Development of a Method for Finding Scientific Partners Based on Document Clustering in the Form of Key Phrase Vectors

The article is dedicated to the development of a method for identifying key phrases in the works of subjects engaged in scientific activities with the aim of automating the process of searching for scientific partners. The method is capable of identifying key phrases from documents, taking into account the context and semantics of the subject area requested by the user in the form of a vector. This method represents an effective tool for the analysis and identification of potential scientific partners.The proposed method is implemented as a software module of the information system for evaluating the scientific activities of universities, research institutes, and their departments. The paper also presents the algorithm of this method, which includes extracting semantic structures, determining the similarity between the identified key words and the user's query, and searching for scientific partners. The results of this research are of interest to scientific fields oriented towards collaboration and partnership in scientific research.