network space security field is convenient for providing unified management and dynamic allocation service of different computing resources, has low cost and high efficiency, can process the capacity of mass resources, can reflect the characteristics of more stereo, wider, multilevel and diversified knowledge in the network space security field, and is beneficial to deeper analysis and prediction of network space security research and development.
Description
Technical Field
The invention relates to the technical field of knowledge graph in the field of network space security, in particular to a knowledge graph cloud platform in the field of network space security.
Background
With the rapid development of network technology and information technology, network space security is becoming a hotspot and focus of social attention. Network environments are becoming increasingly complex, and network users, hardware devices, and logical topologies are interconnected with each other in network space to create a vast amount of data information such as network topology, network assets, and the like. Meanwhile, network security events are increasingly frequent, and massive data information such as network loopholes, attack threats, security alarms and the like are generated at moment by intrusion detection equipment deployed by countries and enterprises. The safety data information is in explosive growth, and faces the dilemma of huge data volume, but the lack of relativity and no knowledge among the data, so that the safety data information is difficult to obtain and effectively utilized by network space safety analysis personnel.
At present, a network space security domain platform in the prior art aims at unified management and dynamic allocation service of different computing resources, and has the advantages of high cost, low efficiency and inconvenience in processing mass resources; therefore, the invention aims to design and provide a knowledge graph cloud platform in the field of network space security so as to solve the problems.
Disclosure of Invention
The invention aims to provide a knowledge graph cloud platform in the field of network space security based on solving the technical problems.
The technical aim of the invention is realized by the following technical scheme: a knowledge graph cloud platform in the field of network space security comprises an OpenStack cloud management system, an original data crawler module, a knowledge extraction module, a knowledge storage graph database and a knowledge graph application management service system;
the OpenStack cloud management system is used for providing a hardware foundation and a system management function for the platform; the OpenStack cloud management system adopts three-node deployment, and the hardware distribution and the logic distribution of the OpenStack cloud management system are the same and are uniformly divided into a control node, a computing node and a network node;
the original data crawler module is written by adopting a Python based on a Scrapy framework, is packaged into a Python file, and is reserved with an interface API for a knowledge graph server to call and run on a network node;
the knowledge extraction module is written by Python based on a Pytorch frame, and is packaged into a py file, and an interface API is reserved for the knowledge graph application service to call and run on a computing node;
the knowledge storage graph database adopts a Neo4j graph database and operates on a computing node;
the knowledge graph application management service system is operated on the control node, is written by adopting a Python based on a Django framework and is used for displaying and responding application functions.
In the scheme of the invention, the OpenStack cloud management system can realize the effect of providing a hardware foundation and a system management function for the cloud platform in the scheme; the knowledge graph server is called by an original data crawler module running on the network node; the knowledge extraction module is convenient for completing entity extraction firstly, and then carrying out relation extraction by combining the original sentence and the identified entity; the knowledge storage diagram database is convenient for inquiring and analyzing complex relations among mass data, and is convenient for storing the knowledge in the field of 'network space safety' in the invention; the knowledge graph application management service system is responsible for the display and response of application functions, and is convenient for rapid platform development and later maintenance. The knowledge graph cloud platform in the network space security field is convenient for providing unified management and dynamic allocation service of different computing resources, has low cost and high efficiency, can process the capacity of massive resources, can reflect the characteristics of more stereo, wider, multilevel and diversified knowledge in the network space security field, and is beneficial to deeper analysis and prediction of network space security research and development.
The invention is further provided with: the knowledge extraction module is a knowledge extraction model based on transfer learning and a deep neural network, and comprises a BERT-based word embedding layer, a BiLSTM-CRF network learning prediction layer and a transfer learning module based on self-labeling data.
The invention is further provided with: the workflow of the knowledge extraction model comprises the following steps:
(1) Cleaning original data of the field of 'network space safety' crawled from the Internet, building a self-labeling platform and labeling the field data to obtain a small-scale field data set, namely a target field data set;
(2) Acquiring a general data set as a source domain data set, wherein the general data set is a labeling data set taking common sense content as a main part; fully training a general data set through the model to obtain a source domain model, wherein the source domain model has the capability of extracting general corpus (entity and relation) characteristics;
(3) Migrating the source domain model obtained by training to a BiLSTM layer of a target domain sequence network, wherein the BiLSTM layer is mainly used for extracting characteristics of input information; adjusting the output dimension of the CRF layer according to the label type of the target domain data set, wherein the layer mainly decodes the feature vector output by the BiLSTM into a globally optimal prediction label; and finally, inputting the target domain data set into the migrated model for full training to obtain the model with knowledge extraction capability for the domain data.
