Deep-learning-based entity relationship extraction method and device and server

A technology of entity relationship and deep learning, applied in neural learning methods, instruments, dynamic search technology, etc., can solve problems such as difficult extraction of entity relationship patterns, achieve easy maintenance and expansion, and improve connectivity

Active Publication Date: 2018-03-13
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF6 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the above two methods are difficult to comprehensively and accurately extract entities and their entity relationship patterns from massive, unstructured information.

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
  • Deep-learning-based entity relationship extraction method and device and server
  • Deep-learning-based entity relationship extraction method and device and server
  • Deep-learning-based entity relationship extraction method and device and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] An embodiment of the present invention provides an entity relationship extraction method based on deep learning. Such as figure 1 Shown is the deep learning-based entity relationship extraction method of the embodiment of the present invention. The entity relationship extraction method based on deep learning in the embodiment of the present invention comprises the following steps:

[0069] S101. Preprocessing the text to be mined to obtain sentences containing entities and relationships in the text to be mined.

[0070] The preprocessing in this embodiment is a very important step. Specifically, the preprocessing of the text to be mined mainly refers to the sentence segmentation of the input text to be mined, so as to process the text to be mined at the text granularity into the text to be mined at the sentence granularity; and then filter the sentences after sentence segmentation , specifically lexical and syntactic analysis of the sentence to identify the entities ...

Embodiment 2

[0077] An embodiment of the present invention provides an entity relationship extraction method based on deep learning. Such as figure 2 Shown is the deep learning-based entity relationship extraction method of the embodiment of the present invention. The entity relationship extraction method based on deep learning in the embodiment of the present invention comprises the following steps:

[0078] S201. Segment the to-be-mined text into sentences.

[0079] S202. Perform lexical and syntactic analysis on the sentence obtained after the sentence segmentation to identify entities in the sentence, and obtain the sentence containing the relationship of the entity.

[0080] S203, circle all entity pair combinations in the sentence.

[0081] Specifically, S203 includes: A, identifying all entities included in the sentence; B, performing two ordered arrangements on the entities to form possible candidate entity pair combinations.

[0082] That is to say, all entities identified in...

Embodiment 3

[0098] An embodiment of the present invention provides an entity relationship extraction device based on deep learning. Such as Figure 5 Shown is an entity relationship extraction device based on deep learning according to an embodiment of the present invention. The entity relationship extraction device based on deep learning in the embodiment of the present invention includes the following steps:

[0099] The preprocessing module 51 is configured to preprocess the text to be mined to obtain sentences containing entities and relationships in the text to be mined;

[0100] The obtaining module 52 is configured to obtain the entity pair combination existing in the sentence, and the candidate relationship existing in the entity pair combination;

[0101] The first processing module 53 is configured to determine a candidate relationship corresponding to the entity pair combination.

[0102] Specifically, the preprocessing module 51 includes:

[0103] The sentence segmentation...

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 deep-leaning-based entity relationship extraction method and device and a sever. The method comprises the steps that preprocessing is conducted on to-be-mined text, so that sentences containing entities and relations in the to-be-mined text are obtained; entity pair combinations existing in the sentences and candidate relations of the entity pair combinations are obtained;the candidate relations corresponding to the entity pair combinations are determined. According to the embodiment, the relations are not limited in category and field, all words, capable of representing the relations among the entities, of any part of speech serve as mining targets, the relations among the entities can be better described, the entities are not limited in entities limiting the field but are expanded to the total amount of the entities and concepts, and connectivity of a knowledge graph can be effectively improved.

Description

technical field [0001] The present invention relates to the technical field of data processing and data mining, in particular to a deep learning-based entity relationship extraction method, device and server. Background technique [0002] With the development of information technology, a large amount of information is generated and is still growing, such as information in news, blogs, and microblogs. The generated information contains a lot of entities (pairs) and entity relationship patterns among entities. If it is possible to extract various entities and their entity relationship patterns from the generated information, the extracted entities and their entity relationship patterns can be used to perform information retrieval, knowledge mining, and scientific hypothesis generation more effectively. Wait. [0003] There are two commonly used methods for entity relationship mining: one is based on restricted relationship mining under the schema (schema), that is, in the ca...

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): G06F17/30
CPCG06F16/367G06F16/3335G06F16/3344G06N3/08G06F40/216G06F40/295G06N5/01G06F40/211G06F40/284
Inventor 李双婕史亚冰梁海金张扬李京峰
Owner BEIJING BAIDU NETCOM SCI & TECH 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