Commodity recommendation method combining attention network and user emotion

Abstract

The invention discloses a commodity recommendation method combining an attention network and user emotion. The method comprises the steps: 1) extracting the score and comment data of a user for a commodity, carrying out the preprocessing, and constructing a sample set T; 2) continuously training to obtain an attribute matrix W of a corresponding field by adopting an unsupervised learning model andutilizing text data commented in the T; 3) constructing a neural network structure C based on attention; constructing a user preference vector U and a commodity feature vector I by using a W-based memory network and a recurrent neural network as bases and using the predicted emotion score as a weight, calculating a prediction value of a missing score by using the U and the I, and calculating attribute vectors of a current user and a commodity for final recommendation explanation; and 4) performing descending sort according to the predicted scores, recommending the first N commodities to the user, and providing explanation of attribute levels for a recommendation result according to the attribute matrix and the attribute vectors, thereby solving the problems of lack of explanation, difficulty in processing large-scale data and the like of a traditional score prediction recommendation method.

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