Scientific literature key content potential association mining method based on graph neural network

Abstract

The invention discloses a scientific literature key content potential association mining method based on a graph neural network, and the method comprises the following steps: S1, obtaining scientificliterature data related to a certain specific event, and carrying out the data cleaning and preprocessing; s2, extracting a literature content keyword by utilizing a TF-IDF method; s3, constructing aword co-occurrence network for the extracted keywords and references to which the keywords belong by taking sentences as units; s4, learning vector representation of the keywords by using a graph convolutional neural network; and S5, obtaining the relevancy between different keywords by utilizing a similarity calculation function, and mining the potential incidence relation of the different keywords. According to the method, modeling is carried out on the keyword relationship extracted from the article content, and the potential association of the main keywords of the literature is mined by utilizing the graph convolutional neural network technology, so that the analysis requirement on the scientific literature content is met, and the correlation of the scientific literature in different fields is analyzed; and an effective method is provided for systematic analysis of scientific literatures.

Description

technical field [0001] The invention relates to the technical field of document analysis, in particular to a method for mining potential associations of key contents of scientific documents based on a graph neural network. Background technique [0002] Graph neural network is currently being gradually applied in the field of natural language processing, such as text classification, information retrieval, machine translation and other tasks. As a common data set in natural language, scientific literature data refers to the data composed of paper information and author information. Based on the paper references and author information provided by the scientific literature data, a bipartite network composed of scientists and papers, a scientist cooperation network, a scientific citation network, a journal-paper coupling network, a scientific research unit-paper coupling network, etc. can be established. [0003] In recent years, with the development of complex network research, ...

AI Technical Summary

Problems solved by technology

[0003] In recent years, with the development of complex network research, effective methods and tools have been provided for the systematic analysis of scientific literature, and related analysis software such as CiteSpace and Sci2 have been developed, which can analyze the topological structure, evolution model and evolution mechanism of the above-mentioned network. In addition to the basic information of scientific literature, the content of articles in scientific literature itself also contains rich information, but the existing literature analysis methods have not made full use of it.

Images