Aiming at the problem of uneven computational load among multi-UAVs in the edge network environment， which causes the failure of offloading tasks， a multi-UAV collaborative intelligent task offloading scheme is proposed. By jointly considering task allocation， computing resource allocation， and UAV trajectory， the optimization problem is established to maximize the fairness of computing load among UAVs and minimize the power consumption. Firstly， the optimization problem is modeled as multiple intelligent agent Markov decision process model. Then， a collaborative offloading algorithm based on multi-agent deep deterministic policy gradient （MADDPG） is proposed. The simulation results show that the proposed multi-UAV collaborative scheme can effectively improve task completion rate and fairness of computing load， and it is effectively applicable to large-scale user device scenarios.