Marketing recommendation method and system based on artificial intelligence and visual perception

Abstract

The invention relates to the technical field of marketing, in particular to a marketing recommendation method and system based on artificial intelligence and visual perception. The method comprises the steps of obtaining a human body key point information graph and an instance segmentation graph according to an obtained shopping mall RGB image; obtaining crowd density according to the human body key point information graph, thereby obtaining a distance threshold value; according to the human body key point information graph and the instance segmentation graph, obtaining a matching result graph; grouping the customers in the RGB image according to the distance threshold and the matching result graph; obtaining an RGB image of each customer according to the instance segmentation map; obtaining theme features of each customer in each group according to the RGB image of each customer in each group, and obtaining group theme features corresponding to each group; and matching shops consistent with the group theme characteristics for each group. According to the invention, the shop consistent with the style of each group is automatically matched for each group and recommended to the customer, so that the time of the customer can be effectively saved, and the shopping experience of the customer is improved.

Description

technical field [0001] The invention relates to the technical field of marketing, in particular to a marketing recommendation method and system based on artificial intelligence and visual perception. Background technique [0002] With the continuous improvement of people's living standards, various large shopping malls emerge in endlessly, and the shops contained in them are becoming more and more diverse. Since the shopping malls have not many floors, but the area of ​​each floor is relatively large, there are many types of shopping malls distributed on each floor. shops. [0003] In many large shopping malls, the sales areas of different products are only divided on different floors, such as the clothing area on the first floor, but there is no detailed division of shops. For the clothing area in the shopping mall, the styles of clothes sold in each store are different, so when customers choose clothes that suit their own dressing style, they often browse many stores with...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of poor shopping experience of customers in the mall, the object of the present invention is to provide a marketing recommendation method and system based on artificial intelligence and visual perception, and the adopted technical solutions are as follows:

Images