Publikation

Disconnected Query Evaluation and Proactive Caching in Distributed Mobile Recommender Systems

Frederik Leonhardt, Andreas Emrich, Alexandra Theobalt, Peter Loos

In: Leena Suhl, Dennis Kundisch (Hrsg.). Tagungsband der Multikonferenz Wirtschaftsinformatik 2014. Multikonferenz Wirtschaftsinformatik (MKWI-14) February 26-28 Paderborn Germany dblp 2/2014.

Abstrakt

A slow or unavailable internet connectivity in remote scenarios with possibly poor network availability forces permanently available mobile recommender systems to utilise disconnected query evaluation and proactive caching. The need emerges to design robust systems, which can deliver reliable results even without existing internet connectivity. This paper will demonstrate an efficient approach for proactive caching and disconnected query evaluation to support a mobile recommender system in monitoring crit-ical local data of its users in real-time. A use case scenario to support in-training recommendations bound to vital parameters of the trainees is shown, and finally performance metrics are discussed for the caching and recommendation mechanisms.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence