Extracting knowledge about users' activities from raw workstation contents

A long-standing goal of AI is the development of intelligent workstation-based personal agents to assist users in their daily lives. A key impediment to this goal is the unrealistic cost of developing and maintaining a detailed knowledge base describing the user's different activities, and which people, meetings, emails, etc. are affiliated with each such activity. This paper presents a clustering approach to automatically acquiring such a knowledge base by analyzing the raw contents of the workstation, including emails, contact person names, and online calendar meetings. Our approach analyzes the distribution of email words, the social network of email senders and recipients, and the results of Google Desktop Search queried with text from online calendar entries and person contact names. For each cluster it constructs, the program outputs a frame-based representation of the conesponding user activity. This paper describes our approach and experimentally assesses its perfonnance over the workstations of three different users.