Interface Agents in Complex Systems

  • Wayne Zachary
  • Jean-Christophe le Mentec
  • Joan Ryder
Part of the The Kluwer International Series in Engineering and Computer Science book series (SECS, volume 372)


It is argued in this paper that interface agent concepts and technology previously applied primarily to generic tasks, such as electronic mail management, are applicable to complex domain-based systems. Interface agents in these specialized domains require substantial amounts of domain-specific and task-specific knowledge in order to be useful to the system end-users. This makes their development potentially lengthy and costly. A way of removing this obstacle is to create a workbench for developing interface agents in complex domains. The paper describes research to create such a workbench, based on the COGNET framework for user-modeling (Zachary et al., 1992). COGNET is a well-established and validated technique for user cognitive modeling. A COGNET-based Generator of Intelligent Agents (GINA) workbench is described, in which an agent-developer creates a cognitive model of a user’s task/work strategy, and automatically translates the model into an executable user model within a interface agent ‘shell’. Specific functionality is then added to allow the agent to use the embedded user model to reason about and help the system user perform tasks, solve problems, and manage attention. Examples of GINA-based agent applications in complex system environments are given.


User Model Problem Representation Problem Context Execution Engine Interface Agent 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Alluisi, E A. (1991) The development of technology for team training: SIMNET, a case history, Human Factors, 33(3), 343–366.Google Scholar
  2. Card, S., Moran, T., & Newell, A. (1983). The psychology of human-computer interaction. Hillsdale, NJ: Lawrence Erlbaum Associates, Inc.Google Scholar
  3. Chignell, M.H., & Hancock, P.A. (1988). Intelligent interface design. In M. Helander (Ed.), Handbook of human-computer interaction (pp. 969–995). New York: North-Holland.Google Scholar
  4. Englemore, J., & Morgan, T. (1988). Blackboard systems. Reading, MA: Addison-Wesley.Google Scholar
  5. Genesereth, M.R. & Ketchel, S.P. (1994). Software agents. Communications of the ACM, 37(7), 48–53 & 147.CrossRefGoogle Scholar
  6. Hicinbothom, J. H., Weiland, W., Santarelli, T., Fry, C. A., Voorhees, J. W., & Zaklad, A. L. (1995, May 9–11). AMMI: Intelligent support for alarm systems in advanced rotocraft. Paper presented at the American Helicopter Society 51st Annual Forum, Fort Worth, TX.Google Scholar
  7. Hill, G.C. (1994). Electronic ‘agents’ bring virtual shipping a bit closer to reality, Wall Street Journal, Vol. CCXXIII, No. 63, pp. 1 & 12.Google Scholar
  8. Kieras, D. (forthcoming). GOMS and related modeling techniques. In M. Helander, T. Landauer, & P. Prabhu (Eds.). Handbook of human computer interaction (2nd Edition). New York: North Holland.Google Scholar
  9. Klein, G., Orasanu, J., Calderwood, R., & Zsambok, C. (Eds.). (1993). Decision making in action: Models and methods. Norwood: Ablex Publishing Corporation.Google Scholar
  10. Kobsa, A., & Wahlster, W. (Eds.) (1989). User models in dialog systems. Berlin: Springer-Verlag.MATHGoogle Scholar
  11. Kzierok, R., & Maes, P. (1993). A learning interface agent for scheduling meetings. In Proceedings of ACM SIGCHI International Workshop on Intelligent User Interfaces (pp. 81–88). New York: ACM Press.Google Scholar
  12. Newell. (1990). Unified theories of cognition. Cambridge: Harvard University Press.Google Scholar
