Scott Brown and Eugene Santos
The need exists in the work force for generic intelligent user interface agents to address the problem of increasing taskload that is overwhelming the human user. Interface agents could help alleviate user taskload by providing abstractions and intelligent assistance in a self-contained software agent that communicates with the user through the existing user interface and also adapts to user needs and behaviors. The benefits of a generic intelligent user interface agent environment is it can be applied to any highly interactive and information intensive software system from freight and parcel management systems to Wall Street financial investment and analysis. We desire to address the two following difficulties with developing interface agents: (1) The extensive number of existing computer systems makes it impractical to build these agents by hand for each system; (2) Any such agent must be compliant with existing user interface standards and business practices (e.g., the United States Air Force’s Common Operating Environment (COE) standards as defined by the Defense Information Infrastructure (DII)). Thus, an environment for constructing intelligent interface agents that facilitates standards compliance is necessary. We investigate the feasibility of developing an integrated environment for constructing generic intelligent user interface agents. We base our proposed design on three components: (1) a knowledge acquisition tool for support of specification and design of interface agents taking in to account compliance with existing computer-based systems and user interface standards; (2) a utility theory-based methodology for interface agent requirements, assistance, and adaptivity; and (3) a correction model for user adaptivity based on user metrics evaluation.