Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Knowledge graph mining method, device and equipment and storage medium

A knowledge map and representation technology, applied in natural language data processing, special data processing applications, instruments, etc., can solve the problems of large subjective influence factors, high expert cost, and large manpower input, so as to reduce the cost of manual experience and avoid Effects of subjective influence factors, improvement of determination efficiency and accuracy

Pending Publication Date: 2019-04-23
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, both manual and electronic judgment methods in the prior art need to completely rely on the experience and knowledge of experts, which leads to high cost of experts required for system design and a large amount of manpower input; and due to the subjective influence of experience The factors are large and the reasoning logic is complex, which makes it difficult to standardize experience and integrate it into the system, reducing the efficiency and accuracy of knowledge map mining

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 graph mining method, device and equipment and storage medium
  • Knowledge graph mining method, device and equipment and storage medium
  • Knowledge graph mining method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] figure 1 It is a flow chart of a knowledge graph mining method provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of mining knowledge graphs related to entities and representations, and the method can be executed by a knowledge graph mining device. The method specifically includes the following:

[0030] S110. Generate each candidate entity representation pair according to the entity candidate representation set and / or each user dialogue material.

[0031] In a specific embodiment of the present invention, an entity may refer to a thing or a virtual concept that needs to be judged, and a representation refers to a perceivable and identifiable phenomenon exhibited by a thing or a virtual concept. Correspondingly, an entity is embodied by at least one representation, and an entity is a subject constructed by at least one representation. And then determine the entity by judging the representation.

[0032] Exemplarily, in the me...

Embodiment 2

[0047] On the basis of the first embodiment above, this embodiment provides a preferred implementation of the knowledge graph mining method, which can determine the weights of entity representation pairs based on various methods. Specifically, the determining the weights of each candidate entity representation pair according to the entity information and representation information included in each user dialogue material may also include: taking each candidate representation of the same entity in each candidate entity representation pair as a node set, according to The co-occurrence relationship of each candidate characterization determines the node edge, constructs a candidate characterization graph, and uses a ranking algorithm to determine the weight of each candidate characterization based on the candidate characterization graph; or, uses each user dialogue corpus as a training corpus to determine the The vector representation of the included words, according to the vector r...

Embodiment 3

[0073] Image 6 A schematic structural diagram of a knowledge map mining device provided in Embodiment 3 of the present invention. This embodiment is applicable to the case of mining knowledge maps related to entities and representations. The device can realize the knowledge map described in any embodiment of the present invention. mining method. Specifically, the device includes:

[0074] An entity representation pair generation module 610, configured to generate each candidate entity representation pair according to the entity candidate representation set and / or each user dialogue material;

[0075] An entity representation pair weight determination module 620, configured to determine the weight of each candidate entity representation pair according to the entity information and representation information included in each user dialogue material;

[0076] A key representation determining module 630, configured to determine the key representation of an entity according to th...

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 embodiment of the invention discloses a knowledge graph mining method, device and equipment and a storage medium. The method comprises the following steps of generating each candidate entity representation pair according to a candidate feature set of an entity and / or each user dialogue corpus; determining the weight of each candidate entity characterization pair according to entity informationand characterization information included in each user dialogue corpus; and determining the key representation of the entity according to the weight of each candidate entity representation pair. According to the embodiment of the invention, the subjective influence factors when a worker determines the entity and the representation relationship are avoided, the labor experience cost for determining the entity and the representation relationship and the complex logical reasoning process are reduced, and the determination efficiency and the accuracy of effective representation under the entity are improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of data mining, and in particular, to a knowledge graph mining method, device, device, and storage medium. Background technique [0002] With the development of society, things and phenomena in society tend to be more diversified, and the correct judgment of information is particularly important. [0003] In the prior art, people usually judge intuitively through experience; or, an artificial intelligence-based entity judgment system is designed based on expert experience and inference rules, and judgment results are obtained through user input of representational data. [0004] However, both manual and electronic judgment methods in the prior art need to completely rely on the experience and knowledge of experts, which leads to high cost of experts required for system design and a large amount of manpower input; and due to the subjective influence of experience The factors are lar...

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): G06F16/36G06F17/27
CPCG06F40/295
Inventor 郭辉林义明戴祥鹰
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com