In summary, the invention has the following beneficial effects:
1. the knowledge graph cloud platform in the network space security field is convenient for providing unified management and dynamic allocation service of different computing resources, and has low cost and high efficiency;
2. the knowledge graph cloud platform in the network space security field can process the capacity of mass resources, can reflect the characteristics of more stereo, wider, multilevel and diversified knowledge in the network space security field, and is beneficial to further analysis and prediction of network space security research and development.
Drawings
FIG. 1 is a functional block diagram of an overall implementation of a knowledge graph cloud platform in the field of network space security in an embodiment of the invention;
FIG. 2 is a schematic diagram of a user login interface according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of user management (administrator) in an embodiment of the present invention;
FIG. 4 is a schematic diagram of adding users (administrator side) in an embodiment of the present invention;
FIG. 5 is a schematic diagram of a home interface (introducing platform core functionality) in an embodiment of the invention;
FIG. 6 is a schematic diagram of a platform data overview function in accordance with an embodiment of the present invention;
FIG. 7 is a schematic diagram of an entity query function in an embodiment of the present invention;
FIG. 8 is a schematic diagram of a relationship query function in an embodiment of the present invention;
FIG. 9 is a schematic diagram of a single data update function according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to fig. 1-3.
Examples:
the general implementation function of the knowledge graph cloud platform in the network space security field is shown in fig. 1, and the general implementation function comprises an OpenStack cloud management system, an original data crawler module, a knowledge extraction module TBBC, a knowledge storage graph database, a knowledge graph application management service and the like.
Wherein, each module has the following functions:
(1) The OpenStack cloud management system provides a hardware base and a system management function for the whole platform. The OpenStack of the platform has good use stability, adopts a conventional three-node deployment scheme, has the same hardware distribution and logic distribution, and is divided into control nodes (responsible for cloud platform management and running application management service), computing nodes (responsible for cloud platform performance monitoring, data storage, running functional modules and the like) and network nodes (responsible for intra-platform communication and crawler service).
(2) The original data crawler module is written based on a Scrapy framework by using Python, then is packaged into a Python file, and an interface API is reserved for a knowledge graph server to call and run on a network node;
(3) A knowledge extraction module (TBBC) is written by using a Python based on a Pytorch framework, and then is packaged into a py file, and an interface API is reserved for a knowledge graph application service to call and run on a computing node;
(4) The knowledge graph storage database adopts a Neo4j graph database and operates on the computing nodes. The query algorithm of the graph database is realized based on graph theory, and compared with the traditional relational databases such as Oracle, mySQL and the like, the graph database is better at querying and analyzing complex relations among massive data, so that the graph database is more suitable for storing the 'network space security' domain knowledge. The Neo4j official provides a free community version whose performance supports a maximum of 320 hundred million nodes, 320 hundred million relationships and 640 hundred million attributes, and a maximum of 4 cores of parallel processing capacity sufficient to meet our requirements.
(5) The application management service runs on the control node and is written based on the Django framework by using Python and is responsible for the display and response of application functions. Django is an open-source Web application framework, and an MTV model framework is used, and a plurality of powerful third-party plugins are further contained in the framework, so that the Django has strong expandability. Due to the characteristics of easy maintainability, high expansibility, data drivability and the like of Django, platform development and post maintenance can be more conveniently and rapidly carried out, meanwhile, due to the fact that the Django uses a mainstream B/S architecture, a client does not need to be installed, and user experience is better.
In this embodiment, the implementation algorithm of the knowledge graph cloud platform in the network space security domain of the present invention is as follows:
1. knowledge extraction
By combining the data characteristics of the network space safety field, the invention designs a knowledge extraction model (TBBC) model based on transfer learning and a deep neural network, which is divided into three core functional modules in total: the BERT-based word embedding layer, the BiLSTM-CRF network learning prediction layer and the self-labeling data-based transfer learning module. The entity recognition and relation extraction adopts Pipeline mode (Pipeline), namely, the entity extraction is finished firstly, and then the relation extraction is carried out by combining the original sentence and the recognized entity.
The workflow of the knowledge extraction model (TBBC) model is as follows:
(1) And cleaning the original data of the field of 'network space safety' crawled from the Internet, constructing a self-labeling platform and labeling the field data to obtain a small-scale field data set, namely a target field data set.
(2) A common data set, i.e. a labeling data set based on common sense content, is acquired as a source domain data set. And fully training the universal data set through the model to obtain a source domain model, wherein the source domain model has the capability of extracting the characteristics of the universal corpus (entity and relation).
