Knowledge base alignment method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a knowledge base alignment method and device, computer equipment and a storage medium, and the method comprises the following steps: obtaining a knowledge entity vector set which is a vectorized representation of knowledge entities in a to-be-aligned knowledge base; Inputting the knowledge entity vector set into a preset knowledge entity clustering model to obtain a clustering result of knowledge entities in the to-be-aligned knowledge base; Selecting any two knowledge entities belonging to the same class according to the clustering result, and calculating the similarity between the two knowledge entities; And when the similarity is greater than a set first threshold, combining the two knowledge entities. comparison of the similarity of the two knowledge entities is limited to the same kind of entities, the calculated amount is greatly reduced, clustering is achieved through the artificial intelligence technology, the clustering result betterconforms to the expectation, the similarity calculation integrates the attribute similarity and the vector similarity of the entities, the similarity calculation is more reasonable, and redundant information can be more effectively found and removed.

Description

technical field [0001] The present invention relates to the technical field of knowledge base processing, in particular to a knowledge base alignment method, device, computer equipment and storage medium. Background technique [0002] With the development of the Internet, more and more knowledge bases have been built in various fields, and these knowledge bases are also widely used in Internet applications such as search services and automatic question answering. Knowledge base has positive significance for information sharing and dissemination. However, the information of a single knowledge base is limited, and in some cases it cannot meet the needs of users; and usually the knowledge base is continuously expanded, and the scale of the storage resources occupied is also continuously expanded, but the data that is continuously expanded to the knowledge base may be redundant. In addition, this redundancy causes waste of storage resources, and at the same time, increases the ...

AI Technical Summary

Problems solved by technology

[0004] A common method for knowledge base alignment is to use entity attribute information to determine whether different source entities can be aligned. Since the data of different entities belong to the type of User Generated Content (UGC), the quality of data edited by different users is uneven. Only through It is difficult to accurately determine whether the entity attribute information edited by the user is the same entity

Images