Personalized application enablement by web session analysis and multisource user profiling

Authors:
Armen Aghasaryan;Murali Kodialam;Sarit Mukherjee;Yann Toms;Christophe Senot;Stéphane Betgé-Brezetz;T. V. Lakshman;Limin Wang
Affiliations:
Service Infrastructure Research Domain, Alcatel-Lucent Bell Labs, Villarceaux, France;Network Protocols and Systems Research Department, Alcatel-Lucent Bell Labs, Holmdel, New Jersey;Alcatel-Lucent Bell Labs Network Protocols and System Research Department, Murray Hill, New Jersey;Infrastructure Research Domain, Alcatel-Lucent Bell Labs, Villarceaux, France;Infrastructure Research Domain, Alcatel-Lucent Bell Labs, Villarceaux, France;Infrastructure Research Domain, Alcatel-Lucent Bell Labs, Villarceaux, France;Protocols and Systems Research Department, Alcatel-Lucent Bell Labs, Murray Hill, New Jersey;Network Protocols and Systems Research Department, Alcatel-Lucent Bell Labs, Murray Hill, New Jersey
Venue:
Bell Labs Technical Journal - General Papers
Year:
2010

Citing 0
Cited 2

Deep packet inspection and bandwidth management: Battles over BitTorrent in Canada and the United States

Telecommunications Policy
Modelling user behaviour and experience: the R2D2 networks approach

DUXU'13 Proceedings of the Second international conference on Design, User Experience, and Usability: design philosophy, methods, and tools - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Mastering knowledge of the user profile is one of the technical cornerstones for service providers who handle a large amount of end user service consumption data and are well positioned to dynamically infer user interest domains. This paper presents a holistic approach to service personalization by offering a means to gather a user's consumption data from different multimedia services, to create and track user profiles in real time, and to monetize these profiles through targeted content or other personalized service offers. We describe a multisource profiling engine that deals with both operator-controlled domains and over-the-top (OTT) applications. In particular, to cover the Web domain, we combine the multisource profiling engine with a deep packet inspection (DPI)-based keyword inference engine characterizing users' Web browsing sessions in terms of the most relevant keywords searched. © 2010 Alcatel-Lucent.