CN114741526A - Knowledge graph cloud platform in network space security field - Google Patents
Knowledge graph cloud platform in network space security field Download PDFInfo
- Publication number
- CN114741526A CN114741526A CN202210287641.4A CN202210287641A CN114741526A CN 114741526 A CN114741526 A CN 114741526A CN 202210287641 A CN202210287641 A CN 202210287641A CN 114741526 A CN114741526 A CN 114741526A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- network
- data set
- knowledge graph
- 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.)
- Granted
Links
- 238000000605 extraction Methods 0.000 claims abstract description 37
- 230000006870 function Effects 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 11
- 239000013598 vector Substances 0.000 claims description 11
- 238000002372 labelling Methods 0.000 claims description 9
- 238000013526 transfer learning Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 3
- 238000012827 research and development Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 22
- 238000010586 diagram Methods 0.000 description 12
- 238000013523 data management Methods 0.000 description 8
- 238000000034 method Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000012423 maintenance Methods 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
- 238000013507 mapping Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 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
Images
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 network space security field, which relates to the technical field of knowledge graphs in the network space security field, and the key points of the technical scheme are as follows: the system comprises an OpenStack cloud management system, an original data crawler module, a knowledge extraction module, a knowledge storage database and a knowledge graph application management service system; the OpenStack cloud management system is deployed by adopting three nodes, the hardware distribution and the logic distribution of the OpenStack cloud management system are the same, and the OpenStack cloud management system is divided into a control node, a computing node and a network node. The knowledge map cloud platform in the network space security field is convenient to provide unified management and dynamic allocation service of different computing resources, low in cost, high in efficiency, capable of processing the capacity of mass resources, capable of reflecting the characteristics of more three-dimensional, wider domain, more levels and more knowledge in the network space security field and beneficial to carrying out deeper analysis and prediction on network space security research and development.
Description
Technical Field
The invention relates to the technical field of knowledge graphs 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 gradually becomes a focus and focus of social attention. Network environments are becoming more complex, and network users, hardware devices and logic topologies are interconnected in a network space to generate a large amount of data information such as network topologies, network assets and the like. Meanwhile, network security events are occurring frequently, and intrusion detection devices deployed by countries and enterprises generate massive data information such as network vulnerabilities, attack threats and security alarms constantly. The safety data information is increased explosively, and faces the dilemma that the data amount is huge, but the data lacks relevance and knowledge, and the safety analysis personnel in network space are difficult to obtain and effectively utilize the safety data information.
At present, a platform in the field of network space security in the prior art is used for unified management and dynamic allocation service of different computing resources, and has high cost, low efficiency and inconvenience in processing mass resources; therefore, the invention aims to provide a knowledge graph cloud platform in the network space security field 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 purpose of the invention is realized by the following technical scheme: a knowledge graph cloud platform in the network space security field comprises an OpenStack cloud management system, an original data crawler module, a knowledge extraction module, a knowledge storage database and a knowledge graph application management service system;
the OpenStack cloud management system is used for providing a hardware base and a system management function for a platform; the OpenStack cloud management system is deployed by adopting three nodes, the hardware distribution and the logic distribution of the OpenStack cloud management system are the same, and the hardware distribution and the logic distribution are divided into control nodes, computing nodes and network nodes;
the original data crawler module is compiled by adopting Python based on a Scapy framework and packaged into a Python file, and an interface API is reserved for the calling of a knowledge graph server and runs on a network node;
the knowledge extraction module is compiled by adopting Python based on a Pythrch framework and is packaged into a py file, and an interface API (application programming interface) is reserved for the calling of a knowledge graph application service and is operated on a computing node;
the knowledge storage database adopts a Neo4j database and runs on the computing nodes;
the knowledge graph application management service system runs on the control node, is compiled by adopting 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 method comprises the steps that a knowledge graph server calls an original data crawler module running on a network node; through the knowledge extraction module, entity extraction is conveniently completed firstly, and then the relation extraction is performed by combining the original sentence and the identified entity; by the knowledge storage graph database, complex relationships among mass data can be conveniently inquired and analyzed, and the knowledge in the field of network space safety can be conveniently stored; the knowledge graph application management service system is responsible for displaying and responding application functions and is convenient and rapid for platform development and later maintenance. The knowledge map cloud platform in the network space security field is convenient to provide 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 three-dimensional, wider domain, more levels and more knowledge in the network space security field, and is favorable for carrying out deeper analysis and prediction on network space security research and development.
The invention is further configured to: the knowledge extraction module is a knowledge extraction model based on transfer learning and a deep neural network, and the knowledge extraction model 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 configured to: the workflow of the knowledge extraction model comprises the following steps:
(1) cleaning original data in a '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 domain data set;
(2) acquiring a universal data set as a source domain data set, wherein the universal data set is a marked data set which mainly comprises common sense contents; fully training a universal data set through the model to obtain a source domain model, wherein the source domain model has the extraction capability of universal 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 layer mainly performs characteristic extraction on input information; adjusting the output dimension of a 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 the knowledge extraction capability on the domain data.
