Construction of College Labor Education Evaluation System Based on Big Data and K-Means

The labor education evaluation system often has problems such as strong subjectivity and a single evaluation index, which makes it difficult to comprehensively and objectively reflect the students’ labor literacy and practical ability. Therefore, a college labor education evaluation system based on big data and [Formula: see text]-means is constructed. To enhance labor education, we first collect relevant data. An evaluation ratio threshold is then set to eliminate low-quality data. By leveraging big data and cloud computing technology, we build a personalized labor education and teaching evaluation system. Within this system, the [Formula: see text]-means clustering algorithm is employed to classify a vast amount of college labor education data. To optimize the clustering center, particle swarm optimization is introduced. Furthermore, a multi-level evaluation system is constructed using the AHP method. This approach enables a comprehensive and systematic assessment of the effectiveness of labor education. The experimental results show that the resource utilization efficiency of the design methods is more than 90%, the loss value is the lowest 0.39, the average iteration time is 4.462[Formula: see text]s, and the evaluation time is 15[Formula: see text]s. The data clustering results show higher clustering clarity.