Amid the global digital transformation, Central China Normal University (CCNU) is dedicated to becoming a world-class university with distinct Chinese characteristics in “Artificial Intelligence + Education.” The university is actively advancing its digital education transformation strategy, using digital technologies to build a top-tier institution. Guided by the principles of “data-driven development and integrated innovation,” CCNU leads pioneering efforts through its “Digital CCNU” initiative. By continuously forging its unique path, the university is strengthening the training of outstanding digital educators and creating a distinctive “CCNU experience.”

As the 2025 World Digital Education Conference approaches—where CCNU will host a parallel session on “Teacher Role Transformation and Capacity Enhancement in the Intelligent Era”—the university’s official WeChat account has launched a special column, “Digital Education at CCNU,” to showcase its achievements and innovations in using digital technologies for high-quality development.

For years, quality monitoring of digital course resources has mainly relied on expert reviews and manual feedback. These traditional methods often suffer from limited detail, coverage, and inconsistent standards. The large volume and diversity of course resources make manual screening difficult and inefficient, highlighting the need for a smart overhaul of resource management. To tackle this challenge, CCNU, supported by the National Engineering Research Center for Digital Learning, has innovatively combined large language models with multimodal analysis techniques to create a data-driven approach for evaluating course resource quality. The system collects and analyzes multimodal data—such as audio, video, and text—to build a multi-level evaluation framework. This marks a major shift from “experience-based judgment” to “data-driven decision-making,” providing intelligent support for course resource evaluation and management in universities.

Large Model-Driven Multimodal Analysis: Enabling AI to Truly “Understand” a Lesson

Based on a detailed study of the key factors that affect course resource quality, the research team created an evaluation framework covering teaching content, instructional management, learning activities, classroom interaction, and technical support. Using multimodal data analysis combined with large model technology, they developed an intelligent digital course resource evaluation system that provides deep insights and smart assessments of educational materials.

The system detects important quality features in real time, accurately identifying high-quality resources as well as those that may have risks. It then provides specific recommendations for improvement, helping to continuously optimize and enhance the resources. By smoothly integrating ongoing monitoring, precise analysis, and impact evaluation, the system creates a closed-loop process for ongoing quality improvement, bringing new energy to the goal of high-quality education and teaching.

Widespread Implementation Empowering Modern Education Governance

So far, the system has been implemented in over 100 schools across the country, completing more than 40,000 intelligent evaluations of course resources. It has played a significant role in advancing digital education reforms in regions like Hubei and Ningxia. Thanks to its real-time monitoring and accurate analysis, education administrators can continuously track the status of resources, quickly spot both outstanding and potentially problematic courses, and promote targeted teaching research, teacher development, and ongoing resource improvement. This creates a new model of resource management based on “real-time monitoring — precise diagnosis — dynamic improvement,” helping universities build a high-quality educational ecosystem.