(3) Migrating the source domain model obtained by training to a BiLSTM layer of a target domain sequence network, wherein the BiLSTM layer is mainly used for extracting characteristics of input information; adjusting the output dimension of the CRF layer according to the label type of the target domain data set, wherein the layer mainly decodes the feature vector output by the BiLSTM into a globally optimal prediction label; and finally, inputting the target domain data set into the migrated model for full training to obtain the model with knowledge extraction capability for the domain data.
Because the TBBC is used for training the extraction model, the time consumption is relatively large, the display card is required to be used for operation, and the server cannot be configured with the display card, in the initial construction of the platform, a workstation with the display card is used for extracting knowledge from all the original texts currently crawled, knowledge data are obtained and then stored in a database such as a computing node, and meanwhile, the trained pkl model file is also stored in the computing node. When knowledge updating is required, the TTBC extraction module is only required to be called, the trained model is loaded to carry out knowledge extraction on the CPU, and the model is not required to be trained again. Since only incremental updates are not large in data size, the computing resources of the computing nodes can be substantially satisfied. After the incremental data are scaled, the corresponding hardware resource platform is used, the plk files in the computing nodes are replaced according to the process training model, and updating and iteration of the extraction capacity can be achieved.
2. Entity disambiguation
In practical application scenes, named entities have the characteristics of diversity and ambiguity, for example, the word "peak" may represent a mountain in different sentences, and also may represent a name of a person, and the entities represented by different meanings are different, and the connected relationships are also different. Therefore, the problem of entity disambiguation is solved, and a knowledge graph with practical application significance can be better constructed.
In the TBBC knowledge extraction model, BERT is used for mapping each word into a high-dimensional vector, so that when entity disambiguation is carried out, a vector model-based method is adopted, and simultaneously, an entity disambiguation algorithm based on cosine similarity is designed by combining with Ha Gong synonym forest LTP. The cosine similarity is calculated by calculating the cosine value of the angle between the two vectors to determine their similarity, which is determined by the angle between the two vectors. If the included angle theta is 180 degrees and the cosine value is-1, the directions of the two vectors are completely opposite; if the included angle θ is 0 degrees and the cosine value is 1, the directions of the two vectors are identical.
Replacing the cosine value with the high-dimensional mapping vector of the word to be disambiguated, and converting the calculation formula into a formula (1):
based on the principle, the entity disambiguation algorithm based on cosine similarity is realized through the following programming in the embodiment of the invention, and the algorithm is described as follows:
3. knowledge storage, query and visualization
Knowledge storage, query and visualization all involve operations with the Neo4j database, and Neo4j native only supports operations using Cypher statements. Cypher, created by Neo Technology for Neo4j, is a graph database query language whose position and role is comparable to SQL in a relational database. Although Cypher is a declarative query language with features that perform efficiently, it still has a certain learning threshold for potential users of the knowledge graph. If the Cypher language is directly used for inquiring, the design original purpose of humanization and convenience of the platform is violated.
Therefore, in the embodiment of the invention, when the platform is constructed, all operations on Neo4j are packaged by using a third party SDK-py 2Neo based on Python, so that decoupling of the front end and the rear end is achieved, and business logic is not interfered with each other.
4. Data management
The data management function comprises platform data management and knowledge data management.
In an embodiment of the invention, platform data management incorporates personnel management, including personnel category and personnel rights. The administrator has full authority, can create new users and add, delete and check the database, and can also carry out full backup and incremental update on the database; the common user can only inquire the data and cannot change the data. Such settings are more consistent with the daily use scenario of the platform.
The knowledge data management function is to update and backup the data in the database. The domain knowledge is in the dynamic state, and when the data explodes, the accuracy and completeness of the platform can be ensured only by updating the knowledge in time. The disaster recovery capability of the platform is met through backup, and the invention supports manual backup and meets the diversification of the use scene besides the backup of the OpenStack cloud system level.
The operation verification of the cloud platform related to the invention is as follows:
1. user login interface (as shown in fig. 2):
in the embodiment of the invention, the user login interface of the cloud platform comprises the common functions of registering new users, forgetting passwords and the like, and meanwhile, an interface is reserved for supporting the connection with the Internet to use the common expansion functions of social account login and the like.
2. User management interface (as shown in fig. 3 and 4): the users of the platform in the embodiment of the invention have two levels of rights of an administrator and a common user, and different rights have different operation capacities.
3. Overview of knowledge-graph data:
in this embodiment, all functions of the cloud platform of the present invention and data content are illustrated in the form of fig. 5 and 6, the illustrated content supporting dynamic updating, the data and functions remaining synchronized with the platform.
4. Knowledge query interface: in the embodiment of the invention, the knowledge query of the invention is a core function and mainly comprises three sub-functions: entity queries, relationship queries, and relationship depth queries. Entity queries, i.e., querying all 1-degree adjacency entities related thereto based on entity names; a relational query, namely querying a related 1-degree relation when an entity name and a relation type are defined; and inquiring the depth of the relationship, namely inquiring all entities corresponding to the relationship and the depth when the name, the relationship and the depth of the relationship are defined. The specific functional schematic is shown in fig. 7 to 8.
5. Data management interface: the data management function of the invention mainly comprises three sub-functions of single data addition and deletion, batch (entity and relation) data update, batch data backup and the like, can realize the operation of entity relation data at each level of granularity, and can also carry out full data backup. The specific functions are shown in fig. 9.
The present embodiment is only for explanation of the present invention and is not to be construed as limiting the present invention, and modifications to the present embodiment, which may not creatively contribute to the present invention as required by those skilled in the art after reading the present specification, are all protected by patent laws within the scope of claims of the present invention.
Claims (1)
1. A knowledge graph cloud platform in the field of network space security is characterized in that: the system comprises an OpenStack cloud management system, an original data crawler module, a knowledge extraction module, a knowledge storage graph database and a knowledge graph application management service system; the knowledge extraction module is a knowledge extraction model based on transfer learning and a deep neural network, and comprises a BERT-based word embedding layer, a BiLSTM-CRF network learning prediction layer and a transfer learning module based on self-labeling data;
the OpenStack cloud management system is used for providing a hardware foundation and a system management function for the platform; the OpenStack cloud management system adopts three-node deployment, and the hardware distribution and the logic distribution of the OpenStack cloud management system are the same and are uniformly divided into a control node, a computing node and a network node;
the original data crawler module is written by adopting a Python based on a Scrapy framework, is packaged into a Python file, and is reserved with an interface API for a knowledge graph server to call and run on a network node;
the knowledge extraction module is written by Python based on a Pytorch frame, and is packaged into a py file, and an interface API is reserved for the knowledge graph application service to call and run on a computing node;
the workflow of the knowledge extraction model comprises the following steps:
(1) Cleaning original data of the network space safety field crawled from the Internet, building a self-labeling platform and labeling the field data to obtain a small-scale field data set, namely a target field data set;
(2) Acquiring a general data set as a source domain data set, wherein the general data set is a labeling data set taking common sense content as a main part; fully training the universal data set to obtain a source domain model, wherein the source domain model has the capability of extracting the universal corpus entity and the relationship characteristics;
(3) Migrating the source domain model obtained by training to a BiLSTM layer of a target domain network, wherein the BiLSTM layer performs feature extraction on input information; adjusting the output dimension of the CRF layer according to the label type of the target domain data set, and decoding the feature vector output by the BiLSTM into a globally optimal prediction label by the layer; finally, inputting the target domain data set into the migrated model for full training to obtain a model with knowledge extraction capability for domain data;
the knowledge storage graph database adopts a Neo4j graph database and operates on a computing node;
the knowledge graph application management service system is operated on the control node, is written by adopting a Python based on a Django framework and is used for displaying and responding application functions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210287641.4A CN114741526B (en) | 2022-03-23 | 2022-03-23 | Knowledge graph cloud platform in network space safety field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210287641.4A CN114741526B (en) | 2022-03-23 | 2022-03-23 | Knowledge graph cloud platform in network space safety field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114741526A CN114741526A (en) | 2022-07-12 |
| CN114741526B true CN114741526B (en) | 2024-02-02 |
Family
