Vector representation generation method, device and equipment of knowledge map

A technology of knowledge graph and vector representation, which is applied in the fields of artificial intelligence and computers, can solve problems such as the need to improve accuracy and limited representation ability, and achieve the effect of improving modeling ability, sufficient representation ability, and refined semantic representation
CN110795569BActive Publication Date: 2021-06-15BEIJING BAIDU NETCOM SCI & TECH CO LTD
9 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING BAIDU NETCOM SCI & TECH CO LTD
Publication Date
2021-06-15

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

This application proposes a method, device and equipment for generating vector representations of knowledge graphs, which relate to the field of artificial intelligence technology. The specific implementation scheme is: acquiring knowledge graphs, wherein the knowledge graphs include multiple entity nodes; acquiring the context corresponding to the knowledge graphs type and context data; and generating vector representations corresponding to multiple entity nodes through the context model according to the context data and context type. As a result, a more refined semantic representation of entities in the context is achieved, thereby further improving the accuracy of knowledge graph representation learning.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present application relates to the field of computer technology, in particular to the field of artificial intelligence technology, and proposes a method, device and equipment for generating vector representations of knowledge graphs. Background technique

[0002] The knowledge map is a directed graph structure knowledge base that describes the real knowledge of the world. The goal of knowledge map representation learning is to represent the entities / relationships of discrete symbols in the knowledge map as vectors: on the one hand, the vector representation can retain the structural aspects of entities in the knowledge map On the other hand, it facilitates the use of knowledge graphs for application tasks. At present, in tasks such as information extraction, question answering, and reading comprehension, knowledge graphs are applied and function in the form of vectors.

[0003] Knowledge map representation learning in related technologies learns s...

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