Case study : is there a space for TRIZ in the era of ChatGPT?
(2025) ICED25 - 25th International Conference on Engineering Design 5. p.871-880- Abstract
 - This study investigates the integration of Large Language Models with the TRIZ to improve problem solving and innovation in industrial product development. By combining the structured problem-solving framework of TRIZ with LLMs to process large amounts of data and generate ideas, this hybrid approach seeks to overcome the limitations of traditional TRIZ and optimize solution generation. In a case study conducted in an industrial setting, the effectiveness of this integration was investigated by comparing team-generated solutions with those derived using LLMs and TRIZ-enhanced LLMs. The results show that while LLMs accelerate idea generation and provide practical solutions, the additional structure of TRIZ can provide unique insights,... (More)
 - This study investigates the integration of Large Language Models with the TRIZ to improve problem solving and innovation in industrial product development. By combining the structured problem-solving framework of TRIZ with LLMs to process large amounts of data and generate ideas, this hybrid approach seeks to overcome the limitations of traditional TRIZ and optimize solution generation. In a case study conducted in an industrial setting, the effectiveness of this integration was investigated by comparing team-generated solutions with those derived using LLMs and TRIZ-enhanced LLMs. The results show that while LLMs accelerate idea generation and provide practical solutions, the additional structure of TRIZ can provide unique insights, however depending on the application context. (Less)
 
    Please use this url to cite or link to this publication:
    https://lup.lub.lu.se/record/f2eed6b2-e7fc-4e52-aebf-1f652dd9b799
- author
 - 						Čok, Vanja
	; 						Samsa, Luka
	; 						Brojan, Miha
	; 						Tavčar, Jože
				LU
				
	 and 						Vukašinović, Nikola
	 - organization
 - publishing date
 - 2025-08-27
 - type
 - Chapter in Book/Report/Conference proceeding
 - publication status
 - published
 - subject
 - keywords
 - TRIZ, Large language models, Design methodology, Conceptual design, Design engineering
 - host publication
 - Proceedings of the Design Society : ICED25 - ICED25
 - volume
 - 5
 - edition
 - 2025
 - pages
 - 10 pages
 - publisher
 - Cambridge University Press
 - conference name
 - ICED25 - 25th International Conference on Engineering Design
 - conference location
 - Texas, United States
 - conference dates
 - 2025-08-11 - 2025-08-14
 - DOI
 - 10.1017/pds.2025.10101
 - language
 - English
 - LU publication?
 - yes
 - id
 - f2eed6b2-e7fc-4e52-aebf-1f652dd9b799
 - date added to LUP
 - 2025-09-05 13:01:50
 - date last changed
 - 2025-09-30 11:06:09
 
@inproceedings{f2eed6b2-e7fc-4e52-aebf-1f652dd9b799,
  abstract     = {{This study investigates the integration of Large Language Models with the TRIZ to improve problem solving and innovation in industrial product development. By combining the structured problem-solving framework of TRIZ with LLMs to process large amounts of data and generate ideas, this hybrid approach seeks to overcome the limitations of traditional TRIZ and optimize solution generation. In a case study conducted in an industrial setting, the effectiveness of this integration was investigated by comparing team-generated solutions with those derived using LLMs and TRIZ-enhanced LLMs. The results show that while LLMs accelerate idea generation and provide practical solutions, the additional structure of TRIZ can provide unique insights, however depending on the application context.}},
  author       = {{Čok, Vanja and Samsa, Luka and Brojan, Miha and Tavčar, Jože and Vukašinović, Nikola}},
  booktitle    = {{Proceedings of the Design Society : ICED25}},
  keywords     = {{TRIZ; Large language models; Design methodology; Conceptual design; Design engineering}},
  language     = {{eng}},
  month        = {{08}},
  pages        = {{871--880}},
  publisher    = {{Cambridge University Press}},
  title        = {{Case study : is there a space for TRIZ in the era of ChatGPT?}},
  url          = {{http://dx.doi.org/10.1017/pds.2025.10101}},
  doi          = {{10.1017/pds.2025.10101}},
  volume       = {{5}},
  year         = {{2025}},
}