In conclusion, 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 map cloud platform in the network space security field can process the capacity of mass resources, can reflect the characteristics of more three-dimensional, wider domain, more layers and more knowledge in the network space security field, and is favorable for carrying out deeper analysis and prediction on the network space security research and development.
Drawings
FIG. 1 is a functional block diagram of a general implementation of a network space security domain knowledge graph cloud platform in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a user login interface in an embodiment of the invention;
FIG. 3 is a schematic diagram of user administration (administrator side) in an embodiment of the invention;
FIG. 4 is a schematic diagram of adding a user (administrator side) in the embodiment of the present invention;
FIG. 5 is a diagram of a home interface (introduction platform core functionality) in an embodiment of the present invention;
FIG. 6 is a functional diagram illustrating platform data overview in an embodiment of the present invention;
FIG. 7 is a functional diagram of entity query in an embodiment of the invention;
FIG. 8 is an exemplary diagram of entity queries (querying all relationships of "national network shooting range") in an embodiment of the invention;
FIG. 9 is a functional diagram of a relational query in an embodiment of the invention;
FIG. 10 is an exemplary diagram of a relational query (query a 3-degree "association" relationship of "national network shooting range") in an embodiment of the invention;
FIG. 11 is a diagram illustrating a single data add/delete/modify function according to an embodiment of the present invention;
fig. 12 is a diagram illustrating a single data update function in an embodiment of the present invention.
Detailed Description
The present invention is described in further detail below with reference to FIGS. 1-3.
Example (b):
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 database, knowledge graph application management services and the like.
Wherein, each module has the following functions:
(1) the OpenStack cloud management system provides hardware foundation and system management functions for the full platform. The OpenStack of the platform uses an O version with good stability, a conventional three-node deployment scheme is adopted for deployment, hardware distribution and logic distribution are the same, and the OpenStack is divided into control nodes (responsible for cloud platform management and application management service running), computing nodes (responsible for cloud platform performance monitoring, data storage, functional module running and the like) and network nodes (responsible for communication and crawler service in the platform).
(2) The original data crawler module is compiled by using a Python based on a Scapy framework, and then packaged into a Python file, and an interface API is reserved for being called by a knowledge graph server and running on a network node;
(3) a knowledge extraction module (TBBC) is compiled by using Python based on a Pythrch framework, and then packaged into a py file, and an interface API is reserved for calling a knowledge graph application service and running on a computing node;
(4) the knowledge graph storage database adopts a Neo4j database and runs 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 the complex relation among mass data, so that the graph database is more suitable for storing the knowledge in the field of network space security. Neo4j officially offers a free community version whose performance supports a maximum of 320 million nodes, 320 million relations and 640 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, is written by Python based on the Django framework and is responsible for displaying and responding to the application function. Django is an open-source Web application framework, an MTV model architecture is used, and a plurality of third-party plug-ins with strong functions are contained in the framework, so that Django has strong expandability. Due to the characteristics of easy maintainability, high expansibility, data driveability and the like of Django, platform development and later maintenance can be carried out more conveniently and rapidly, and simultaneously, due to the fact that a mainstream B/S framework is used, a client does not need to be installed, and user experience is better.
In this embodiment, an implementation algorithm of the knowledge graph cloud platform in the network space security field of the present invention is as follows:
1. knowledge extraction
By combining the data characteristics of the network space security field, the invention designs a knowledge extraction model (TBBC) model based on the transfer learning and the deep neural network, which is totally divided into three core functional modules: the system comprises a BERT-based word embedding layer, a BilSTM-CRF network learning prediction layer and a self-labeling data-based migration learning module. The entity extraction is completed first, and then the relation extraction is performed by combining the original sentence and the identified entity.
The workflow of the knowledge extraction model (TBBC) is as follows:
(1) the method comprises the steps of cleaning original data of a '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 domain data set.
(2) And acquiring a universal data set as a source domain data set, wherein the universal data set is a marked data set which takes common sense content as a main part. And fully training the universal data set through the model to obtain a source domain model, wherein the source domain model has the extraction capability of universal linguistic data (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 layer mainly performs feature extraction on input information; adjusting the output dimension of a 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 the knowledge extraction capability on the domain data.
