융합정보논문지 (Journal of Convergence for Information Technology)

중소기업융합학회 (Convergence Society for SMB)
권호 표지
DOI QR코드

DOI QR Code

NTIS 시스템에서 딥러닝과 형태소 분석 기반의 대화형 검색 서비스 설계 및 구현

Design and Implementation of Interactive Search Service based on Deep Learning and Morpheme Analysis in NTIS System

  • 이종원 (한국과학기술정보연구원) ;
  • 김태현 (한국과학기술정보연구원) ;
  • 최광남 (한국과학기술정보연구원)
  • Lee, Jong-Won (Korea Institute of Science and Technology Information) ;
  • Kim, Tae-Hyun (Korea Institute of Science and Technology Information) ;
  • Choi, Kwang-Nam (Korea Institute of Science and Technology Information)
  • 투고 : 2020.10.16
  • 심사 : 2020.12.20
  • 발행 : 2020.12.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

현재 NTIS(National Technology Information Service)는 인공지능 기술을 기반으로 대화형 검색 서비스를 구축하고 있다. 이용자의 검색 의도를 파악하고 과제정보를 제공하기 위해 딥러닝 모델과 형태소 분석기를 기반으로 대화형 검색 서비스를 구축한다. 딥러닝 모델은 NTIS와 대화형 검색 서비스를 활용할 때 적재되는 로그 데이터를 기반으로 학습을 진행하고 이용자의 검색 의도를 파악한다. 그리고 단계별 검색을 통해 과제정보를 제공한다. 검색 의도 파악은 예외처리를 용이하게 해주며 단계별 검색은 통합검색보다 쉽고 빠르게 원하는 정보를 얻을 수 있도록 한다. 향후연구로는 인공지능 기술이 접목된 성장형 대화형 검색 서비스로써 이용자에게 제공하는 정보의 범위를 확대해야 한다.

Currently, NTIS (National Technology Information Service) is building an interactive search service based on artificial intelligence technology. In order to understand users' search intentions and provide R&D information, an interactive search service is built based on deep learning models and morpheme analyzers. The deep learning model learns based on the log data loaded when using NTIS and interactive search services and understands the user's search intention. And it provides task information through step-by-step search. Understanding the search intent makes exception handling easier, and step-by-step search makes it easier and faster to obtain the desired information than integrated search. For future research, it is necessary to expand the range of information provided to users.

키워드

참고문헌

  1. J. T. Kim & H. G. Lee & H. S. Kim. (2020). Effective Generative Chatbot Model Trainable with a Small Dialogue Corpus. Journal of Korean Institute of Information Scientists and Engineers, 46(3), 246-252. DOI : 10.5626/JOK.2019.46.3.246
  2. D. A. Park. (2017). A Study on Conversational Public Administration Service of the Chatbot Based on Artificial Intelligence. Journal of Korea Mutimedia Society, 20(8), 1347-1356 DOI : I410-ECN-0101-2018-004-001287355
  3. M. J. Kang. (2018). A Study of Chatbot Personality based on the Purposes of Chatbot. Journal of the Korea Contents Association, 18(5), 319-329. DOI : I410-ECN-0101-2018-310-002251103 https://doi.org/10.5392/JKCA.2018.18.05.319
  4. J. J. Kim & H. J. Jo. (2019). Development of Conversational News Chatbot System Based on User Intent Analysis. Journal of Digital Contents Society, 20(5), 963-972. DOI : 10.9728/dcs.2019.20.5.963
  5. M. C. Sung. (2020). Pre-Service Primary English Teachers' AI Chatbots. Journal of Language Research, 56(1), 97-115. DOI : 10.9728/dcs.2019.20.2.241
  6. S. H. Choi & J. Y. Kim & J. H. Song & S. M. Jung & S. J. Hong. (2019). Labor Law Consulting System With IBM Watson Chatbot. Journal of Digital Contents Society, 20(2), 241-249. DOI : 10.9728/dcs.2019.20.2.241
  7. J. W. Kim & H. I. Jo & B. G. Lee. (2019). The Study on the Factors Influencing on the Behavioral Intention of Chatbot Service for the Financial Sector - Focusing on the UTAUT Model. Journal of Digital Contents Society, 20(1), 41-50. DOI : 10.9728/dcs.2019.20.1.41
  8. X. F. Wang & H. C. Kim. (2018). Text Categorization with Improved Deep Learning Methods. Journal of Information and Communication Convergence Engineering, 16(2), 106-113. DOI : 10.6109/jicce.2018.16.2.106
  9. D. H. Seo & J. S. Lyu & E. J. Choi & S. H. Cho & D. K. Kim. (2018). Web based Customer Power Demand Variation Estimation System using LSTM. Journal of the Korea Institute of Information and Communication Engineering, 22(4), 587-594. DOI : 10.6109/jkiice.2018.22.4.587
  10. J. W. Lee & H. Y. Kim & H. K. Jung. (2020). Deep Learning Module Optimization based on Sequential Data Prediction. ASM Science Journal, 13(1), 82-91.
  11. Y. H. Kim & Y. K. Hwang & T. G. Kang & K. M. Jung. (2016). LSTM Language Model Based Korean Sentence Generation. The Journal of Korean Institute of Communications and Information Sciences, 41(5), 592-601. DOI : 10.7840/kics.2016.41.5.592
  12. I. T. Joo & S. H. Choi. (2018). Stock Prediction Model based on Bidirectional LSTM Recurrent Neural Network. Journal of Korea institute of information, electronics, and communication technology, 11(2), 204-208. DOI : 10.17661/jkiiect.2018.11.2.204
  13. H. I. Kim & J. Y. Lee. (2020). Prediction of Urban Flood Extent by LSTM Model and Logistic Regression. Journal of the Korean Society of Civil Engineers, 40(3), 273-283. DOI : 10.12652/Ksce.2020.40.3.0273
  14. T. H. Min & H. J. Shin & J. S. Lee. (2019). Korean Spatial Information Extraction using Bi-LSTM-CRF Ensemble Model. The Journal of the Korea Contents Association, 19(11), 278-287. DOI : 10.5392/JKCA.2019.19.11.278
  15. H. Y. Yu & Y. J. Ko. (2017). Expansion of Word Representation for Named Entity Recognition Based on Bidirectional LSTM CRFs. Journal of Korean Institute of Information Scientists and Engineers, 44(3), 306-313. DOI : 10.5626/JOK.2017.44.3.306