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

A method and system for identifying knowledge domains in text

A technology of knowledge field and recognition method, applied in the field of text data processing, can solve problems such as low recognition efficiency and difficulty in guaranteeing the reliability of domain knowledge

Active Publication Date: 2020-01-24
JILIN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most of the research on knowledge discovery of social media text data is the application and improvement of existing knowledge discovery methods, and there are few discussions on the semantic relationship between entities in text content. Only through the identification and judgment of keywords, the identification efficiency is not high, and the reliability of domain knowledge in text data is difficult to guarantee

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
  • A method and system for identifying knowledge domains in text
  • A method and system for identifying knowledge domains in text
  • A method and system for identifying knowledge domains in text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0090] According to steps S6 to S9, the specific embodiment two is as follows:

[0091] When the relevant domain concept φ and related domain concept τ are not in the same sentence as the target domain concept χ, the formula of the inference rule for extracting entity semantic relations is as follows.

[0092]

[0093] in Represents a sentence set consisting of sentences containing concepts in the target domain and their adjacent sentences, S i represents the current sentence, S i-1 and S i+1 Respectively represent the previous sentence and the next sentence of the sentence where the target domain concept is located.

[0094] According to the above definition, the inference rule corresponding to the inference rule formula is:

[0095] ① When the related domain concept φ appears in the adjacent sentence of the sentence containing the target domain concept, and there are no other related domain concepts in the adjacent sentence, the concept / relation pair is considered to...

Embodiment 3

[0101] For the situation where there are multiple related domain concepts and the collection of multiple target domain concepts, the specific embodiment three is as follows:

[0102] When there are multiple related domain concepts or multiple target domain concepts, the inference rule formula for extracting entity semantic relations is as follows:

[0103]

[0104] in, Indicates either or, in this reasoning formula, the left end means that the multi-domain set is greater than 1 and has never been confirmed as the result of the target domain concept, and the right end means that the multi-field set is greater than 1 and has never been recognized as the result of the target domain concept , Represents a set of concepts in multiple related fields, X=(x 1 ,x 2 ,...,x m ) represents a collection of multiple target domain concepts, represents the set of concept / relation pairs that have been proven to be the result of the concepts in the target domain, where represent co...

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 recognition method of the knowledge field in text. The method comprises the steps that with a judgment of positions of related concept fields and a target concept field, if the number of the related concept fields is unique, a concept / relation pair is found; if the number of the related concept fields is not unique, a relative distance between the related concept fields and the target concept field in the same sentence or the adjacent sentences is calculated; if the relative distance is greater than or equal to the threshold value, the related concept fields which are closer to the target concept field are concept / relation pairs; if the relative distance is less than the threshold value, an analysis and judgment is needed according to a context, so that the matching relation between the knowledge fields in the text can be processed quickly, thereby improving the recognition efficiency of the knowledge fields in the text. The invention further discloses a recognition system of the knowledge field in the text, which has a technical effect with the same requirement of rights and is not specifically repeated here any more.

Description

technical field [0001] The invention relates to the technical field of text data processing, in particular to a method and system for identifying knowledge domains in text. Background technique [0002] The revealing of the semantic relationship between entities in the text is an important prerequisite and guarantee for realizing domain knowledge discovery in the text. At present, most of the research on knowledge discovery of social media text data is the application and improvement of existing knowledge discovery methods, and there are few discussions on the semantic relationship between entities in text content. Only through the recognition and judgment of keywords, the recognition efficiency is not high, and the reliability of domain knowledge in text data is difficult to guarantee. [0003] To sum up, how to improve the recognition efficiency of the knowledge domain in the text is a technical problem to be solved by those skilled in the art. Contents of the invention...

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): G06F40/30G06F40/205G06N5/04
CPCG06F40/205G06F40/30G06N5/046
Inventor 牟冬梅黄丽丽李茵琚沅红戴文浩王萍赵丹宁郑晓月
Owner JILIN UNIV
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