Abstract
The educational institutions have been grappling with trying to come up with effective schedules of classes to satisfy different competing demands and resource maximization. The traditional manual processes are resource consuming and have the tendency to be subject to errors that in most situations cause scheduling inconveniences and inefficient resource distribution. The research presents a novel model that combines the notions of constraint satisfaction in addition to the contemporary huge language models to automate the production of academic schedules. We also apply multistage validation, conflict resolution, as well as intelligent workload distribution algorithms. Experimental analysis found on varying institutional dimensions depicts immense improvements in terms of efficiency in scheduling, conflicts diminution and improved computational performances in comparison with the traditional methods. The proposed system has the ability to produce conflict free schedules having a high index of 98.7 percent in comparison to the 76 percent decrease in processing time in comparison to manual processes. The results of the empirical tests indicate that the application will be applicable in the real world in most educational institutions with established new trends of automated scheduling systems.
References
- E. K. Burke, J. Marecek, A. J. Parkes, and H. Rudova´, “A supernodal formulation of vertex colouring with applications in course timetabling,” Annals of Operations Research, vol. 153, no. 1, pp. 105–130, 2007.
- H. Babaei, J. Karimpour, and A. Hadidi, “A survey of approaches for university course timetabling problem,” Computers & Industrial Engineering, vol. 86, pp. 43–59, 2015.
- Y. Wang, X. Chen, and L. Zhang, “Reinforcement learning for university course timetabling,” in Proc. Int. Conf. Machine Learning Applications, Boca Raton, FL, USA, Dec. 2019, pp. 845–850.
- N. Pillay, “A survey of school timetabling research,” Annals of Operations Research, vol. 218, no. 1, pp. 261–293, 2014.
- J. S. Tan, K. L. Goh, S. C. Ong, and C. K. Ngan, “A neural network approach for timetabling using deep learning,” IEEE Access, vol. 9, pp. 58142–58156, 2021.
- S. Ceschia, L. Di Gaspero, and A. Schaerf, “Educational timetabling: Problems, benchmarks, and state-of-the-art results,” European Journal of Operational Research, vol. 308, no. 1, pp. 1–18, 2023.
- S. Kristiansen, M. Sørensen, and T. R. Stidsen, “Integer programming for the generalized high school timetabling problem,” Journal of Scheduling, vol. 18, no. 4, pp. 377–392, 2015.
- T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, J. Dhariwal, et al., “Language models are few-shot learners,” in Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 1877–1901.
- A. Vaswani, N. Shazeer, N. Parmar, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in Neural Information Processing Systems, vol. 30, 2017, pp. 5998–6008.
- F. Rossi, P. van Beek, and T. Walsh, Eds., Handbook of Constraint Programming. Amsterdam: Elsevier, 2006.
- S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Hoboken, NJ: Pearson, 2020.
- R. Qu, E. K. Burke, B. McCollum, L. T. G. Merlot, and S. Y. Lee, “A survey of search methodologies and automated system development for examination timetabling,” Journal of Scheduling, vol. 12, no. 1, pp. 55–89, 2009.
- OpenAI, “GPT-4 technical report,” arXiv preprint arXiv:2303.08774, 2023.
- Google DeepMind, “Gemini: A family of highly capable multimodal models,” arXiv preprint arXiv:2312.11805, 2023. numder is not showing in word file please check
