AI Packing Recommendation System for Package Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Individuals face challenges in selecting the appropriate package type and packing items efficiently for shipment, leading to wasted space, increased shipping costs, and potential damage to items during transit.

Innovation Solution

A method utilizing artificial intelligence, involving machine learning models to process images of items and reference items, and rules-based models to generate recommendations for package types and filler materials based on item dimensions and fragility predictions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of substance

If manual packing selection is used, then individuals can choose package types, but it leads to wasted space, increased shipping costs, and potential item damage

Engineering Contradiction:
Improvewasted spaceVSAvoidpacking process complexity
Core Design Contradiction:
Loss of substanceVSEase of operation

Solution Approach 1:

The system enables self-service by automatically determining optimal package types and filler material requirements through image processing and AI analysis, eliminating the need for manual measurement and selection while minimizing wasted space

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical measurement and decision-making with an automated digital system that uses image processing, machine learning models, and rules-based algorithms to determine packing recommendations

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

2Loss of energy

If manual packing selection is used, then individuals can choose package types, but shipping costs increase

Engineering Contradiction:
Improveshipping costsVSAvoidpacking process complexity
Core Design Contradiction:
Loss of energyVSEase of operation

Solution Approach 1:

The system automatically optimizes shipping cost by selecting the most appropriate package type based on item dimensions and carrier requirements, eliminating manual intervention while reducing energy loss in the form of shipping costs

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system incorporates feedback loops where packing recommendations are generated, evaluated against carrier dimensional weight policies, and refined to minimize shipping costs while maintaining proper item protection

Inventive Principle:
Principle #23Feedback

3Reliability

If manual packing selection is used, then individuals can choose package types, but item safety during shipping is compromised

Engineering Contradiction:
Improveitem safety during shippingVSAvoidpacking process complexity
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system automatically determines item fragility characteristics through image analysis and texture detection, then recommends appropriate filler materials and package types to ensure item safety without requiring manual assessment

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system proactively identifies fragile items through AI analysis and pre-recommends appropriate filler materials and packaging configurations before shipping, ensuring item protection is built into the packing process from the start

Inventive Principle:
Principle #11Beforehand cushioning (Prior cushioning)

4Ease of operation

If AI image processing is used to determine item dimensions, then packing recommendations are simplified, but processing complexity increases

Engineering Contradiction:
Improvepacking recommendation processVSAvoidAI processing system complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary layer of bounding box generation and dimension calculation that translates complex AI image processing results into simple, actionable packing recommendations, shielding users from the underlying system complexity

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates simplified representations (bounding boxes) of complex image data, copying only the essential dimensional information needed for packing decisions while discarding unnecessary visual complexity

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4560545A1Artificial intelligence for generating recommendations for packing items
Publication Date: 2025.05.28 UNITED PARCEL SERVICE OF AMERICAN INC
  • EP4560545A1 patent drawingFigure 1
  • EP4560545A1 patent drawingFigure 2
  • EP4560545A1 patent drawingFigure 3

AI summary

In general, various embodiments of the present disclosure provide systems, methods, apparatuses, and technologies, and/or the like for providing novel artificial intelligence (AI) functionality for generating a recommendation on packing an item or combination of items.