A session sequence recommendation method and system based on a graph convolutional neural network

Abstract

The invention provides a session sequence recommendation method and system based on a graph convolutional neural network, a directed graph is constructed for each session sequence, and for each directed graph, the directed graph is input to the graph convolutional neural network to obtain the hidden representation vectors of all nodes. Based on the implicit representation vectors of the obtained nodes, a soft attention mechanism network is used for generating a global preference vector and a local click preference vector, wherein the global preference vector and the local click preference vector are both composed of implicit representation vectors of the nodes, and then each session sequence is represented as a combination of the global preference vector and the local click preference vector of the user in the session. And for each session sequence, the probability that each item becomes a next click is predicted according to the combination of the calculated global preference vector and the local click preference vector of the user in the session. Some noises in an original vector space are removed by introducing global and local implicit vector representations, and a more accurate prediction effect is obtained.

Description

technical field [0001] The present disclosure relates to the field of computer processing technology, in particular to a method and system for recommending conversation sequences based on graph convolutional neural networks. Background technique [0002] With the rapid growth of information available on the Internet, information overload has always been criticized by users. The recommendation system can help users get the desired information quickly and accurately. Most existing recommender systems assume the ability to continuously record user activities. However, in many cases, the user's personal identity may not be known to the website side, and only the user's behavior history during the current ongoing session is known to the website. Therefore, it is meaningful to model limited behaviors in a session and make content recommendations accordingly. In contrast, traditional recommendation methods that rely on sufficient user-item interactions are prone to inaccurate re...

AI Technical Summary

Problems solved by technology

It can be seen as a local factor affecting user clicks in session-based recommendations, but these methods only consider the one-way conversion between consecutive click items, ignoring the conversion relationship between context (other click items of the user)

Images