KQML and Intelligent Information Integration

Previous: Introduction Up: KQML as an Agent Communication Language Next: The KQML Language

KQML and Intelligent Information Integration

We could address many of the difficulties of communication between intelligent agents described in the Introduction by giving them a common language. In linguistic terms, this means that they would share a common syntax, semantics and pragmatics.

Getting information processes, especially AI processes, to share a common syntax is a major problem. There is no universally accepted language in which to represent information and queries. Languages such as KIF [15], extended SQL, and LOOM [22] have their supporters, but there is also a strong position that it is too early to standardize on any representation language [19]. As a result, it is currently necessary to say that two agents can communicate with each other if they have a common representation language or use languages that are inter-translatable.

Assuming a common or translatable language, it is still necessary for communicating agents to share a framework of knowledge in order to interpret message they exchange. This is not really a shared semantics, but a shared ontology. There is not likely to be one shared ontology, but many. Shared ontologies are under development in many important application domains such as planning and scheduling, biology and medicine.

Pragmatics among computer processes includes 1) knowing who to talk with and how to find them and 2) knowing how to initiate and maintain an exchange. KQML is concerned primarily with pragmatics (and secondarily with semantics). It is a language and a set of protocols that support computer programs in identifying, connecting with and exchanging information with other programs.

-----------------------------------------------

finin@cmsc