A proposal of the person-centered approach for personal task management

This paper proposes a human-centered approach for personal task management in which people can decide management of their tasks according to their environments, including their subjective and multivalent judgement and human relationships. In our approach task management is modeled as a decision-making process on their own resources. The human decision-making process consists of three types of activity, i.e., the intelligence activity, design activity, and choice activity. The proposed system assists each activity by three sub-systems, i.e., visualizer, optimizer and recommender respectively. At first, visualizer indicates the attributes associated with each task such as deadline, subjective priority, and workload, which are determined by the user. The optimizer generates executable schedules from these tasks using an active scheduler and multi-objective genetic algorithm. Finally, the recommender evaluates these alternatives using an analytic hierarchy process. The system is also able to analyze the human relationships of the user group using the PageRank algorithm, and this result is utilized to improve the performance of the task scheduler. We implement a client/server system which uses mobile phones and verify the function of the proposed system along the lines of two scenarios.