Shopping behavior analysis method and device

• Main Authors: SU XUNYUAN, ZHUANG YITANG, XIE HUAIQI, JIN XIAOPING, LIANG MIN, CHEN YUNKAI, OTHER INVENTORS HAVE WAIVED THE RIGHT TO BE MENTIONED, GU MENGTING
• Format: Patent
• Language: Chinese; English
• Published: 10.08.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a shopping behavior analysis method and device, and belongs to the technical field of artificial intelligence. The shopping behavior analysis method comprises the steps: obtaining an image of a shopping region, the image comprising at least one customer; recognizing the position information of the customer in the image through a pedestrian detection algorithm; performing matting processing on the image according to the position information to obtain at least one subimage, one subimage only comprising one customer; performing behavior recognition on the sub-images; classifying the sub-images into corresponding categories, wherein the categories comprise a fetched category and a non-fetched category; and under the condition that the customer takes a certain target commodity for multiple times, defining the customer as an entangled state, and recording the target commodity. By analyzing the image containing the customer, the shopping behavior of the customer is judged, the customer is def