A hybrid personal assistant based on Bayesian networks and a rule-based system inside a smartphone

Article type: Research Article

Authors: Han, Sang-Jun | Cho, Sung-Bae^{; *}

Affiliations: Department of Computer Science, Yonsei University, 134 Shinchon-dong, Sudaemoon-ku, Seoul 120-749, Korea

Correspondence: [*] Corresponding author. E-mail: sbcho@cs.yonsei.ac.kr

Abstract: As technology improves, mobile phones are becoming essential aspects of human communication. As more and more people begin to use mobile phones, various services based on mobile phone networks and high-end devices are developing. In addition, with the growth of ubiquitous computing, there have been many ongoing studies regarding novel and useful services inside smartphones. In order to develop personalized and intelligent services in these smartphones, we propose an intelligent service-providing method based on Bayesian networks and rule-based service selection. This method infers the user's state with the use of a Bayesian network and provides appropriate services based on the inferred knowledge. We also show a prototype of a personal assistant agent based on the proposed method. This prototype is applied to a group of realistic situations, in order to confirm the usefulness of the proposed method.

Keywords: Intelligent agents, Bayesian networks, personal assistants, smartphones, ubiquitous computing

DOI: 10.3233/HIS-2005-2304

Journal: International Journal of Hybrid Intelligent Systems, vol. 2, no. 3, pp. 221-234, 2005