Enhancing Unified Communication Services with Communication Context

Abstract

Unified communication services aggregate user's communication sessions and data across various modalities. While this aggregation provides users easy access to their data, the complexity of organizing, analyzing, and searching the data in real-time is left to the user. Our work focuses on an approach that analyzes and correlates users' communication data to their communication context. We use this communication context to realize rich novel unified communication services. Our approach identifies common threading and topic correlations across user data, and proposes a framework that supports rapid creation of such new services. We present several novel services and discuss services specific algorithms and offer our recommendations. The framework and the services described in this paper have been deployed for trial in an enterprise environment.<br /><br /&gt

Profile Sharing Recommendation System for Enterprise Collaboration

“…Secondly, this separation allows us to draw a clear distinction with our earlier work on computing contextual awareness for collaboration [5], [6], [7], [8], where we focus on computing context awareness that enhances enterprise collaboration applications. Focusing on the profile pictures and keeping the problem we are solving generic will allow us to present our work independently.…”

“…Our earlier work [8], [5], [20], [7] on contextual awareness in unified communications deals with various aspects of enhancing a user's unified communication experience by predicting relevant people, documents, conversation threads, and events. Our prior work does not deal with any notion of sharing profiles or sharing computed context across different users.…”

“…Our earlier work [5], [20] presents detailed description of how various correlations across communication units, which we refer as comunits, such as email, calls, conferences, etc., are computed and used for relevance ranking. We omit details of our work on these except for computing person-to-person relationships because our work on profile sharing recommendation is independent of those computations.…”