Eunsoo Shim

Enhancing Unified Communication Services with Communication Context

Unified communication services aggregate users 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.

Communication data based user activity recommendations

The amount of information exchanged in the communication increases rapidly as the user plays a more role in her organization and social networks. It has become overwhelming to many people in this communication and information centric era and the need for assistance to manage communicated information and the communication relations has grown. We present a communication data based user activity recommender system that aims to help the user use the communication services more effectively and easily. The communication data of a user provides abundant information about the topics the user is working on, the people the user communicates with, and the communication and information needs of the user. Our system analyzes the communication data and extracts such information, generates recommendations for users communication services, and provides the information the user needs according to the users communication context. Machine learning and natural language processing methods are utilized for communication data analysis and the performance of an example of our recommenders -- predictive meeting assistant -- is presented in details. Our recommender system has been implemented for large-scale deployments and its core architecture is presented.

Automatic phone number mapping verification for phone number based SIP peering

While VoIP spread widely, its deployments are isolated islands interconnected via the PSTN and E.164 phone numbers are still the universal addresses for phones. Mapping phone number to SIP address is essential for SIP peering based on phone numbers. The public ENUM designed for this has not been successful due to the complexity of phone number ownership delegation. This paper proposes a secure and reliable mechanism for automatic phone number mapping verification, addressing the problem of the public ENUM and also enabling phone number based P2P SIP peering establishment.