Cultivation Methods and Effectiveness Assessment in Teaching University Language Courses in the Context of the Artificial Intelligence Era

Abstract

Aiming at the blind spots of university language course learning in the age of artificial intelligence, this paper builds a technical framework of intelligent cultivation method with a university language intelligent question bank, classroom student behavior recognition model, and intelligent teaching evaluation model as the main modules. The knowledge point mastery model is constructed, the knowledge point test question matrix is composed, and the learner similarity calculation is carried out to design the intelligent question bank. Introduce the YOLO algorithm to solve the problem of occlusion and small target detection of students’ behavioral actions, and propose a student behavior recognition model based on the improved YOLOv5. Intelligent selection of language teaching evaluation indexes, adoption of the recursive goal evaluation method, and establishment of the teaching evaluation model. In the evaluation of the cultivation method, HZ University is used as the research site, and experimental and control classes are set up to conduct comparative experiments. The language score of the experimental class is significantly higher than that of the control class by 4.83 points (P<0.05), and the mean values of all dimensions of learning problem-solving ability are higher than those of the control class, which also show significant differences (P<0.05). The experimental class also outperformed the control class in a number of aspects, including course learning level, cooperative communication, pre-study, and classroom learning status.

Keywords

• artificial intelligence technology
• yolo algorithm
• knowledge mastery model
• recursive goal evaluation method
• language course
• 97a40