Entity behavior extraction method and device, computer device and computer readable storage medium

A behavior and entity technology, applied in the Internet field, can solve problems such as lack of information, incomplete semantics, and inaccurate extraction of entity behavior, to achieve the effect of ensuring integrity and improving accuracy

Active Publication Date: 2019-08-09
湖南星汉数智科技有限公司
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Embodiments of the present invention provide a method, device, computer device, and computer-readable storage medium for extracting entity behavior, aiming at solving the problem that sometimes entity behavior extraction can only express one behavior due to the diversity of existing natural languages ​​in the prior art. Partial information, there will be missing information and incomplete semantics, resulting in inaccurate extraction of entity behavior

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
  • Entity behavior extraction method and device, computer device and computer readable storage medium
  • Entity behavior extraction method and device, computer device and computer readable storage medium
  • Entity behavior extraction method and device, computer device and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following further describes the present invention in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0041] figure 1 Shown is a flowchart of an entity behavior extraction method provided by an embodiment of the present invention. The entity behavior extraction method includes the following steps:

[0042] Step S101: Extract triples from sentences in the pre-acquired corpus through the Open IE function of the NLP tool, where the triples include subject elements, predicate elements and elements to be classified.

[0043] In this embodiment, NLP refers to natural language processing, which is short for English Nnatural Language Processing, and OpenIE refers to open domain information extraction, ...

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 is applicable to the technical field of Internet, and provides an entity behavior extraction method, which comprises the following steps of: extracting a triple from statements in a corpus set obtained in advance; aggregating the triplet with the same core words of the subject element, the predicate element and the to-be-classified element together to obtain a triplet group; on the premise that it is guaranteed that ambiguity is not caused by semantic information defects, determining the shortest triple from the triple groups; dividing a subject element and a predicate element inthe shortest triple into a subject and a predicate of an entity behavior respectively, and dividing to-be-classified elements in the shortest triple into one of an object, time, a place and an organization of the entity behavior; and generating a first entity behavior according to the subjects and predicates of the entity behavior and the categories of the to-be-classified elements. The semanticsand information integrity of the shortest triple selected from the triple groups can be guaranteed, elements to be classified in the shortest triple are accurately classified, and the entity behaviorextraction accuracy is improved.

Description

Technical field [0001] The invention belongs to the field of Internet technology, and in particular relates to a method, device, computer device and computer-readable storage medium for extracting entity behaviors. Background technique [0002] With the development and maturity of various natural language processing technologies, the goals and directions of natural language extraction are constantly deepening and expanding. The more important direction in natural language extraction is entity relationship extraction, that is, from a sentence or a paragraph of free text, discover whether there is a relationship between an entity and other entities, and be able to classify the relationship between the two. Since texts with implicit entity relationships account for an extremely low proportion of open source Internet data, the sentences used to characterize entity actions and entity behaviors in the remaining text play an important role in entity relationship reasoning, character ana...

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 & AuthorityApplications(China)
IPC IPC(8): G06F17/27
CPCG06F40/211G06F40/295
Inventor王志超赫中翮郑敏黄九鸣张圣栋
Owner湖南星汉数智科技有限公司