CROSS-FIELD RECOMMENDATION METHOD AND APPARATUS BASED ON BIG DATA

摘要

A cross-field recommendation method and apparatus based on big data. The method comprises: performing topic modeling separately on the basis of online input records and offline behavior records of users in a specific user set, wherein the users in the specific user set are users having both the online input records and the offline behavior records (S101); determining a transition probability from each online input topic to each offline behavior topic according to a topic modeling result (S102); and for any target user having the online input records, recommending a content of an offline behavior to the target user on the basis of the online input records of the target user and the transition probability (S103). The solution can realize cross-introduction of users among multiple fields, precise marketing for users, precise positioning of potential customers and the like, improving the precision in brand recommendation and user positioning, while greatly increasing the gross merchandise volume (GMV) of offline retail.