ID=82277440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210287641.4A Active CN114741526B (en) | 2022-03-23 | 2022-03-23 | Knowledge graph cloud platform in network space safety field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114741526B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633364A (en) * | 2019-09-23 | 2019-12-31 | 中国农业大学 | Graph database-based food safety knowledge graph construction method and display mode |
| CN110990590A (en) * | 2019-12-20 | 2020-04-10 | 北京大学 | Dynamic financial knowledge map construction method based on reinforcement learning and transfer learning |
| CN111428054A (en) * | 2020-04-14 | 2020-07-17 | 中国电子科技网络信息安全有限公司 | Construction and storage method of knowledge graph in network space security field |
| CN111967266A (en) * | 2020-09-09 | 2020-11-20 | 中国人民解放军国防科技大学 | Chinese named entity recognition model and construction method and application thereof |
| CN112199511A (en) * | 2020-09-28 | 2021-01-08 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Cross-language multi-source vertical domain knowledge graph construction method |
| CN112860908A (en) * | 2021-01-27 | 2021-05-28 | 云南电网有限责任公司电力科学研究院 | Knowledge graph automatic construction method based on multi-source heterogeneous power equipment data |
| CN113569124A (en) * | 2021-01-14 | 2021-10-29 | 腾讯科技（深圳）有限公司 | Medical title matching method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11494665B2 (en) * | 2015-10-28 | 2022-11-08 | Qomplx, Inc. | Multi-tenant knowledge graph databases with dynamic specification and enforcement of ontological data models |
-
2022
- 2022-03-23 CN CN202210287641.4A patent/CN114741526B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633364A (en) * | 2019-09-23 | 2019-12-31 | 中国农业大学 | Graph database-based food safety knowledge graph construction method and display mode |
| CN110990590A (en) * | 2019-12-20 | 2020-04-10 | 北京大学 | Dynamic financial knowledge map construction method based on reinforcement learning and transfer learning |
| CN111428054A (en) * | 2020-04-14 | 2020-07-17 | 中国电子科技网络信息安全有限公司 | Construction and storage method of knowledge graph in network space security field |
| CN111967266A (en) * | 2020-09-09 | 2020-11-20 | 中国人民解放军国防科技大学 | Chinese named entity recognition model and construction method and application thereof |
| CN112199511A (en) * | 2020-09-28 | 2021-01-08 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Cross-language multi-source vertical domain knowledge graph construction method |
| CN113569124A (en) * | 2021-01-14 | 2021-10-29 | 腾讯科技（深圳）有限公司 | Medical title matching method, device, equipment and storage medium |
| CN112860908A (en) * | 2021-01-27 | 2021-05-28 | 云南电网有限责任公司电力科学研究院 | Knowledge graph automatic construction method based on multi-source heterogeneous power equipment data |
Non-Patent Citations (3)
| Title |
|---|
| 信息化运维系统的图模型存储;周振煜;计算机系统应用;全文 * |
| 大规模企业级知识图谱实践综述;王昊奋;丁军;胡芳槐;王鑫;;计算机工程(07);全文 * |
| 网络安全实验平台K-划分映射方法;王会梅 等;国防科技大学学报;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114741526A (en) | 2022-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jia et al. | A practical approach to constructing a knowledge graph for cybersecurity | |
| Kumar Kaliyar | Graph databases: A survey | |
| CN111523003A (en) | Data application method and platform with time sequence dynamic map as core | |
| Yang et al. | Research on enterprise risk knowledge graph based on multi-source data fusion | |
| KR102593171B1 (en) | Information processing method and device, electronic equipment and storage medium | |
| CN109657072B (en) | Intelligent search WEB system and method applied to government aid decision | |
| US11449477B2 (en) | Systems and methods for context-independent database search paths | |
| Chen et al. | Bert-log: Anomaly detection for system logs based on pre-trained language model | |
| US11726999B1 (en) | Obtaining inferences to perform access requests at a non-relational database system | |
| EP3493076A1 (en) | Cognitive decision system for security and log analysis using associative memory mapping in graph database | |
| CN114741526B (en) | Knowledge graph cloud platform in network space safety field | |
| Xue et al. | Aggregating heterogeneous sensor ontologies with fuzzy debate mechanism | |
| Wu et al. | A summary of the latest research on knowledge graph technology | |
| Chen et al. | Machine Learning for Cyber Security: Third International Conference, ML4CS 2020, Guangzhou, China, October 8–10, 2020, Proceedings, Part II | |
| Yang | Variable weight semantic graph‐based ontology mapping method | |
| Abdallah et al. | Towards a GML-Enabled Knowledge Graph Platform | |
| Lathar et al. | Comparison study of different NoSQL and cloud paradigm for better data storage technology | |
| Peng | Analysis of Computer Information Processing Technology Based on Unstructured Data | |
| Zhang et al. | Research and Application of Agriculture Knowledge Graph | |
| Liu et al. | Current status and application analysis of graph database technology | |
| Huang et al. | On the application technology of computer database system in information management | |
| Li et al. | Real-Time Controllable Optimization Algorithm for Correlated Big Data in Cloud Computing Environment | |
| Li et al. | Discovering top-k probabilistic frequent itemsets from uncertain databases | |
| Zhang et al. | Design and implementation of power question answering and visualization system based on knowledge graph | |
| Yin et al. | Structural-based graph publishing under differential privacy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |