DOI QR코드

DOI QR Code

시청 시간대 정보를 활용한 LSTM 기반 IPTV 콘텐츠 추천

LSTM-based IPTV Content Recommendation using Watching Time Information

  • 투고 : 2019.09.26
  • 심사 : 2019.10.29
  • 발행 : 2019.11.30

초록

수많은 채널과 VoD 콘텐츠, 웹 콘텐츠들이 존재하는 콘텐츠 소비 환경에서의 추천은 이제 선택이 아닌 필수가 되었다. 현재 OTT서비스나 IPTV서비스에서도 많은 사람들이 선호하는 콘텐츠를 추천하거나 사용자가 시청한 콘텐츠와 유사한 콘텐츠들을 추천하는 등, 다양한 종류의 추천 서비스들이 제공되고 있다. 하지만 TV, IPTV와 같이 대체로 한 가구당 하나의 가입정보와 하나의 TV, 셋탑박스를 공유하는 TV를 통한 콘텐츠 시청환경의 경우, 하나의 가입정보에 1명 이상의 사용 이력이 쌓여 특정 사용자에 대한 추천을 제공하기에 어려움이 존재한다. 본 논문에서는 이러한 문제를 해결하기 위해 가족의 개념을 {사용자, 시간}으로 해석하여, 기존의 {사용자, 콘텐츠}로 정의하는 추천 관계를 {사용자, 시간, 콘텐츠}으로 확장하고 이를 딥러닝 기반으로 해결하는 방법을 제안한다. 제안한 방법을 통해 추천 성능을 정성적 정량적으로 평가하였으며, 기존의 시간대를 고려하지 않은 방법과 비교하여 추천 정확도가 향상됨을 확인할 수 있었다.

In content consumption environment with various live TV channels, VoD contents and web contents, recommendation service is now a necessity, not an option. Currently, various kinds of recommendation services are provided in the OTT service or the IPTV service, such as recommending popular contents or recommending related contents which similar to the content watched by the user. However, in the case of a content viewing environment through TV or IPTV which shares one TV and a TV set-top box, it is difficult to recommend proper content to a specific user because one or more usage histories are accumulated in one subscription information. To solve this problem, this paper interprets the concept of family as {user, time}, extends the existing recommendation relationship defined as {user, content} to {user, time, content} and proposes a method based on deep learning algorithm. Through the proposed method, we evaluate the recommendation performance qualitatively and quantitatively, and verify that our proposed model is improved in recommendation accuracy compared with the conventional method.

키워드

참고문헌

  1. S. Hochreiter, and J. Schmidhuber, "Long shortterm memory, Neural Computation," Vol. 9, No. 8, pp. 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  2. H. Bang, H. Lee, and J. Lee, “TV Program Recommender System Using Viewing Time Patterns,” Journal of Korean Institute of Intelligent Systems, Vol. 25, No. 5, pp. 431-436, Oct. 2015. https://doi.org/10.5391/JKIIS.2015.25.5.431
  3. H. Chang and C. Chung, "TV Show Recommendation considering the Distinctive Features of TV Show Contents," Proceeding of conference of Korean Institute of Information Scientists and Engineers, Vol. 39, No. 2(B) pp.162-164, Nov.. 2012
  4. E. Kim and M. Kim, "Topic-tracking-based dynamic user modeling with TV recommendation applications, " Applied Intelligence, Vol 44 Issue 4, pp. 771-792, June 2016 https://doi.org/10.1007/s10489-015-0720-8
  5. S Zhang, L. Yao, A. Sun amd Y. Tay, "Deep learning based recommender system a survey and new perspectives," arXiv:1707.07435, 2016
  6. Bing Bai, Yushun Fan, Wei Tan, and Jia Zhang, DLTSR: A Deep Learning Framework for Recommendation of Long-tail Web Services. IEEE Transactions on Services Computing, PP(99), 1-1, 2017.
  7. T. Donkers, B. Loepp, and J Ziegler. "Sequential user-based recurrent neural network recommendations," In Recsys. pp. 152-160, 2017
  8. Paul Covington, Jay Adams, and Emre Sargin, "Deep neural networks for youtube recommendations," In Recsys, pp.191-198, 2016
  9. B. Hidasi, A. Karatzoglou, L. Baltrunas and D. Tikk, "Session-based Recommendations with Recurrent Neural Networks," arXiv:1511.06939, 2016
  10. J. Chung, C. Gulcehre, K. Cho, Y. Bengio, "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling," CoRR, abs/1412.3555, 2014
  11. R. Devooght, and H. Bersini, "Collaborative filtering with recurrent neural networks," arXiv preprint, arXiv:1608.07400, 2016.
  12. T. Mikolov, K. Chen, G. Corrado and J. Dean, "Efficient Estimation of Word Representations in Vector Space," arXiv:1301.3781,2013