Commodity recommendation method and device, storage medium and computer equipment

Abstract

The invention relates to a commodity recommendation method. The method comprises the steps of obtaining first feature information and second feature information of a target commodity; obtaining reference information of candidate commodities matching the first feature information from a preset database containing reference information of a plurality of candidate commodities, and generating a firstrecommendation list; obtaining reference information of candidate commodities matching the second feature information from a preset database to serve as second reference information; obtaining user browsing data of commodity detail pages corresponding to the target commodity and each candidate commodity, and generating a first association degree according to the user browsing data; generating a second recommendation list according to the first correlation degree and the second reference information; and generating a third recommendation list according to the first recommendation list and the second recommendation list, and when a commodity recommendation request of the target commodity submitted by the terminal is received, sending the third recommendation list to the terminal for display.According to the invention, the to-be-recommended commodity of the target commodity is obtained in combination with multiple dimensions, so that the obtained to-be-recommended commodity is more accurate.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a commodity recommendation method, device, storage medium and computer equipment. Background technique [0002] In the era of big data, there are various recommendation algorithms designed to improve the conversion rate of users to purchase products. However, compared with general commodities, users are more inclined to directly locate service commodities through commodity names or keywords in commodity profile information for consumption. How to provide users with products that meet their needs in the shortest possible time and tap users' deep-seated service needs has become a key problem that e-commerce companies need to solve urgently. [0003] Most of the existing recommendation systems only rely on keyword matching or collaborative filtering to recommend products. This product recommendation scheme has a single recommendation dimension, and the recommenda...

AI Technical Summary

Problems solved by technology

This product recommendation scheme has a single recommendation dimension, and the recommendation mechanism is not flexible enough, which may easily lead to inaccurate recommendation results.

Images