A Product Recommendation Method Combining Attention Network and User Sentiment

Abstract

The invention discloses a commodity recommendation method combining attention network and user emotion, including steps: 1) extracting and preprocessing user rating and comment data on commodities, and constructing a sample set T; 2) adopting an unsupervised learning model , use the text data of comments in T to continuously train to obtain the attribute matrix W of the corresponding field; 3) Construct an attention-based neural network structure C, use W-based memory network and recurrent neural network as the basis, and use the predicted sentiment score as Weight, construct user preference vector U and product feature vector I, use U and I to calculate the predicted value of missing rating, and calculate the attribute vector of current user and product at the same time, which is used for the final recommendation explanation; 4) according to the predicted rating Sort in descending order, recommend the top N items for users, and provide attribute-level explanations for the recommendation results based on the attribute matrix and attribute vector. The invention solves the problems of lack of interpretation and difficulty in processing large-scale data in traditional score prediction and recommendation methods.

Description

technical field [0001] The invention relates to the technical field of e-commerce, in particular to a product recommendation method combining attention network and user emotion. Background technique [0002] With the advent of the era of big data and the vigorous development of the Internet, e-commerce has emerged as the times require. On the e-commerce platform, users often find it difficult to make choices when faced with a wide range of products, and the recommendation algorithm can use the data accumulated on the e-commerce platform, including user purchases, ratings, comments and other data, to tap the potential interests of users, and then recommend corresponding products. Products of. The purpose of an excellent recommendation algorithm is to make personalized and accurate recommendations to users and provide corresponding explanations, which can not only improve user experience, but also increase the revenue of e-commerce platforms. For users, providing explanation...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, and propose a product recommendation method that combines attention networks and user emotions, which solves the problems of insufficient interpretability and difficulty in processing large data in traditional rating prediction methods, and improves ratings. predictive accuracy and increased interpretability of the method

Images