DOI QR코드

DOI QR Code

TV Watching Pattern Analysis System based on Multi-Attribute LSTM Model

다중속성 LSTM 모델 기반 TV 시청 패턴 분석 시스템

  • Lee, Jongwon (National Science & Technology Information Service, KISTI) ;
  • Sung, Mikyung (Department of Computer Engineering, Paichai University) ;
  • Jung, Hoekyung (Department of Computer Engineering, Paichai University)
  • Received : 2021.01.31
  • Accepted : 2021.03.09
  • Published : 2021.04.30

Abstract

Smart TVs provide a variety of services and information compared to existing TVs based on the Internet. In order to provide more personalized services or information, it is necessary to analyze users' viewing patterns and provide customized services or information based on them. The proposed system receives the user's TV viewing pattern, analyzes it, and recommends a TV program or movie as customized information to the user. For this, the system was constructed with a preprocessor and a deep learning model. The preprocessor refines the name of the TV program watched by the user, the date the TV program was watched, and the watched time. Then, the multi-attribute LSTM model trains the refined data and performs prediction.The proposed system is a system that provides customized information to users, and is believed to be a leading technology in digital convergence that combines existing IoT technology and deep learning technology.

스마트 TV는 인터넷을 기반으로 기존의 TV에 비해 다양한 서비스와 정보를 제공하고 있다. 보다 개인화된 서비스나 정보를 제공하기 위해서는 사용자의 시청 패턴을 분석하고 이를 기반으로 맞춤형 서비스나 정보를 제공해야한다. 제안하는 시스템은 사용자의 TV 시청 패턴을 입력받고 이를 분석하여 사용자에게 맞춤형 정보로써 TV 프로그램이나 영화를 추천한다. 이를 위해 전처리기와 딥러닝(deep learning) 모델로 시스템을 구성하였다. 전처리기는 사용자가 시청한 TV 프로그램의 이름과 해당 TV 프로그램을 시청한 날짜, 시청한 시간 등을 입력하면 이를 정제한다. 그리고 정제된 데이터를 다중속성 LSTM 모델이 학습하고 예측을 수행하게 된다. 제안하는 시스템은 사용자에게 맞춤형 정보를 제공하는 시스템으로써 기존의 IoT 기술과 딥러닝 기술을 융합한 디지털 컨버전스(convergence)의 선도 기술이 될 것으로 사료된다.

Keywords

Acknowledgement

This work was supported by the research grant of Pai Chai University in 2021.

References

  1. S. O. Kim, J. H. Koo, and S. J. Lee, "A Study on Combinations of Prediction Methods by Using Basic Statistics in Collaborative Filtering Recommender Systems," Journal of The Korean Data Analysis Society, vol. 21, no. 2, pp. 733-744, Apr. 2019. https://doi.org/10.37727/jkdas.2019.21.2.733
  2. J. Y. Kang and H. S. Lim, "Proposal of Content Recommend System on Insurance Company Web Site Using Collaborative Filtering," Journal of Digital Convergence, vol. 17, no. 11, pp. 201-206, Nov. 2019.
  3. J. Y. Park, "Estimation of Electrical Loads Patterns by Usage in the Urban Railway Station by RNN," The Transactions of the Korean Institute of Electrical Engineers, vol. 67, no. 11, pp. 1536-1541, Feb. 2018. https://doi.org/10.5370/KIEE.2018.67.11.1536
  4. X. F. Wang and H. C. Kim, "Text Categorization with Improved Deep Learning Methods," Journal of Information and Communication Convergence Engineering, vol. 16, no. 2, pp. 106-113, Jun.. 2018. https://doi.org/10.6109/JICCE.2018.16.2.106
  5. D. H. Seo, J. S. Lyu, E. J. Choi, S. H. Cho, and D. K. Kim, "Web based Customer Power Demand Variation Estimation System using LSTM," Journal of the Korea Institute of Information and Communication Engineering, vol. 22, no. 4, pp. 587-594, Apr. 2018. https://doi.org/10.6109/JKIICE.2018.22.4.587
  6. J. W. Lee, H. Y. Kim, and H. K. Jung, "Deep Learning Module Optimization based on Sequential Data Prediction," ASM Science Journal, vol. 13, no. 1, pp. 82-91, Feb. 2020.
  7. H. I. Kim and J. Y. Lee, "Prediction of Urban Flood Extent by LSTM Model and Logistic Regression," Journal of the Korean Society of Civil Engineers, vol. 40, no. 3, pp. 273-283, Jun. 2020. https://doi.org/10.12652/KSCE.2020.40.3.0273
  8. J. S. Park and H. H. Lee, "Prediction of high turbidity in rivers using LSTM algorithm," Journal of the Korean Society of Water and Wastewater, vol. 34, no. 1, pp. 35-43, Feb. 2020. https://doi.org/10.11001/jksww.2020.34.1.035