Generative AI Patent Drawing Creation With Adaptive Hatching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating drawings for patent applications of engineering products with fine layouts, such as IC chips, using CAD software is time-consuming and requires subjective enlargement and hatching, while different software is often used for circuit design and drawing creation, leading to inefficiencies and potential inaccuracies.
Innovation Solution
A drawing creation support system utilizing a generative AI model to efficiently create drawings for patent applications by enlarging selected parts, adding appropriate hatching patterns, and optimizing magnifying power based on design data, ensuring the drawings reflect actual product dimensions and layouts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If CAD software is used to create drawings for patent applications with enlargement processing, then characteristic portions can be emphasized and made understandable, but it takes time and requires subjective judgment by the drawing creator
Solution Approach 1:
The patent replaces the mechanical manual operation of CAD software with an AI-based automated system. The AI model processes design data and automatically generates patent drawings with appropriate enlargements, eliminating the need for manual subjective judgment and significantly reducing creation time while maintaining accuracy
Solution Approach 2:
The system enables self-service by allowing the AI model to autonomously perform drawing creation tasks. The AI automatically determines which portions to enlarge and how to process them based on the design data, without requiring continuous human intervention or subjective decision-making
2Adaptability or versatility
If different software is used for circuit design and drawing creation, then design flexibility is maintained, but efficiency is reduced and potential inaccuracies occur
Solution Approach 1:
The patent implements a universal system where a single AI-based platform can process design data from various circuit design software tools. The system maintains compatibility with multiple input formats and design tools while providing consistent automated drawing generation, thereby maintaining flexibility without sacrificing efficiency
Solution Approach 2:
The AI-based drawing creation system acts as an intermediary layer between different circuit design software and the final patent drawing output. This mediator can process data from various design tools and standardize the output format, enabling efficient automation while preserving compatibility with diverse design workflows
3Area of stationary object
If hatching pattern with magnifying power lower than 1 is used, then the drawing can cover larger areas, but it becomes difficult to distinguish hatching patterns in small regions
Solution Approach 1:
The patent applies dynamic adjustment of hatching pattern magnifying power based on the specific characteristics of each region in the design data. The AI model automatically determines appropriate magnification levels for different areas, ensuring that small regions maintain distinguishable hatching patterns while larger areas are still effectively covered
Solution Approach 2:
The system implements local quality by applying different hatching pattern magnifying powers to different regions of the drawing based on their specific needs. Critical small regions receive higher magnification for distinguishability, while less critical larger areas use lower magnification to maintain overall drawing coverage and balance
Data Source
AI summary
One embodiment of the present invention is to provide an information processing system enabling a user to obtain a drawing the user needs. For assisting the user in creating a drawing for a patent application, a drawing creation support system is built, in which the enlargement of a drawing, addition of hatching patterns, selection of the hatching patterns are performed with a generative AI model and a magnifying power for optimizing a hatching line spacing is calculated by the generative AI model.