Evaluation method and system based on domain knowledge graph

A technology of domain knowledge and evaluation methods, applied in the fields of unstructured text data retrieval, instruments, computing, etc., can solve the problem of inability to objectively evaluate knowledge graphs, and achieve the effects of strict article review, moderate distribution frequency, and cost savings

Active Publication Date: 2022-03-11
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

[0067] like figure 1 As shown, the evaluation method based on the domain knowledge graph of an embodiment of the present invention includes:

[0068] 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;

[0069] 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 triplet i extended set Wi. If H1 has m elements, T1 has n elements, and R1 has p elements, K is generated by combination i =m×n×p triplets, extract the entity words and relational words of each triplet in the extended set Wi of triplets to form a professional dictionary C in the field after deduplication, if the number of triplets in DKG is Z, then the number of triples after expansion is The value range of y is 1-Z...

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

An evaluation method and system based on a domain knowledge map includes obtaining core journals and general journals in the field for the DKG to be evaluated; expanding the three elements of the DKG triplet to form a triplet extension set Wi; Do strong correlation count ST1 in a sentence; If only two elements in the triplet appear in the same sentence, do inconsistent count ST2; If two or more elements in the triplet are weakly correlated count ST3 in a paragraph; V= [v1,v2,v3] indicates the degree of association between the triplet and the document, the correlation strength between the triplet and the document s=||α1v1||+||α2v2||+||α3v3||; triplet quality q =||α1v1||‑||α2v2||; the above method and system directly match the triples with the text, omitting the process of extracting the triples from the text, and do not need to consider the relationship between the two triples.

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 Patents(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 Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products