Cross-platform commodity recommendation method and device and computer equipment

Abstract

The invention discloses a cross-platform commodity recommendation method, and the method comprises the steps: receiving a commodity recommendation task, and creating an initial crowd package according to a target commodity in the commodity recommendation task; finding out a target user set comprising a target label of the initial crowd package from a user information table comprising first user portrait information of a first category of users of a first platform and second user portrait information of a second category of users of a second platform; performing de-duplication filtering on the target user set, and adding the target user set to the initial crowd package to obtain a target commodity crowd package; and recommending the target commodity to each user in the target commodity crowd package. The invention further provides a cross-platform commodity recommendation device, computer equipment and a computer readable storage medium. According to the method, cross-platform commodity recommendation can be realized, and the commodity recommendation is executed after the user data of the two platforms are fused, so that the recommendation is more comprehensive, and the accuracy is also improved.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a cross-platform commodity recommendation method, device, computer equipment and computer-readable storage medium. Background technique [0002] With the development of Internet technology, more and more users choose to browse, select or purchase the commodities they need online. As the number and types of commodities increase, users often need to spend a lot of time to find the commodities they need. In order to solve this problem, various e-commerce platforms use various forms of recommendation technologies to recommend products to users to varying degrees. Most of the existing recommendation methods are that the e-commerce platform uses the user's browsing, clicking, searching, purchasing and other records on the platform, as well as user information such as the user's own age, gender, active city, consumption level, etc. to make product recommendations for us...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the present invention proposes a cross-platform product recommendation method, device, computer equipment, and computer-readable storage medium, which can solve the above-mentioned problems of insufficient product recommendation and low recommendation accuracy

Images