In this paper, the initial population, coding design, adaptive crossover and mutation operators and conflict detection methods of traditional genetic algorithm are studied. Using the operator operation with better performance, the crossover rate and mutation rate are adjusted nonlinearly according to the individual fitness between average fitness and maximum fitness, and an improved new adaptive genetic operator is constructed, An improved new adaptive genetic algorithm is designed, which makes the algorithm jump out of the local optimal solution and improves the accuracy. On this basis, the elements and constraints of college course scheduling are analyzed, the mathematical model of College intelligent course scheduling system is established, and the improved adaptive genetic algorithm is applied to college intelligent course scheduling system.