Package Routing Using Damaged Label Recovery and Match Algorithms

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems struggle to efficiently identify and route packages with damaged shipping labels within a shipping network, leading to difficulties in determining the correct destination for such packages.

Innovation Solution

A method involving a combination of identification algorithms and machine learning models is used to match packages with damaged labels to their undamaged images, utilizing characteristics like weight, color, dimensions, and expected delivery routes, to accurately identify and route the packages through the shipping network.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional label-based identification is used for packages, then routing is straightforward and automated, but packages with damaged labels cannot be identified or routed correctly

Engineering Contradiction:
Improvepackage identification reliabilityVSAvoidhandling capability for damaged labels
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent introduces an intermediary identification system that uses package characteristics (weight, dimensions, color, shape) as mediators to link damaged packages with their corresponding undamaged reference images. This intermediary approach enables identification without relying on damaged labels, resolving the contradiction between reliable identification and adaptability to label damage.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates and stores reference copies of packages with intact labels before they enter the shipping network. These copies serve as templates for matching against damaged packages later, enabling identification through characteristic comparison rather than label reading, thus maintaining reliability while adapting to label damage.

Inventive Principle:
Principle #26Copying

2Measurement precision

If comprehensive package data collection and analysis is performed to identify damaged packages, then identification accuracy improves, but computational resources and processing time increase

Engineering Contradiction:
Improvepackage identification accuracyVSAvoidcomputational system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The identification process is segmented into distinct stages: data collection (weight, dimensions, color), candidate generation based on characteristic matching, and final verification using reference images. This segmentation allows the system to achieve high accuracy through multiple focused steps rather than one complex operation, managing computational complexity while maintaining precision.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Package reference images and characteristics are captured and stored in advance before labels are damaged. This preliminary action creates a ready-to-use database for rapid matching when damage occurs, reducing real-time computational requirements while maintaining high identification accuracy through pre-processed data.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4529657B1Package location services and routing
Publication Date: 2026.03.11 FEDEX DATAWORKS INC
  • EP4529657B1 patent drawingFigure 1
  • EP4529657B1 patent drawingFigure 2A
  • EP4529657B1 patent drawingFigure 2B

AI summary

Methods, systems, and computer-readable storage media for identification and routing of a first package within a shipping network that has a damaged shipping label is described. First data for the first package with the damaged label is obtained. Second data for a plurality of packages within the shipping network is obtained. A particular package from the plurality of packages that matches the first package is identified. The identification is performed by applying one or more identification algorithms to the first data and the second data. Applying the identification algorithms includes obtaining as output from each algorithm a subset of possible matches from among the plurality of 10 packages, the possible matches including packages identified by the one or more identification algorithms as having one or more characteristics similar to the first package. Information from a label of the particular package is used to route the first package through the shipping network.