An explanatory and “argumentative” interface for a model-based diagnostic system

ABSTRACT

That intelligent systems need an explanatory capability if they are to aid or support human users has long been understood. A system which can justify its decisions generally obtains improved user trust, greater accuracy in use and offers embedded training potential. Extensive work has been done to provide rule-based systems with explanatory interfaces, but little has been done to provide the same benefits for model-based systems. We develop an approach to organizing the presentation of large amounts of model-based data in an interactive format patterned after a model of human-human explanatory and argumentative discourse. Portions of this interface were implemented for Honeywell's model-based Flight Control Maintenance and Diagnostic System (FCMDS). We conclude that sufficient information exists in a model-based system to provide a wide range of explanation types, and that, the discourse approach is a convenient, powerful and broadly applicable method of organizing and controlling information exchange involving this data.

REFERENCES

• 1: Berkowitz, Marvin (Ed.), Peer Conflict and Psychological Growth, In W. Damon, (Ed-in-chief), New Directions in Child Development, 29, San Francisco: Josr~y-Ba,~ Inc., 1985.
• 2: Berkowitz, Marvin and Gibbs, j., Meastmng the developmental features of moral discusswn, Memll-Palmer Quarterly, 29, 1983, pp. 399-410.
• 3: Bursch, P.and Meisner, J., Comparison of Paper and Automat~ Fault Isolation Techniques, To appear in Proceedings of A UTOTESTCON '92, Dayum, Ohio, September, 1992.
• 4: Jeff Conklin , Michael L. Begeman, gIBIS: a hypertext tool for exploratory policy discussion, ACM Transactions on Information Systems (TOIS), v.6 n.4, p.303-331, Oct. 1988 [doi>10.1145/58566.59297]
• 5: R. Davis , W. Hamscher, Model-based reasoning: troubleshooting, Exploring artificial intelligence, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1988
• 6: Eastertx'ook, S. Handling conflict between domain desaripfiom with computer supported negotiation, In Proceedings of the 5th Banff Knowledge Azquisit/on for Knowledge-Based Systems Workshop, Banff, Alberta, Novemeber, 1988, pp. 5.1.22.
• 7: Fischoff, Baruch. Judgement and Decision Making. In RJ. Sternberg and E.E. Smith (Eds.) The Psychology of Human Thou~. New York: Cambridge University Press, 1988.
• 8: Formen, E.A. and Kr~ker, M.J., The social origins of logic: The contributions of Piaget and Vygotsky. In M. Berkowitz, M. (Ed.). Peer Conflict and Psychological Growth, In W. Damon, (Ed-in-chief), New Directions m Child Development, 29, San Francisco: Jossey-Bass Inc., 1985, pp. 23-29.
• 9: Graeser, A.C. and Black. J.B.. (Eds.) The Psychology of Questions, Hillsdale, N.J.; Erlbatmt, 1985.
• 10: Thomas R. Gruber, Automated Knowledge Acquisition for Strategic Knowledge, Machine Learning, v.4 n.3-4, p.293-336, December 1989 [doi>10.1007/BF00130716]
• 11: Gructim J. Why CSCW applications fail: Problems in the design and ~v~on of organizational imeffaces, MCC Technical Report #ACA-HI-211-88, July, 1988.
• 12: Anne Marie Keuneke , B. Chandrasekaran, Machine understanding of devices: causal explanation of diagnostic conclusions, 1989
• 13: Kunz, W. and Rittel, H. Issues as elements of m~onnauon systems. Working Paper No. 131, Institute of Urban and Regional Develol:snent,,University of California, Berkeley, CA., 1970.
• 14: Catherine C. Marshall, Exploring representation problems using hypertext, Proceeding of the ACM conference on Hypertext, p.253-268, November 1987, Chapel Hill, North Carolina, United States [doi>10.1145/317426.317445]
• 15: McKeown, K. R. and Swartout, W. R., Language Generation and Explanation. In Annual Review of Computer Science, 2, Annual Reviews, Inc., 1987, pp. 401 449.
• 16: Miller, Christopher A., Learning to Disagree: ArgumentauveReasonmg Skill in Development }, Ph.D. Dissertataon: University of Chicago, 1991.
• 17: Nickerson, R., Reflections on Reasoning, Hillsdale, N.Y.; Lawrence Erlbaum Associates, Publishers, 1986.
• 18: Rottenberg, Annette, T., Elements of Argument, St. Martin: Bedford Books, 1987.
• 19: Sembugamoorthy, V. and Chan~karart, B., Funcuonal Representation of devices and comlmlation of diagnostic problem-solving systems, in Kolodn er J. and Reisbeclc, C. (Eds.) Experi~, Memory and Reasoning, Lawrence Erlbaum Associates, Hillsdale, NJ., 1986.
• 20: Smolemky, P. Fox, B., King, R. and Lewis, C. Computer-aided reasoned discourse or, how to argue with a computer. In R. Guindon (Ed.), Cognitive science and its applications for human-computer interaction. Norwood, NJ: Ablex, 1988, pp. 109-162.
• 21: Stein. Nancy L, and Miller, Christopher A., I win, You Lose: The development of argumentative thinking, In J.F. Voss, D,N. Perkins, and J. Segal (Eds.) Informal Reasoning and Instruction, Hillsdale: Lawrence Erlbaum Associates, Publishers, 1990.
• 22: N. A. Streitz , J. Hannemann , M. Thüring, From ideas and arguments to hyperdocuments: travelling through activity spaces, Proceedings of the second annual ACM conference on Hypertext, p.343-364, November 1989, Pittsburgh, Pennsylvania, United States [doi>10.1145/74224.74251]
• 23: William. Swartout , Cecile Paris , Johanna Moore, Explanations in Knowledge Systems: Design for Explainable Expert Systems, IEEE Expert: Intelligent Systems and Their Applications, v.6 n.3, p.58-64, June 1991 [doi>10.1109/64.87686]
• 24: Toulmm. S, The Uses of Argument, Cambridge: Cambridge University Press, 1958.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: Interaction styles (e.g., commands, menus, forms, direct manipulation)

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

General Terms:
Design, Human Factors