CN115952247A - Spatial target situation perception method based on knowledge graph - Google Patents
Spatial target situation perception method based on knowledge graph Download PDFInfo
- Publication number
- CN115952247A CN115952247A CN202211614810.7A CN202211614810A CN115952247A CN 115952247 A CN115952247 A CN 115952247A CN 202211614810 A CN202211614810 A CN 202211614810A CN 115952247 A CN115952247 A CN 115952247A
- Authority
- CN
- China
- Prior art keywords
- information
- corpus
- spatial target
- target situation
- spatial
- 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.)
- Pending
Links
Images
Classifications
-
- 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 relates to the technical field of spatial target situation perception, and particularly discloses a spatial target situation perception method based on a knowledge graph, which comprises the following specific steps of: establishing a spatial target situation awareness language material library, and importing related entity information and relationship information of a spatial target into the language material library; constructing a language model for spatial target situation awareness according to a corpus; creating semantic tags for information in a corpus; threat detection is carried out on the spatial target situation; importing the detected related data into a corpus, performing primary semantic understanding on the data through the corpus, and extracting related semantic tags; matching and extracting corresponding information data in the corpus through semantic tags; threat analysis is carried out on the corresponding specific space target through the matched information data; after the analysis is completed, providing a relevant threat risk judgment result, a threat reason and a countermeasure corresponding to the space target; and importing the analysis content into a language model for displaying.
Description
Technical Field
The invention relates to the technical field of spatial target situation perception, in particular to a spatial target situation perception method based on a knowledge graph.
Background
The processing of spatial target situations is of great significance for managing and monitoring spatial targets. The spatial massive target situation display mainly comprises the visualization of the position information and the track information of the spatial target.
However, due to the huge number of space targets, when a specific space target is displayed, most of the related data corresponding to the space target needs to be extracted from a huge database and then integrated and displayed on corresponding equipment, so that the efficiency is low, and it is difficult to provide more intuitive and effective data.
The knowledge graph is used as an important branch of artificial intelligence, has unique advantages in the aspects of big data analysis and decision making, can represent data into a mesh knowledge structure based on 'entity-relation-entity', helps to understand big data through semantic linkage, obtains overall insight of the big data, and provides decision support, so that a spatial target situation perception method based on the knowledge graph is urgently needed to solve the technical problems.
Disclosure of Invention
The invention aims to provide a spatial target situation perception method based on a knowledge graph to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a spatial target situation perception method based on a knowledge graph comprises the following specific steps:
the method comprises the following steps: establishing a spatial target situation awareness language database, and importing related entity information and relationship information of a spatial target into the language database;
step two: constructing a language model for spatial target situation awareness according to a corpus;
step three: creating semantic tags for information in a corpus;
step four: threat detection is carried out on the spatial target situation;
step five: importing the detected related data into a corpus, performing primary semantic understanding on the data through the corpus, and extracting related semantic tags;
step six: matching and extracting corresponding information data in the corpus through semantic tags;
step seven: threat analysis is carried out on the corresponding specific space target through the matched information data;
step eight: after the analysis is completed, providing a relevant threat risk judgment result, a threat reason and a countermeasure corresponding to the space target;
step nine: and reintroducing the analyzed content into the language model for displaying.
As a preferred aspect of the present invention, the entity information in the first step refers to something which is distinguishable and exists independently, such as number information of the spatial object, country information of the spatial object, and the relationship information refers to connection relationship words between different entities, such as "country of the country", "transmission time", "type of the country", "transmission field".
As a preferred embodiment of the present invention, in the second step, constructing the language model for spatial target situation awareness specifically includes the following steps: extracting specific entities from the data of the corpus, linking the entities by extracting the association relationship between the entities from the corpus, extracting the attribute information of the identified entities from the corpus, integrating and processing the extracted attribute information, and connecting the extracted attribute information with the corresponding entity information and the corresponding relationship information to form a language model.
As a preferred embodiment of the present invention, the semantic tag matching function in the step six includes breadth matching and depth matching.
As a preferred embodiment of the present invention, the threat resolution in the step seven specifically includes the following steps: and performing association analysis on two or more spatial targets detected in the threat detection of the spatial target situation in the fourth step.
As a preferred embodiment of the present invention, the parsing content in the ninth step further includes a relationship path diagram between the at least two spatial targets.
As a preferred scheme of the present invention, in step nine, after the related entity information and the relationship information of the new spatial target are required to be introduced into the corpus, the introduced information is integrated to eliminate contradictions and ambiguities, for example, some entities have multiple names, and a specific name corresponds to multiple different entities.
