On the use of shared task models in knowledge acquistion, strategic user interaction and clarification agents

In this paper, three di!erent roles of a shared task model as an intermediate representation of a task are presented and illustrated by applications developed in cooperation with industry. First the role of a shared task model in knowledge acquisition is discussed. In one of the two applications, decision support in the domain of soil sanitation, one of the existing generic task models for diagnostic reasoning provided a means to structure knowledge acquisition. In the second application, diagnosis of chemical processes, the acquisition process resulted in a shared task model for diagnostic reasoning on Nylon-6 production. Secondly, the role of a shared task model in designing user interaction is addressed. Three levels of interaction are considered of importance: interaction at the object level, at the level of strategic preferences, and at the level of task modi"cation. In an application in the domain of environmental decision making, this led to the design of a user interface based on the acquired shared task model, within which all three levels of interaction were available to users. Finally, the role of shared task models within a multi-agent system including a clari"cation agent is addressed. Two software agents were designed that each share a task model with the user: one for a diagnosis task, and one for a clari"cation task. The shared model of the clari"cation task re#ects the shared task model of diagnosis; clari"cation includes clari"cation of the overall diagnostic reasoning process. The multi-agent architecture presented has been developed to support a user both at the level of the diagnostic task he or she is performing and at the level of clari"cation. The architecture has been applied to the diagnosis of chemical processes. ( 2000 Academic Press