Literature recommendation system and literature recommendation method

Abstract

The invention provides a literature recommendation system and a literature recommendation method. The system comprises a literature information acquisition module used for acquiring literature information; a semantic calculation module which is used for calculating the semantic similarity of the literatures based on the literature abstracts and sorting the literatures according to the semantic similarity; a subject evaluation module which classifies the literatures based on subject terms of the literatures and ranks the literatures according to the similarity of the subject terms, and the subject terms are determined based on abstracts and medical subject terms of the literatures; an influence analysis module which is used for determining the influence of the literature based on the influence score of the literature and the influence score of the author, and sorting the literature based on the influence; a knowledge graph construction module which is used for constructing knowledge graphs on the basis of the literature sorting results; and a comprehensive display module which is used for outputting a result in a visual map mode. When the system is applied to document recommendation, the comprehensive information of the documents can be comprehensively displayed, the recommendation accuracy is improved, and the recommendation content is more visual.

Description

technical field [0001] The invention relates to the field of biomedicine, in particular to a document recommendation system and a document recommendation method. Background technique [0002] While the field of life sciences has made great progress in recent years, it is also facing many problems. On the one hand, the output of academic papers has grown exponentially. Excessive information makes it difficult for researchers to find documents, track concerns, and see the relationship between documents. On the other hand, information or knowledge descriptions are not uniform, resulting in a lack of correlation. How to efficiently find and use these new research results has become a major problem for scientific researchers. [0003] The literature recommendation system aims to help researchers reduce information overload, find relevant papers through calculation and ranking, and recommend the top N papers that are highly relevant to the current paper. Different document recomm...

AI Technical Summary

Problems solved by technology

[0004] Although these methods can give some documents as recommendation results, due to poor results, insufficient description information, and lack of relationship between documents, it is difficult for researchers to have a comprehensive and clear thinking

Images