رابط سخنرانی هوشمند برای دستیاران شخصی در پروژه های "تحقیق و توسعه"

Groupware and collaborative tools have been proposed to support cooperative work. However, they suffer from some rather severe limitations. Alternatively, multi-agent systems can be proposed to improve the situation. In the latter case, the user normally interacts with the system through a special agent called a personal assistant. In this paper, we describe the design of an ontology-based speech interface for personal assistants applied in the context of cooperative projects. We believe that this type of interface will improve the quality of assistance and increase collaboration between project members. We present the interface and its insertion into a multi-agent system designed for research and development projects. We describe the design of the interface, highlighting the role of ontologies for semantic interpretation. As a result of this conversational speech interface, we expect an increase in the quality of assistance and a reduction in the time needed to answer user’s requests.

During the past few years, different projects have been developed involving multi-agent systems (MAS) for improving computer-supported cooperative work Shen and Wang, 2003, Spinosa et al., 2002, Tacla and Barthès, 2002 and Wu et al., 2002. The application of such an approach can potentially improve the exchange of information among the participants, provide support, improve workflows and procedure controls, and provide convenient user interfaces to CSCW systems. They are an alternative to groupware or collaborative tools that suffer from some limitations as reported by Enembreck and Barthès (2002). Tacla mentioned (Tacla, 2001) that groupware and collaborative tools offer a solution by bundling applications needed by the user. As a result, users can rely on shared spaces to organize their documents and can automate some simple tasks. However, as shown in Enembreck and Barthès (2002), four main problems arise when using them:

In this paper we presented an ontology-based speech interface for PAs. We described it and implemented it in a PA that works in a KM multi-agent system used in the context of research and development projects. Our goal is to develop intelligent user interfaces through which unsophisticated users can have their request treated in a fast and useful manner, allowing knowledge capture on the fly and improving KM. To achieve these goals we developed a PA with a speech interface based on some principles: (i) ontology-based syntactic and semantic analysis; and (ii) a cooperative strategy for the mixed-initiative dialogue system.