Personal software assistants that help users with tasks like finding information, scheduling calendars, or managing work-flow will require significant customization to each individual user. For example, an assistant that helps schedule a particular user’s calendar will have to know that user’s scheduling preferences. This paper explores the potential of machine learning methods to automatically create and maintain such customized knowledge for personal software assistants. We describe the design of one particular learning assistant: a calendar manager, called CAP (Calendar APprentice), that learns user scheduling preferences from experience. Results are summarized from approximately five user-years of experience, during which CAP has learned an evolving set of several thousand rules that characterize the scheduling preferences of its users. Based on this experience, we suggest that machine learning methods may play an important role in future personal software assistants.

Abstract requesting certain types of meetings. In order to be Personalized knowledge-based systems have not yet become widespread, despite their potential for valuable assistance in many daily tasks. This is due, in part, to the high cost of developing and maintaining customized knowledge bases. The construction of personal assistants as learning apprentices-- interactive assistants that learn continually from their users-- is one approach which could dramatically reduce the cost of knowledge-based advisors. We present one such personal learning apprentice, called CAP, which assists in managing a meeting calendar. CAP has been used since June 1991 by a secretary in our work place to manage a faculty member’s meeting calendar, and is the first instance of a fielded learning apprentice in routine use. This paper describes the organization of CAP, its performance in initial field tests, and more general lessons learned from this effort about learning apprentice systems.

Abstract not found

. To be highly useful, office automation systems require customization to individual users, work environments, and tasks. We consider the question of whether office automation systems can be developed that allow users who are not skilled programmers to easily "program", or customize, these tools themselves. In other words, can we deploy very general, non-customized programs that can be extended and adapted during usage? Besides the well-known knowledge acquisition and automated learning methods we propose an approach called dialog-based learning (DBL), that allows the user to teach the system directly while performing the task. It acquires knowledge through a dialog in which the user both illustrates the procedure using a grounded example, and provides instructions about how to perform the task in the general case. We focus discussion on CAP II (a program that schedules meetings by negotiation via email), and on RAP (a program that makes room reservation via email). 1 Introduction We ...