This paper presents a simultaneous optimization method of a case-based reasoning (CBR) system using a genetic algorithm (GA) for product designing. Prior research proposed many hybrid models of CBR and the GA for product design. However, those models were not good at aiding at creative designing. In this study, CBR and GA combine with an algorithm process for simulation of directed similarity association according to human being's thinking models. Experimental results show that the new hybrid model outperforms other conventional approaches for creative design.