A recommendation system and a recommendation method based on attention mechanism

Abstract

The invention provides a recommendation system and a recommendation method based on an attention mechanism, wherein the merchandise in the user history and the merchandise to be predicted are mapped to the feature vector of the merchandise through the feature embedding layer, according to the self-attention mechanism, the attention layer learns the user's expression to obtain the user's feature vector, a prediction value for the merchandise from a user is output according to the feature vector of the merchandise and the feature vector of the user through a fusion output layer. The invention provides a recommendation system based on attention mechanism, which adopts a neural attention mechanism to automatically distribute weights to each merchandise in a user's history record, so that the interpretability is enhanced. The invention outputs a prediction value of the user to the merchandise according to the characteristic vector of the merchandise and the characteristic vector of the userthrough a fusion output layer. The neural attention mechanism can be used to simulate user behavior more reasonably and get finer grained weights so as to obtain better recommendation effect.

Description

technical field [0001] The invention relates to the technical field of big data, in particular to an attention mechanism-based recommendation system set recommendation method. Background technique [0002] With the increase of Internet users and the accumulation of information on the Internet, it has become a hot topic in the computer field to automatically recommend products that users may be interested in based on user history records. For how to recommend the products that users really need in the massive information, the existing methods have the problem of poor interpretability. [0003] For example, item-based collaborative filtering methods explain recommendation results by computing cosine similarity or Pearson similarity of items. But this explanation is often the same, such as: "This item is similar to something you bought before". Due to shallow feature learning, complex and high-level product features cannot be obtained, resulting in a recommendation system tha...

AI Technical Summary

Problems solved by technology

Due to shallow feature learning, complex and high-level product features cannot be obtained, resulting in a recommendation system that cannot describe the user's interest well. Only the similarity between individual products can be explained, which severely limits the recommendation system. interpretability

Images