Commodity recommendation method and system
The invention discloses a commodity recommendation method and system. The method comprises the steps of obtaining user comments and commodity comments; inputting the user comments and the commodity comments into the trained commodity recommendation model, and outputting a commodity recommendation re...
Saved in:
Main Authors | , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
14.10.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a commodity recommendation method and system. The method comprises the steps of obtaining user comments and commodity comments; inputting the user comments and the commodity comments into the trained commodity recommendation model, and outputting a commodity recommendation result; wherein the working principle of the trained commodity recommendation model comprises the following steps: respectively coding user comments and commodity comments to obtain a user comment coding result and a commodity comment coding result; respectively carrying out feature extraction on the user comment coding result and the commodity comment coding result to obtain user comment features and commodity comment features; performing weighted interactive fusion on the user comment features and the commodity comment features, and extracting splicing vectors of user comments and article comments from a fusion result; and carrying out score prediction on the splicing vector, sorting the commodities according to a |
---|---|
Bibliography: | Application Number: CN202210813884 |