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

Text-oriented method for extracting cognitive relationships among knowledge topics

A relation extraction and text technology, applied in text database query, unstructured text data retrieval, special data processing applications, etc., can solve problems such as slow construction process, and achieve the effect of helping learning

Active Publication Date: 2019-08-30
XI AN JIAOTONG UNIV
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, high-quality cognitive relationships between knowledge topics require domain experts to label according to domain knowledge, and the construction process is slow

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
  • Text-oriented method for extracting cognitive relationships among knowledge topics
  • Text-oriented method for extracting cognitive relationships among knowledge topics
  • Text-oriented method for extracting cognitive relationships among knowledge topics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention will be further described in detail below in conjunction with specific embodiments, which are explanations of the present invention rather than limitations.

[0052] Taking Wikipedia as the knowledge source as an example, the Wikipedia entries are extracted to form a knowledge thesaurus, and the extracted entries correspond to the text abstracts of Wikipedia pages to form the text to be recognized. The data acquisition and processing process of Wikipedia is as follows: figure 2 shown. Extracted Wikipedia entries such as image 3 As shown, the content of the abstract of the extracted Wikipedia text is as follows Figure 4 shown.

[0053] The present invention specifically comprises the following steps, see figure 1 :

[0054] (1) Preprocessing the text to be recognized to obtain the preprocessing result text, such as Figure 6 As shown, it mainly includes 5 steps:

[0055] (1.1) Extract the domain terms in the text to be recognized to form a k...

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 provides a text-oriented method for extracting cognitive relationships among knowledge topics, which not only judges the dependency relationships among the knowledge topics, but also hasdirectivity. Learning of knowledge themes can be guided according to the filtered cognitive relationship triple. The method comprises the following steps: (1) preprocessing a to-be-identified text toobtain a preprocessing result text; (2) extracting word features and sentence features influencing the cognitive relationship in the preprocessing result text in combination with the words and sentence layer factors to form a cognitive relationship feature set; (3) utilizing a multi-node marking rule to mark a sentence level sequence through the trained conditional random field model; according to the cognitive relationship feature set, extracting all cognitive relationship triplets in the sentence; and (4) calculating the importance of knowledge subject words in the cognitive relationship triplet, and filtering the extracted cognitive relationship triplet according to a word importance principle so as to extract the cognitive relationship among the knowledge subjects.

Description

technical field [0001] The invention relates to a method for cognitive relations among knowledge subjects, in particular to a text-oriented method for extracting cognitive relations among knowledge subjects. Background technique [0002] The rapid development of information technology and the popularization of the Internet have brought massive digital resources. The huge digital resources have caused great difficulties for learners to quickly, orderly and accurately obtain the required knowledge, and it is easy to cause problems such as learning lost. Therefore, how to alleviate this problem has become one of the urgent problems in the information field. Its core is how to realize the Internet information with huge data and lack of information, according to the internal connection between knowledge topics, that is, the cognitive relationship between knowledge topics, and organize knowledge topics together in an orderly manner. Taking knowledge topics as the main research ob...

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): G06F17/27G06F16/335G06F16/33
CPCG06F16/335G06F16/3344G06F40/242G06F40/216G06F40/295G06F40/30
Inventor 刘均麻珂欣曾宏伟任若清
Owner XI AN JIAOTONG 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