Product recommendation method based on image and social tag

Abstract

The present invention discloses a product recommendation method based on an image and a social tag, and mainly solves the problem that the existing recommendation method cannot capture the user preference well. The implementation scheme is: 1. extracting color features, texture features and shape features of a product picture; 2. designing an optimal semantic space: according to the relationship between two of the users, the tag and the product image, constructing a bipartite graph and a neighbor graph, and mapping the three data of the user, the tag and the product image into the same space,that is, the optimal semantic space; and 3. in the optimal semantic space, storing the product pictures in order from near to far according to the Euclidean distance between the user and the product picture, and recommending the top N product pictures closest to the user to the user. According to the method disclosed by the present invention, the similarity between pictures can be more accuratelycalculated, the complex association structure among the three types of objects of the tag data can be effectively processed, better recommendation performance can be obtained, and the method can be used for the personalized recommendation system of e-commerce.

Description

technical field [0001] The invention belongs to the technical field of data mining, and in particular relates to a commodity recommendation method, which can be used in a personalized recommendation system of e-commerce. Background technique [0002] In recent years, with the continuous expansion of the scale of e-commerce, the number and types of commodities have increased rapidly, and customers need to spend a lot of time to find the commodities they want to buy. This process of browsing a large amount of irrelevant information and products will undoubtedly cause consumers who are submerged in the massive information to continue to lose. In order to solve this problem, personalized recommendation system came into being. Personalized recommendation system is an active information service system based on massive data mining to help e-commerce sites provide fully personalized decision support and information services for their customers. [0003] Most of the traditional rec...

AI Technical Summary

Problems solved by technology

However, the rating data cannot directly reflect the user's preferences, such as movie ratings. Using user rating data can only tell whether the user likes the movie, but not the user's specific concerns about the movie.

Therefore, the recommendation system based on user rating data cannot capture the user's specific preferences very well.

Images