Computational Intelligence, 3 (2), 78-93.

Review of Artificial Intelligence for Microcomputers: The Guide for Business Decision Makers

Letters to the Editor

The everyday problem-solving activity within the organization can be thought of as conducted by a network of experts knowledgeable about the products and the physical and paperwork processes that constitute the business, that is, the knowledge network. The focus of our attention has not been just at the factory level; we have been addressing the order-process cycle: marketing, sales, order administration, manufacturing, distribution, and field service. This loop is the product life cycle: marketing and new product requirements, design and manufacturing startup, and volume or steady-state manufacturing. In addition to an overview of this knowledge network, we feature DEC's newest system in order processing: the configuration-dependent sourcing (CDS) expert.

The AI lab at the Courant Institute at New York University (NYU) is pursuing many different areas of artificial intelligence (AI), including natural language processing, vision, common sense reasoning, information structuring, learning, and expert systems. Other groups in the Computer Science Department are studying such AI-related areas as text analysis, parallel Lisp and Prolog, robotics, low-level vision, and evidence theory.

Writing about AI has turned out to be a considerably more difficult undertaining than many people had suspected. This book, although the best general introduction to AI that I have seen, still contains inadequacies.

This article describes an effort to develop a knowledge-based financial marketing consultant system. Financial marketing is an excellent vehicle for both research and application in artificial intelligence (AI). This domain differs from the great majority of previous expert system domains in that there are no well-defined answers (in traditional sense); the goal here is to obtain satisfactory arguments to support the conclusions made. The experience gained in the initial prototyping effort is currently being used to further expert systems research and to develop an extensive system that ultimately can be used by the marketing organization.

The operations sheets generator (OPGEN) is an expert system that helps industrial engineers at the Hazeltine manufacturing and operations facilities plan the assembly of printed circuit boards. In this article, we describe the evolution of OPGEN from its initial development in the Hazeltine research laboratories to its routine use in an integrated manufacturing environment. We describe our approaches to the problem that occurred during the development, integration, and rehosting of OPGEN and provide some methodological guidelines to expert system builders who are concerned with the final delivery of an expert system.

Large engineering projects, such as the engineering development of computers, involve a large number of activities and require cooperation across a number of departments. The Callisto project was born out of realization that the classical approaches to project management do not provide sufficient functionally to manage large engineering projects. Callisto was initiated as a research effort to explore project scheduling, control and configuration problems during the engineering prototype development of large computer systems and to devise intelligent project management tools that facilitate the documentation of project management expertise and its reuse from one project to another. In the first phase of the project, rule-based prototypes were used to build quick prototypes of project management expertise and the project management knowledge required to support expert project managers.

Initial Development Approach In the following eight subsections, we present a brief discussion of methodology for expert system development, selection of problem and tools, knowledge engineering and prototype implementation, operational feasibility, and the actual development of a working prototype of a process planning expert system. Methodology for Expert System Development Expert systems require a software development methodology that differs in some respects from those methodologies used for conventional systems. Most knowledge-based development methodologies used by organizations experienced in building expert systems are similar in that they concentrate on the early (feasibility) stages of a project. Very little has been published on the later stages, which are concerned with expert system delivery, integration, and maintenance. During the development of OPGEN, we incorporated the lessons learned in these early stages and revised our original approach to provide for integration and maintenance. Most expert system development methodologies are a variation on the following theme, which paraphrases Haycs-Roth (1985): (1) expert system technology is determined to be relevant to a product; (2) management provides an opportunity for action; (3) a preliminary business application is assembled; (4) a knowledge engineering consultant verifies the opportunity; (5) a knowledge engineering project team is formed and assesses the knowledge; (6) the knowledge engineering project manager plans the project; (7) the user organization Figure 2 OPGEN bzput Circuit Layout Diagram.