Calibrated Camera Task Generation for Hardware-Light Retail Placement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Retailers face challenges in arranging products in stores to optimize sales, enhance shopping experiences, and manage inventory efficiently, which existing technologies like RFID tags and smart shelving cannot fully address, and implementing these solutions is costly.
Innovation Solution
A computer-implemented method using a mobile electronic device with a calibrated camera and machine learning model to generate tasks for product arrangement in a store, including actions and positions, which can be displayed as AR objects, guiding users through the process without requiring costly hardware installations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If RFID tags and smart shelving are implemented to monitor product levels and automate reordering, then automation and productivity are improved, but device complexity and implementation cost increase significantly
Solution Approach 1:
The patent uses image capture devices to create visual copies of product shelves and states. Instead of implementing physical RFID tags and smart shelving hardware, the system captures images of the store environment and processes these visual copies to extract product information, monitor stock levels, and generate reordering tasks. This eliminates the need for expensive physical sensors and tags while achieving the same monitoring functionality.
Solution Approach 2:
The patent replaces the mechanical and electronic hardware system (RFID tags, readers, smart shelving) with a software-based image processing system. Machine learning models process captured images to detect product positions, identify items, and monitor inventory levels, substituting physical sensing mechanisms with optical capture and algorithmic analysis.
2Measurement precision
If RFID tags and smart shelving are deployed throughout the store, then measurement precision of product levels is improved, but implementation cost and device complexity worsen
Solution Approach 1:
The system creates detailed visual copies of shelf states through image capture. Machine learning models process these images to precisely determine product positions, stock levels, and arrangement compliance, achieving measurement precision comparable to physical sensors without requiring tag attachment to each product or installation of smart shelving infrastructure.
3Productivity
If a comprehensive system for strategic product placement optimization is implemented, then productivity and sales optimization are improved, but device complexity and implementation cost increase
Solution Approach 1:
The patent creates a universal task generation system that handles multiple retail operations through a single image processing platform. The same machine learning models and image capture infrastructure support product inventory monitoring, product placement verification, reordering task generation, and strategic arrangement optimization, eliminating the need for separate specialized systems for each function.
Solution Approach 2:
The system uses visual copying of store states to enable strategic decision-making. By capturing and analyzing images of current product arrangements, the system generates optimized placement recommendations and task instructions, providing comprehensive retail management capabilities through software analysis rather than hardware control mechanisms.
Data Source
AI summary
The present disclosure relates to a computer implemented method for generating a task to be performed in a real space. The method comprising: obtaining i) a first image captured by a camera of a first mobile electronic device being calibrated in a virtual representation of the real space such that the first mobile electronic device has a known pose in the virtual representation of the real space and ii) an associated first pose of the first mobile electronic device at a moment of capturing the first image; inputting the first image to a machine learning model trained to output an action based on context in an image and a location in the image associated with the action, thereby obtaining i) an action to be performed and ii) a location within the first image associated with the action; for the action to be performed, determining a position of the action to be performed within the virtual representation of the real space as an intersection between a known structure of the virtual representation of the real space and a raycast from the first pose against a screen space coordinate of the location associated with the action to be performed in the first image; and generating a task to be performed, the task comprising the action to be performed and its position within the virtual representation of the real space.