Optimization and Allocation of Innovation and Entrepreneurship Education Resources in Universities based on Particle Swarm Optimization Algorithm with Long Short-Term Memory
Jing Liu · 2025
The optimization and allocation of innovation and entrepreneurship education resources in universities are crucial for fostering creativity and technological advancement. However, traditional resource allocation methods often struggle with inefficiencies due to the dynamic nature of educational needs and constraints in resource distribution. This research introduces a novel optimization framework leveraging the Particle Swarm Optimization (PSO) algorithm with Long Short-Term Memory (LSTM) networks to enhance resource allocation strategies. The proposed model utilizes PSO for global search optimization, ensuring efficient distribution of resources, while LSTM captures complex temporal dependencies in educational demands, enabling adaptive and data-driven decision-making. By integrating these advanced computational techniques, the model optimizes resource utilization and improves the effectiveness of entrepreneurship education. Experimental results show that the model significantly enhances allocation efficiency, reducing resource wastage and maximizing student learning outcomes. The framework achieves an Allocation Efficiency of 97.8% and a Prediction Accuracy of 98.5%, ensuring optimal resource distribution and accurate demand forecasting. Performance metrics, including a Mean Absolute Error (MAE) of 1.6, Root Mean Square Error (RMSE) of 2.4, and an R2Score of 0.97, validate its precision and reliability. Additionally, the model attains an Optimization Convergence Rate of 95.2%, demonstrating the effectiveness of the PSO algorithm in rapidly achieving optimal allocation. These results emphasize the potential of AI-driven methodologies in transforming educational resource management, offering scalable, intelligent solutions for higher education institutions seeking to strengthen innovation-driven learning environments.