MACHINE LEARNING METHOD, DEVICE, AND COMPUTER PROGRAM FOR PROVIDING PERSONALIZED EDUCATIONAL CONTENTS ON BASIS OF LEARNING EFFICIENCY

摘要

The present invention relates to a method by which a service server provides user-customized learning content, the method comprising: a step (a) of constructing a question database including one or more multiple-choice questions containing one or more examples about a specific subject, providing the questions to user devices, and collecting, from the user devices, users' example selection data about the questions; a step (b) of estimating probabilities of correct answers to the questions for each of the users by using the example selection data of each of the users; and a step of calculating, for each question, probability change rates of correct answers to all of the questions, included in the question database, of the users on the assumption that certain users have selected respective examples for certain questions, and arranging the questions included in the question database in descending order of the change rates so as to recommend same to the users.