Because the TBBC training extraction model consumes a lot of time, a display card is needed for operation, and a server cannot configure the display card, during platform initial construction, a workstation with the display card is used for extracting knowledge of all currently crawled original texts, the knowledge data is obtained and then stored in a database such as a computing node, and meanwhile, a trained pkl model file is also stored in the computing node. When knowledge updating is required, only the TTBC extraction module is called, the trained model is loaded, and knowledge extraction is carried out on the CPU without retraining the model. Because only incremental updating is carried out, the data size is not large, and therefore the computing resources of the computing nodes can be basically met. After the incremental data is scaled, replacing plk files in the computing nodes by using corresponding hardware resource platforms according to the process training model, and thus updating and iterating the extraction capacity can be realized.
2. Entity disambiguation
In a practical application scenario, named entities have characteristics of diversity and ambiguity, for example, a term "peak" may represent a peak in different sentences, and may also represent a person's name, and different meanings represent different entities and different connected relationships. Therefore, solving the problem of entity disambiguation can better construct the knowledge graph with practical application significance.
In the TBBC knowledge extraction model, each word is mapped into a high-dimensional vector by using BERT, so that when entity disambiguation is carried out, an entity disambiguation algorithm based on cosine similarity is designed by adopting a vector model-based method and combining with the Hash-Jordan synonym forest LTP. The cosine similarity is determined by calculating the cosine value of the included angle between two vectors, and the similarity of the two vectors is determined by the included 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 angle θ is 0 degrees and the cosine value is 1, the directions of the two vectors are identical.
And replacing the cosine values with the high-dimensional mapping vector of the word to be disambiguated, and converting the calculation formula into the formula (1):
based on the principle, the entity disambiguation algorithm based on the cosine similarity is realized by the following programming in the embodiment of the invention, and the algorithm is described as follows:
3. knowledge storage, query and visualization
The storage, query and visualization of knowledge all involve operations with the Neo4j database, and Neo4j natively supports operations using Cypher statements. Cypher was created by Neo Technology corporation for Neo4j and is a graph database query language that is comparable in place and function to SQL in a relational database. Although Cypher is a declarative query language with features of high performance, it still has some learning threshold for potential users of the knowledge graph. If the Cypher language is directly used for query, the original design purpose of humanization and convenience of the platform is violated.
Therefore, in the embodiment of the invention, when the platform is constructed, the third-party SDK-py 2Neo based on Python is used for encapsulating all operations of Neo4j, so that the front end and the back end are decoupled, and mutual interference of service logics is realized.
4. Data management
The data management functions include platform data management and knowledge data management.
In embodiments of the present invention, platform data management incorporates personnel management, including personnel categories and personnel permissions. The administrator has full authority, can create new users, add, delete, modify and check the database, and can also perform full backup and incremental update on the database; an ordinary user can only inquire data and cannot change the data. Such a setting is more consistent with the daily usage scenario of the platform.
The knowledge data management function is to update and backup data in the database. The domain knowledge is in a dynamic state, and the accuracy and the completeness of the platform can be ensured only by updating the knowledge in time when data explodes. The disaster recovery capability of the platform is met through backup, and the invention not only supports the backup of the OpenStack cloud system level, but also supports manual backup, thereby meeting the diversification of the use scene.
The operation of the cloud platform of the present invention is verified 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 functions of commonly used 'registering a new user' and 'forgetting a password', and the like, and an interface is reserved for supporting the internet connection and using the extended functions of commonly used social account login, and the like.
2. User management interface (as shown in fig. 3 and 4): the user of the platform in the embodiment of the invention has two levels of authority of an administrator and a common user, and different authorities have different operation capabilities.
3. And (3) overview of knowledge graph data:
in the embodiment, all functions and data contents of the cloud platform of the invention are shown in the form of fig. 5 and fig. 6, the shown contents support dynamic update, and data and functions are kept synchronous with the platform.
4. A knowledge query interface: in the embodiment of the present invention, the knowledge query of the present invention is a core function, and mainly includes three sub-functions: entity queries, relational queries, and relational depth queries. Entity query, namely querying all 1-degree adjacent entities related to the entity query based on the entity name; relation query, namely querying a relevant 1-degree relation when the body name and the relation type are known; and (4) relation depth query, namely querying all entities corresponding to the relation and the depth when the name, the relation and the relation depth of the entity are known. The specific functional schematic is shown in fig. 7 to 10.
5. A data management interface: the data management function of the invention mainly comprises three subfunctions of single data addition and deletion, batch (entity, relationship) data updating, batch data backup and the like, can realize the operation of entity relationship data at each level of granularity, and can also carry out full data backup at the same time. The specific function is shown in fig. 11 and 12.
The present embodiment is only for explaining the present invention, and it is not limited to the present invention, and those skilled in the art can make modifications of the present embodiment without inventive contribution as needed after reading the present specification, but all of them are protected by patent law within the scope of the claims of the present invention.
