Artificial Intelligence Support for Graphics-Based Information Access

We propose an innovative combination of artificial intelligence and data visualization techniques in the design of a tool for graphical manipulation and browsing of document collections. By drawing on our experience with information processing environments and our work developing useful graphical representations of complex information, we have devised an eclectic approach which incorporates a variety of technologies. We propose to support multiple visual representations of textual data with a number of novel artificial intelligence techniques. We further propose to use machine learning techniques to automatically learn user preferences and improve the tool's organizational abilities by observing the user at work. The resulting tool will augment the user's reasoning capabilities by allowing intuitive access to information through a visual medium. The prototype tool developed in our Phase I effort will form the basis for the Phase II development of a complete collaborative data visualization and processing environment for command and control operations.