A Personalized Recommendation Method Based on Graph Autoencoder

Abstract

The invention discloses a personalized recommendation method based on a graph autoencoder, which utilizes the interactive behavior between users and items to construct an adjacency matrix, and performs normalization processing on it, uses a graph convolution network to perform convolution operations, and obtains nodes Hidden layer representation; use user comment text and item description text as the source of node information to obtain the initial feature vector of each node, and then use graph attention network to aggregate neighbor node features and update node information; use user and item attribute features , build a fully connected network to calculate the hidden layer features; splicing the hidden layer features to obtain new node information, construct a fully connected network, encode, and use a bilinear decoder to reconstruct the user's rating of the item as a predicted score, for the obtained The prediction score of the Top‑N recommendation is used to generate a list of recommended items. The invention can more accurately help analyze the user's preference for items, find out the user's focus, and thus make more effective recommendations.

Description

technical field [0001] The invention relates to the technical field of text classification, deep learning, and recommendation system research, and in particular to a personalized recommendation method based on a graph autoencoder. Background technique [0002] With the continuous development of Internet technology, network information has grown explosively, but the rapid growth has also brought about the problem of information overload. Therefore, the importance of the process of accurately finding out what users are really interested in from a large amount of information is self-evident, and the proposal of the personalized recommendation algorithm is used to solve this problem, and it has gradually become an important aspect in the development prospect of the Internet. A big hot spot. [0003] Traditional recommendation methods such as collaborative filtering recommendation technology generally use user rating data on items to obtain user preferences. Although the algorit...

AI Technical Summary

Problems solved by technology

[0006] (2) The same rating given by the user cannot identify the user's concerns well

For example, when users give 5 points to the same item, some users focus on quality, while others focus on price. It is difficult for general recommendation systems to identify this difference.

Images