Commodity category prediction method based on portrait generation

• Main Authors: LIU QING, ZHANG ZHENZHEN, ZHU ZHIYUE, ZHU YANNA
• Format: Patent
• Language: Chinese; English
• Published: 13.10.2023
• Subjects: CALCULATING; 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 relates to the field of commodity classification, in particular to a commodity category prediction method based on portrait generation, and the method comprises the steps: collecting commodity information of a target commodity, inputting the commodity information into a trained portrait generation model, and outputting a commodity portrait of the target commodity; inputting the commodity portrait into a trained classification model, and outputting a first hierarchical category of the target commodity, the first hierarchical category being a category corresponding to a leaf node in a preset category tree; and determining category information of the target commodity based on the first level category and a preset category tree, wherein the category information comprises category information of multiple levels to which the target commodity belongs. According to the invention, the commodity portrait obtained through the portrait generation model can reflect the category characteristics of the first l