Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Evaluation method and system based on domain knowledge graph

A technology of domain knowledge and evaluation methods, applied in special data processing applications, unstructured text data retrieval, instruments, etc., can solve problems such as inability to objectively evaluate knowledge graphs, and achieve strict article review, cost savings, and extensive research content. Effect

Active Publication Date: 2021-08-03
深圳市曙光信息技术有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the scale and quality of the knowledge graph have an impact on the evaluation of the question answering system, this evaluation introduces additional links such as the design of the question answering system, content selection, and evaluation of the question answering results. Objective evaluation of the map itself

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
  • Evaluation method and system based on domain knowledge graph
  • Evaluation method and system based on domain knowledge graph
  • Evaluation method and system based on domain knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Such as figure 1 As shown, the evaluation method based on the domain knowledge graph of an embodiment of the present invention includes:

[0063] Obtain literature: For the domain knowledge graph DKG to be evaluated, obtain the core journals and general journal literature in the last N years in this field;

[0064] Expansion: expand the triple of the domain knowledge map DKG triple i to be evaluated, the entity words h and t are respectively expanded to obtain H1 and T1, and the relational word r is expanded to obtain R1, after expansion Combinations form the extended set Wi of triples. If H1 has m elements, T1 has n elements, and R1 has p elements, K=m×n×p triplets are generated through combination, and the entity words of each triplet in the triplet extension set Wi and related words are extracted and deduplicated to form a professional dictionary C in the field. If the number of triples in DKG is Z, the number of triples after expansion is

[0065] Matching: Se...

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 an evaluation method and system based on a domain knowledge graph. The method comprises the following steps: acquiring core periodicals and common periodicals of a domain for a to-be-evaluated DKG; expanding three elements of the DKG triad to form a triad expansion set Wi; if the triple matching appears in one sentence of the literature, performing strong correlation counting ST1; if only two elements in the triple appear in the same sentence, performing inconsistent counting ST2; if two or more elements in the triple are in one paragraph, performing weak correlation counting ST3; v = [v1, v2, v3] representing the correlation degree of the triad and the literature, and the correlation intensity quantity s of the triad and the literature = alpha1v1 + alpha2v2 + alpha3v3; the mass q of the triple is equal to alpha1v1-alpha2v2. According to the method and the system, the triad is directly matched with the text, the process of extracting the triad from the text is omitted, and the relationship between two triads does not need to be considered.

Description

technical field [0001] The present invention relates to the field of knowledge graph evaluation, in particular to an evaluation method and system based on domain knowledge graph. Background technique [0002] Knowledge graph is a recent and rapidly developing branch in the field of artificial intelligence. Because knowledge graphs allow machines to master and use knowledge and possess cognitive intelligence, which opens the door for deeper and wider applications of artificial intelligence. Although Domain Knowledge Graph (DKG for short) is limited in scope compared with General Knowledge Graph (GKG for short), it may become the first technology to be implemented because of its high data quality and closeness to industry applications. At present, industry knowledge graphs in the fields of finance, medical care, agriculture and law have achieved good application results. It also includes the use of industry knowledge graphs to evaluate existing technical achievements. For ex...

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): G06F16/36G06F40/242G06F40/247G06F40/289
CPCG06F16/367G06F40/242G06F40/247G06F40/289
Inventor 郑传双樊向东韩红玉万享
Owner 深圳市曙光信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com