In the research of job shop scheduling problem based on genetic algorithm, the improved genetic algorithm is used to obtain the optimal scheduling results. The scheduling model is established with the shortest processing time of the workpiece as the target. An adaptive crossover and mutation probability formula is proposed, and the elite retention strategy is used to solve job shop scheduling problem. The benchmark cases LA01 and FT06 are used as simulation objects. The corresponding Gantt chart and the search process curve are obtained, and the feasibility of the improved algorithm is obtained from the simulation results.