Machine learning method, device and computer program for providing personalized customized content based on learning efficiency

摘要

The present invention relates to a method of providing user-customized learning content in a service server, constructs a problem database including at least one multiple-choice question including at least one option for a specific subject, and solves the problem by a user. A step of providing to the device and collecting the user's option selection data related to the problem from the user device, and a step b of estimating the correct answer rate for the problem of each user using the option selection data of each user. And, assuming that any user selects each option for any question, the change rate of the correct answer rate of the user is calculated for each question in the whole question included in the question database, and the question database is stored. It is characterized by including a step of rearranging the included problems in descending order of the change rate and recommending the problem to the user. [Selection diagram] Fig. 1