Knowledge representation learning method in combination with entity images and server

A technology of entity image and knowledge representation, applied in the field of artificial intelligence, can solve problems such as ignoring the visual information of entity images, and achieve the effect of improving accuracy

Active Publication Date: 2018-02-27
TSINGHUA UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the vast majority of knowledge representations in the prior art learn the structural information of the main knowledge graph triplet itself, while ignoring the visual information possessed by the entity image

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 representation learning method in combination with entity images and server
  • Knowledge representation learning method in combination with entity images and server
  • Knowledge representation learning method in combination with entity images and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the present invention Examples, not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0023] figure 1 It is a schematic flow chart of a knowledge representation learning method combined with an entity image according to an embodiment of the present invention, such as figure 1 As shown, the knowledge representation learning method combined with entity images provided by the present invention includes:

[0024] S101. According to the acquired entity image, obtain ...

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 representation learning method in combination with entity images and a server. The method comprises the steps of obtaining representations of the entity images corresponding to entities in a knowledge space according to the obtained entity images; according to the representations of the entity images corresponding to the entities in the knowledge space and structure-based representations of the entities, constructing image-based representations of the entities; and according to a triple of a knowledge graph and a preset training model, jointly training the image-based representations of the entities and the structure-based representations of the entities to obtain knowledge representations of the entities. According to the knowledge representation learning method in combination with the entity images and the server, provided by the invention, entity image information can be applied to knowledge representation learning, so that the knowledge representation learning accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a knowledge representation learning method combined with entity images and a server. Background technique [0002] With the rapid development of society, we have entered the era of information explosion, and massive amounts of knowledge and information are generated every day. These multi-source information often have various heterogeneous forms and are stored in unstructured multi-modal ways such as text or images. AI-related applications, such as information retrieval and question-answering systems, require more structured information. With the increasing demand of users for information screening, how to mine and apply knowledge from massive data has become a research problem. [0003] In order to solve this problem, the knowledge graph came into being. The knowledge graph is a structured knowledge storage database, which represents concrete things in the wor...

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): G06F17/30G06N3/08
CPCG06F16/367G06N3/08
Inventor 孙茂松谢若冰刘知远栾焕博
Owner TSINGHUA UNIV
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