<![CDATA[As the transition to lifelong learning continues to advance, Recognition of Prior Learning (RPL) programs have been widely adopted across the higher education sector. For a long time, manual evaluation relying on experience-based archives has consistently faced core pain points: high labor intensity, long processing time, and significant risk of subjective bias. It is therefore extremely urgent to implement and roll out improvements to information technology-driven business processes. To address this gap, this study developed an automated decision support system for archive evaluation. Its core innovation is adapting the Profile Matching algorithm from a static single-objective framework into a dynamic multi-objective gap analysis model. The system includes four core processes: matching applicants’ verified competencies with their course learning outcomes, categorizing course learning outcomes into core and secondary groups, calculating weighted gaps, and generating standardized credit recommendations. Tested on a small dataset containing only 10 historical archives, the system compressed the original multi-day evaluation period to less than 5 minutes. The system boasts both mathematical consistency and traceable audit trails, which allow it to eliminate evaluation bias and safeguard academic integrity. It can also be extended for use in scenarios including higher education micro-credential programs and human resource management.]]>
Copyrights © 2026
