First neural network processing item usage history data and second neural network processing item usage and user taste history data to determine user-preferred item candidates and user taste information

Abstract

The disclosure relates to an artificial intelligence (AI) system, which imitates functions of the human brain, such as recognition and determination, using a machine learning algorithm such as deep learning, and an application thereof. A computing device includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to execute the one or more instructions to: using at least one neural network, infer user-preferred item candidates and user tastes based on user information; and select and provide an item suited to the user tastes from among the user-preferred item candidates.