본문 바로가기 주메뉴 바로가기
22대 대한민국 국회 국회정보길라잡이 국회의원검색
회원가입 로그인
HOME

정보검색

소장정보 검색

국회도서관 홈으로 정보검색 소장정보 검색
결과 내 검색 동의어 포함
결과 내 검색 동의어 포함

-

초록보기

본 연구에서는 GPT, Stable Diffusion과 같은 생성형 인공지능을 이용한 교수·학습 자료 추천 성능향상을 위해 프롬프트를 개선하는 프롬프트 엔지니어링에 대해 탐색하였다. 분석할 교수·학습 자료의 종류는 그림 자료이다. 프롬프트 구성에 따른 영향을 탐색하기 위해 명령만 담긴 Zero-Shot 프롬프트, 학습 대상 학년 정보가 담긴 프롬프트, 학습 목표가 담긴 프롬프트, 학습 대상 학년과 학습 목표가 모두 담긴 프롬프트를 설계하여 각각을 GPT-3.5모델에 입력하고 응답을 수집하였다.

수집한 응답을 Sentence Transformers로 임베딩 하고 t-SNE를 활용하여 차원 축소하여 시각화 한 다음 프롬프트와 응답 간의 관계를 탐색하였다. 그리고 각 응답을 k-means clustering algorithm을 활용하여 군집화 한 다음 가장 넓은 클러스터의 첫 번째 값을 대표로 선택하여 Stable Diffusion을 이용하여 이미지화 한 다음 교수·학습자료 평가 기준에 따라 초등학교 교사 30명에게 평가 받았다.

초등학교 교사 30인은 추천한 4종의 그림 자료 중 3종은 교육적 가치가 있다고 판단하였으며, 그 중 2종은 실제 수업에 사용할 수 있다고 하였다. 가장 가치 있는 그림 자료를 추천한 프롬프트는 대상 학년과 학습 목표가 모두 담긴 프롬프트로 나타났다.

In this study, prompt engineering that improves prompts was explored to improve the performance of teaching and learning materials recommendations using generative artificial intelligence such as GPT and Stable Diffusion. Picture materials were used as the types of teaching and learning materials. To explore the impact of the prompt composition, a Zero-Shot prompt, a prompt containing learning target grade information, a prompt containing learning goals, and a prompt containing both learning target grades and learning goals were designed to collect responses.

The collected responses were embedded using Sentence Transformers, dimensionalized to t-SNE, and visualized, and then the relationship between prompts and responses was explored. In addition, each response was clustered using the k-means clustering algorithm, then the adjacent value of the widest cluster was selected as a representative value, imaged using Stable Diffusion, and evaluated by 30 elementary school teachers according to the criteria for evaluating teaching and learning materials.

Thirty teachers judged that three of the four picture materials recommended were of educational value, and two of them could be used for actual classes. The prompt that recommended the most valuable picture material appeared as a prompt containing both the target grade and the learning goal.

권호기사

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 목차
FFRM : foundation-policy recommendation model to improve the performance of NAND flash memory Won Ho Lee, Jun-Hyeong Choi, Jong Wook Kwak p. 1-10

Metrics for low-light image quality assessment Sangmin Kim p. 11-19

(A) study on deep learning model for discrimination of illegal financial advertisements on the Internet Kil-Sang Yoo, Jin-Hee Jang, Seong-Ju Kim, Kwang-Yong Gim p. 21-30

Optimization of attention map based model for improving the usability of style transfer techniques Junghye Min p. 31-38

Personalized size recommender system for online apparel shopping : a collaborative filtering approach Dongwon Lee p. 39-48

Performance comparison of neural network and gradient boosting machine for dropout prediction of university students Hyeon Gyu Kim p. 49-58

Time-invariant stock movement prediction after golden cross using LSTM Sumin Nam, Jieun Kim, ZoonKy Lee p. 59-66

Comparison of stock price prediction using time series and non-time series data Min-Seob Song, Junghye Min p. 67-75

Mobile text readability improvement study of Korean font : focusing on Google noto sans typeface Jae-Hong Park p. 77-86

(An) accurate forward head posture detection using human pose and skeletal data learning Jong-Hyun Kim p. 87-93

(A) study on the application of colmap in 3D reconstruction for cultural heritage restoration Byong-Kwon Lee, Beom-jun Kim, Woo-Jong Yoo, Min Ahn, Soo-Jin Han p. 95-101

Design and implementation of economical smart wall switch with IEEE 802.11b/g/n Myeong-Chul Park, Hyoun-Chul Choi, Cha-Hun Park p. 103-109

Implementation of joystick for flight simulator using WiFi communication Myeong-Chul Park, Sung-Ho Lee, Cha-Hun Park p. 111-118

(An) estimation model for defence ability using big data analysis in Korea baseball Ju-Han Heo, Yong-Tae Woo p. 119-126

(The) effects of mental health problems on stress coping, perception of social support and life satisfaction in nursing students Youn-Kyoung Kwag p. 127-135

Analysis of work-related musculoskeletal disorders research trends using keyword frequency analysis and CONCOR technique Geon-Hui Lee, Seo-Yeon Choi p. 137-144

