Explainable fashion clothing personalized recommendation method

Abstract

The invention discloses a explainable fashion clothing personalized recommendation method. The method comprises: acquiring historical purchased commodities of a user and corresponding commodity images; constructing a commodity recommendation model, projecting the commodity and the user to a semantic attribute space, and scoring the commodity by the user based on the obtained user feature vector and the feature vector of the commodity; positioning the position of each semantic attribute and the preference degree of the user for each semantic attribute in the commodity image; training the commodity recommendation model to obtain a trained commodity recommendation model; and for a user and a series of new commodities, generating a commodity recommendation sequence through the trained commodity recommendation model, and marking the position of each semantic attribute and the preference degree of the user on the image of each new commodity. According to the method, fine-grained semantic attribute level modeling is carried out on commodities and users by carrying out automatic semantic attribute positioning and recognition on the commodities, and accurate personalized recommendation services can be provided for the users.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to View More

AI Technical Summary

Benefits of technology

The technology described in this patented solution allows us to compare different types of clothes (fashion) together rather than just comparing them individually or only considering their overall appearance). This helps people who want to wear these items more easily find what they're looking good without having everything else look bad.

Problems solved by technology

This patented technical solution discusses two main issues: 1) How to efficiently integrate semantic attribute knowledge onto fashionable shoe sales websites by providing customizable suggestions based solely upon customer preference; 2) It involves learning about what each item looks like during purchase decision time through various techniques used overall, including categorization or clustering analysis, color histograms, shape descriptors, texture recognition, and others.

Images