In order to realize a high-quality and goodperformance service composition, based on current approach, we propose a new QoS-driven dynamic selection of composite Web Services, which takes account of both the QoS properties and interface parameters matching degree. When doing the selection, we aware that the task is more or less a multistage decision-making process. Motivated by transiently chaotic neural networks? high parallel performance and powerful computation ability, a new structured transiently chaotic neural network algorithm is proposed in this paper for such task. In order to make this algorithm more adaptable for multistage decision-making problem, we propose a new structured neural network to express the composed service instead of using the traditional neural networks, which minimizes the neurons involved and shows high performance than the earlier ones. Finally, through experimentation one can find that method proposed in this paper is more practical and effective than others.