Claims (3)
1. A knowledge graph cloud platform in the network space security field is characterized in that: the system comprises an OpenStack cloud management system, an original data crawler module, a knowledge extraction module, a knowledge storage database and a knowledge graph application management service system;
the OpenStack cloud management system is used for providing a hardware base and a system management function for a platform; the OpenStack cloud management system is deployed by adopting three nodes, the hardware distribution and the logic distribution of the OpenStack cloud management system are the same, and the hardware distribution and the logic distribution are divided into control nodes, computing nodes and network nodes;
the original data crawler module is compiled by adopting Python based on a Scapy framework and packaged into a Python file, and an interface API is reserved for the calling of a knowledge graph server and runs on a network node;
the knowledge extraction module is compiled by adopting Python based on a Pythrch framework and is packaged into a py file, and an interface API (application programming interface) is reserved for the calling of a knowledge graph application service and is operated on a computing node;
the knowledge storage database adopts a Neo4j database and runs on the computing nodes;
the knowledge graph application management service system runs on the control node, is compiled by adopting Python based on a Django framework, and is used for displaying and responding application functions.
2. The cyberspace security domain knowledge graph cloud platform of claim 1, wherein: the knowledge extraction module is a knowledge extraction model based on transfer learning and a deep neural network, and the knowledge extraction model comprises a BERT-based word embedding layer, a BilSTM-CRF network learning prediction layer and a transfer learning module based on self-labeling data.
3. The cyberspace security domain knowledge graph cloud platform of claim 2, wherein: the workflow of the knowledge extraction model comprises the following steps:
(1) cleaning original data in a '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 domain data set;
(2) acquiring a universal data set as a source domain data set, wherein the universal data set is a marked data set which mainly comprises common sense contents; fully training a universal data set through the model to obtain a source domain model, wherein the source domain model has the extraction capability of universal 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 layer mainly performs characteristic extraction on input information; adjusting the output dimension of a 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 the knowledge extraction capability on the domain data.
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 true CN114741526A (en) | 2022-07-12 |
| CN114741526B 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 (8)
| 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 |
| US20200364584A1 (en) * | 2015-10-28 | 2020-11-19 | Qomplx, Inc. | Multi-tenant knowledge graph databases with dynamic specification and enforcement of ontological data models |
| 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 |
-
2022
- 2022-03-23 CN CN202210287641.4A patent/CN114741526B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200364584A1 (en) * | 2015-10-28 | 2020-11-19 | Qomplx, Inc. | Multi-tenant knowledge graph databases with dynamic specification and enforcement of ontological data models |
| 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 |
|---|
| 周振煜: "信息化运维系统的图模型存储", 计算机系统应用 * |
| 王会梅 等: "网络安全实验平台K-划分映射方法", 国防科技大学学报 * |
| 王昊奋;丁军;胡芳槐;王鑫;: "大规模企业级知识图谱实践综述", 计算机工程, no. 07 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114741526B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kumar Kaliyar | Graph databases: A survey | |
| US10467250B2 (en) | Data model design collaboration using semantically correct collaborative objects | |
| Yang et al. | Research on enterprise risk knowledge graph based on multi-source data fusion | |
| CN111026874A (en) | Data processing method and server of knowledge graph | |
| 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 | |
| CN105045933B (en) | Mapping method between apparel maintenance support information relationship database schema and body | |
| Li et al. | PICKT: a solution for big data analysis | |
| US20230334046A1 (en) | Obtaining inferences to perform access requests at a non-relational database system | |
| da Silva Machado et al. | EXEHDA-HM: A compositional approach to explore contextual information on hybrid models | |
| Zhang et al. | Geoscience knowledge graph (GeoKG): Development, construction and challenges | |
| US11968214B2 (en) | Efficient retrieval and rendering of access-controlled computer resources | |
| WO2021186287A1 (en) | Vector embedding models for relational tables with null or equivalent values | |
| CN110928963A (en) | Column-level authority knowledge graph construction method for operation and maintenance service data table | |
| CN114741526B (en) | Knowledge graph cloud platform in network space safety field | |
| Mian et al. | The study of multimedia data model technology based on cloud computing | |
| Zhang et al. | Construction of educational resource metadata management platform based on service-oriented architecture | |
| Yao et al. | LandQ v1: A GIS cluster-based management information system for arable land quality big data | |
| Li et al. | Fedsa: A data federation platform for law enforcement management | |
| Shan et al. | A Semantics-preserving Approach for Extracting RDF Knowledge from Object-oriented Databases | |
| Asgari et al. | An ontology-based approach for integrating heterogeneous databases | |
| Peng | Analysis of Computer Information Processing Technology Based on Unstructured Data | |
| Wang | Optimization of Network Security in University Laboratories Based on Anomaly Intrusion Detection in Public Cloud Networks | |
| Yin et al. | Structural-based graph publishing under differential privacy | |
| Chen et al. | Evolution and computing challenges of distributed GIS |
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 |