Product recommendation method and device based on behavior analysis, equipment and storage medium

Abstract

The application relates to an artificial intelligence technology and discloses a product recommendation method based on behavior analysis, which comprises the following steps: generating a standard user portrait according to basic information of a user; adding specific behavior information of the user into the standard user portrait and inquiring N users with the specific behavior information as associated users; obtaining associated user portraits of the associated users, calculating distance values between the standard user portrait and the associated user portraits, and determining associated users with the associated user portraits with distance values less than a preset threshold as target users; obtaining specific behavior information of the target users, statistically analyzing preference probabilities of the users to different information according to the specific behavior information of the target users; and generating an information recommendation list in the order of the preference probabilities and outputting the information recommendation list to the user. In addition, the application also relates to a blockchain technology, and the basic information can be stored in a node of the blockchain. The application further provides a product recommendation device, equipment and medium based on behavior analysis. The application can improve information recommendation accuracy.

Images