Case-based reasoning (CBR), which is based on the cognitive assumption that similar problems have similar solutions, is an important problem-solving and learning method in the field of artificial intelligence. In this article, the development of CBR is mainly reviewed, and the major challenges of CBR are summarized. The paper is organized into four parts. First, the basic framework and concepts of CBR are introduced. Then, the developed technology and innovative work that were formed in solving problems by CBR are summarized. Moreover, the application fields of CBR are sorted. Finally, according to the idea of deep learning and interpretable artificial intelligence, the main challenges for the future development of CBR are proposed.

To improve the accuracy of similarity measures in case-based reasoning, in this paper, we propose a deep metric learning method based on a self-attention mechanism and a Siamese neural network to realize the weighted similarity measure between cases. In this method, weight assignment and similarity measurement processes are integrated into a deep network. The method can map cases to a new feature space through nonlinear processing of the network layer to obtain better feature representation. The inner relationship between the features is captured by the self-attention mechanism, which is connected to the previous network layer, and the weight of the features is determined by the scoring function. Finally, a metric function is added to the contrastive loss to measure the case similarity. Experiments show that the accuracy of this method is better than that of other algorithms in the similarity measure and can improve the accuracy of case retrieval.

To improve the accuracy of similarity measures in case-based reasoning, in this paper, we propose a deep metric learning method based on a self-attention mechanism and a Siamese neural network to realize the weighted similarity measure between cases. The method maps the original case features to the new feature space through the Siamese neural network and then assigns the feature weights through the scoring function in the self-attention mechanism. Finally, a metric function is added to the contrastive loss to measure the case similarity. Experiments show that the accuracy of this method is better than other algorithms in the similarity measure and can improve the accuracy of case retrieval.