An integrated case-based reasoning approach for intelligent help desk fault management
| Autor: | Shee Eng Jeremiah Kwan, Yuh Foong David Law, Sew Bun Foong |
|---|---|
| Rok vydání: | 1997 |
| Předmět: |
Reasoning system
Knowledge representation and reasoning business.industry Computer science General Engineering Intelligent decision support system Cognition Legal expert system Machine learning computer.software_genre Model-based reasoning Fuzzy logic Expert system Computer Science Applications Workflow Artificial Intelligence Facilitator Information system Case-based reasoning Artificial intelligence Software engineering business computer |
| Zdroj: | Expert Systems with Applications. 13:265-274 |
| ISSN: | 0957-4174 |
| DOI: | 10.1016/s0957-4174(97)00042-0 |
| Popis: | As modern business functions become more complex and knowledge-intensive, with increasing demands for quality services, there is an emerging trend for organisations to develop and deploy intelligent knowledge-based systems for mission-critical operations. Some of the challenges in successfully implementing this breed of systems depend on how well the intelligent system is integrated with conventional existing information systems and workflow, and the quality of the intelligent system itself. Developing quality expert systems lies in the effective modelling of cognitive processes of human experts and representation of various forms of related knowledge in a domain. An integrated intelligent system called the Intelligent Help Desk Facilitator (IHDF), has been developed for computer and network fault management. The system, which comprises various modules including an expert system, is successfully deployed in a problem response help desk environment of a local bank. This paper describes a cognitive-driven approach to the development of the expert system based on a hybrid knowledge representation and reasoning strategy. The approach incorporates a hybrid case-based reasoning (CBR) framework of techniques which include case memory organisation structures (discrimination networks and shared-featured networks), case indexing and retrieval schemes (fuzzy character-matching, nearest-neighbour similarity matching and knowledge-guided indexing); and an interactive and incremental style of reasoning. The paper discusses the design and implementation of the expert system component of IHDF and illustrates the appropriateness of the hybrid architecture for problem resolution and diagnostic types of applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect