PERSONALIZED RECOMMENDATION SYSTEM FOR MATCHING USER AND CONVERSATION PARTNER BASED ON INTEGRATION OF MACHINE LEARNING MODELS AND THE OPERATION METHOD THEREOF

摘要

In the computer program stored in a computer-readable storage medium according to various embodiments of the present application, the computer program includes instructions for causing a processor of a server to perform the following steps, the steps being: through a first questionnaire, Performing preprocessing on first text data included in a response received from a user to extract and merge features of the first text data; Performing preprocessing on second text data included in responses received from a plurality of partners through a second survey to extract and merge features of the second text data; A plurality of sets of at least one topic model corresponding to each method through LDA, NMF, LSI, and BERTopic methods using the extracted and merged features of the first text data and features of the second text data. generating a topic model; generating a partner pool by extracting at least one partner having second text data that shares features and topic models of the first text data; Applying principal component analysis to the second text data of at least one partner included in the partner pool and the first text data of the user to reduce the dimensionality and calculate the degree of similarity between the user and the at least one partner; and selecting partners whose similarity exceeds a preset threshold to create a recommended partner pool.