Emergency Case Retrieval Based on Fuzzy Sets and Text Mining

Emergency management is such a domain where experiential knowledge could be easily collected, and is quite suitable for the application of case based reasoning. However, in practice there are two problems limiting the effectiveness of case based reasoning (CBR), the unstructured information and changing situation. This paper proposed an approach based on fuzzy sets and text mining to solve those two problems, which contains three steps: (a) representing the case based on fuzzy sets and text mining, (b) retrieving the similar case based on text classification, and (c) establishing connections of attributes and solutions based on Hownet. This approach could not only retrieve the most similar case, but also extract specific solutions from several cases.