Application of Competency-oriented Multidimensional Teaching Effect Evaluation Model in Data Structures and Algorithms Course

Aiming at the problem that the “single-dimension” teaching effect evaluation, which is mainly based on the result evaluation, cannot effectively evaluate the students' learning effect in the online and offline teaching mode, we constructed a “competence-oriented multi-dimension teaching effect evaluation model”. Based on the analytic hierarchy process (AHP), the model constructs a competence evaluation system with four evaluation dimensions: self learning, hands-on practice, innovative thinking and collaborative learning to evaluate students' learning effects. The weights of the indicators at all levels were calculated by AHP, and the competence evaluation model was constructed based on machine learning and validated to ensure the scientificity and rationality of the evaluation. Taking the Data Structure and Algorithms course as a practical case, relying on diversified online teaching platforms, course knowledge map and AI tools, we collect students' learning process data through multiple channels, and utilize the model to conduct a multi-dimensional and comprehensive evaluation of students' learning effects. The research and practice show that the model provides powerful data support for the evaluation and improvement of students' practical ability, comprehensive quality and personalized learning effect.