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

Knowledge graph construction method and device and electronic equipment

A technology of knowledge map and construction method, which is applied in the field of electronic equipment, knowledge map construction method, and device, and can solve the problems that concepts and upper-lower relations cannot be extracted

Active Publication Date: 2020-01-10
HITACHI LTD
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this time, the existing knowledge map construction methods cannot accurately and effectively extract concepts and hyponymy relationships from non-defined domain texts

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
  • Knowledge graph construction method and device and electronic equipment
  • Knowledge graph construction method and device and electronic equipment
  • Knowledge graph construction method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] An embodiment of the present invention provides a method for constructing a knowledge map, such as figure 1 shown, including:

[0056] Step 101: Perform word segmentation and syntactic dependency analysis for each sentence in the text to be processed to obtain word segmentation results and word sequence databases;

[0057] In this step, the sentence can be segmented first, and then based on the word segmentation result, the syntactic dependency analysis of each sentence is performed, and then the word segmentation result is corrected according to the syntactic dependency analysis result to obtain a word sequence library including word sequences of all sentences .

[0058] Step 102: Screen out frequent sequences whose length is greater than the preset first threshold from the word sequence database, and calculate the frequency and promotion degree of each frequent sequence, wherein the frequency indicates that the frequent sequence is in the word sequence The probabili...

Embodiment 2

[0079] The embodiment of the present invention also provides a knowledge map construction device, such as figure 2 shown, including:

[0080] The analysis module 21 is used to perform word segmentation and syntactic dependency analysis for each sentence in the text to be processed, to obtain word segmentation results and word sequence databases;

[0081] The first processing module 22 is used to screen out frequent sequences whose length is greater than the preset first threshold from the word sequence library, and calculate the frequency and promotion degree of each frequent sequence, where the frequency represents the frequent sequence The probability of occurrence in the word sequence library, the degree of promotion represents the correlation between words in the frequent sequence;

[0082] The first update module 23 is used to merge the words included in the frequent sequence whose promotion degree is greater than the preset second threshold and whose frequency is great...

Embodiment 3

[0100] The embodiment of the present invention also provides an electronic device 30 for building a knowledge map, such as image 3 shown, including:

[0101] processor 32; and

[0102] memory 34 in which computer program instructions are stored,

[0103] Wherein, when the computer program instructions are executed by the processor, the processor 32 is made to perform the following steps:

[0104] Perform word segmentation and syntactic dependency analysis for each sentence in the text to be processed, and obtain word segmentation results and word sequence databases;

[0105] Screen out frequent sequences with a length greater than a preset first threshold from the word sequence library, and calculate the frequency and promotion of each frequent sequence, where the frequency indicates that the frequent sequence appears in the word sequence library The probability of , the lift represents the correlation between words in the frequent sequence;

[0106] Combining the words i...

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 knowledge graph construction method and device and electronic equipment, and belongs to the technical field of artificial intelligence. The knowledge graph construction methodcomprises the steps of performing word segmentation and syntactic dependency relationship analysis on each sentence in a to-be-processed text to obtain a word segmentation result and a word sequencelibrary; screening out a frequent sequence of which the length is greater than a preset first threshold from the word sequence library; combining words included in the frequent sequence of which the lifting degree is greater than a preset second threshold value and the frequency is greater than a preset sixth threshold value into a newly added word, and updating the word segmentation result; and establishing a synonym combination according to the updated word segmentation result, updating a word sequence library according to the synonym combination, calculating variant confidence coefficientsamong words in the word sequence, and judging hyponymy concepts among the words according to a calculation result, the variant confidence coefficients representing correlation among the words in the word sequence or among the word sequences. According to the method, the concept and hyponymy relation can be accurately and effectively extracted from the non-defined domain text.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a construction method, device and electronic equipment of a knowledge map. Background technique [0002] The construction of knowledge graph is an important part of natural language processing and machine language. At present, most of the construction methods of knowledge graphs are to extract texts from the Internet, discover concepts from these texts, and determine the upper and lower relationships. Existing knowledge map construction methods often require certain pre-specified sentence patterns when extracting hyponymy relationships, for example, "Deep learning is a type of machine learning method", "Word is a Microsoft Office software specially used for Word processing software", etc. Such sentence patterns can often be found in large numbers in corpora such as manuals and encyclopedic dictionaries. However, in real life, there are also many scenari...

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): G06F16/36
CPCY02D10/00
Inventor 郑萌耿璐李岚
Owner HITACHI LTD
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