Wolfgang Wilke

Techniques and Knowledge Used for Adaptation During Case-Based Problem Solving

This paper presents a survey of different adaptation techniques and the used knowledge during adaptation. A process model of CBR and the used knowledge according to the different knowledge containers is introduced. The current models of adaptation are described and illustrated in an example domain.

On the Role of Abstraction in Case-Based Reasoning

This paper addresses the role of abstraction in case-based reasoning. We develop a general framework for reusing cases at several levels of abstraction, which is particularly suited for describing and analyzing existing and designing new approaches of this kind. We argue that in synthetic tasks (e.g. configuration, design, and planning), abstraction can be successfully used to improve the efficiency of similarity assessment, retrieval, and adaptation. Furthermore, a case-based planning system, called Paris, is described and analyzed in detail using this framework. An empirical study done with Paris demonstrates significant advantages concerning retrieval and adaptation efficiency as well as flexibility of adaptation. Finally, we show how other approaches from the literature can be classified according to the developed framework.

Building and refining abstract planning cases by change of representation language

Abstraction is one of the most promising approaches to improve the performance of problem solvers. In several domains abstraction by dropping sentences of a domain description - as used in most hierarchical planners - has proven useful. In this paper we present examples which illustrate significant drawbacks of abstraction by dropping sentences. To overcome these drawbacks, we propose a more general view of abstraction involving the change of representation language. We have developed a new abstraction methodology and a related sound and complete learning algorithm that allows the complete change of representation language of planning cases from concrete to abstract. However, to achieve a powerful change of the representation language, the abstract language itself as well as rules which describe admissible ways of abstracting states must be provided in the domain model. This new abstraction approach is the core of PARIS (Plan Abstraction and Refinement in an Integrated System), a system in which abstract planning cases are automatically learned from given concrete cases. An empirical study in the domain of process planning in mechanical engineering shows significant advantages of the proposed reasoning from abstract cases over classical hierarchical planning.

Intelligent Sales Support with CBR

Electronic commerce applications are just about to leave their infancy. While electronic cash has been around for quite a few years, the amount of business carried out through the Internet is still relatively small compared to the potential of this young technology. There are plenty of reasons for this. Tennenbaum summarizes the barriers for using this medium today with the three words: confidence, convenience, and content. Customers must have confidence that their transactions are secure, their privacy is maintained, and they will not be subject to liability. It must be convenient, as simple to use as ATMs and as ubiquitous. Finally, there must be incentives to purchase goods via the Internet, be they a better price, service, or selection.

Case-based reasoning support for online catalog sales

Case-based reasoning uses similarity measures and domain-specific knowledge for information retrieval and problem solving. The paper considers how CBR techniques can be applied to e-commerce applications to enable intelligent sales support. It reviews the limitations of ordinary databases to this task and then examines CBR techniques that can improve the usefulness of electronic catalogs. It describes an implementation of a CBR-based system in a specific application domain, and concludes with brief descriptions of two projects at the University of Kaiserslautern that advance these systems.

Using Configuration Techniques for Adaptation

Configuration is a design task that is the target of much AI research. It is a comparatively tractable design task and thus can be completely automated in a knowledge based system (KBS). Indeed the earliest commercially successful KBS was XCON, a rule-based system for configuring VAX computers developed by Digital Equipment Corporation.

An Architecture for Maintaining Case-Based Reasoning Systems

This paper describes an architecture which supports the user of a CBR system during the modelling and maintaining of the used knowledge. Different maintenance operations are described and characterised along different dimensions. We give an overview of possible operations with their resulting repair strategies. Exemplary, we describe two operations in detail. We examine the impact of maintenance operations to the overall CBR system which leads to the design of an evaluation component. As a result, we describe our architecture for the maintenance of a CBR system. We close with a short discussion.

The Development of HOMER: A Case-Based CAD/CAM Help-Desk Support Tool

The increasing number of hardware and software at Daimler-Benz personal car development in Sindelfingen combined with the constant number of help-desk operators demanded a help-desk system which goes beyond the classical trouble-ticket approach. In this application paper we give an overview of the situation at the CAD/CAM Help-Desk in Sindelfingen and the development of the case-based help-desk support tool HOMER. We describe our modeling approach and its influence on the system architecture as well as the different user roles and the help-desk tool itself. We conclude with the lessons learned during the course of this project and future prospects.

Explanation-Based Similarity: A Unifying Approach for Integrating Domain Knowledge into Case-Based Reasoning for Diagnosis and Planning Tasks

Case-based problem solving can be significantly improved by applying domain knowledge (in opposition to problem solving knowledge), which can be acquired with reasonable effort, to derive explanations of the correctness of a case. Such explanations, constructed on several levels of abstraction, can be employed as the basis for similarity assessment as well as for adaptation by solution refinement. The general approach for explanation-based similarity can be applied to different real world problem solving tasks such as diagnosis and planning in technical areas. This paper presents the general idea as well as the two specific, completely implemented realizations for a diagnosis and a planning task.

Considering Decision Cost During Learning of Feature Weights

This paper is to present a new algorithm, called KNNcost, for learning feature weights for CBR systems used for classification. Unlike algorithms known so far, KNNcost considers the profits of a correct and the cost of a wrong decision. The need for this algorithm is motivated from two real-world applications, where cost and profits of decisions play a major role.