The Virtual Assistant: Framework and Algorithms for User-Adaptive Communication Management
Key: SKHS07-1
Author: Johannes Schmitt, Matthias Kropff, Matthias Hollick, Ralf Steinmetz
Date: December 2007
Kind: @techreport
Keywords: Context, Communication, Service, Learning, Adaptive, Sensor
Abstract: Today, a plethora of communication technologies promises ubiquitous connectivity. Aspects such as communication management and service control are crucial for efficient and productive usage of the existing communication services. However, the burden of complex configuration and parameterization of these aspects is typically left to the end user. We introduce the virtual assistant, which aids the end user to manage his diverse communication needs in a technological environment characterized by heterogeneity and dynamics. We thoroughly discuss the requirements for a virtual assistant that adapts to the communication behavior of the end user and propose a context-aware architecture to implement this service. While our architecture is generic, we here instantiate it for the special case of ubiquitous communications. Our architecture applies methods from the area of machine learning. This paper lays special emphasis on the selection of appropriate learning algorithms. We further discuss the necessary building blocks to support heterogeneous and dynamic communication systems. In particular, we discuss the aspect of semantic sensor discovery for the context determination. As a proof-of-concept, our architecture has been implemented in a real world communication system.
View Full paper (PDF) | Download Full paper (PDF)

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.