Aiming at the active distribution network service restoration with distributed wind power and PV generation connected, the uncertain bi-level programming theory is applied to establish the active distribution network service restoration model considering the uncertainty of new energy power generation. The established model takes switch state change as the upper control variable, while comprehensive satisfaction degree in the form of confidence is considered as the objective function of upper-level model. The energy scheduling scheme of distribution network after service restoration is taken as the lower decision variables. The comprehensive cost in the form of confidence is used as the objective function of the lower-level model. Based on game theory and chaos particle swarm optimization algorithm, the upper-level optimization and lower-level solving procedure are designed respectively, and then the distribution network service restoration scheme can be obtained. Finally, a numerical example is given to illustrate the correctness and effectiveness of the proposed method. This work is supported by Science and Technology Project of State Grid Corporation of China (No. kj2018-063) and Science and Technology Program of State Grid Hebei Electric Power Company (No. kj2017-20).