There is a contradiction between the high-density residential area development form and comfortable outdoor physical environment. The existing studies on wind environment of high-rise residential areas only provide the guidance for the simple general layouts, which cannot cope with the fact that most high-rise residential areas are mixed of point buildings and board buildings, and it would cost a lot of time and resources to carry out computer simulation of each layout. This paper presents a new tool, which uses the automatic optimization function of genetic algorithm and the prediction function of fully convolutional neural network to integrates three functions: the automatic generation of high-rise residential layout, the simulation of wind environment and the comparison for optimization, to learn plan scheduling and obtain the optimal solution for high-rise residential layout under specific plot ratio and plot conditions, provides guidance for today's fast-paced architectural design.