High-Discrimination Comparison Algorithm for the Comprehensive Evaluation of Innovation Ability in Colleges and...

Area of Science:

• Educational Assessment
• Fuzzy Mathematics
• Management Science

Background:

• Cultivating student innovation ability is a key objective in higher education.
• Traditional algorithms struggle with the quantitative evaluation of innovation.
• A robust method is needed to accurately assess and rank innovative potential.

Purpose of the Study:

• To propose a novel algorithm for the quantitative evaluation of student innovation ability.
• To address the challenges of data fuzziness and uncertainty in evaluation.
• To develop a system for ranking students based on their innovative potential.

Main Methods:

• Development of an algorithm integrating management thought and fuzzy mathematics.
• Introduction of an incompletely probabilistic fuzzy set data structure to handle data fuzziness and hesitation.
• Proposal of a consistency optimization model to manage unknown or contradictory evaluation data.
• Implementation of an automatic adjustment module for data consistency verification.

Main Results:

• The proposed algorithm effectively handles the fuzziness and uncertainty inherent in innovation ability evaluation.
• The incompletely probabilistic fuzzy set data structure preserves detailed data while accounting for decision-making hesitations.
• The consistency optimization model successfully addresses unknown and contradictory data points.
• Experimental results demonstrate the algorithm's effectiveness, high discrimination ability, and superiority over existing methods.

Conclusions:

• The developed algorithm provides a superior quantitative method for evaluating student innovation ability.
• The novel data structure and optimization model enhance the accuracy and reliability of the evaluation process.
• This approach offers a significant advancement in assessing and fostering innovation in higher education.