Search

The current state of user interfaces for large information spaces imposes an unmanageable cognitive burden upon the user. Determining how to get the right information into the right form with the right tool at the right time has become a monumental task. Interface agents address the problem of increasing task load by serving as either an assistant or associate, extracting and analyzing relevant information, providing information abstractions of that information, and providing timely, beneficial assistance to suers. Interface agents communicate with the user through the existing user interface and also adapt to user needs and behaviors. User modeling, on the other hand, is concerned with how to represent users' knowledge and interaction within a system to adapt the system to the needs of users. The inclusion of a user model within the overall system architecture allows the system to adapt its response to the preferences, biases, expertise level, goals and needs.

Knowledge elicitation/acquisition continues to be a bottleneck to constructing, decision-theoretic systems. Methodologies and techniques for incremental elicitation/acquisition of knowledge especially under uncertainty in support of users' current goals is desirable. This paper presents PESKI, a probabilistic expert system development environment. PESKI provides users with a highly interactive and integrated suite of intelligent knowledge engineering tools for decision-theoretic systems. From knowledge acquisition, data mining, and verification and validation to a distributed inference engine for querying knowledge, PESKI is based on the concept of active user interfaces actuators to the human-machine interface. PESKI uses a number of techniques to reduce the inherent complexity of developing a cohesive, real-world knowledge-based system. This is accomplished by providing multiple communication modes for human-computer interaction and the use of a knowledge representation endowed with the ability to detect problems with the knowledge acquired and alert the user to these possible problems. We discuss PESKI's use of these intelligent assistants to help users with the acquisition of knowledge especially in the presence of uncertainty.

This paper describes two forms of information visualization for mixed-initiative systems associated with team collaboration and begins to discuss how plans might be formulated to achieve the visualizations. Common understanding visualization is concerned with visualizing the information a team employs, whereas visual collaboration is concerned with visualizing the ongoing, incremental information collection, the credibility and origins of that information, and the dynamic interpersonal relationships of the team itself. The first is the more "classic" form of visualization where data and information is collected, analyzed, abstracted, and tailored for display to the user. We are concerned not only with visualization for the single user, but also with visualizing the relationship the information holds in regard to the entire team. At the level of the individual user, a mixed-initiative system must consider how to tailor the appropriate information given the user's skill, expertise, and preferences. At the corporate level, a system must manage the display of information across multiple human users and system components that share a common goal. The second form of visualization deals with the collaboration between a user and his/her mixed-initiative system, between users, and between systems. That is, the user needs to understand and visualize the collaboration, how the user fits into it, and the associated human/information interaction and processes involved in human/information interaction and processes involved in such collaboration. We claim both types of visualization are important for effective collaboration.

An underlying problem of current interface agent research is the failure to adequately address effective and efficient knowledge representations and associated methodologies suitable for modeling the users' interactions with the system. These user models lack the representational complexity to manage the uncertainty and dynamics involved in predicting user intent and modeling user behavior. A utility theory-based approach is presented for effective user intent prediction by incorporating the ability to explicitly model users' goals, the uncertainty in the users' intent in pursuing these goals, and the dynamics of users' behavior. We present an interface agent architecture, CIaA, that incorporates our approach and discuss the integration of CIaA with three disparate domains — a probabilistic expert system shell, a natural language input database query system, and a virtual space plane —that are being used as test beds for our interface agent research.