Commodity recommendation method and system

• Main Authors: LI BINGTING, YIN JIAN, CHANG YUPENG, WU GUOQING, LIU XIAOWEI
• Format: Patent
• Language: Chinese; English
• Published: 14.10.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

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