Answers are grounded in this paper and cite their sources.
Computational modeling study demonstrates dynamic optimization of higher education resource allocation, suggesting significant efficiency gains via reinforcement learning.
With the continuous expansion of higher education, smart campuses increasingly rely on multi-source sensing, wireless communication, and real-time data propagation to support teaching, research, and engineering resource scheduling. However, the traditional static quota management model cannot dynamically respond to changes in teaching and research demand, resulting in structural contradictions between idle and scarce resources. Existing evaluation methods also remain weak in linking efficiency diagnosis with management intervention and cross-period optimization. To address these problems, this study constructs a higher education resource allocation and management framework integrating dynamic evaluation and intelligent optimization. Human, financial, material, and information resources are taken as four input factors, and a unified analytical view is established through multi-source data acquisition and preprocessing. A dynamic network SBM-DEA model is then designed to measure intertemporal allocation efficiency, while STL decomposition, spatial clustering, and LSTM prediction are used to extract spatiotemporal resource operation patterns and demand trends. Finally, a deep Q-network-based reinforcement learning algorithm is developed to form a closed loop from efficiency diagnosis to management intervention. The results show that the proposed model effectively identifies efficiency evolution trends and fairness differences among colleges. The median resource demand response lag decreased from 17.65 h in 2018 to 10 h in 2023, while the strategy adoption conversion rate increased from 0.551 to 0.861. The study provides a big-data-driven decision tool for precise resource allocation, and its sensing-data fusion logic is also relevant to engineering management scenarios involving electromagnetic signal acquisition, wireless monitoring, and distributed information propagation.
No takes yet. Share an insight, caveat, or question.
Liang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: