The promotion of TOD (transit oriented development) concept has given new optimization requirements to the street space of rail transit station area. The scientific evaluation and quantitative research of station area construction environment need to be carried out urgently. As an important transportation corridor in rail transit station area, the space quality of street is an important level of built environment. In this paper, 73 subway stations in Chengdu are selected to support multi-source big data such as street network, POI (point of interest), street view pictures, etc., using machine learning and spatial design network Analysis (sDNA) and other technologies, constructed an evaluation system with convenience, functionality and comfort as the core, carried out large-scale quantitative evaluation of the station area street space quality, and proposed guidance and control strategies for different levels of stations. The results show that 68.03% of the station area streets score is lower than the medium level, the street function and comfort are generally good, and the convenience is poor; at the station level, the street space quality presents the distribution characteristics of high in the South and low in the north, high in the West and low in the East, high in the inside and low in the outside. The research makes the analysis accuracy of human-oriented scale, the analysis depth of site scale and the analysis breadth of urban scale can be taken into account, which is helpful to create an efficient dynamic feedback mechanism of urban management.