An author disambiguation method based on paper key attribute network

Abstract

The invention discloses an author disambiguation method based on the key attribute network of papers. The key attribute relationship network is a relationship network formed by collecting key attributes in papers and their correlations, respectively forming the relationship between co-authors of papers Network, the relationship network of the same institution, the relationship network of the same field, and finally form the relationship network of the key attributes of the paper. The method of the present invention extracts the title of the paper, the author's organization, and the field of the author and establishes a relational network around the author's name. When disambiguating the author of the paper, the author in the relational network is merged by matching the name of the author of the paper. The field of organization and author can effectively solve the situation that the same name in the paper corresponds to different actual authors. In addition, by combining the name of the paper to match the co-author of the current author to be disambiguated and then matching the co-author again, it can effectively solve the situation that the same actual author has different names.

Description

technical field [0001] The invention belongs to the technical field of disambiguation between authors with the same name and different authors in a paper, and in particular relates to an author disambiguation method based on a paper key attribute network. Background technique: [0002] In recent years, with the development of the Internet, all aspects of people's lives have been closely related to the Internet, and so are academic activities. Most of today's academic achievements can be queried through the Internet. But in the face of massive data, how to accurately query the data we need is particularly important. At present, most of the paper platforms can search through the author, and retrieve the paper information published by the queried author. In this case, the accuracy of the author's name is particularly important. However, in reality, the following two situations usually occur. [0003] One is that the name of the author of the paper published by the same auth...

AI Technical Summary

Problems solved by technology

[0005] The above two situations have caused great difficulties for paper retrieval. In the existing system, many paper search engines directly search for string matching. As the amount of data increases, the retrieved results are very large. To a certain extent, its accuracy cannot be guaranteed, and in most cases, it is necessary to manually screen the results

With the improvement of the accuracy requirements for the author of the paper, there are also many ways to disambiguate the author of the paper, but these traditional methods are only simple matching from the dimensions of organization, keywords, publication information, etc., with the data With the increase of volume, these traditional methods lead to more and more disorganized papers, which require researchers to carry out long-term screening in the later stage

Seriously affected the research efficiency

Images