Supercharge Your Innovation With Domain-Expert AI Agents!

Construction and fusion method of layered structure multi-level knowledge graph

A technology of knowledge graph and layered structure, applied in unstructured text data retrieval, semantic tool creation, instruments, etc., can solve the problem that general graph and domain graph cannot be integrated with each other, and reduce storage pressure and query pressure. , quick disambiguation, contact organized effect

Pending Publication Date: 2022-05-24
新华智云科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that the general graph and the domain graph cannot be integrated and promoted together, the present invention provides a method for constructing a multi-level knowledge graph with a layered structure and an update maintenance and query method based on the aforementioned graph construction

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Construction and fusion method of layered structure multi-level knowledge graph
  • Construction and fusion method of layered structure multi-level knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] This embodiment provides a method for constructing a multi-level knowledge graph with a layered structure. figure 1 The hierarchical structure shown in the multi-level knowledge graph includes:

[0032] Build several levels of vertically cascaded graphs, each level includes multiple similar graphs; each graph includes an ontology structure, and each graph needs to build its own ontology structure, and the ontology structure includes one or more types and inter-types. association relationship.

[0033] When any low-level ontology structure is involved in the ontology structure to be constructed in the high-level graph, the high-level graph can refer to the involved ontology structure to construct its own ontology structure. When a type in a higher-level graph refers to a type in any lower-level graph, the types involved in the lower-level graph are colored.

[0034] The types include places, celebrities, etc., and the type of places can also include sub-types such as a...

Embodiment 2

[0054] A method for fusing a multi-level knowledge graph of a layered structure, which is used to fuse the multi-level knowledge graph of a layered structure constructed according to the construction method described in Embodiment 1, and fuses the ontology structures in the graph according to the involved ontology structure, The entities with the same entity name in each graph establish a mapping relationship or virtual connection according to the entity ID, and the entities with the same entity name are fused according to the mapping relationship and the virtual connection.

[0055] When the high-level graph and the low-level graph need to be fused, the overall framework can be fused first according to the involved ontology structure and the involved attribute structure.

[0056] The entities with the same entity name in each graph establish a mapping relationship or virtual connection according to the entity ID, and the entities with the same entity name are fused according t...

Embodiment 3

[0066] This embodiment provides a method for maintaining a multi-level knowledge graph with a layered structure, which is used to maintain the graph in Embodiment 1. The specific steps include:

[0067] Determine whether the entity belongs to a low-level graph or a high-level graph according to the type of the maintenance entity, and maintain the maintenance entity in the corresponding graph. When the identified type has an attribute extension identifier, it means that the type belongs to the high-level graph.

[0068] Generally speaking, the types of low-level graphs are relatively simple and belong to general knowledge, while the types of high-level graphs are more complex, including exclusive types or exclusive attributes in the field, so first determine whether the entities to be maintained belong to low-level graphs or high-level graphs according to the type. level map. If the type belongs to the type of the low-level graph, but there is an attribute extension mark on it,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a layered structure multi-level knowledge graph construction and fusion method, and the construction method comprises the steps: longitudinally cascading a plurality of levels of graphs, and enabling each level to comprise a plurality of types of graphs of the same kind; each map comprises a body structure; when the ontology structures needing to be constructed in the high-level atlas relate to the ontology structures of any low-level atlas, the high-level atlas quotes the related ontology structures; the body structure comprises one or more types and association relationships among the types; when the type in the high-level atlas relates to the type in any low-level atlas, coloring the related type in the low-level atlas; the entities are filled according to the types and the ontology structures, and the entities comprise entity IDs and entity data. According to the multi-level knowledge graph with the layered structure, through reference of the ontology structure and the attribute structure, the steps and energy of repeated construction can be omitted in the construction stage, and information can be rapidly integrated through the same framework in the fusion or query stage.

Description

technical field [0001] The invention relates to a method for constructing a knowledge graph, in particular to the establishment, maintenance, fusion and query of a multi-level knowledge graph with a layered structure. Background technique [0002] From the perspective of coverage and usage scenarios, knowledge graphs are usually divided into general knowledge graphs and domain knowledge graphs. The general knowledge graph is oriented to the whole field, mainly based on common sense knowledge, emphasizing the breadth of knowledge, such as the encyclopedic knowledge graph; the domain knowledge graph is mainly subdivided knowledge fields, more emphasis on professionalism, and more fine-grained knowledge in the field. portray. [0003] The general knowledge graph cannot cover the needs of the fine-grained knowledge of the domain knowledge graph. For example, the attributes of the same object will have different data content and different storage structures in different fields. ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/36G06F40/279
CPCG06F16/367G06F40/279
Inventor 杨丛聿仇应俊郝凯
Owner 新华智云科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com