A self-improving helpdesk service system using case-based reasoning techniques
Computers in Industry
Information Retrieval
Hybrid Recommender Systems: Survey and Experiments
User Modeling and User-Adapted Interaction
Exploiting hierarchical domain structure to compute similarity
ACM Transactions on Information Systems (TOIS)
Intelligent Sales Support with CBR
Case-Based Reasoning Technology, From Foundations to Applications
Evaluating collaborative filtering recommender systems
ACM Transactions on Information Systems (TOIS)
Information retrieval system evaluation: effort, sensitivity, and reliability
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Measures of semantic similarity and relatedness in the biomedical domain
Journal of Biomedical Informatics
Next best step and expert recommendation for collaborative processes in it service management
BPM'11 Proceedings of the 9th international conference on Business process management
A case retrieval approach using similarity and association knowledge
OTM'11 Proceedings of the 2011th Confederated international conference on On the move to meaningful internet systems - Volume Part I
CoKIM: Collaborative and Social Knowledge-Based Incident Manager
ASONAM '12 Proceedings of the 2012 International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2012)
Hi-index | 0.00 |
The aim of incident management is to restore a given IT service disruption, simply called incident, to normal state as quickly as possible. In incident management, it is essential to resolve a new incident efficiently and accurately. However, typically, incident resolution process is largely manual, thus, it is time-consuming and error-prone. This paper proposes a new knowledge-rich similarity measure for improving this process. The role of this measure is to retrieve the most similar past incident cases for a new incident without human intervention. The solution information contained the retrieved incident cases can be utilized to resolve the new incident. The main feature of our similarity measure is to incorporate additional useful meta knowledge, outside of incident description that is the only exploited information in typical similarity measures used in CBR, to improve effectiveness. Moreover, this measure exploits as much semantic knowledge as possible about features contained in previous incident cases. Through an experimental evaluation, we show the effectiveness, technical coherence and feasibility of this measure using a real dataset.