Commodity recommendation method and system based on gated graph convolutional network, and storage medium

Abstract

The invention relates to a commodity recommendation method based on a gated graph convolutional network. The commodity recommendation method comprises: modeling a session sequence into an undirected graph, wherein in the undirected graph, one vertex represents one commodity, each edge represents that the user clicks the commodities at the two ends of the edge in two consecutive clicks of the session, and the weight of the corresponding frequency is given to each edge according to the frequency of occurrence of each edge in the session; initializing commodities in all sessions in the session sequence into a unified embedding space to obtain an embedding representation of the commodities in each session, and learning the embedding representation of the commodities in the sessions through a graph convolution network and a gating cycle unit; learning the embedded representation of the session according to the learned embedded representation of the commodity in the session; multiplying theembedded representation of all the commodities and the embedded representation of each session according to the obtained embedded representation of all the commodities and the embedded representationof each session, then performing normalization processing through a softmax function to obtain recommendation scores for all the commodities of each session, and performing commodity recommendation according to the recommendation scores.

Description

technical field [0001] The present invention relates to the technical field of deep learning, and more specifically, to a product recommendation method, system and storage medium based on a gated graph convolutional network. Background technique [0002] With the rapid growth of the amount of information on the Internet, the recommendation system can help users alleviate the problem of information overload, and then effectively help users choose the information they are interested in in many web applications (such as: search, e-commerce, media streaming sites, etc.) . Most existing recommendation systems assume a premise: user profile and historical activity information are continuously recorded. [0003] However, in practice, in many services, the user's information may be unknown, and only the user's historical behavior in the current ongoing session is available. Session is a mechanism used by the server to record and identify users. In a typical scenario such as a shop...

AI Technical Summary

Problems solved by technology

However, in session-based recommendation systems, sessions are usually anonymous and numerous, and user behaviors involved in session clicks are usually limited, so these models are difficult to accurately estimate each user representation from each session. ) to generate effective recommendations

The second point is that the conversion mode between products is very important, but these methods only consider the unidirectional conversion between continuous products, cannot get accurate representation of users and ignore the complex conversion characteristics of products

The first point is to regard a session as an out-degree matrix and an in-degree matrix constructed by a directed graph, which are often very sparse, and each session needs to save two matrices, which consumes space resources

The second point is that when local information is considered in the embedded representation of each session, only the embedded representation of the last product in each session is considered, and the information of the product in each session is not fully utilized.

Images