Knowledge graph-based entity description extraction method and apparatus, and computing device

Abstract

The invention discloses an entity description extraction method and device based on a knowledge graph and computing equipment. The method comprises the steps: S1, extracting an entity description setof a given entity from a knowledge graph database; s2, for each non-repetitive entity description in the entity description set, calculating the confidence coefficient of the entity description according to the similarity between each non-repetitive entity description and the entity description and the occurrence frequency of each non-repetitive entity description in the entity description set; and S3, screening out at least one entity description from the entity description set as a standby entity description of the entity according to the confidence of each entity description. In the schemeof the invention, when the quality of a certain entity description is quantified, the quantization result is obtained by depending on the frequency of occurrence of each entity description and the similarity between each entity description and the entity description, so that the calculation result is more reliable.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a knowledge map-based entity description extraction method, device and computing equipment. Background technique [0002] Modern search engines are constantly improving their product functions in the process of development to provide users with more comprehensive and convenient information services. Among them, the recommendation system on the right displays the entities related to the user's query to the user in the form of pictures, corresponding names, and category labels, so that users can more easily understand and query other relevant knowledge information, thereby obtaining a good user experience. figure 1 It shows a schematic diagram of the recommendation on the right side when searching for a Pomeranian without a reason for recommendation. Such as figure 1 As shown, users can obtain other knowledge and information related to Pomeranians according to the recom...

AI Technical Summary

Problems solved by technology

However, frequency is only an external factor to measure the quality of knowledge, and it cannot comprehensively measure the quality of knowledge. For example, although some knowledge appears in a low frequency, the quality may be high; Knowledge with the same result cannot be further distinguished

And, another main way is to manually label a batch of high-quality data, and then sort the sentences through sorting learning. This method is time-consuming, labor-intensive, costly, and cannot be expanded well in the open field.

Images