Store Server Image Recognition for Condition-Based Item Pricing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional information processing systems fail to automatically adjust selling prices based on the condition of items such as discoloration or deformation, which can affect the value of perishable goods like fresh foods.
Innovation Solution
A system comprising a store server and a portable terminal that uses image recognition and machine-learning models to identify item discoloration or deformation, adjusting the selling price accordingly and displaying it on the terminal.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional barcode recognition is used to set selling prices, then the process is simple and quick, but the system cannot detect item condition changes such as discoloration or deformation
Solution Approach 1:
The patent replaces conventional barcode recognition (mechanical/optical scanning) with image recognition and machine learning models that analyze visual characteristics of items. The store server captures images of items, extracts features using deep learning models, and detects discoloration or deformation patterns to automatically adjust selling prices, eliminating the need for manual inspection while achieving accurate condition detection
Solution Approach 2:
The patent introduces an image recognition intermediary system between the customer's portable terminal and the store server. This intermediary includes feature extraction units and machine learning models that process images to detect item conditions, serving as a bridge that enables automatic condition-based pricing without direct human intervention
2Productivity
If manual inspection of item conditions is performed, then accurate pricing can be achieved, but store efficiency and productivity are reduced
Solution Approach 1:
The system enables self-service automatic pricing where the machine learning model independently analyzes item images and determines appropriate selling prices based on detected conditions. The store server automatically processes images, extracts features, compares them with learned patterns, and adjusts prices without requiring store staff intervention, thereby increasing productivity and eliminating time loss
Solution Approach 2:
The patent implements preliminary action by pre-training machine learning models with extensive data on normal and defective item patterns before actual pricing operations. The feature extraction units are pre-configured with learned characteristics of discoloration and deformation, enabling rapid automatic pricing decisions during store operations without time-consuming manual inspections
3Extent of automation
If image recognition and machine learning are used to detect item conditions, then automatic condition-based pricing is achieved, but computational resources and processing time increase
Solution Approach 1:
The patent segments the image processing task into distinct functional modules: image capture, feature extraction, pattern matching, and price determination. Each module handles specific computational tasks independently, allowing optimized resource allocation. The feature extraction unit processes images separately from the pattern matching unit, reducing overall computational burden while maintaining automation
Solution Approach 2:
The system applies partial action by using machine learning models that process only the most relevant visual features of items rather than analyzing every pixel in detail. The feature extraction units identify and process key characteristics (color, shape, texture patterns) that are sufficient for condition detection, avoiding excessive computational energy consumption while achieving accurate automatic pricing
Data Source
AI summary
A system for setting and displaying a selling price of an item, includes a server that stores item information; and a terminal including: a camera, a display, a communication controller, and a processor configured to: capture an image, display the image, and transmit the image to the server, and upon receipt of a selling price of an item from the server, control the display to display the price over the image. The store server is configured to, upon receipt of an image from the terminal: execute image recognition on the image and identify an item, input the image to a machine-learning model trained to recognize a discoloration state or a deformation state of the item in the image, set a selling price for the item based on the discoloration state or the deformation state, and transmit the price to the terminal.