Case-Based Reasoning (CBR) and TRIZ

CBR

by Cindy Marling, marling@alpha.ces.cwru.edu
Computer Science Dept. University of Melbourne, Australia.

Case-Based Reasoning (CBR) is an Artificial Intelligence (AI) paradigm, in which new problems are solved by storing, retrieving, and adapting the solutions to previously encountered problems. It offers both a cognitive model of human problem solving and a concrete methodology for building knowledge-based systems. CBR is based on the premise that expertise is experiential in nature. What separates an expert from a novice is the breadth of his or her experience [1]. For example:

A doctor who has seen many cases of some ailment is quick to recognize it in a new patient.
A lawyer refers to past legal cases in defending a new client.
A mechanic who has heard many rattles can tell you why your car is rattling.

A CBR computer system typically includes:

a case library, or set of example problems and solutions, called cases
a method of storing cases in the case library that facilitates their subsequent retrieval
an indexing scheme for organizing the cases
a method of partial matching to determine which cases are most relevant to a current problem
a method of adapting an old solution to fit a current problem

CBR systems have been implemented in many domains. Some representative systems are:

CASEY, which diagnoses cardiac patients based on the diagnoses of previous patients
Hypo, which helps lawyers make arguments based on legal precedents in the domain of trade secrets law
Clavier, which determines how to load an autoclave (a large, pressurized convection oven) with parts to cure, based on past successful configurations
CHEF, which creates new recipes from old ones, by adapting them to requests for new ingredients or tastes

[1] Janet Kolodner, Case-Based Reasoning, Morgan Kaufman, San Mateo, CA, 1993.

CBR WWW Sites

TRIZ

by Semyon D. Savransky

G.S. Altshuller and his team have shown that the general knowledge generated by previous solutions can be organized and used by the inventors through the comparison of their problems with similar standard problems. Then possible standard solution associated with the standard problem, are applied the specific problem. That is why the search and knowledge of "strong solutions" is a part of TRIZ studies.

Actually, this process is studied by CBR in various area of human knowledge . Via this process, TRIZ accumulates innovation experience and provides the most effective solutions independent on particular knowledge inside some industry. Note that till 1990 TRIZ and CBR were developed independently.

Back