A General Framework for Incorporating Intelligent Agents into User Interfaces

Period of Performance: 03/18/1998 - 12/18/1998

$100K

Phase 1 SBIR

Recipient Firm

Stottler Henke Associates
1650 South Amphlett Boulevard, Suite 300
San Mateo, CA 94402
Principal Investigator

Research Topics

Abstract

We propose an innovative combination of modern artificial intelligence (AI) and human-computer interaction (HCI) techniques in the design of an adaptive interface agent architecture. By drawing on our experience developing software agents, machine learning, and plan recognition techniques we have devised an eclectic approach to the incorporation of intelligence in a wide variety of user interfaces. Specifically, the proposed generalized intelligent interface framework (GIIF) will offer significant improvements in operational effectiveness by working collaboratively with the user to streamline tasks, automate repetitive procedures, and otherwise adapt the user interface to reduce complexity and increase user effectiveness. In this endeavor, we will take advantage of a natural synergy between "programming by demonstration," decision process modeling, and new plan recognition techniques in order to develop a set of generic tools that can be used to integrate intelligent interface agents into present and future Common Operating Environment (COE) applications. The GIIF will also provide the capability to assist less-experienced users of the applications by offering in-situ advice. We will prove the feasibility of our approach by developing and demonstrating a proof-of-concept prototype in Phase I.