An Inference Engine for Personalized Content Adaptation in Heterogeneous Mobile Environment

Abstract

In order to overcome the various constraints of wireless environments and provide content according to device specifications and user preference, research relating to content adaptation is gaining in significance. For content adaptation, existing research either prepares content in advance, a reflection of client types which may have access to server, or describes the adaptation rules for dynamic content conversion. However, these require a lot of effort from the content author or system developer, and prospecting the appearance of a new device is a difficult work in today’s rapidly changing computing environment. This paper proposes an intelligent adaptation system that automatically extends adaptation rules. The system classifies users into basic categories, then dynamically converts content according to the rule mapping category, offering this result to the user. Then, the system monitors the user action, and performs learning based on this feedback. Moreover, the system has characteristics of offering more personalized content as well as reducing the response time due to reuse of the content generated by same group category. A prototype was implemented in order to evaluate the proposed system in terms of system maintainability, by automatic rule extension, correctness of generated rules, and response time. The effectiveness of the system is confirmed through the results.

This work was supported in parts by Ubiquitous Autonomic Computing and Network Project, 21th Century Frontier R&D Program, MIC, Korea, ITRC IITA-2005-(C1090-0501-0019), Grant No. R01-2006-000-10954-0, Basic Research Program of the Korea Science & Engineering Foundation, and the Post-BK21 Project.