Weight Sensor Shelf Inventory Tracking via Joint Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional systems for tracking inventory movement in facilities are intrusive, require special tags or devices, and are costly, leading to inefficiencies and inaccuracies in monitoring item location and movement.
Innovation Solution
A system utilizing weight sensors at inventory locations to generate sensor data, which is processed to determine interaction data such as item type, quantity, and location, eliminating the need for user-carried devices and improving precision and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional tracking systems with special tags or devices are used, then item location and movement can be monitored, but the system becomes costly and intrusive
Solution Approach 1:
The patent extracts the tracking functionality from intrusive user-carried devices and special tags, and relocates it to the inventory location itself through weight sensors. This eliminates the need for users to carry scanning devices while maintaining reliable tracking of item movement through automated weight change detection at the shelf level.
Solution Approach 2:
The system enables inventory locations to self-monitor their own contents through integrated weight sensors. The sensors automatically detect when items are removed or placed without requiring external intervention from users carrying tracking devices, thus reducing system complexity while maintaining reliable tracking.
2Productivity
If user-carried scanning devices are used, then item interaction can be tracked, but operational efficiency decreases and costs increase
Solution Approach 1:
The weight sensor system operates continuously and automatically detects item movements without interruption. Unlike manual scanning where users must actively scan each item, the sensor system passively and continuously monitors weight changes, eliminating downtime and improving operational efficiency by maintaining constant tracking capability.
Solution Approach 2:
The patent replaces the mechanical action of users manually carrying and operating scanning devices with an automated sensor-based system. The weight sensors automatically detect item removal and placement through weight changes, eliminating the need for manual scanning operations and significantly reducing the time lost to tracking activities.
3Measurement precision
If RFID tags are required for tracking, then item location can be monitored, but the system becomes less accessible and more expensive
Solution Approach 1:
The weight sensor system provides universal tracking capability that works for all items regardless of whether they have RFID tags or not. The sensors detect item movement through weight changes alone, making the system accessible and applicable to diverse item types without requiring special tags, thus improving versatility while maintaining location accuracy.
Data Source
AI summary
Sensor data from load cells at a shelf is processed using a first time window to produce first event data describing coarse and sub-events. Location data is determined that indicates where on the shelf weight changes occurred at particular times. Hypotheses are generated using information about where items are stowed, weights of those of items, type of event, and the location data. If confidence values of these hypotheses are below a threshold value, second event data is determined by merging adjacent sub-events. This second event data is then used to determine second hypotheses which are then assessed. A hypothesis with a high confidence value is used to generate interaction data indicative of picks or places of particular quantities of particular types of items from the shelf.