E-commerce recommendation method based on dynamic interest group identifier and generative adversarial network

Abstract

The invention relates to the technical field of data analysis and recommendation systems, in particular to an e-commerce recommendation method based on a dynamic interest group identifier and a generative adversarial network, which comprises the steps of inputting scoring characteristics of user behavior data, performing prediction by using a trained scoring prediction model, and outputting a scoring prediction value by the scoring prediction model, and generating a recommendation list according to the predicted value of the score to recommend items for the user. The generative adversarial network is utilized to compensate the data, interest group categories are identified for the compensated data, the problems that the user has no interest preference information and interest is generalized are solved, and the invention has important application value for the user and a merchant.

Description

technical field [0001] The invention relates to the technical field of data analysis and recommendation systems, in particular to an e-commerce recommendation method based on a dynamic interest group identification and a generated confrontation network. Background technique [0002] With the development of information technology and the Internet, people have gradually entered the era of information overload from the era of information scarcity. In this era, both information consumers and information producers have encountered great challenges: as an information consumer, it is very difficult to find the information they are interested in from a large amount of information; as an information producer, How to make the information produced by oneself stand out and attract the attention of the majority of users is also a very difficult thing. The recommendation system is an important tool to solve this contradiction. The task of the recommendation system is to connect users an...

AI Technical Summary

Problems solved by technology

Although the user interest group has a clear identification, the identification of the interest group has not been dynamically changed over time, so that the score prediction has no preference relationship, resulting in inaccurate recommendation results.

[0007] 3. Multidimensional complexity of feature space

Considering the addition of user interest group features, how to transform data dimensions and compress data is facing difficulties

Images