Automatic assignment method of educational and teaching resource tags based on active learning

The rapid development of computer technology has provided a strong impetus for the digital transformation in the field of education. In response to the defects such as low efficiency and insufficient accuracy in the automatic assignment of tags for educational and teaching resources, this study proposes an automatic resource tag assignment model that integrates active learning and density peak clustering algorithm. With its adaptive clustering capability and sample utilization rate of "driving more with less", the model is expected to improve the accurate and efficient automatic assignment of tags for educational and teaching resources. The research tests show that when the model is tested on the training set, its precision rate is 99.12%, recall rate is 99.25%, and F1 score is 98.98%, which are significantly higher than those of the comparison models. In the recognition of different resource labels, the accuracy rate is above 0.99, among which the recognition accuracy rate for college mathematics labels is 1. The experimental results show that the proposed model can accurately capture the label characteristics of educational and teaching resources, effectively improve the accuracy and efficiency of educational and teaching resource label assignment, and thus enhance the quality of educational and teaching resource management. This provides new ideas for the application of artificial intelligence technology in the field of automatic assignment of educational and teaching resource labels and promotes the intelligent development of digital management of educational resources.