In order to overcome the shortcomings of particle swarm optimization(PSO) in solving multimodal function optimization problems which includes easily falling into local minimum, low accuracy and difficultly searching extreme points as many as possible, a novel cloud model particle swarm optimization algorithm based on the pattern search method(PCPSO) is proposed. The cloud model particle swarm optimization(CPSO) algorithm is used to do global searching in the feasible zone, and then the pattern search method(PSM) is used to improve the accuracy of the sub-optimal solution. The simulation tests demonstrate that the proposed method can ensure the convergence speed, meanwhile the convergence accuracy and the number of extreme points are strikingly improved.