A novel global optimization method based on artificial neural network and genetic algorithm is proposed for laser parameters design. An artificial neural network (ANN) is built to simulate the mechanism of the effects of laser parameters on its output power. And then the laser parameters are further optimized with genetic algorithm (GA) with the above obtained network as objective function. As an example,parameters of a typical plano-concave cavity He-Ne laser are globally optimized to testify the feasibility and effectiveness of the method. As concluded from the optimization experiment,the mean square error between the experimental data and simulation data from laser output power network is only 0.0127 mW. The output power of laser with parameters optimized by genetic algorithm is larger than the other laser with the same cavity length,which proves the effectiveness of the method.