COMMODITY RECOMMENDATION METHOD AND APPARATUS

• Main Authors: DING JINGTAO, LI YONG, JIN DEPENG
• Format: Patent
• Language: Chinese; English
• Published: 25.12.2018
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

Embodiments of the present invention provide a commodity recommendation method and apparatus. The method comprises the following steps: obtaining a number of a user, inputting the number of the user into a preset Bayesian personalized sorting model, and obtaining a prediction preference of the user for commodities according to the output of the preset Bayesian personalized sorting model; a list ofrecommended items for the user being obtained according to the user's predicted preferences for the items. According to the merchandise recommendation method and apparatus provided by embodiments ofthat present invention, by using the auxiliary feedback data of users and based on the traditional Bayesian personalized ranking model, the prediction preferences of users for commodities can be obtained, and the list of recommended commodities can be obtained. The user preferences can be modeled more accurately, the auxiliary feedback data of users can be utilized effectively, and the precision of recommendation results c