Method, device, equipment and medium for entity alignment

Abstract

The entity alignment method provided by this application can be used for entity alignment in the knowledge base in the field of artificial intelligence, including: obtaining attribute information of all entities, which is text information related to the entity; segmenting the attribute information to obtain a word set ; Obtain the word vector of each word in the word set to obtain the word vector set; according to the word vector set, obtain the text attribute value vector of the text where each word vector is located; according to the text attribute value vector of the text contained in each entity, obtain each The entity similarity vector of the entity; it is determined that two entities whose similarity of the entity similarity vector is higher than a preset value are similar entities, so as to realize entity alignment. The embodiment of the present application also provides a device, equipment, and medium, which convert word vectors into text vectors through natural language processing technology, vectorize entity attribute information, and apply entity text features through semantic analysis. Improved accuracy of entity alignment.

Description

technical field [0001] The present invention relates to the field of computer technology, and more specifically, to a method, device, equipment and medium for entity alignment. Background technique [0002] Entity refers to things that exist objectively and can be distinguished from each other, including specific people, things, things, abstract concepts or connections. For example, if player A's team is team B, then player A and team B are both Entities, their relationship is the relationship between the team and the player, player A ---> team ---> team B, team B ---> player ---> player A. [0003] The knowledge base contains various categories of entities. Entity Alignment, also known as Entity Matching, refers to finding the same entity in the real world for each entity in the heterogeneous data source knowledge base. For example, for the "Zhang San" entity, the encyclopedia information about Zhang San is recorded on the A website, and the brief introduction...

AI Technical Summary

Problems solved by technology

[0006] However, in the actual work process, the accuracy of knowledge map entity information from each source cannot be guaranteed, resulting in noise in the key attributes of entities. When some entities lack records about key attributes, the similarity of attribute values ​​cannot be calculated, resulting in entity alignment. It cannot be realized. At the same time, due to the diversity of text description methods, there is no deep semantic feature using entity text information

Images