Metodologias para o desenvolvimento de sistemas especialistas para planejamento em construção
Metodologias para o desenvolvimento de sistemas especialistas para planejamento em construção
Formoso, Carlos Torres
http://dx.doi.org/10.1590/S0103-65131993000100001
Prod, vol.3, n1, p.5-13, 1993
Resumo
Nos últimos anos um número relativamente grande de sistemas especialistas têm sido produzidos, tanto pela indústria quanto em centros de pesquisa. Algumas destas aplicações têm sido empregadas para resolver problemas práticos, mas a maior parte delas não foi além do estágio de protótipo.
Estes sistemas são normalmente desenvolvidos através de um processo relativamente informal e empírico, o qual envolve a implementação de um protótipo simplificado já nos estágios iniciais de aquisição do conhecimento. Esta abordagem tem sido bastante criticada pelas dificuldades de re-implementaçâo do conhecimento.
Mais recentemente, algumas metodologias formais para a produção de sistemas especialistas têm sido propostas. Embora tais metodologias prescrevam diversas recomendações úteis, que podem ser seguidas em inúmeros casos práticos, nenhuma delas provou ainda ser aplicável de forma integral em uma ampla gama de situações.
A primeira parte deste artigo consiste em uma rápida revisão das principais metodologias propostas. A segunda parte descreve o procedimento adotado durante o desenvolvimento de um sistema especialista para o planejamento de conjuntos habitacionais, denominado House Planner.
Palavras-chave
Sistemas Especialistas, Engenharia do Conhecimento, Inteligência Artificial
Abstract
Several knowledege based systems have been produced in the last decade, both in the industry and in research institutes. Some of these applications have been used in practical situations, but most of them have not been developed beyond the prototype stage.
Such systems are usually desingned through an informal and empiric process which involves the implementation of a simple prototype of the system in the early phases of knowledge acquisition. This approach has beem widely criticized because it can make both the re-implementation and updating of knowledege bases cubersome, and seriously distort the way knowledge is represented.
For this reason, a number of more formal methodologies for developing knowledge based systems have been proposed in recent years. Although such methodologies have provided some useful advice, none of them has yet proved to be applicable as whole in a wide range of situations.
The first part of this paper consists of a general review of some of the existing formal methodologies. In the second part, the approach used for developing a knowledge based system for planning house building projects, named House Planner, is discussed.
Keywords
Expert Systems, Knowledge Engineering, Artificial Inteligency
References
BASDEN, A. ( 1990) Towards a methodology for building expert systems. Codex, Uxbaridge, Creative Logic, 2(1): pp. 15-19.
BERRY, D. C. & BROADBENT, D. E. (1986) Expert systems and the man-machine interface. Expert Systems, Osford, learned Information, 3(4): pp. 228-231.
BORN, G. (1989) Guidelines for quality assurance of exper systems. Specialist Group on Expert Systems Newsletter, London, British Computer Society, 22: pp. 25-43.
BREUKER, J. & WIELIGNGA, B. (1989) Models of expertise in Knowledge acquisition. In: GUIDA, G. & TASSO, C. (Eds.) Topics in expert system design. Amsterdam, North-Holland, pp. 265-295.
BUCHANAN, B. G. et al. (1983) Constructing an expert systems. In: HA YESRO-TH, B. G. et al. (Eds.) Building expert systems. Reading, Massachusetts, Addison-Wesley. Ch. 5, pp. 127-167.
DE LA GARZA et al. (1988) Knowledge elicitation techniques for construction scheduling. In: ADELI, H. (Ed.) Microcomputer base expert systems in civil engineering. New York, ASCE.
FORMOSO, C. T. A Knowledge based framework for planning house building projects. Salford, Univ. of Salford, Aurveying Dept., 1991. Ph. D. Thesis
GAINES, B. R. (1987) Foundations of Knowledge engineering. In: BRAMER, M. A. Research and Development in Expert Systems III. Cambridge, Cambridge Univ. Press, pp. 13-24. British Computer Society Workshop Series.
LEVITT, R. E. & KUNZ, F. C. (1987) Using artificial intelligence techniques to support project management. Stanford, Stanford Univ. Working Paper #1
MITTAL, S. & DYM, C. L. (1985) Konowledge acquisition from multiple experts. AI Magazine, 6(2): pp. 32-36.
MOTTA, E. et al. (1989) A methodology and tool for knowledge acquisition in KEATS-2 In: GUIDA, G. & TASSO, C. (Eds.) Topics in expert system design: methodologies and tools. New York, North Holland, pp. 297-322.
SLATTER, P. E. (1989) Building expert systems: cognitive emulation. Chichester, Ellis Horwood.
WATSON, I. (1989) a methodology for knowledge analysis. Liverpool, Univ. of Liverpool. Ph. D. Thesis.
YOUG, R. (1989) Role of intermediaterepresentations in knowledge elicitation. In: MORALEE, D. S. (Ed.) Research and Development in Expert Systems IV. Cambridge, Cambridge Univ. Press, pp. 285-286. British Computer Society Workshop Series.