Product recommendation method, device, electronic device and storage medium

Abstract

The embodiment of the present invention discloses a commodity recommendation method, device, electronic equipment, and storage medium, wherein the method includes: determining the inherent feature matrix of the current period of the commodity, the score matrix of recommended exploration commodities for the current period, and the reinforcement learning of the current period Parameter vector; based on the inherent feature matrix of the current period, the recommended exploration commodity score matrix of the current period and the reinforcement learning parameter vector of the current period to determine the initial ranking result vector of the commodities in the current period; based on the commodity in the current period The initial ranking result vector and the actual product sales ranking result determine the current cycle product sorting intermediate result vector; the current cycle product recommendation result is determined based on the current cycle product sorting intermediate result vector. The technical solutions provided by the embodiments of the present invention can have a faster response speed for high-quality commodities or popular commodities, the recommended commodities are highly attractive, and the overall conversion rate is high.

Description

A product recommendation method, device, electronic device and storage medium technical field Embodiments of the present invention relate to data processing technology, in particular to a method, device, electronic device and storage medium. Background technique [0002] With the continuous expansion of the scale of e-commerce, the number of commodity categories and the number of commodities of each commodity category increase rapidly, Due to the large amount of information, users need to spend a lot of time browsing a lot of irrelevant product information to find what they want to buy Therefore, the platform needs to give better product recommendation results to meet the needs of users to purchase products. And in C2M (Customer‑to‑Manufacturer, user direct connection to manufacturing) mode, not only the e-commerce platform will recommend products to users, Manufacturers, namely merchants themselves, will also recommend products to users, but the product recommendat...

AI Technical Summary

Problems solved by technology

However, in the C2M (Customer-to-Manufacturer, user direct manufacturing) mode, not only the e-commerce platform will recommend products to users, but also the manufacturer, that is, the merchant itself, will recommend products to users. However, the product recommendation methods in the prior art, Recommendations are inaccurate and inefficient

Images