LLM Material Filtering for Faster CAD Material Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The selection of appropriate materials for designs in computer-aided design (CAD) processes requires technical expertise, leading to sub-optimal choices and increased design time due to the complexity of material interactions and limited exploration of the design space.

Innovation Solution

A method using large language models (LLMs) to generate material attribute filters based on user intent and design context, combined with simulation results to identify suitable materials automatically, reducing the need for specialized knowledge and accelerating the material selection process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If engineers and designers manually evaluate materials using traditional methods, then material selection accuracy can be improved, but the time required and expertise needed increase significantly

Engineering Contradiction:

Improvematerial selection accuracyVSAvoidmaterial selection time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent introduces an AI assistant as an intermediary between designers and material databases. This assistant automatically queries material databases, retrieves relevant material properties, and provides recommendations based on design requirements, eliminating the need for designers to manually evaluate numerous materials while maintaining high accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual mechanical process of material evaluation with an automated AI-based system. The AI assistant uses natural language processing to understand design requirements and automatically queries material databases, substituting the traditional manual review process with an intelligent automated system that delivers accurate results faster

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If engineers consult materials experts for material selection, then material selection quality improves, but the complexity of the process and cost increase

Engineering Contradiction:

Improvematerial selection qualityVSAvoidprocess complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent enables designers to perform material selection independently through an AI assistant that provides expert-level guidance automatically. The system self-services by querying material databases, analyzing design requirements, and generating recommendations without requiring external materials experts, thereby reducing process complexity while maintaining high quality

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The AI assistant serves multiple functions: it acts as a materials expert consultant, a database query system, and a design requirement analyzer all in one tool. This multi-functional approach consolidates what previously required multiple specialized resources into a single automated system, reducing overall process complexity

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Manufacturing precision

If designers test multiple materials through simulations, then design optimization improves, but the number of iterations and time required increase

Engineering Contradiction:

Improvedesign optimizationVSAvoiddesign iteration speed

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The patent applies preliminary action by having the AI assistant query material databases and retrieve relevant material properties before simulations are conducted. This pre-preparation of material information allows designers to perform simulations more efficiently with better-informed material selections, reducing the number of iterative cycles needed while maintaining design optimization quality

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20260003858A1Filtering materials based on user intent capture using large language models

Publication Date: 2026.01.01 AUTODESK INC

AI summary

Various embodiments are directed towards techniques for determining materials for computer-generated designs that include generating a query prompt based on an assembly context, transmitting the query prompt to a plurality of large language model (LLM) agents for processing, receiving a plurality of material attribute filters from the plurality of LLM agents, where each LLM generates a different material attribute filter when processing the query prompt, combining the material attribute filters included in the plurality of material attribute filters to produce a material query, querying a material database using the material query to identify at least one potential material to use for a design, evaluating simulation results to determine whether the at least one material is an appropriate material to use for the design.