CONTENT RECOMMENDATION METHOD BASED ON FUNDAMENTAL USER PREFERENCE

摘要

The present invention relates to a method to recommend content based on a basic preference of a user. The method includes: a step of vectorizing content into a numerical value; a step of dividing a user into virtual users, having at least one basic preference, based on the vectorized content; and a cooperative filtering step of finding a virtual user, similar to a target user, among the virtual users, and calculating a preference for the content of the target user. Therefore, the present invention is capable of providing a higher performance content recommending method by recommending the content from the preference, separated from the user.