(The) effect of application of PBL(problem-based-learning) class on nursing process education Ji-Un Seo p. 145-153

Structural equation model analysis of factors influencing overall job satisfaction of working-age workers Jae-Nam Kim p. 155-164

(A) study on the relationship between exposure to hazardous and risk factors and absenteeism according to the period of the Korean Working Conditions Survey Jin-Yeub Jung, Seo-Yeon Choi p. 165-174

Analyzing the factors of gentrification after gradual everyday recovery Yoon-Ah Song, Jeongeun Song, ZoonKy Lee p. 175-186

Effects of metaverse experience factors(4Es) on perceived value and intention to continue use Ji-Hee Jung, Jae-Ik Shin p. 187-194

Prompt engineering to improve the performance of teaching and learning materials recommendation of generative artificial intelligence Soo-Hwan Lee, Ki-Sang Song p. 195-204

참고문헌 (17건) : 자료제공( 네이버학술정보 )

참고문헌 목록에 대한 테이블로 번호, 참고문헌, 국회도서관 소장유무로 구성되어 있습니다.
번호 참고문헌 국회도서관 소장유무
1 Ggwang, “Natural Language Analysis of Korean Texts of Al-based Chatbots and Exploration of Korean Education Utilization - Focusing on ChatGPT and New-Bing,” The Society of Korean Culture and Convergence, Vol.45, No.5, 1-17, May 2023 DOI: 10.33645/cnc.2023.05.45.01 미소장
2 Shlee, Kssong, “Exploring the possibility of using ChatGPT and Stable Diffusion as a tool to recommend picture materials for teaching and learning”, Journal of the Korea society of computer and information, Vol. 28, No. 4, pp. 209-216, April 2023 DOI:10.9708/jksci.2023.28.04.209 미소장
3 Igyou, Hypark, “Developing an AI-based Sentence-Generating Web Service for Writing Activities in Elementary Language Education,” Journal of Research in Curriculum & Instruction, vol. 27, No. 2, pp. 210-221, April 2023 DOI: 10.24231/rici.2023. 27.2.210 미소장
4 Hslee, Hsshim, “Study on the Design of a ChatGPT-Based Metaverse Platform Model” Journal of Industrial Technology Research, Vol.28 No.2, PP131-136, June 2023 미소장
5 Gwyong, “Prompt engineering for improving the performance of CLIP-based defect detection,“ Master‘s Degree thesis, Yonsei University, Dec 2022. 미소장
6 Isjoen, Kssong, “Development of Block-based Code Generation and Recommendation Model Using Natural Language Processing Model,” JOURNAL OF The Korean Association of information Education, Vol. 26, No. 3, pp197-207, June 2022 DOI: 10.14352/jkaie.2022.26.3.197 미소장
7 Ekin, Sabit (2023): Prompt Engineering For ChatGPT: A Quick Guide To Techniques, Tips, And Best Practices. TechRxiv. Preprint. DOI: 10.36227/techrxiv.22683919.v2 미소장
8 Wei, Jason, et al. "Finetuned language models are zero-shot learners." arXiv preprint arXiv:2109.01652 (2021). DOI: 10.48550/arXiv.2109.01652 미소장
9 Wei, Jason, et al. "Chain-of-thought prompting elicits reasoning in large language models." Advances in Neural Information Processing Systems 35 (2022): 24824-24837. 미소장
10 Yao, Shunyu, et al. "Tree of thoughts: Deliberate problem solving with large language models." arXiv preprint arXiv:2305.10601 (2023). DOI: https://doi.org/10.48550/arXiv. 2305.10601 미소장
11 Hjprk, Hsim, “A Study on Use Case Analysis and Adoption of NLP:Analysis Framework and Implications,” Journal of Information Technology Services, Vol. 21, No. 2, pp. 61-84, April 2022 DOI: 10.9716/KITS.2022.21.2.061 미소장
12 Reimers, Nils, and Iryna Gurevych. "Sentence-bert: Sentence embeddings using siamese bert-networks." arXiv preprint arXiv:1908.10084 (2019). DOI: 10.48550/arXiv.1908.10084 미소장
13 SBERT, https://www.sbert.net/ 미소장
14 Van der Maaten, Laurens, and Geoffrey Hinton. "Visualizing data using t-SNE." Journal of machine learning research 9.11(2008). 미소장
15 Swjeon et al, “Document Summarization Using TextRankBased on Sentence Embedding,” Journal of KIISE, Vol. 46, No. 3, pp. 285-289, Dec 2019 DOI : 10.5626/JOK.2019.46.3.285 미소장
16 Jmha, Gjmoon, “An Application of k-Means Clustering to Vehicle Routing Problems,”, Journal of Korean Society of Industrial and Systems Engineering, , Vol. 38, No. 3, pp. 1-7, Sep 2015. DOI : https://doi.org/10.11627/jkise.2015.38.3.01 미소장
17 KICE, “A Study on the Development of Teaching and Learning Data Types and Standards according to the Revised Curriculum - Focusing on secondary technology, home, art, and English-,”April, 2008. 미소장

추천서가 (다양한 추천 자료를 만나보세요)

권호기사보기

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 기사목차