Interactive movie recommendation system and method based on graph neural network and reinforcement learning

Abstract

The invention discloses an interactive movie recommendation system and method based on a graph neural network and reinforcement learning, and aims to realize optimization of user experience within a period of time. Meanwhile, the movie similarity undirected graph is constructed through historical interaction data of the user, more accurate movie expression is obtained, and movie recommendation accuracy is improved. According to the technical scheme, the design is divided into four modules, namely a composition module, a movie vector generation module, a user vector generation module and a recommendation module. The method comprises the steps of constructing a movie similarity undirected graph, constructing a graph neural network to obtain a movie vector representation matrix, constructing an attention module to extract and fuse information contained in a user movie watching history to obtain user vector representation, constructing a multilayer perceptron model to fit a recommendation strategy, and sorting according to state action values and generating recommended movies. The invention provides construction of a movie similarity undirected graph, and movie recommendation accuracy is effectively improved through introduction of a graph neural network.

Description

technical field [0001] The invention belongs to the technical field of interactive recommendation, and in particular relates to an interactive movie recommendation system and method based on graph neural network and reinforcement learning. Background technique [0002] With the advent of the big data era, both users and platforms are facing the problem of information overload. Therefore, the platform hopes to filter effective information for users through a personalized recommendation system, improve user experience and promote platform revenue at the same time. Personalized recommendation systems have been widely used in various fields of the information industry such as e-commerce platforms, video sites, and social media. [0003] Traditional personalized recommendation systems can be divided into user-based personalized recommendation, content-based personalized recommendation and collaborative filtering-based personalized recommendation. Traditional personalized recomm...

AI Technical Summary

Problems solved by technology

[0006] Purpose of the invention: Aiming at the problem of low recommendation accuracy of the recommendation method based on reinforcement learning, the present invention designs a new type of movie similarity undirected graph, and combines graph neural network to realize an interaction based on graph neural network and reinforcement learning Movie Recommendation System and Method

Images