Helmut Simonis
Cork Constraint Computation Centrem, University College Cork, Ireland
Download article
Published in: The Swedish AI Society Workshop May 20-21; 2010; Uppsala University
Linköping Electronic Conference Proceedings 48:2, p. 6-6
Published: 2010-05-19
ISBN:
ISSN: 1650-3686 (print), 1650-3740 (online)
Todays cable and satellite systems provide a multitude of TV viewing choices for a user; making it difficult to select the best program to watch at any one time. Digital video recording and IPTV add even more options; allowing to time- and sometimes place-shift TV watching. CPTV is a system which generates a personalized viewing schedule for a user; integrated with his current calendar tools. The system is based on three main elements:
- a rule based system to express viewing preferences;
- a content-based recommender system to suggest films based on past viewing selections and information extracted from Wikipedia; and
- a constraint-based scheduler which plans and schedules recording and viewing schedules around existing events and availability time periods of a user.
The application thus combines different AI methods in one Web-based application; and is implemented using the constraint logic programming system ECLiPSe.
