Research on Precise Matching Models for Talent Cultivation Needs in Industry-Education Integration Using Clustering Algorithms

The demand for industry talent has grown increasingly diverse due to advancements in industrial structure and technology, while the existing education system struggles to align with these evolving needs. This study proposes a clustering-based matching model to address the mismatch between talent cultivation and industry demand. Using industry demand data from Guangdong Province and a university's education training data, the study evaluates the performance of K-Means and DBSCAN clustering algorithms on different datasets. The results demonstrate that DBSCAN outperforms K-Means in handling complex and non-uniformly distributed data, achieving a 6% higher matching accuracy by effectively identifying noise and anomalies. K-Means, while stable with uniformly structured data, is less effective in noisy environments. This research provides actionable insights for educational institutions to refine curricula and enhance students' employability while enabling industries to recruit suitable talent more efficiently through improved alignment.