A Personalized Software Assistant Framework To Achieve User Goals
The growing trend of devices participation in Internet of Things (IoTs) platforms has created billions of IoT devices for users. The rapid trend has made users to install IoT devices at homes to achieve their goals, such as to reduce electricity cost. Moreover, the increasing popularity of service-oriented computing makes more and more services available on the Web. Users make use of these services to achieve their personal goals, such as to book right tickets. Existing research with personalized software assistants has been conducted to assist users majorly in e-commerce sites for customized search recommendations. However, the potential of personalized software assistant systems usage in a user-centric model is highly unrealized in assisting users to achieve their personal goals through personalized context-aware interactions with users based on behavioural habits, such as to smartly recommend IoT devices usage in smart-homes to reduce electricity expenses, and engage users more during the process of service selection to achieve their goals. In this thesis, First, we propose an engine that identi es the behavioural patterns of IoT device users to make smart recommendations to reduce users cognitive overload. Then we propose an intellectually cognitive personalized assistant framework which helps users to achieve their personal goals through personalized context-aware interactions for selection of services. We have designed and developed a prototype as a proof of concept. We perform a case study to evaluate the e ectiveness of our framework. Our framework, utilizing the learning-to-rank algorithm, namely AdaRank, improves the nine baseline approaches by 12.02% - 31.52% in helping users nd the desired services to achieve their goals. Further, we conduct a user study to obtain users' perception of using our framework to achieve their personal goals. Our user study results show that our framework is helpful in achieving user's goals and saves users time in nding their personalized services faster.
URI for this recordhttp://hdl.handle.net/1974/22704
Request an alternative formatIf you require this document in an alternate, accessible format, please contact the Queen's Adaptive Technology Centre
The following license files are associated with this item: