Knowledge extraction method and device

A knowledge extraction and knowledge technology, applied in the computer field, can solve the problems of waste of manpower, high labor cost and low accuracy, and achieve the effect of improving the extraction effect, reducing labor cost and reducing waste.

Active Publication Date: 2019-09-24
IFLYTEK (SUZHOU) TECH CO LTD
View PDF19 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] One completion method is to use crowdsourcing to extract triples to complete the knowledge map, but this method will waste a lot of manpower, and the labor cost is relatively high; another completion method is intelligently from unstructured Extracting triples from the text to complete the knowledge map, but the difficulty and low precision of processing unstructured text makes the triple extraction results not ideal and the knowledge extraction effect is poor

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 extraction method and device
  • Knowledge extraction method and device
  • Knowledge extraction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] see figure 1 , which is a flow chart of the knowledge extraction method provided by the method embodiment of the present application.

[0032] The knowledge extraction method provided in the embodiment of the present application includes steps S1-S3:

[0033] S1: Obtain a first set of tables, each table in the first set of tables is a table with knowledge.

[0034] Among them, the table with knowledge refers to the table that can provide useful information for the target knowledge graph, for example, the table with knowledge can be Figure 2 to Figure 4 the table shown. Conversely, non-knowledge tables refer to tables that cannot provide any useful information for the target knowledge graph, for example, non-knowledge tables can be used for page layout or for navigation, etc.

[0035] The present application does not limit the source of the first table set, for example, the first table set may come from the Internet. In order to facilitate explanation and understand...

Embodiment 2

[0066] It should be noted that the second method embodiment will mainly introduce the specific implementation of the action "identify the type of the tables in the first table set" (hereinafter referred to as the type identification process) in step S2 of the first method embodiment.

[0067] In this application, the specific implementation of the type identification process is associated with "at least one target form type", and different target form types may correspond to different implementations of the type identification process. For ease of explanation and understanding, four implementations of the type identification process will be described below as examples.

[0068] As a first implementation manner, the identification process of the first type of table may specifically be: identifying the first type of table in the first table set according to the number of attribute names and relationship names belonging to the first target set in the first column of the tabl...

Embodiment 3

[0132] The third method embodiment will mainly introduce the specific implementation of step S3 in the first method embodiment.

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 knowledge extraction method and device. The method comprises the steps of obtaining a first table set, performing type identification on the first table set, obtaining each semi-structured table under at least one target table type as the first target tables, and extracting knowledge information capable of being used for complementing the target knowledge map from the first target tables based on table layout characteristics of the first target tables, so as to automatically complement the target knowledge map by utilizing the knowledge information, thereby realizing automatic complementation of the knowledge map. Manual participation is not needed in the whole automatic compensation process, so that the labor cost expense is reduced, and the waste of manpower resources is reduced. Besides, due to the fact that the table layout characteristics can affect the extraction effect of the knowledge information, when the knowledge information in all the first target tables is extracted based on the table layout characteristics of all the semi-structured first target tables, the knowledge information can be extracted rapidly, and the extraction effect of the knowledge information is improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a knowledge extraction method and device. Background technique [0002] At present, due to the continuous update of knowledge, it is necessary to use new knowledge to complement the original knowledge graph on the basis of the original knowledge graph. [0003] One completion method is to use crowdsourcing to extract triples to complete the knowledge map, but this method will waste a lot of manpower, and the labor cost is relatively high; another completion method is intelligently from unstructured Triplets are extracted from text to complete the knowledge map, but it is difficult to deal with unstructured text and the accuracy is low, which makes the triplet extraction results not ideal and the knowledge extraction effect is poor. Contents of the invention [0004] The main purpose of the embodiments of the present application is to provide a knowledge extraction ...

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): G06F16/36G06F17/27G06F16/35
CPCG06F16/367G06F16/35G06F40/295
Inventor 李直旭宋晓兆陈志刚
Owner IFLYTEK (SUZHOU) 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