Towards a natural interface to adaptive service composition

ABSTRACT

Novel modes of interaction and tailored application delivery are a key challenge in ubiquitous computing. This paper proposes a method of adaptively delivering lightweight, disposable service compositions to a user in a smart space. The user intuitively requests these services through a single, natural interface, which infers goals through observing behaviour and context. The composition is driven by generating tasks from these inferences, which can be resolved down to candidate services. We will discuss the proposed interaction between these components and highlight what direction our research will take.

REFERENCES

• 1: {Edgar, 2001} Web Services: A Position Paper, Edgar, G, W3C workshop on Web services, 2001
• 2: {Dey et al, 2001} References Distributed and Disappearing User Interfaces in Ubiquitous Computing, Dey, Anind, Ljungstrand, Peter, Schmidt, Albrecht, 2001
• 3: Pat Langley, Machine Learning for Adaptive User Interfaces, Proceedings of the 21st Annual German Conference on Artificial Intelligence: Advances in Artificial Intelligence, p.53-62, September 09-12, 1997
• 4: Eric Horvitz, Principles of mixed-initiative user interfaces, Proceedings of the SIGCHI conference on Human factors in computing systems: the CHI is the limit, p.159-166, May 15-20, 1999, Pittsburgh, Pennsylvania, United States [doi>10.1145/302979.303030]
• 5: {Dagger, 2003} An Architecture for Candidacy in Adaptive eLearning Systems to Facilitate the Reuse of Learning Resources, Dagger D., Conlan O., Wade V., eLearn 2003
• 6: {Horvitz et al, 1998} The Lumiere Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users, Horvitz E., Breese J., Heckerman D., Hovel D. & Rommelse K., In Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, pages 256--265, 1998
• 7: Roel Vertegaal, Introduction, Communications of the ACM, v.46 n.3, March 2003 [doi>10.1145/636772.636794]