A cross-domain recommendation method and device based on user behavior sequence features

Abstract

The invention discloses a cross-domain recommendation method based on user behavior sequence features, which includes: separately obtaining the interaction item sequences of the target user in the auxiliary domain and the target domain, respectively obtaining the target user's interaction item sequences in the auxiliary domain and the The user embedding matrix and item embedding matrix in the target domain, and then the total preference features of the target user in the auxiliary domain and the target domain are respectively obtained through the LSTM layer, and finally processed by the MLP layer to transfer the user’s total preference features in the auxiliary domain to In the target domain, the target user's preference score for each item in the target domain is obtained by calculation, and the target user is recommended to the target user in the next period of time to purchase or visit the item. Applying the technical solution provided by the implementation of the present invention improves the recommendation accuracy of the target domain and improves the recommendation performance. The invention also discloses a cross-field recommendation device based on user behavior sequence features, which has corresponding technical effects.

Description

technical field [0001] The present invention relates to the technical field of recommendation, in particular to a cross-domain recommendation method and device based on user behavior sequence features. Background technique [0002] With the continuous development of mobile Internet technology, the amount of information in the network is rapidly expanding and increasing exponentially, and the problems of information overload and information wandering on the network are becoming more and more serious. In order to provide users with satisfactory information and services, recommender systems emerged as the times require, and have become a research field that many researchers pay attention to. The recommendation system performs information filtering by predicting the user's preference for information resources. [0003] In the field of recommendation systems, data sparsity and cold start are still challenging problems, and researchers have proposed many solutions. In recent yea...

AI Technical Summary

Problems solved by technology

However, due to the lack of full use of the data information of the two fields, this method has certain limitations, and the recommendation performance is not good.

Images