Скачать презентацию TV RECOMMENDATION SYSTEM 인터넷 기술 012 ITI 10 Скачать презентацию TV RECOMMENDATION SYSTEM 인터넷 기술 012 ITI 10

79765b64910a1997cd68e4304ff164d0.ppt

  • Количество слайдов: 14

TV RECOMMENDATION SYSTEM 인터넷 기술 012 ITI 10 박강혜 TV RECOMMENDATION SYSTEM 인터넷 기술 012 ITI 10 박강혜

TV RECOMMENDATION SYSTEM CONTENTS 1. Introduction 2. Approach 3. Now 4. Reference TV RECOMMENDATION SYSTEM CONTENTS 1. Introduction 2. Approach 3. Now 4. Reference

TV RECOMMENDATION SYSTEM INTRODUCTION Advent of Digital satellite TV and Device Redundancy of Channels, TV RECOMMENDATION SYSTEM INTRODUCTION Advent of Digital satellite TV and Device Redundancy of Channels, Programs. Problem of Choice How can user watch the TV program that s/he want to watch, when she want. TV Recommendation System

TV RECOMMENDATION SYSTEM INTRODUCTION EPG Electronic Program Guide TV Recommendation System에서 중요한 역할 TV화면을 TV RECOMMENDATION SYSTEM INTRODUCTION EPG Electronic Program Guide TV Recommendation System에서 중요한 역할 TV화면을 통해 개인화된 recommendation이 제공. EPG의 핵심은 viewer의 기호 파악.

TV RECOMMENDATION SYSTEM APPROACH 1 Cold Start Problem “어떻게 충분한 user data가 공급되지 않은 TV RECOMMENDATION SYSTEM APPROACH 1 Cold Start Problem “어떻게 충분한 user data가 공급되지 않은 상태에서 성능 좋은 recommendation이 제공될 수 있는가” Stereotype user가 자신을 특정 성향의 stereotype으로 결정한다면, 해당 stereotype에 맞는 recommendation이 제공. 잘 만들어진 stereotype이 cold start problem을 해결

TV RECOMMENDATION SYSTEM APPROACH 2 효과적이고 빠르게 작동하는 recommendation system architecture multi-agent model implicit TV RECOMMENDATION SYSTEM APPROACH 2 효과적이고 빠르게 작동하는 recommendation system architecture multi-agent model implicit + explicit + feedback implicit + explicit stereotypical UM expert + implicit preference expert + explicit preference expert implicit agent 와 explicit agent

TV RECOMMENDATION SYSTEM APPROACH 2 Feedback interface Feedback history View history profiler Feedback profile TV RECOMMENDATION SYSTEM APPROACH 2 Feedback interface Feedback history View history profiler Feedback profile Implicit profile weight sum Explicit profile Fig. 1. implicit + explicit + feedback – multi agent Explicit interface

TV RECOMMENDATION SYSTEM APPROACH 2 UMC Dynamic UM Expert Explicit Preference Expert UMC Manager TV RECOMMENDATION SYSTEM APPROACH 2 UMC Dynamic UM Expert Explicit Preference Expert UMC Manager Stereotypical UM Expert Fig. 2. stereotypical UM expert + explicit preference expert

TV RECOMMENDATION SYSTEM APPROACH 3 – 기타 접근들. 보다 효과적인 recommendation celebrity recommender program의 TV RECOMMENDATION SYSTEM APPROACH 3 – 기타 접근들. 보다 효과적인 recommendation celebrity recommender program의 metadata를 이용, conversational sentence로 recommendation 제공 metadata의 분석과 편집 user modeling과 관련 multi user의 기호를 반영한 recommendation을 위해 FIT(Family Interactive TV System) 제안

TV RECOMMENDATION SYSTEM NOW EPG 디지털 위성 TV에서 서비스 중. STB가 EPG server와 연결, TV RECOMMENDATION SYSTEM NOW EPG 디지털 위성 TV에서 서비스 중. STB가 EPG server와 연결, 다운로드 받아서 서비스 되는 형태. EPG의 viewer의 기호를 분석해 recommendation해야 한다는 목적에는 미치지 못하고 있음. Fig. 3. EPG의 화면 예 ( skylife 에서)

TV RECOMMENDATION SYSTEM NOW PVR 미국의 TIVO, Replay. TV, 우리나라는 digital & digital이 대표적. TV RECOMMENDATION SYSTEM NOW PVR 미국의 TIVO, Replay. TV, 우리나라는 digital & digital이 대표적. 하드디스크를 매체로 영상을 MPEG II의 압축형태로 실시간 저장, 재생, 재가공 등의 서비스를 제공하는 digital video recorder EPG와 연동해서 서비스가 제공됨. Fig. 4. PVR과 관련한 EPG 화면 예

