Relation extraction method and system based on knowledge map

A technology of knowledge graph and relation extraction, applied in the field of data mining, to reduce costs and improve the efficiency of relation extraction

Active Publication Date: 2018-05-25
PEKING UNIV SHENZHEN GRADUATE SCHOOL
View PDF6 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, supervised learning methods require a large amount of manually labeled training corpus. With the advent of the era

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
  • Relation extraction method and system based on knowledge map
  • Relation extraction method and system based on knowledge map
  • Relation extraction method and system based on knowledge map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0036] Such as figure 1 As shown, the relationship extraction method based on the knowledge map of the present application, an implementation thereof, includes the following steps:

[0037] Step 102: extract the description attribute of the entity and the shortest path set connecting the entity pair from the knowledge graph.

[0038] In one embodiment, extracting the shortest path set connecting entity pairs may specifically include:

[0039] The knowledge map is regarded as a directed graph, and the combination of the bidirectional breadth-first search algorithm and the depth-first search algorithm is used to extract the connected shortest path set between two entities.

[0040] Step 1022: Extract the shortest path set connecting entity pairs. The knowledge map is regarded as a directed graph. For the current entity pair, the bidirectional breadth-first search algorithm is used to confirm the shortest path length between entity pairs, and then the depth-first search algorit...

Embodiment 2

[0082] Such as figure 2 As shown, an implementation of the knowledge graph-based relationship extraction system of the present application includes a basic information extraction module, a path structure information extraction module, an attribute text information extraction module, and a relationship extraction module. The basic information extraction module is used to extract the description attribute of the entity and the shortest path set connecting the entity pair from the knowledge graph; the path structure information extraction module is used to extract the path structure information of the entity pair according to the shortest path set; the attribute text information extraction module is used to extract the attribute text information of the entity pair according to the description attribute of the entity; the relationship extraction module is used to extract the relationship between the entity pair according to the path structure information and the attribute text inf...

Embodiment 3

[0088] The present application provides a computer-readable storage medium, including a program, and the program can be executed by a processor to implement the method in Embodiment 1.

[0089] Those skilled in the art can understand that all or part of the steps of the various methods in the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, Random access memory, disk or CD, etc.

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 relation extraction method and system based on a knowledge map. The method includes extracting entity description attributes and a shortest path set for connecting entity pairs from the knowledge map; extracting path structure information of the entity pairs according to the shortest path set; extracting attribute text information of the entity pairs according to the entity description attributes; and extracting a relation between the entity pairs according to the path structure information of the entity pairs and the attribute text information. In specific embodiments of the invention, as the entity description attributes and paths for connecting the entity pairs, which are extracted from the knowledge map, are included, a relation extraction model based on the path structure information of the knowledge map and the entity attribute information is constructed, by extracting the path information and attribute information of the knowledge map, latent semantic information is mined from the knowledge map, the collection of corpus and the annotation of a training set are omitted, so that the cost of constructing data sets is reduced, and the efficiency of relation extraction is improved.

Description

technical field [0001] The present application relates to the technical field of data mining, in particular to a method and system for relation extraction based on knowledge graphs. Background technique [0002] With the continuous development of cognitive neuroscience, deep learning and other fields, artificial intelligence has gradually entered various fields and is committed to improving people's lives. It has surpassed the human level in image recognition, speech recognition and other fields. However, in the field of natural language processing, due to the complexity of human language and the diversity of things, the current technology is still unable to fully understand the semantics, so a bridge of semantic connectivity - knowledge graph is needed. The knowledge graph is composed of knowledge and the relationship between knowledge. It is essentially a semantic network. The nodes in the network represent entities (Entities) that exist in the real world, and the edges be...

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): G06F17/30G06K9/62
CPCG06F16/288G06F16/367G06F18/2155G06F18/2414
Inventor 雷凯沈颖温德斯
Owner PEKING UNIV SHENZHEN GRADUATE SCHOOL
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