As a preferred embodiment of the present invention, after the related entity information and the relationship information of the new spatial target are integrated, a plurality of evaluations are performed on the integrated information, and then qualified partial information is added to the corpus to ensure the quality of the corpus.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the spatial target situation awareness method based on the knowledge graph, the spatial target situation awareness corpus is established, the language model is constructed to intuitively express the information of the spatial target and the association condition between the spatial target, the spatial target is accurately and efficiently perceived conveniently, scientific and visual data support is provided for potential threats of the spatial target, and the depth and the breadth of spatial target situation awareness are expanded.
2. According to the spatial target situation perception method based on the knowledge graph, the semantic tags are built in the corpus, so that when the spatial target is subjected to situation perception at the later stage, the associated data corresponding to the spatial target can be rapidly extracted, further threat analysis is performed on the associated data, a risk judgment result, a threat reason, a countermeasure and the like of the corresponding spatial target are obtained through analysis, and then the updated entity information and the updated associated information are imported into the language model, so that the perception result of the spatial target situation can be visually displayed conveniently.
Drawings
Fig. 1 is a schematic view of the overall structure of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: a spatial target situation perception method based on a knowledge graph comprises the following specific steps:
the method comprises the following steps: establishing a spatial target situation perception language database, and importing related entity information and relationship information of a spatial target into the language database, wherein the entity information refers to something which is distinguishable and independent, such as number information of the spatial target and country information to which the spatial target belongs, and the relationship information refers to connection relationship words between different entities, such as country to which the entity belongs, transmission time, type to which the entity belongs, and transmission field.
Step two: constructing a language model for spatial target situation awareness according to a corpus;
the method specifically comprises the following steps:
extracting a specific entity from data of a corpus;
extracting the association relationship among the entities from the corpus to link the entities;
extracting attribute information of the identified entity from the corpus;
and then integrating and processing the extracted attribute information, and connecting the attribute information with corresponding entity information and relationship information to form a language model.
Step three: semantic tags are created for information within the corpus.
Step four: and carrying out threat detection on the spatial target situation.
Step five: and importing the detected related data into a corpus, performing primary semantic understanding on the data through the corpus, and extracting related semantic tags.
Step six: and matching and extracting corresponding information data in the corpus through semantic tags, wherein the semantic tag matching function comprises breadth matching and depth matching.
Step seven: threat analysis is carried out on the corresponding specific space target through the matched information data;
the method specifically comprises the following steps:
and performing association analysis on two or more spatial targets detected in the threat detection of the spatial target situation in the fourth step.
Step eight: after the analysis is completed, providing a relevant threat risk judgment result, a threat reason and a countermeasure corresponding to the space target;
step nine: reintroducing the analysis content and the relationship path graph between the at least two space targets into the language model for display;
the method specifically comprises the following steps: when related entity information and relationship information of a new space target need to be introduced into a corpus, the introduced information is integrated to eliminate contradictions and ambiguity, for example, some entities have multiple titles, and a certain title corresponds to multiple different entities;
after the related entity information and the relationship information of the new space target are integrated, a plurality of items of evaluation are carried out on the information, and qualified partial information is added into the corpus so as to ensure the quality of the corpus.
The working principle is as follows: according to the scheme, a spatial target situation perception corpus is established, entity information (such as XX satellite, china, XXXX year XX month XX day) and relation information (spatial target title, launching country and launching time) about a spatial target are imported into the corpus, and a corresponding language model is constructed according to the relation information and the entity information, so that the self information of the spatial target and the correlation condition between a plurality of spatial targets are expressed visually. After the language model is established, corresponding semantic tags are established in the language database according to the association condition between each space target established by the language model for standby.
According to the relation condition of a plurality of space targets, threat detection is carried out on the space targets with threats through space target situation sensing equipment, detection data are guided into a corpus during detection, preliminary semantic understanding and analysis are carried out on the detection data, appropriate semantic labels are extracted and placed into a semantic label library for matching, relevant information data corresponding to the space targets are extracted according to the labels obtained through matching, further threat analysis is carried out on the relevant information data, risk judgment results, threat reasons, countermeasures and the like corresponding to the space targets are obtained through analysis, and then entity information and relevant information are guided into a language model and updated, so that the sensing results of the space target situations can be conveniently and visually displayed.
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 alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A spatial target situation perception method based on a knowledge graph is characterized by comprising the following steps: the method comprises the following specific steps:
the method comprises the following steps: establishing a spatial target situation awareness language database, and importing related entity information and relationship information of a spatial target into the language database;
step two: constructing a language model for spatial target situation awareness according to a corpus;
step three: creating semantic tags for information in a corpus;
step four: threat detection is carried out on the spatial target situation;
step five: importing the detected related data into a corpus, performing primary semantic understanding on the data through the corpus, and extracting related semantic tags;
step six: matching and extracting corresponding information data in the corpus through semantic tags;
step seven: threat analysis is carried out on the corresponding specific space target through the matched information data;
step eight: after the analysis is completed, providing a relevant threat risk judgment result, a threat reason and a countermeasure corresponding to the space target;
step nine: and reintroducing the analyzed content into the language model for displaying.
2. The spatial target situation awareness method based on the knowledge-graph according to claim 1, wherein: the entity information in the step one refers to something which is distinguishable and independent, and the relationship information refers to a connection relationship word between different entities.
3. The spatial target situation awareness method based on the knowledge-graph according to claim 1, wherein: in the second step, the construction of the language model for spatial target situation awareness specifically comprises the following steps: extracting specific entities from the data of the corpus, linking the entities by extracting the association relationship between the entities from the corpus, extracting the attribute information of the identified entities from the corpus, integrating and processing the extracted attribute information, and connecting the extracted attribute information with the corresponding entity information and the corresponding relationship information to form a language model.
4. The spatial target situation awareness method based on the knowledge-graph according to claim 1, wherein: and the semantic label matching function in the sixth step comprises breadth matching and depth matching.
5. The spatial target situation awareness method based on the knowledge-graph according to claim 1, wherein: the threat resolution in the seventh step specifically comprises the following steps: and performing association resolution on two or more spatial targets detected in the threat detection of the spatial target situation in the fourth step.
6. The knowledge-graph-based spatial target situation awareness method according to claim 1, wherein: the parsing content in the step nine further includes a relationship path diagram between the at least two space targets.
7. The spatial target situation awareness method based on the knowledge-graph according to claim 1, wherein: in step nine, after the related entity information and the relationship information of the new space target need to be introduced into the corpus, the introduced information is integrated to eliminate contradiction and ambiguity.
8. The spatial target situation awareness method based on the knowledge-graph according to claim 1, wherein: after the related entity information and the relationship information of the new space target are integrated, a plurality of items of evaluation are carried out on the information, and then qualified partial information is added into the corpus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211614810.7A CN115952247A (en) | 2022-12-15 | 2022-12-15 | Spatial target situation perception method based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211614810.7A CN115952247A (en) | 2022-12-15 | 2022-12-15 | Spatial target situation perception method based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115952247A true CN115952247A (en) | 2023-04-11 |
Family
ID=87286797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211614810.7A Pending CN115952247A (en) | 2022-12-15 | 2022-12-15 | Spatial target situation perception method based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115952247A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115859305A (en) * | 2022-12-26 | 2023-03-28 | 国家工业信息安全发展研究中心 | Knowledge graph-based industrial control security situation sensing method and system |
-
2022
- 2022-12-15 CN CN202211614810.7A patent/CN115952247A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115859305A (en) * | 2022-12-26 | 2023-03-28 | 国家工业信息安全发展研究中心 | Knowledge graph-based industrial control security situation sensing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11593408B2 (en) | Identifying data relationships from a spreadsheet | |
| CN101614781B (en) | Intelligent diagnosis method of radio and television equipment based on spatial rule index | |
| CN103605651A (en) | Data processing showing method based on on-line analytical processing (OLAP) multi-dimensional analysis | |
| CN112613038B (en) | Knowledge graph-based security vulnerability analysis method | |
| CN111881224A (en) | Multidimensional data analysis method and system | |
| CN105488130A (en) | Associated data visualization display method | |
| CN105046328A (en) | Three-dimensional visual bridge disease information collection management system and three-dimensional visual bridge disease information collection management method | |
| CN107872454A (en) | A kind of monitoring of ultra-large type internet platform protection based on security rank threat information and analysis system and method based on big data technology | |
| CN112182077B (en) | Intelligent operation and maintenance system based on data middling platform technology | |
| CN115952247A (en) | Spatial target situation perception method based on knowledge graph | |
| CN113010696A (en) | Engineering field knowledge graph construction method based on metadata model | |
| CN115080765A (en) | Aerospace quality knowledge map construction method, system, medium and equipment | |
| CN113487211A (en) | Nuclear power equipment quality tracing method and system, computer equipment and medium | |
| Guo et al. | Text quality analysis of emergency response plans | |
| Kopf et al. | The business intelligence based business process management challenge | |
| CN111552679A (en) | Rapid modeling method and device based on simple requirements | |
| US20130268855A1 (en) | Examining an execution of a business process | |
| CN114529383A (en) | Method and system for realizing tax payment tracking and tax loss early warning | |
| CN104809216A (en) | Analysis model and engine system based on data mining | |
| Marinescu | Identification of design roles for the assessment of design quality in enterprise applications | |
| Li | Research on financial risk prediction and prevention countermeasures based on big data | |
| Miao et al. | Intelligent auxiliary operation and maintenance system of power communication network based on knowledge graph | |
| Shao et al. | Mining actionable combined high utility incremental and associated patterns | |
| CN112115174A (en) | KYC method and system based on graph computing technology | |
| CN111612604A (en) | Risk control method and system in internal audit |
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 |