A Data-Driven Knowledge Discovery Framework for Smart Education Management Using Behavioral Characteristics

Based on the characteristics of behavioral patterns, this paper constructs a data-driven knowledge discovery framework for smart education management. The aim is to realize automatic education effect evaluation using digital intelligent algorithms. The designed framework includes four parts: online course evaluation based on data mining, mining of association rules based on rough sets, dynamic adjustment of evaluation index weights, and the fuzzy comprehensive evaluation based on association rules. Their joint effect constructs a digital workflow, which realizes evaluation of both teaching effect of teachers and learning effect of students. In the simulation process, the designed framework is constructed based on the browser/server mode. Modeling tools such as business flow chart and unified modeling language are used to build the system logic model. The experimental results show that the performance of the education management framework based on 4 first-level indicators, 11 second-level indicators and 3 third-level indicators is stable. The testing case demonstrates an efficient method of evaluating perceived behavior patterns for intelligent educational management. From the perspective of system theory, the key elements of wisdom teaching in colleges and universities are summarized and refined; the behavioral model of wisdom teaching in colleges and universities is proposed, which deepens the understanding of the inner structure and laws of teaching and education practices in college classrooms.

Automated summary

This paper constructs a data-driven knowledge discovery framework for smart education management based on the characteristics of behavioral patterns. Its aim is to realize automatic education effect evaluation using digital intelligent algorithms. The framework includes online course evaluation, mining of association rules, dynamic adjustment of evaluation index weights, and fuzzy comprehensive evaluation based on association rules. These parts work together to construct a digital workflow that evaluates both the teaching effect of teachers and the learning effect of students.