Generating recommended items in unfamiliar domain

Abstract

The present invention provides a method and apparatus for generating recommended items for a current user in an unfamiliar domain. The method includes selecting a reference user of the current user, in a reference domain different from the unfamiliar domain, wherein the behavior of the current user and the behavior of the reference user have a user similarity index in the reference domain which satisfies a condition. The method further includes generating the recommended items in the unfamiliar domain for the current user according to history behavior data of the reference user in the unfamiliar domain. Even if there is little or no history behavior data of the current user in the unfamiliar domain, an effective recommendation can be made to the current user. To carryout the steps of the method, the apparatus includes a reference user determining module, a current user recommending module and a demarcating module.

Dependencies are inferred from the claim text.