現今企業在招募社會新鮮人時，除了重視個人的專業能力之外，自身的軟實力也是招募時看重的能力。為了讓學生們能瞭解自己的興趣以及在職場上的競爭力，教育部推出「大專校院就業職能平台」(UCAN)提供職業興趣探索及職能診斷，職能診斷包含了職場共通職能診斷及專業職能診斷，其中職場共通職能代表著職場中常見的軟實力，分別為溝通表達、持續學習、人際互動、團隊合作、問題解決、創新、工作責任及紀律還有資訊科技應用，透過診斷，將能力量化以了解個人的能力程度。
根據列出的共通職能項目，依經驗可判斷當中有些項目彼此間存有相關性，本研究利用決策樹找出學生課程成績與共通職能之間的規則，透過規則分析評估項目間是否相關且能進行合併，使項目的總數減少，並且透過規則分析每項共通職能的學生課程成績分布，藉此協助校務研究在進行決策時，可以根據結果來決定如何改善學生的軟實力，以提升學生在未來職場中的競爭力。

When companies recruit fresh graduates, in addition to their personal professional abilities, their own soft power is also an ability that they value. In order for students to understand their own interests and competitiveness in the workplace, the Ministry of Education launched the "University and College Employment Function Platform" (UCAN) to provide career interest survey and competency assessment. Competency assessment includes general competency assessment and professional competency assessment. General competencies represent common soft power in the workplace. They are communication, continuous learning, interpersonal interaction, teamwork, problem solving, innovation, job responsibility and discipline, and information technology applications. Quantify these abilities through assessment to understand the individual’s abilities.
The listed general competency items can be judged based on experience that some of them are related to each other. This research uses decision trees to find the rules between student's course performance and general competencies. Through rule analysis to evaluate whether the items are related and can be merged, so that the total number of items is reduced. And through rules to analyze the distribution of students' course scores for each general competencies, to assist institutional research in making decisions. According to the results to determine how to improve students' soft power, so as to enhance students' competitiveness in the workplace.

[1] 李紋霞、符碧真（2017）。全球視野在地化的校務研究：以國立臺灣大學經驗為例。教育科學研究期刊，62（4），1-25。
[2] 劉孟奇（2016）。以校務研究為校務決策之本。評鑑雙月刊，60，10-12。
[3] Quinlan, J. R., “Induction of Decision Trees”, Machine Learning 1: 81-106, Kluwer Academic Publishers, 1986.
[4] Quinlan, J. R., C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, 1993.
[5] Breiman, Leo; Friedman, J. H., Olshen, R. A., & Stone, C. J., Classification and regression trees, Monterey, CA: Wadsworth & Brooks/Cole Advanced Books & Software, 1984.
[6] C. E. Shannon, “A mathematical theory of communication”, The Bell System Technical Journal, vol. 27, no. 3, pp. 379-423. doi:10.1002/j.15387305.1948.tb01338.x., July 1948.
[7] Quinlan, J. R. “Simplifying decision trees”, International Journal of Man-Machine Studies, 27(3), 221–234. doi:10.1016/s0020-7373(87)80053-6, 1987
[8] Mingers, John., “Expert Systems—Rule Induction with Statistical Data”, The Journal of the Operational Research Society. 38. 10.1057/jors.1987.5., 1987.
[9] BRESLOW, L. A., & AHA, D. W., “Simplifying decision trees: A survey”, The Knowledge Engineering Review, 12(01), 1–40. doi:10.1017/s0269888997000015, 1997.
[10] Breiman, L., “Random Forest”, Machine Learning, 45(1), 5–32. doi:10.1023/a:1010933404324, 2001.