A Software Engineering Approach Combining Rational and Conversational Agents for the Design of Assistance Applications

A Conversational Agent can be useful for providing assistance to naïve users on how to use a graphical interface. Such an assistant requires three features: understanding users’ requests, reasoning, and intuitive output. In this paper we introduce the DAFT-LEA architecture for enabling assistant agents to reply to questions asked by naive users about the structure and functioning of graphical interfaces. This architecture integrates via a unified software engineering approach a linguistic parser for the understanding the user’s requests, a rational agent for the reasoning about the graphical application, and a 2D cartoon like agent for the multimodal output. We describe how it has been applied to three different assistance application contexts, and how it was incrementally defined via the collection of a corpus of users’ requests for assistance. Such an approach can be useful for the design of other assistance applications since it enables a clear separation between the original graphical application, its abstract DAFT model and the linguistic processing of users’ requests.