Swarm Intelligence-Driven Dynamic Resource Allocation Model for Optimizing Innovative Entrepreneurship Teaching in Higher Education

Traditional innovative entrepreneurship teaching resource allocation is difficult to adapt to the dynamic changes in demand and personalized needs cannot be met. In addition, different types of resources are difficult to coordinate, which affects the teaching quality and resource utilization efficiency. This paper solves the problem of unreasonable resource allocation in innovative entrepreneurship teaching dynamically and scientifically through a model integrating swarm intelligence algorithms. Particle swarm optimization (PSO) is used to optimize the matching of teachers and course resources and ant colony optimization (ACO) is adopted to optimize fund allocation. Personalized matching of practical projects and student needs is achieved through adaptive particle swarm optimization (APSO) and a cross-departmental resource coordination mechanism is established. Based on the proposed model, experiments were conducted across 10 universities, with historical data used as a control for multi-dimensional evaluation. The results show that the utilization rate of teaching resources increased from 68.73% to 85.54%, the course matching degree improved from 62.49% to 81.04%, student participation rose from an average of 54.94% to 73.17%, the completion rate of teaching projects increased from 62.6% to 71.98% and the proportion of cross-departmental resource sharing and entrepreneurship collaboration successfully implemented grew from 58.23% to 75.17%. These quantitative results demonstrate that the model significantly improves the allocation of innovative entrepreneurship teaching resources in higher education, with strong adaptability and potential for broader application.