The Combined FP-Growth and Ant Colony Optimization Algorithms in Scientific Research Project Management

This study addresses the complexity of resource allocation and task scheduling in scientific research project management. To this end, a hybrid optimization framework integrating the Frequent Pattern Growth (FP-Growth) algorithm and Ant Colony Optimization (ACO) is proposed. First, FP-Growth is applied to preprocessed project data to identify key tasks and strongly associated task combinations. Based on these results, an improved ACO algorithm is then employed for task allocation and resource scheduling, where ant-inspired search behavior is used to optimize task execution paths. Experimental comparisons with conventional methods demonstrate the effectiveness of the proposed model. The FP-Growth–ACO approach reduces path length by 45.22%, decreases iteration counts by 78.85%, and improves convergence efficiency by 83.92%. In addition, the number of turning points is reduced by 31.94%, indicating more efficient path structures. From a project management perspective, the proposed model also achieves superior performance across multiple evaluation metrics, including resource utilization (0.87), cost-effectiveness (0.96), operational efficiency (0.91), technological benefit (0.87), and social benefit (0.76). Overall, the results confirm that the proposed hybrid optimization model effectively improves resource allocation and task scheduling efficiency in scientific research project management, outperforming traditional approaches in both computational and managerial performance.