Construction system and method of knowledge map

A knowledge graph and relationship technology, applied in the fields of natural language processing and computer information processing, can solve problems such as difficult rule mode to process, not a solution, unable to automate deployment, etc., to achieve strong relationship extraction ability and processing efficiency, The effect of improving efficiency and reducing the cost of manual participation

Active Publication Date: 2018-11-23
ZHONGAN INFORMATION TECH SERVICES CO LTD
View PDF6 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The four sentences all reflect the relationship between spouses. Although there are some characteristics to follow, it is difficult to deal with it purely by rules
Although this solution c

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
  • Construction system and method of knowledge map
  • Construction system and method of knowledge map
  • Construction system and method of knowledge map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] figure 1 is a schematic structural diagram of the knowledge map construction system provided by the embodiment of the present invention, such as figure 1 As shown, the knowledge map construction system provided by the embodiment of the present invention includes the following components: a crawler module, a basic annotation module, a candidate relationship extraction module, a feature extraction module, a relationship classifier training module, and a relationship review module.

[0075] Crawler module, used to crawl text and clean data. Specifically, the crawler crawls relevant information, cleans the text and inputs it to the basic labeling module.

[0076] The basic labeling module is used for basic labeling work including subject completion operations. Specifically, the basic tagging module is used for basic tagging work including word-segmentation (word-seg), part-of-speech tagging (POS), named entity recognition (NER), syntactic dependency analysis (dep-parser),...

Embodiment 2

[0105] Figure 7 It is a schematic structural diagram of the knowledge map construction system provided by Embodiment 2 of the present invention, such as Figure 7 As shown, the knowledge map construction system provided by the embodiment of the present invention includes the following components: crawler module, NLP (Natural Language Processing) basic labeling module, candidate relationship extraction module, feature extraction module, relationship classifier training module, heuristic rules library, relationship auditing module, log analysis module, and feature weighting module.

[0106] The crawler module, NLP (Natural Language Processing) basic labeling module, candidate relationship extraction module, feature extraction module, and relationship classifier training module are the same as the corresponding modules described in Embodiment 1, so they will not be repeated here.

[0107] Heuristic rule base for setting heuristic rules for relation extraction.

[0108] Specifi...

Embodiment 3

[0117] Figure 10 is a flow chart of the method for constructing a knowledge map provided by an embodiment of the present invention, such as Figure 10 As shown, the knowledge map construction method provided by the embodiment of the present invention includes the following steps:

[0118] 301. Crawling text and cleaning data:

[0119] 302. Perform basic labeling work including subject completion operations;

[0120] 303. Extract candidate relationships including candidate relationship sentences and / or relationship entity pairs;

[0121] 304. Perform feature extraction;

[0122] 305. Perform model training according to candidate relationship extraction results and feature extraction results, and construct a relationship classifier;

[0123] 306. Examine and determine the candidate sentence relationships obtained by the relationship classifier, and adjust the relationship classifier accordingly according to the results of the audit determination.

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 construction system and method of a knowledge map, and belongs to the technical fields of natural language processing (NLP) and computer information processing. The system includes: a crawler module, which carries out crawling and data cleaning on text; a basic labeling module, which is used for carrying out basic labeling work including subject completion operations; a candidate relationship extraction module, which is used for extracting candidate relationships including candidate relationship sentences and/or relationship entity pairs, a feature extraction module,which is used for carrying out feature extraction; a relationship classifier training module, which is used for carrying out model training according to candidate relationship extraction results and feature extraction results to construct a relationship classifier; and a relationship audit module, which is used for carrying out audit determination on candidate sentence relationships obtained by the relationship classifier, and accordingly adjusting the relationship classifier according to results of audit determination. The system realizes higher relationship extraction capability, reduces costs of manual participation, and improves efficiency of constructing the knowledge map.

Description

technical field [0001] The invention relates to the technical fields of natural language processing and computer information processing, and in particular to a system and method for building a knowledge map. Background technique [0002] Knowledge graph is a knowledge organization form and specification centered on natural language processing (NLP) and combined with various technologies of applied mathematics, graphics, and information visualization. Recently, knowledge graphs have mature applications in many industries of artificial intelligence, such as search engines, chat robots, smart medical care, smart hardware, etc. Knowledge graphs are divided into industry knowledge graphs and general knowledge graphs. In 2012, Google proposed the concept of general knowledge graphs. The general knowledge map emphasizes the breadth, and it is difficult to generate a unified management of the global ontology layer. Common general knowledge graphs include: Freebase, DBpedia, zhishi...

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
IPC IPC(8): G06F17/30
Inventor 李勇倪博溢周笑添
Owner ZHONGAN INFORMATION TECH SERVICES CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap