DOI QR코드

DOI QR Code

A Study on AI Prompt Engineering for Jewelry Production Ideation - Focusing on Text Generator -

주얼리 제작 아이데이션을 위한 AI 프롬프트 엔지니어링연구 - Text Generator를 중심으로 -

  • Hye-Rim Kang (Major in Jewelry and Gemology, Department of Creative Arts, Hankyong National Univ)
  • 강혜림 (한경국립대학교 창의예술학부 귀금속보석공예전공)
  • Received : 2024.08.10
  • Accepted : 2024.11.01
  • Published : 2024.11.30

Abstract

AI interprets user prompts, surveys data, and generates output. Users input natural language into the prompt in the form of a two-way conversation, and the methodology for conveying accurate intentions to AI is called prompt engineering. Generative AI was used during jewelry production ideation during a major course at H University, and the need for prompt-related research was observed during the training evaluation process. Using the prompt methodology derived from this study, we aim to reduce deviations in output and strengthen prompt capabilities for jewelry production ideas through upward standardization. As a result of applying prompting engineering through previous research, it was confirmed that there is a positive correlation between the advancement of prompts and the completeness of AI output. In the future, through this study, we hope to learn the fundamental principles of prompting and to be helpful in utilizing AI.

AI는 사용자의 프롬프트를 해석하여 데이터를 서베이하고 산출물을 생성한다. 사용자는 프롬프트에 자연어를 양방향 대화의 형식으로 입력하는데, AI에게 정확한 의사를 전달하기 위한 방법론이 프롬프트 엔지니어링이다. H대학교 전공 교과목 수업 중 주얼리 제작 아이데이션 시 생성형 AI를 활용하였고, 훈련 평가 과정에서 프롬프트 관련연구의 필요성이 관찰되었다. 본 연구로 도출된 프롬프트 방법론으로 산출물 편차를 줄이고, 상향 평준화를 통해 주얼리 제작 아이데이션을 위한 프롬프트 역량을 강화하고자 한다. 선행 연구를 통한 프롬프트 엔지니어링 적용 결과, 프롬프트의 고도화와 AI 산출물의 완성도는 양의 상관관계가 있음을 확인하였다. 본 연구를 통해 프롬프팅에 대한 근본적 원리를 익히고, AI 활용에 대한 도움이 되기를 바란다.

Keywords

References

  1. https://www.mk.co.kr/news/business/10942416 (June 12, 2024)
  2. https://www.sedaily.com/NewsView/29VYGB49CH (June 17, 2024)
  3. https://www.smaeil.co.kr/news/articleView.html?idxno=3867 (August 1, 2024)
  4. J.J. Kim, Best Prompt Engineering Lectures, Seoul : Recommand, 2024.
  5. B.H. Ban, Prompt Engineering, Gyeonggi-do : Saengneung, 2023.
  6. Y.T. LEE, "The Effects of Type of Case Organization and Reasoning Supporting Tool on Learning Outcomes in Case-Based Learning", Hanyang University Graduate School, February 2009.
  7. https://team-gpt.com/blog/best-chatgpt-promptspersona-examples/ (June 19, 2024)
  8. Vivian Liu, Lydia B Chilton, "Design Guidelines for Prompt Engineering Text-to-Image Generati ve Models", arXiv, arXiv:2109.06977, pp.1-23, Se ptember 2021.
  9. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, Xinyun Chen, "Large Language Models as Optimizers", arXiv, arXiv:2309.03409, pp.1-42, Sep. 2023.
  10. https://www.aitimes.com/news/articleView.html?idxno=157471 (August 4, 2024)
  11. S.W. Seo, Prompt Engineering Textbook, Seoul : Addand, 2023.
  12. S.J. Kang, Prompt Engineer's Work Log, Seoul : Recomand, 2024.
  13. M. Jang, J.K. Ahn, Prompt Engineering, Seoul : Altos, 2023.