This paper introduces an improved hybrid ant colony optimization, that integrates ant colony optimization and three operators to address the vehicle routing problem with time windows. Ant colony optimization often tramps into local optimality, to enhance the possibility of escaping local optima, this paper proposes a hybrid strategy: when ant colony optimization trapping in local optimum, genetic algorithm is used to explore for solutions based on the current optimal solution. And for improving the performance of ant colony optimization, two neighborhood search mechanisms are introduced. The primary operator prioritizes the number of vehicles reduction, while the secondary operator addresses total travel distance minimization. The proposed algorithm undergoes rigorous evaluation across Solomon benchmark dataset, with performance benchmarking against the ant colony optimization and other algorithms. The experimental results show that the improved hybrid ant colony optimization is a competitive algorithm for the vehicle routing problem with time window.