en.Wedoany.com Reported - To address the challenge of retail stores relying on experienced employees for shelf display decisions due to labor shortages, Fujifilm System Service, in collaboration with JR East Cross Station, launched a demonstration experiment on the 8th at the latter's convenience store chain "NewDays." This experiment utilizes image recognition AI technology and sales data to assist store staff in making product display decisions.
After employees photograph shelves using a tablet terminal, the system's AI automatically identifies each product, links with the store's sales data, and presents the analysis results in a visualized format. This solution aims to help stores achieve standardized store layouts that do not depend on individual experience.
The experiment primarily targets shelves for "beverages" and "snacks," which have a large number of products and high replacement frequency. The system combines regularly updated sales data to visually display the sales trends of each product, thereby verifying the actual effectiveness of the shelf display decision-making assistance mechanism.
Image recognition of products on shelves in physical stores poses significant challenges—product shapes and packaging are similar, and display conditions often lead to appearance variations. Fujifilm System Service has integrated its accumulated product information and operational experience from long-term services to the retail industry, such as new product guidelines and head office-to-store information transmission, with its own image recognition AI technology to achieve high-precision product identification.
In the future, the company plans to further develop functions to assist with product category adjustments and display changes, aiming to promote the commercialization of this system across multiple stores and cultivate it into a service that contributes to increased sales.
The demonstration experiment is being conducted at a NewDays store in Tokyo and will continue until September 30, 2026.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
