基于结构化参数模型与特征解耦的工业设计变体生成方法及系统

By constructing a structured parameter model and feature decoupling technology, the problems of lack of structured control and severe coupling of design elements in industrial design are solved, realizing precise control of industrial design objects and generation of diverse variants, thereby improving design efficiency and the rationality of the generated results.

CN121936293BActive Publication Date: 2026-07-17CHENGDU LINGXU ARTIFICIAL INTELLIGENCE TECHNOLOGY CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHENGDU LINGXU ARTIFICIAL INTELLIGENCE TECHNOLOGY CO LTD
Filing Date
2026-01-16
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing generative artificial intelligence models lack structured control capabilities in industrial design, have severe coupling of design elements, and generate highly random results, making it difficult to meet the needs of precise control and diverse variant generation in industrial design.

Method used

By introducing visual semantic parsing, parametric decoupling modeling, and variant programming techniques, a structured parametric model is constructed to decouple the features of the design object, establish a hierarchical relationship topology between attributes, and introduce a strong constraint attribute locking mechanism and variant programming algorithm to ensure that key features remain unchanged during the generation process and generate variants that conform to the design logic.

Benefits of technology

It enables precise control and diverse variant generation of industrial design objects, ensuring that the generated results meet brand visual specifications and product functional requirements, reducing the cost for designers to screen invalid solutions, and improving the efficiency of design iteration and exploration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121936293B_ABST
    Figure CN121936293B_ABST
Patent Text Reader

Abstract

本发明公开了基于结构化参数模型与特征解耦的工业设计变体生成方法及系统,包括以下步骤:响应于针对目标设计对象的变体生成请求,获取所述设计对象的输入图像,并调用预训练的视觉语义解析模型对所述输入图像进行解析,提取包含结构层、形态层及材质工艺层的设计语义单元集合;基于所述设计语义单元集合构建结构化参数模型,对所述设计对象的特征进行解耦处理。本发明通过构建结构化参数模型,将非结构化的图像视觉特征映射为相互独立、可量化的参数化属性。这一技术手段有效克服了现有生成式人工智能模型中特征高度耦合的缺陷。
Need to check novelty before this filing date? Find Prior Art