Generative AI as “One of the Brewers” : Application to Product Development and Process Optimization
生成AIは「蔵人のひとり」―新製品の工程最適化への活用
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20264417
- Paper/Info type
- Journal of Society of Automotive Engineers of Japan
Vol.80 No.5
- Pages
- 98-102(Total 5 p)
- Date of publication
- May 2026
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
| Category(J) | ホットトピックス Translation |
|---|---|
| Category(E) | Hot Topics |
| Author(J) | 1) 鈴木 健吾, 2) 畑瀬 研斗 |
| Author(E) | 1) Kengo Suzuki, 2) Kento Hatase |
| Affiliation(J) | 1) 津南醸造, 2) MEMORY LAB |
| Abstract(J) | 津南醸造はLLMを酒造りに融合した「スマート醸造」を開発した。製造の暗黙知を継承が困難なことと原料の供給状況が変動するという二つの課題に対し、RAG技術で学術・形式・現場知識を統合。Human-in-the-Loop設計のもと、魚沼産コシヒカリ100%純米酒の開発を実現した本取り組みを報告する。 Translation |
| Abstract(E) | Tsunan Sake Brewery Co., Ltd., developed a “Smart Brewing” system integrating large language models (LLMs) into traditional sake production. Facing the dual challenges of difficulty in passing down master brewers’ tacit knowledge to the next generation and climate-driven raw material variability, the authors built a retrieval-augmented generation (RAG) knowledge base combining academic, corporate, and contextual knowledge layers. Maintaining a Human-in-the-Loop design, the system successfully guided development of a pure-rice sake using 100% locally grown Koshihikari rice, achieving award-winning quality at domestic and international competitions. This paper reports the initiative as a case study of generative AI implementation in traditional industry. |
