Abstract
This paper summarizes the current situation of the university education informatization, cloud computing and the application of big data in education, and preliminarily constructs the big data platform model of university informatization intelligent teaching service of Yunnan University Teacher Education Alliance Based on cloud computing Part of the content of the model is described to provide reference for regional alliance education related research.
Introduction: Addressing the Digital Gap
The higher education landscape in Yunnan Province faces a significant "digital gap." While urban universities enjoy robust technological resources, rural institutions often lack the infrastructure to provide high-quality, interactive education. This paper proposes a solution rooted in the "Community of Destiny" philosophy—a regional alliance where schools share resources to ensure collective survival and growth in a post-pandemic world. The goal is to move beyond one-way distance learning toward a scalable, interactive, and intelligent ecosystem.
Proposed Platform Architecture
The core of this initiative is a multi-layered big data platform built on cloud computing. This architecture is designed to integrate disparate resources, from campus IoT devices to high-quality MOOCs, into a unified environment.
As shown in Figure 1, the platform consists of five primary layers:
- Basic Platform: Handles cloud storage, network infrastructure, and IoT/campus monitoring.
- Application Support Layer: Manages identity authentication and hosts big data mining algorithms for personalized recommendations.
- Application Layer: Contains the functional modules for personnel management, remote synchronous teaching, and automated MOOC generation.
- Comprehensive Display Layer: Provides the interface for various terminals (PC, mobile, pads).
- User Layer: Serves students, teachers, researchers, and educational leaders.
Hybrid Teaching and Evaluation Workflow
To bridge the gap between remote and local students, the platform implements a hybrid teaching mode that connects front-end analysis, curriculum design, and evaluation into a single loop.
Figure 2 illustrates the workflow, which emphasizes four key curriculum types: remote synchronous interaction, MOOC classrooms, face-to-face teaching, and online examination systems. A critical component is the Evaluation Design, which balances formative assessment (tracking classroom performance and peer reviews) with summative evaluation (exams) to provide a holistic view of student progress in a digital environment.
Innovative Features: Automated MOOCs and Big Data
Two features stand out in this model to address the "bottlenecks" of traditional distance learning:
- Automated MOOC Generation: To solve the content scarcity problem, the system treats live-streamed lectures as raw data. It programmatically extracts pedagogical structures and teacher-student interactions to generate MOOC elements automatically, lowering the cost and labor barrier to content creation.
- Big Data Mining: Using collaborative filtering algorithms, the platform analyzes learner behavior to provide personalized curriculum recommendations, ensuring that high-quality resources are effectively matched to student needs across the alliance.
Conclusion and Future Directions
While the proposed architecture provides a sound theoretical framework for regional educational equity, it remains a preliminary model. Future work will focus on the empirical deployment of the platform, specifically through mobile-friendly applets, and investigating the psychological impact of highly digitized learning environments on students. Additionally, technical refinements are needed to ensure low-latency synchronous classrooms in areas with limited connectivity.
Summary updated