As a new public transport operation mode, the variable line bus integrates the characteristics of high efficiency and low cost of conventional public transport and strong flexibility of demand response public transport. At present, it has been put into use in many foreign cities and achieved good results. The operation results show that the variable line bus is an effective way to solve the problem of public transport service in low travel density areas. This paper first analyzes five factors that affect the planning of variable route bus stops, and constructs a node importance model based on these five factors, and uses K-means clustering algorithm to determine the nodes suitable for planning variable route bus stops. The results show that the method is feasible and practical, and can provide theoretical basis for domestic enterprises to plan variable route bus.

CICTP