In the actual production process, it has increasingly become an important factor for companies to pay attention to of the processing cost. In this paper, the flexible job-shop scheduling problem aiming at minimizing processing cost and makespan is studied. Firstly, a scheduling model based on actual constraints is constructed, and the improved genetic algorithm is purposed to solve the model. This algorithm introduces quality gene segment to enhance the evaluation of chromosome fitness values, which accelerates the elimination of poor quality chromosomes. A population initialization method based on the minimum overall load and the minimum local load is proposed for quality optimization of the chromosomes, and a precise mutation mechanism is designed to maintain the diversity of the population. Finally, the improved genetic algorithm is tested on a set of benchmark instance taken from the literature and compared with other approaches. The results demonstrate that the proposed algorithm outperforms others in terms of convergence speed and accuracy, which verify the effectiveness.