As to overcome the drawback of easily falling into local optimum and slow convergence rate of the conventional artificial bee colony algorithm, this paper proposes an artificial bee colony algorithm based on the improved neighborhood search strategy. Firstly, in order to enhance the diversity of population and prevent local optimum, a kind of chaotic anti-base initialization mechanism is designed according to the chaotic thoughts and opposed-based learning method. Then, in the following stage of following bee stage, the quantum behavior is introduced to simulate the optimal solution of the artificial bee according to the optimal position of the former individual, the optimal position of the former individual is designed with crossover, and the control parameters of the well model is used to improve the balance exploration and development capability, a strategy of neighborhood search improvement strategy in observation is designed, to improve the convergence accuracy of the algorithm, Finally, the proposed algorithm is compared with the particle swarm optimization algorithm, ant colony algorithms, and other improved artificial colony algorithm, and simulation analysis is made on 12 standard test functions, the results show that the proposed algorithm not only improves the convergence speed and accuracy, but also has certain advantages in terms of high-dimensional function optimization.