A task-based architecture for application-aware adjuncts

Abstract

Users of complex applications need advice, assistance, and feedback while they work. We are experimenting with "adjunct" user agents that are aware of the history of interaction surrounding the accomplishment of a task. This paper describes an architectural framework for constructing these agents. Using this framework, we have implemented a critiquing system that can give task-oriented critiques to trainees while they use operating system tools and software applications. Our approach is generic, widely applicable, and works directly with off-the-shelf software packages.

On the Common Substring Alignment Problem

“…In the Intelligent Tutoring application [8], the alphabet for each sequence is all possible computer interface artifacts (keyboard and mouse input combinations). The student is given the task, and the resulting events are recorded as the student tries to solve the problem.…”

A multi-agent based approach for knowledge transfer in product design contexts

“…Champ in [21] suggests exploiting the tracking of use of tacit knowledge by the designer by means of the mechanisms of reasoning from case.…”

Sparse LCS Common Substring Alignment

“…The objective is to classify the target by finding the source string whose alignment with the target gives the highest similarity score. Examples of Template Matching Applications are found in the domains of Intelligent Tutoring [11], Electronic Commerce [5,6,23], and Network Security [30]. Very often, the competing source strings are variations of a similar signal, or different combinations of a common set of subcomponents.…”