Knowledge graph vector representation generation method, device and equipment

A technology of knowledge graph and vector representation, which is applied in the fields of computer and artificial intelligence, can solve problems such as the need to improve accuracy and limited representation ability, and achieve the effects of improving modeling ability, sufficient representation ability, and improving accuracy
CN110795569AActive Publication Date: 2020-02-14BEIJING BAIDU NETCOM SCI & TECH CO LTD
13 Cites 10 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
BEIJING BAIDU NETCOM SCI & TECH CO LTD
Publication Date
2020-02-14

Smart Images

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

Abstract

The invention provides a knowledge graph vector representation generation method, device and equipment, and relates to the technical field of artificial intelligence, and the specific implementation scheme is that the method comprises the steps: obtaining a knowledge graph, and enabling the knowledge graph to comprise a plurality of entity nodes; obtaining a context type and context data corresponding to the knowledge graph; and generating vector representations corresponding to the plurality of entity nodes through a context model according to the context data and the context type. Therefore,finer semantic representation of the entity in the context is realized, and the knowledge graph representation learning accuracy is further improved.
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