Information Technology Reference
In-Depth Information
the various steps involved in the process of locating services, namely, goal
discovery, goal refinement, Web service discovery, and service discovery.
Below, we shall first briefly describe heuristic classification, summarizing
its relevance to service discovery. We shall then show how this model is applied
in WSMO as an underlying conceptual pattern in order to structure the service
discovery process.
Heuristic Classification
In [29], Clancey provided a landmark analysis in the area of expert systems.
On the basis of an analysis of numerous rule-based systems for classification
and diagnosis, he extracted a pattern of three inference steps that helped to
understand the various production rules implemented in the various systems. 1
The problem-solving method that he called heuristic classification separates
abstraction, matching, and refinement as the three major activities in any
classification and diagnosis task (see Fig. 9.2).
Fig. 9.2. The three major processes of heuristic classification
Abstraction is the process of translating concrete descriptions of a case
into features that can be used for classifying the case. For example, the name
of a patient can be ignored when making a diagnosis, his/her precise age may
be translated into an age class, and his/her precise body temperature may be
translated into a finding “low fever.” The process is about extracting features
relevant to classification from a concrete description of a case.
Matching is the process of inferring potential explanations, diagnoses, or
classifications from the extracted features. It matches the abstracted case
description with abstract categories describing potential solutions.
Refinement is the process of inferring a final diagnosis, that explains the
given findings. This process may include the acquisition of new features that
describe the given case. However, it is now the potential solution that guides
the process of acquisition of these features.
1 In [104], heuristic classification has been used as a model for improving the trans-
lation process between different dialects of XML Schema.
Search WWH ::




Custom Search