  13. Nii, P. H. (1986a). Blackboard systems: The blackboard model of problem solving and the Eevolution of blackboard architectures PART ONE, AI Magazine, 7(2), 38–53.Google Scholar
  14. Nii, P. H. (1986b). Blackboard systems: The blackboard model of problem solving and the Eevolution of blackboard architectures PART TWO, AI Magazine, 7(3), 82–106.Google Scholar
  15. Olson, J. R., & Olson, G. M. (1990). The growth of cognitive modeling in human-computer interaction since GOMS. Human Computer Interaction, 5(2&3), 221–265.CrossRefGoogle Scholar
  16. Pylyshyn, Z. W. (1984). Computation and cognition. Cambridge: The MIT Press.Google Scholar
  17. Rouse, W.B. (1988). Adaptive aiding for human-computer control. Human Factors, 30(4), 431–443.Google Scholar
  18. Rouse, W.B., Geddes, N.D., & Curry, R E. (1987–1988). An architecture for intelligent interfaces: Outline of an approach to supporting operators of complex systems. Human-Computer Interaction, 3, 87–122.CrossRefGoogle Scholar
  19. Rubin, K. S., Jones, P. M., & Mitchell, C. M. (1988). OFMSpert: Inference of Operator Intentions in Supervisory Control Using a Blackboard Architecture. IEEE Transactions on Systems, Man, and Cybernetics, 18(4), 618–636.CrossRefGoogle Scholar
  20. Schlimmer, J., & Hermens, L. (1993). Software agents: Completing patterns and constructing user interfaces. Journal of Artificial intelligence Research, 1, 61–89.Google Scholar
  21. Seamster, T. L., Redding, R. E., Cannon, J. R., Ryder, J. M., & Purcell, J. A. (1993). Cognitive task analysis of expertise in air traffic control. International Journal of Avaiation Psychology, 3(4), 257–283.CrossRefGoogle Scholar
  22. Selfridge, O. G., (1959). Pandemonium: A paradigm for learning. In Proceedings of the Symposium on the Mechanization of Thought Processes, pp. 511–529.Google Scholar
  23. Weiland, M.Z., Cooke, B., Peterson, B. (1992). Designing and implementing decision aids for a complex environment using goal hierarchies. In Proceedings of the Human Factors Society 36th Annual Meeting (pp. 394–398). Santa Monica, CA: Human Factors Society.Google Scholar
  24. Zachary, W. and Ross, L. (1991). Enhancing human-computer interaction through use of embedded COGNET models. In Proceedings of the 35rd Annual Meeting of the Human Factors Society (pp. 425–429). Santa Monica, CA: Human Factors Society.Google Scholar
  25. Zachary, W., Ryder, J., and Le Mentec, J-C. (1995) A Cognitive Architecture, Description Lanuage, and Execution Engine for Modeling Real-Time Multi-Tasking Human-Computer Interaction. Unpublished manuscript, CHI Systems Inc.Google Scholar
  26. Zachary, W., Ryder, J., Weiland, M., & Ross, L. (1992). Intelligent Human-Computer Interaction in Real Time, Multi-tasking Process Control and Monitoring Systems. In M. Helander & M. Nagamachi (Eds.), Human Factors in Design for Manufacturability, (pp. 377–402). New York: Taylor and Francis.Google Scholar
  27. Zachary, W., Ryder, J., Zubritzky, M., (1989). A cognitive model of human-computer interaction in Naval Air ASW mission management (Technical Report 891215.8704). Spring House, PA: CHI Systems Inc.Google Scholar
  28. Zachary, W., Zaklad, A., Hicinbothom, J., Ryder, J., & Purcell, J. (1993). COGNET representation of tactical decision-making in Anti-Air Warfare. In Proceedings of Human Factors and Ergonomics Society, 37th Annual Meeting, Santa Monica, CA.Google Scholar

Copyright information

© Kluwer Academic Publishers 1996

Authors and Affiliations

  • Wayne Zachary
    • 1
  • Jean-Christophe le Mentec
    • 1
  • Joan Ryder
    • 1
  1. 1.CHI Systems, Inc.Lower GwyneddUSA

Personalised recommendations