TV RECOMMENDATION SYSTEM REFERENCE 1. L. Ardissono, F. Portis, P. Torasso. F. Bellifemine, A. TV RECOMMENDATION SYSTEM REFERENCE 1. L. Ardissono, F. Portis, P. Torasso. F. Bellifemine, A. Chiarotto and A. Difino. Architectiure of a system for the generation of personalized Elctronic Program Guide. Workshop on Personali -zation in Future TV, 2001 2. K. . Kurapati, S. Gutta, D. Schaffer, J. Martino and J. Zimmerman. A multi-agent TV Recommender. Workshop on Personalization in Future TV, 2001 3. C. Gena and L. Ardissono. On the construction of TV viewer stereotypes starting from lifestyles surveys. Workshop on Personalization in Future TV, 2001 4. Anna L. Buczak, John Zimmerman and Kaushal Kurapati. Personalization : Improving Ease -of-Use, Trust and Accuracy of a TV show Recommender. Workshop on Personalization in Future TV, 2002 5. Angelo Difino. Barbara Negroand Alessandro Chiarotto. A Multi-Agent System for a Person alized Electronic Program Guide. Workshop on Personalization in Future TV, 2002. 6. Mark van Setten. Mettina Veenstra and Anton Nijholt. Prediction Strategies : Combining Prediction Techniques to Optimize Personalization. Workshop on Personalization in Future TV, 2002 7. John Zimmerman, Lesh Prameswaran and Kaushal Kurapati. Celebrity Recommender. Workshop on Personalization in Future TV, 2002

TV RECOMMENDATION SYSTEM REFERENCE 8. Dina Goren-Bar and Oded Glinansky. Family Stereotyping – A TV RECOMMENDATION SYSTEM REFERENCE 8. Dina Goren-Bar and Oded Glinansky. Family Stereotyping – A Model to Filter TV Programs for Multiple Viewers. Workshop on Personalization in Future TV, 2002 9. Kaushal Kurapati and Srinivas Gutta. TV Personalization through Stereotypes. Workshop on Personalization in Future TV, 2002 10. Hee-Kyung Lee, Han-Kyu Lee, Je. Ho Nam, Beet. Nara Bae, Munchurl Kim, Kyeongok Kang and Jinwoong Kim. Personalized Contents Guide and Browsing Based on User Perference. Workshop on Personalization in Future TV, 2002 11. Patrick Baudisch and Lars Brueckner. TV Scout : Guiding Users from Printed Tv Program Guides to Personalized TV Recommendation. Workshop on Personalization in Future TV, 2002 12. Barry Smith, David Wilson and derry O’Sullivan. Improving the Quality of the Personalized Electronic Program Guide. Workshop on Personalization in Future TV, 2002 13. Barry Smith, Paul Cotter and James Ryan. Evolving the Personalized EPG – An Alternative Architecture for the Delivery of DTV Services. Workshop on Personalization in Future TV, 2002 14. Nuno Correia and Marlene Peres. Design of a Personalization Service for an Interactive TV Environment. Workshop on Personalization in Future TV, 2002

TV RECOMMENDATION SYSTEM REFERENCE 15. Patrick Baudisch. Designing an Evolvong Internet TV Program Guide TV RECOMMENDATION SYSTEM REFERENCE 15. Patrick Baudisch. Designing an Evolvong Internet TV Program Guide 16. Kaushal Kurapati and Srinivas Gutta. Instant Personalization via Clustering TV Viewing Pattern. 17. John Zimmerman and Kaushal Kurapati. Exposing Profiles to Build Trust in a Recommender. Reference Site 1. Workshop on Personalization in Future TV in conjunction with User Modeling 2001 Sonthofen, Germany, 2001 http: //www. di. unito. it/~liliana/UM 01/TV. html 2. TV'02: the 2 nd Workshop on Personalization in Future TV in conjunction with 2 nd International Conference on Adaptive Hypermedia and Adaptive Web Based Systems Malaga, Spain, 2002 http: //www. di. unito. it/~liliana/TV 02/index. html 3. GIST http: //www. gist. com 4. TIVO http: //www. tivo. com 5. DIGITAL & DIGITAL http: //www. digital-digital. com 6. REPLAY TV http: //www. replaytv. com