Can large language models understand engineering design patents? An exploratory study
Proceedings of the Design Society · 2026-08 · 6 · 2353-2362
DOI: 10.1017/pds.2026.10593 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Design Society, online erschienen am 02.07.2026. Verfasst von Pingfei Jiang und 2 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Patents contain valuable design insights, yet manual analysis remains time-consuming and complex. This study explores Large Language Models’ capacity to automate patent analysis for engineering design. GPT-5 and Gemini 2.5 Pro were evaluated across Motivation, Novelty, and Key Invention Features using three patents and expert evaluators assessed outputs through Accuracy & Fidelity, Comprehensiveness, and Analytical Depth. Results indicate LLMs demonstrate proficiency in feature synthesis but exhibit inferential limitations in motivation analysis, underscoring the necessity for human oversight.
Zitieren
APA
Jiang, P., Wang, Y., & Han, J. (2026). Can large language models understand engineering design patents? An exploratory study. Proceedings of the Design Society, 6, 2353-2362. https://doi.org/10.1017/pds.2026.10593
Vancouver
Jiang P, Wang Y, Han J. Can large language models understand engineering design patents? An exploratory study. Proceedings of the Design Society. 2026;6:2353-2362. doi:10.1017/pds.2026.10593
BibTeX
@article{Jiang2026,
author = {Jiang, Pingfei and Wang, Yuxuan and Han, Ji},
title = {Can large language models understand engineering design patents? An exploratory study},
journal = {Proceedings of the Design Society},
year = {2026},
volume = {6},
pages = {2353--2362},
doi = {10.1017/pds.2026.10593}
}
EUVIMED