Structural cases representation in case-based expert systems

In recent years, a lot of case-based expert systems (CBESs) have been proposed to solve problems in many domains, but how to effectively retrieve an approximate case is still a bottleneck in building CBESs. In this work, the embedded relationships between the cases are used to solve the above problem. To elicit the knowledge embedded in the case structure, a new knowledge representation, named structural cases (SCs), which is the basis of our system, is proposed in order to describe the relationships between two different cases. Based on this representation, a process of transforming the cases into a set of SCs is proposed, where two cases with similarity greater than a given threshold are merged into one SC. Moreover, algorithms for the interaction process based on the SCs are also proposed, which can be used to retrieve more suitable results. Finally, some examples are given to demonstrate the practicality of the SCs