Virtual Store Tool for Automated Purchase Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional shopping sessions in physical stores are inefficient due to long wait times for customers and idle time for cashiers, as they require manual payment processing and employee presence, even during off-peak hours.
Innovation Solution
A virtual store tool that generates a virtual store to emulate a physical store, using camera feeds to track customer purchases and create a virtual shopping cart, allowing for automated payment processing and verification of purchases through machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual payment processing is used in traditional physical stores, then customers can complete purchases with human assistance, but wait times increase and cashier idle time occurs during non-peak hours
Solution Approach 1:
The system enables customers to shop and checkout automatically without human cashier intervention. Sensors detect items taken from shelves, track them in virtual shopping carts, and automatically charge customers when they exit the store, eliminating the need for manual payment processing and reducing wait times to near zero
Solution Approach 2:
The patent replaces the mechanical system of manual cashier operations with an automated sensor-based detection system. Cameras, weight sensors, and RFID readers automatically track customer movements and item selections, substituting human labor with electronic detection and processing systems
2Measurement precision
If multiple cameras are deployed to track customer shopping sessions, then purchase verification accuracy improves, but system complexity and processing resources increase
Solution Approach 1:
The system divides the store into multiple detection zones with specific cameras assigned to each zone. Each camera focuses on particular shelves or product areas, and the system processes video feeds segment by segment to identify item interactions. This segmented approach maintains high detection accuracy while reducing the complexity of processing all camera feeds simultaneously
Solution Approach 2:
The patent introduces an intermediary processing layer that receives raw video feeds from multiple cameras, processes them through machine learning models, and outputs structured purchase data. This intermediary layer abstracts the complexity of multi-camera coordination from the core detection logic, making the system more manageable while maintaining precision
3Productivity
If traditional cashier systems are used, then payment processing can be completed, but operational costs increase due to employee wages and training
Solution Approach 1:
The automated system eliminates the need for human cashiers to process payments. Customers simply shop and exit, while the system automatically detects items taken, calculates totals, and charges accounts. This maintains continuous payment processing capability while eliminating labor costs entirely
Solution Approach 2:
The system enables continuous payment processing without the interruptions inherent in human-operated cashiers. Sensors continuously monitor the store environment, and the system processes transactions in real-time as customers exit, ensuring uninterrupted service during all operating hours including non-peak times when human cashiers would be idle
Data Source
AI summary
An apparatus includes a processor. The processor receives an algorithmic shopping cart that includes a first set of items determined by an algorithm to have been selected by a person during a shopping session in a physical store, based on a set of inputs received from sensors located within the physical store. The processor also receives a virtual shopping cart that includes a second set of items. Video of the shopping session was captured by a set of cameras located in the physical store and depicts the person selecting the second set of items. The processor compares the algorithmic cart to the virtual cart and determines that a discrepancy exists between the algorithmic cart and the virtual cart. The processor determines a subset of the set of inputs associated with the discrepancy and attaches metadata explaining the discrepancy to the subset. The processor uses the subset to train the algorithm.