US 12,393,573 B1
Filtering materials based on user intent capture using large language models
Andrew John Harris, Golders Green (GB); Daniele Grandi, South Lake Tahoe, CA (US); Kendra Ann Wannamaker, Calgary (CA); Michael Chen, Toronto (CA); and Allin Irving Groom, Edinburgh (GB)
Assigned to AUTODESK, INC., San Francisco, CA (US)
Filed by AUTODESK, INC., San Francisco, CA (US)
Filed on Jun. 28, 2024, as Appl. No. 18/759,517.
Int. Cl. G06F 16/242 (2019.01); G06F 16/248 (2019.01); G06F 30/20 (2020.01); G06F 119/18 (2020.01)
CPC G06F 16/2425 (2019.01) [G06F 16/248 (2019.01); G06F 30/20 (2020.01); G06F 2119/18 (2020.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method for determining materials for computer-generated designs, the method comprising:
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, wherein 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; and
evaluating simulation results to determine whether the at least one material is an appropriate material to use for the design, wherein the simulation results are generated from at least one simulation of the design using the at least one material.