Using Virtual Commodities to Influence Similarity Analysis Method and System in Recommender System

Abstract

The present invention provides a method and system for the affecting similarity analysis using a virtual commodity in a recommendation system. The aforementioned method is to access an external database at the time of execution to obtain a plurality of users and the corresponding plurality of user attribute information and plural commodity information, then generates the virtual commodities by each user attribute information and mark the content, then calculates the user's similarity by the weighting institution of user's rating to the commodities and virtual commodities to generate the recommended user commodities, finally, excludes the virtual commodities in the commodity items to generate the actual commodity recommendation information, and provides the recommended information to the recommended users. Compared with the conventional recommendation scheme, the present invention analyzes the commodity and non-commodity information in an unified manner, which can reduce the complexity of the system, improve the efficiency of the overall operation, and solve the problem that the similarity cannot be calculated when the commodity transaction volume is small.

Description

technical field [0001] The invention relates to a product recommendation technical solution, in particular to a technical solution for product recommendation through user purchase or calculation of user similarity by rating the product. Background technique [0002] In order to increase the sales volume of commodities, the current e-commerce system mostly analyzes the historical information and purchase information of multiple users to find out the users with the same or similar purchasing habits, and find out the available information from the association of commodities. Recommended products to users. [0003] Since the past recommendation technical solutions rely heavily on the user's consumption records or browsing records on the online store, the current e-commerce system will not be able to effectively find recommended products if the amount of the aforementioned records is insufficient. [0004] In order to solve the above-mentioned problems, some existing technologie...

AI Technical Summary

Problems solved by technology

[0005] For example, if the e-commerce system obtains commodity consumption information and user community information, two sets of evaluation subsystems for analyzing commodity consumption information and user community information need to be built in the system at the same time. When there are more types of information, more evaluation subsystems need to be tailored, which increases the complexity of the system and the difficulty of maintenance, causing considerable trouble to system developers and managers

Images