| Summary: | Intelligent software agents have been used in many applications because they provide
useful integrated features that are not available in "traditional" types of software (e.g., abilities to
sense the environment, reason, and interact with other agents). Although the usefulness of agents
is in having such capabilities, methods and tools for developing them have focused on practical
physical representation rather than accurate conceptualizations of these functions. Like other
computer systems, intelligent agents usually represent some real world phenomena or
environments. Consequently, intelligent agents should closely mimic aspects of the environment
in which they operate. In the physical sciences, a conceptual model of a problem can lead to
better theories and explanations about the area. Therefore, we ask how can an intelligent agent
conceptual framework, properly defined, be used to model complex interactions in various social
science disciplines?
The constructs used in the implementation of intelligent agents may not be appropriate at
the conceptual level, as they refer to software concepts rather than to application domain
concepts. Therefore we propose to use a combination of the systems approach and Bunge's
ontology as adapted to information systems, to guide us in defining intelligent agent concepts.
The systems approach will be used to define the components of the intelligent agents. Once the
components have been identified we will use ontology to understand the configurations,
transitions, and interrelationships between the components. We will then provide a graphical
representation of these concepts for modelling purposes.
As a proof of concept for the proposed conceptual model, we apply it to a marketing
problem and implement it in an agent-based programming environment called Netlogo. With the
aid of the conceptual model, the user was able to quickly visualize the complex interactions of
different agents. The use of the conceptual representation even sparked an investigation of
previously neglected causal factors which led to a better understanding of the problem. The
implications of these findings, and further research avenues, are also discussed. Since the proof
of concept was successful, it can be said that we provide an intelligent agent framework that can
graphically model phenomena in the social sciences. However, there are other contributions
derived from the work, including; a theoretically driven concept of intelligent agent components,
a way of showing the interrelationships between these concepts, and the foundation for an
ontologically complete model of intelligent agents. === Business, Sauder School of === Management Information Systems, Division of === Graduate
|
|---|
