DOI QR코드

DOI QR Code

Development of the Rule-based Smart Tourism Chatbot using Neo4J graph database

  • Kim, Dong-Hyun (Department of Telecommunication Engineering, Jeju National University) ;
  • Im, Hyeon-Su (Department of Telecommunication Engineering, Jeju National University) ;
  • Hyeon, Jong-Heon (Department of Telecommunication Engineering, Jeju National University) ;
  • Jwa, Jeong-Woo (Department of Telecommunication Engineering, Jeju National University)
  • Received : 2021.03.23
  • Accepted : 2021.04.04
  • Published : 2021.05.31

Abstract

We have been developed the smart tourism app and the Instagram and YouTube contents to provide personalized tourism information and travel product information to individual tourists. In this paper, we develop a rule-based smart tourism chatbot with the khaiii (Kakao Hangul Analyzer III) morphological analyzer and Neo4J graph database. In the proposed chatbot system, we use a morpheme analyzer, a proper noun dictionary including tourist destination names, and a general noun dictionary including containing frequently used words in tourist information search to understand the intention of the user's question. The tourism knowledge base built using the Neo4J graph database provides adequate answers to tourists' questions. In this paper, the nodes of Neo4J are Area based on tourist destination address, Contents with property of tourist information, and Service including service attribute data frequently used for search. A Neo4J query is created based on the result of analyzing the intention of a tourist's question with the property of nodes and relationships in Neo4J database. An answer to the question is made by searching in the tourism knowledge base. In this paper, we create the tourism knowledge base using more than 1300 Jeju tourism information used in the smart tourism app. We plan to develop a multilingual smart tour chatbot using the named entity recognition (NER), intention classification using conditional random field(CRF), and transfer learning using the pretrained language models.

Keywords

Acknowledgement

This research was also supported by the 2020 scientific promotion program funded by Jeju National University.

References

  1. Gretzel, U., Sigala, M., Xiang, Z. and Koo, C, "Smart Tourism: Foundations and Developments", Electronic Market, pp.179-188, 2015. DOI:10.1007/s12525-015-0196-8
  2. Sameera A Abdul-Kader and JC Woods. "Survey on chatbot design techniques in speech conversation systems", International Journal of Advanced Computer Science and Applications, 6(7), pp.72-80, 2015. DOI : 10.14569/IJACSA.2015.060712
  3. F.Clarizia, F. Colace, M. Lombardi, F. Pascale, "A Context Aware Recommender System for Digital Storytelling", IEEE 32nd International Conference on Advanced Information Networking and Applications, pp.542-549, 2018. DOI: 10.1109/AINA.2018.00085
  4. Dialogflow, https://dialogflow.com/
  5. Amazon Lex, https://aws.amazon.com/ko/lex/
  6. Watson Assistant, https://www.ibm.com/watson/kr-ko/how-to-build-a-chatbot/
  7. Azure Bot, https://azure.microsoft.com/ko-kr/solutions/architecture/information-chatbot/
  8. Naver Clova Chatbot, https://www.ncloud.com/product/aiService/chatbot
  9. Fabio Clarizia, Francesco Colace, Marco Lombardi, F. Pascale, "A Context Aware Recommender System for Digital Storytelling",2018 IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA), pp. 542-549, May 2018 DOI: 10.1109/AINA.2018.00085
  10. Daishi Suzuki, Kazuya Nunotani, Keisuke Fukusato, Mikiko Sode Tanaka, "A Study of Tourism Proposal System Using AI", IEEE 9th Global Conference on Consumer Electronics (GCCE), pp.634-635, Oct. 2020. DOI: 10.1109/GCCE50665.2020.9292070
  11. Jeong-Woo Jwa, "Pedestrian Network Models for Mobile Smart Tour Guide Services," International Journal of Internet, Broadcasting and Communication, vol.8, no.1, pp.73-78. 2016. https://doi.org/10.7236/IJIBC.2016.8.1.27
  12. KiBeom Kang, JeongWoo Jwa, SangDon Earl Park, "Smart Audio Tour Guide System using TTS", International Journal of Applied Engineering Research, pp.9846-9852, 2017. https://www.ripublication.com/ijaer17/ijaerv12n20_81.pdf
  13. JeongWoo Jwa, "Development of Personalized Travel Products for Smart Tour Guidance Services", International Journal of Engineering & Technology, 7 (3.33) 58-61, 2018. DOI: 10.14419/ijet.v7i3.33.18524
  14. Kakao khaiii(Kakao Hangul Analyzer III), https://tech.kakao.com/2018/12/13/khaiii/
  15. Neo4j graph database, https://neo4j.com/
  16. Visit Jeju Website, https://www.visitjeju.net/kr
  17. Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer "Deep contextualized word representations," arXiv preprintarXiv:1802.05365, 2018. DOI:10.18653/v1/N18-1202
  18. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova, "BERT: Pretraining of deep bidirectional transformers for language understanding," arXiv preprint arXiv:1810.04805, 2018. DOI: 10.18653/v1/N19-1423
  19. ETRI KorBERT, http://aiopen.etri.re.kr/service_dataset.php
  20. AWS-SKT KoGPT-2, https://github.com/SKT-AI/KoGPT2
  21. SKT KoBERT, https://github.com/SKTBrain/KoBERT