Design of a knowledge based interface for a voice actuated computer graphics imaging system

Research was conducted to develop a voice actuated computer graphics imaging system to provide a means of rendering complex computer languages and input/output modalities transparent to experienced and inexperienced users. The system is used for reconstructing and displaying computed tomography and magnetic resonance imaging scan data. A knowledge based artificial intelligence control strategy module was developed and implemented to interface the voice components and support software of the Texas Instruments 955 workstation to the computer graphics functions implemented on the Sun Microsystems 4/280 color graphics workstation. Based on converted renditions of verbal utterances by the user, the control strategy determines the user's intent and develops and validates a plan. The program type and parameters within the plan are used as input to the graphics system for reconstructing and displaying medical imaging data corresponding to the perceived intent. If the plan is not valid, the control strategy queries the user for additional information. The control strategy operates in a conversation mode and vocally provides system status reports. The design of the knowledge based control strategy is presented with emphasis on the artificial intelligence techniques and the compositional heuristics incorporated in the strategy.