Adaptive genetic algorithm for computer course scheduling system under the background of educational informatization

Currently, traditional scheduling methods are difficult to cope with the increasing demand and complexity of education, especially when dealing with large-scale data, diverse course schedules, and personalized teaching needs. In addition, traditional genetic algorithms make it easy to fall into local optimal solutions, and difficult to find global optimal solutions in complex scheduling environments. Based on this, the study proposes an educational course scheduling method based on an improved adaptive genetic algorithm. The simulated annealing algorithm is introduced, combined with the multi-strategy selection operation, to solve the problem that the genetic algorithm is easy to fall into the local optimum in the scheduling problem. The experiments showed that when the system was iterated 180 times, the optimal fitness value of other algorithms was 1572.44, while that of the proposed method was 1578.18. In terms of the accuracy of course scheduling, the proposed method achieved 97.88% accuracy in the second run. In addition, in terms of scheduling time, the proposed method had a scheduling time of 1.84 seconds in the sixth run, whereas the other algorithms had scheduling times greater than 2.00 seconds. The findings indicate that the research offers a novel optimization approach for computerized class scheduling systems within the domain of education informatization. This approach entails enhancing the adaptive genetic algorithm and integrating it with the simulated annealing algorithm. The method can effectively solve the problems existing in the traditional scheduling method, improve the efficiency and accuracy of scheduling, and is of great significance for promoting the development of education informatization.