WOMDI-Apriori Data Mining Algorithm for Clustered Indicators Analysis of Specialty Groups in Higher Vocational Colleges

The cluster effect of specialty groups plays an important role in the development Higher Vocational Colleges. purpose this research is to scientifically explore interaction mech- anism clustering indexes higher vocational colleges, uantitatively analyze correlation these indexes, nd reasonable measures promote ocational olleges. Firstly, data denoising and field screening were car- ried out on original data, then variables clustered divided into LHS (Left Hand Side) RHS (Right Side). Then, improved multi-dimensional interactive Apri- ori association rule mining algorithm considering index weights orientation constraints was proposed. Apriori traditional applied mine structured sets. results show that WOMDI-Apriori study improves accuracy by 79.96% compared with algorithm. indicate that, when indicators brand, key characteristic majors at or above provincial level, proportion full-time teachers double qualifications, number internship students accepted cooperative enterprises are a low projects satisfaction employers graduates would be negatively affected; majr category equipment manufacturing subjected various factors coupling, which may lead different graduates’ counterpart mployment rate; for rules where uccessor dominated negative results, should taken avoid reduce possibility their occurrence as much possible. For successors positive facilitate frequent item sets whenever framework proposed can provide theoretical guidance analyzing operating characteristics promoting effects colleges.