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

Method for extracting conceptual word meaning development veins based on construction

An extraction method and contextual technology, applied in the computer field, which can solve the problem that knowledge services that evolve in time and space are rarely studied.

Pending Publication Date: 2019-11-26
JIANGNAN UNIV
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the other hand, at present, personalized knowledge services on the Internet are quite mature, but there are few studies on knowledge services that can reflect the evolution of time and space.

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
  • Method for extracting conceptual word meaning development veins based on construction
  • Method for extracting conceptual word meaning development veins based on construction
  • Method for extracting conceptual word meaning development veins based on construction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The specific embodiments of the present invention will be described in detail below in conjunction with the technical solutions and accompanying drawings.

[0054] Such as figure 1 As shown, a construction-based extraction method for the development context of concept word meaning includes the following steps:

[0055] Domain knowledge extraction: Crawl different domain knowledge, perform data cleaning, deduplication and denoising, word segmentation, extract key knowledge based on tfidf, loc, wordvec and other features, and organize and synthesize a space-time domain knowledge document in sequence according to the appropriate time period. Use the word vector tool to map keywords to high-dimensional space, calculate the cosine distance between keyword vectors, use the neighbor distance to define the semantic relationship between knowledge, and form a preliminary neighbor knowledge network, such as figure 2 As shown, the domain knowledge acquisition steps include:

[0...

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 belongs to the technical field of computers, and relates to a method for extracting conceptual word meaning development veins based on construction. The method comprises the following steps: firstly, representing domain knowledge in a knowledge network construction form, analyzing a cognitive semantic relationship with interpretability among knowledge, generating a knowledge construction relationship, and obtaining an interpretation support set of the knowledge; then, under different time-space domains, mining the evolution relation between knowledge pairs, and based on knowledgenetwork construction, carrying out evolution fusion on knowledge in different time domains through a clustering algorithm, finally, extracting evolution veins of the knowledge to help a user to accurately understand the relation between the knowledge, and overcome knowledge defects. The method provided by the invention can be used as an important service content of a domain knowledge system, intelligently and efficiently helps a user to tease the evolution process of knowledge, acquire the relationship between knowledge and analyze key knowledge nodes of domain knowledge development, so thatthe user can find high-quality knowledge resources more easily.

Description

technical field [0001] The invention belongs to the technical field of computers and relates to a construction-based extraction method for the development context of concept word meanings. Background technique [0002] Domain knowledge is a system that expands over time. Those important theoretical laws are constantly cited, novel ideas and viewpoints are constantly generated, and dynamic knowledge growth is always maintained between old and new knowledge. In this process, the subject areas are gradually refined, and the knowledge framework will also change, but scientific knowledge always remains a whole, which reflects the evolution of knowledge. [0003] There is a constructive relationship between knowledge. Any new knowledge cannot be created out of thin air, but must be based on existing knowledge experience. It can be said that new knowledge is the evolution and innovation of existing knowledge. The evolution of knowledge embodies the relationship between inheritance...

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): G06F16/36G06F16/31G06F16/35G06F16/951G06F17/27
CPCG06F16/367G06F16/313G06F16/358G06F16/951
Inventor 谢振平任立园刘渊詹千熠
Owner JIANGNAN 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