3D Inventory Model for Real-Time Discrepancy Correction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Inefficient inventory management in large facilities where discrepancies between database models and actual inventory distributions lead to increased costs, errors, and reduced efficiency, as picking agents must traverse long distances to locate items, and periodic shutdowns are necessary to identify and correct discrepancies.

Innovation Solution

A computer-implemented method and system that dynamically manages physical inventory by using image processing software to create a three-dimensional model of actual inventory distribution, identifying discrepancies, and incorporating corrective actions into the picking agents' tasks, allowing for real-time reconciliation of inventory discrepancies while agents perform their usual duties.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If periodic shutdowns are used to identify and correct inventory discrepancies, then inventory accuracy is improved, but productivity and operational efficiency deteriorate

Engineering Contradiction:
Improveinventory accuracyVSAvoidoperational efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system implements continuous inventory monitoring through image capture devices that operate without interruption during normal warehouse operations. The image processing software continuously analyzes inventory data, enabling discrepancy detection and correction to proceed without periodic shutdowns, thereby maintaining both high inventory accuracy and operational productivity

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The system establishes a feedback loop where image capture devices continuously monitor inventory positions, the processing software compares actual positions with database records, and corrective actions are automatically communicated to picking agents. This continuous feedback mechanism maintains inventory accuracy without requiring operational interruptions

Inventive Principle:
Principle #23Feedback

2Productivity

If traditional inventory monitoring methods are used, then operational simplicity is maintained, but inventory management efficiency and error reduction deteriorate

Engineering Contradiction:
Improveinventory management efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system introduces an intermediary image processing software layer that automatically bridges the gap between physical inventory monitoring and database management. This software intermediary captures images, processes them to identify inventory positions, compares data with database records, and generates corrective actions, thereby improving management efficiency without requiring complex manual intervention systems

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates a digital copy of the physical inventory through image capture and processing. This virtual inventory model allows for automated discrepancy detection and analysis without physically interfering with actual warehouse operations, improving efficiency while maintaining manageable system complexity through virtual rather than physical intervention

Inventive Principle:
Principle #26Copying

3Speed

If picking agents manually locate items in large facilities, then adaptability to item locations is maintained, but time consumption and operational speed deteriorate

Engineering Contradiction:
Improveitem delivery speedVSAvoidtime to locate items
Core Design Contradiction:
SpeedVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously capturing images of inventory positions and pre-processing this data to maintain an updated virtual model of item locations. When a picking agent needs an item, the system has already processed image data to determine current positions, enabling the agent to locate items quickly without manual searching, thereby reducing both time loss and increasing delivery speed

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system replaces the mechanical manual searching process with an automated optical and computational system. Image capture devices and processing software automatically track and identify item positions, substituting the mechanical action of agents physically searching for items with an automated visual recognition system, thereby dramatically reducing time consumption and increasing operational speed

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3488392B1System and method for dynamic inventory management
Publication Date: 2023.08.16 EBAY INC
  • EP3488392B1 patent drawingFigure 1
  • EP3488392B1 patent drawingFigure 2
  • EP3488392B1 patent drawingFigure 3

AI summary

A system, method, and computer program product for managing a physical inventory. Image data from a number of cameras is processed to recognize inventory items from identifying indicia and determine their respective locations to build a three-dimensional model of the inventory item distribution. Comparison with a database model of the inventory item distribution may indicate discrepancies, such as misplaced items. A picking agent may be dispatched to pick a target item by following a particular path, which may be designated in an overlay on a portable heads-up display. The picking agent may also perform a corrective inventory management action on a non-target item while picking the target item. The corrective inventory management action may include repositioning an item, reorienting the item for better visibility of its identifying indicia, replacing the item's identifying indicia, determining if the item is of expected weight, and gathering new image data.