Garment Pattern Generation With Component-Level Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing garment design methods rely heavily on manual editing, leading to long processing times, high design costs, and inefficiencies due to unstructured pattern data and individual habits, while content-based image retrieval systems struggle with localized changes and require high professional skills.

Innovation Solution

A method and device for generating garment design drawings and patterns that utilize a pre-built generative network to encode design intent and materials, enabling automatic generation and component-level matching, reducing professional skill requirements and improving efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual editing methods are used for garment design, then design flexibility and creativity can be maintained, but processing time increases and design efficiency decreases

Engineering Contradiction:

Improvedesign flexibilityVSAvoiddesign efficiency

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The patent replaces manual mechanical editing operations with an automated generative network system that uses machine learning models to generate garment designs, patterns, and pattern pieces automatically, eliminating the need for manual dragging, scaling, and editing while maintaining design quality

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service design generation where the generative network automatically creates complete garment designs from input parameters without requiring designer intervention for each individual pattern piece, allowing designers to obtain ready-to-use patterns through automated processes

Inventive Principle:

Principle #25Self-service

2Quantity of substance

If unstructured pattern data is stored for future reference, then data volume increases, but retrieval and reuse efficiency decreases

Engineering Contradiction:

Improvepattern data volumeVSAvoidretrieval time

Core Design Contradiction:

Quantity of substanceVSLoss of time

Solution Approach 1:

The patent transforms unstructured pattern data into structured data with standardized parameters including garment type, size, style attributes, and pattern piece relationships, enabling efficient querying and retrieval by converting the data into a machine-readable format with defined schemas

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system segments pattern data into standardized components such as pattern pieces, sewing information, and garment structure elements, organizing them in a hierarchical structure that facilitates selective retrieval and reuse of specific pattern components

Inventive Principle:

Principle #1Segmentation

3Measurement precision

If content-based image retrieval is used for pattern matching, then global similarity can be assessed, but localized changes and component-level modifications cannot be targeted

Engineering Contradiction:

Improveglobal similarity assessmentVSAvoidcomponent-level matching

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent segments garments into discrete pattern pieces and components, enabling independent identification and manipulation of individual elements such as sleeves, collars, and bodices, allowing localized modifications without affecting the entire garment pattern

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies different processing and matching strategies to different garment components based on their specific characteristics, enabling precise control over individual pattern pieces while maintaining overall garment coherence

Inventive Principle:

Principle #3Local quality

4Manufacturing precision

If professional pattern-making skills are required for design creation, then design quality can be maintained, but the skill requirement barrier increases and automation becomes difficult

Engineering Contradiction:

Improvepattern-making qualityVSAvoidskill requirement complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent replaces skilled human pattern-makers with an automated generative network that encodes professional pattern-making knowledge into machine learning models, eliminating the need for users to possess specialized skills while maintaining high-quality pattern generation through algorithmic expertise

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20260020632A1Methods for generating garment design drawings, garment patterns, and garment pattern pieces

Publication Date: 2026.01.22 LINGDI (ZHEJIANG) TECHNOLOGY CO LTD

AI summary

The present disclosure discloses a method for generating a garment design drawing, a method for generating a garment pattern, and a method for generating a garment pattern piece. The method for generating a garment design drawing comprises: receiving design intent data and/or design materials; initializing the design intent data to obtain a visual design drawing; encoding the design materials to obtain a material feature code; generating a target design drawing by inputting the material feature code and/or the visual design drawing into a pre-built generative network; and outputting the target design drawing.