In this paper, data mining of labor education data in colleges and universities has adopted the normalization algorithm for data processing, while association rules, Apriori algorithm and principal component analysis are proposed as the methods for monitoring the quality of digital transformation of labor education. The association rule examines the relationships between transactions using support, confidence, and enhancement, while the Apriori algorithm identifies all frequent item sets based on support. Through the principal component analysis method to establish the establishment of labor education data sample matrix, after standardized processing and calculation, the performance of each indicator or factor of the digital transformation of labor education is analyzed. In this paper, the quality evaluation of digital transformation is carried out on the basis of labor education data from the first semester of the academic year 2024-2025 at University A. In the evaluation of teachers’ teaching quality, “good labor teaching methods and labor teaching content” and “young and middle-aged teachers whose gender is male, whose title is lecturer and whose age is less than 45 years old” have strong correlation with the good teaching evaluation results, which clarify the direction of teaching improvement of teachers. The direction of teaching improvement is clear. As for students’ academic performance, the factors with the highest variance contribution rate are technology utilization ability (39.026%), practical ability (8.174%), and home-school-society collaboration ability (6.265%), which clarifies the direction of talent cultivation.