Construction and Empirical Study of a Blended Project-Based Collaborative Learning Model Based on Large Models

Fangyuan He; Ming Lu; Shiyuan Liu

doi:10.47297/taposatWSP2633-456907.20260704

PDF
导出
分享
收藏
专辑

Construction and Empirical Study of a Blended Project-Based Collaborative Learning Model Based on Large Models

7卷第4期

浏览量: 0 Downloads: 0

Construction and Empirical Study of a Blended Project-Based Collaborative Learning Model Based on Large Models
Construction and Empirical Study of a Blended Project-Based Collaborative Learning Model Based on Large Models
College of Applied Science and Technology, Beijing Union University, Beijing, 100101, China
2026年7卷第4期页码：37-40
纸质出版：2026-04-30
DOI：10.47297/taposatWSP2633-456907.20260704
Accepted：

Scan QR Code

Fangyuan He, Ming Lu & Shiyuan Liu. (2026). Construction and Empirical Study of a Blended Project-Based Collaborative Learning Model Based on Large Models. 科技理论与实践（英文版）, 7(4), 37-40.

He Fangyuan,Lu Ming,Liu Shiyuan.Construction and Empirical Study of a Blended Project-Based Collaborative Learning Model Based on Large Models[J].Theory and Practice of Science and Technology,2026,07(04):37-40.
Fangyuan He, Ming Lu & Shiyuan Liu. (2026). Construction and Empirical Study of a Blended Project-Based Collaborative Learning Model Based on Large Models. 科技理论与实践（英文版）, 7(4), 37-40. DOI： 10.47297/taposatWSP2633-456907.20260704.

He Fangyuan,Lu Ming,Liu Shiyuan.Construction and Empirical Study of a Blended Project-Based Collaborative Learning Model Based on Large Models[J].Theory and Practice of Science and Technology,2026,07(04):37-40. DOI： 10.47297/taposatWSP2633-456907.20260704.

摘要

Abstract

In response to the problems of single mode

lack of personalization

and insufficient integration of new technologies in current collaborative learning

this article focuses on the collaborative integration of blended learning and project-based learning

and constructs a collaborative learning model based on big model technology. This model integrates the advantages of intelligent decision-making

feature recognition

and knowledge integration of large models

forming a closed-loop system of "requirement diagnosis - solution generation - collaborative execution - quantitative evaluation". By utilizing core mechanisms such as precise learning style identification

personalized task adaptation

and multimodal resource integration

it aims to address the pain points of "one size fits all" and inefficient interaction in traditional collaborative learning. The experimental results show that the application of this model in professional courses in higher education institutions has increased student collaboration efficiency by 35.5%

knowledge retention rate by 5.0%

and significantly reduced the workload of teacher teaching design

providing practical technical solutions and paths for the digital transformation of education in the new era.

关键词

Keywords

references

Kang JA, Xu XH, Yan LL.Leveraging affordances of immersive technology-supported collaborative learning (ITCL): A systematic review[J].Education and Information Technologies, 2025, 30(1):607-647.

Shen DD, Chang CS, Yang JJ. Blended Learning Effectiveness and College Students' Deep Learning Perceptions: The Community of Inquiry Perspective[J]. International Review Of Research In Open And Distributed Learning, 2025, 26(4):38-60.

Yu Xia, Yuan Dan, Qi Yanling. Evaluation of Teaching Effectiveness of Blended Learning Ecosystem under the Concept of OBE: An Example of Logistics Information Technology[C].Proceedings of the 2024 the 16th International Conference on Education Technology and Computers,2024:398-406.

Botezat EA, Dodescu AO, Borza AF.Addressing 21st Century Competencies Challenges Through Project-Based Entrepreneurial Learning: A Systemic Approach[J]. Systems, 2025,13(3).

McCarthy S, Palmer, E, Falkner, N. Personalising with AI in higher education: exploring educator characteristics and their role in shaping blended learning[J]. Higher Education Research & Development.2025, 44(8):2030-2046.

Wu JJ, Tlili A, Salha S. Unlocking the potential of artificial intelligence in improving learning achievement in blended learning: a meta-analysis[J]. Frontiers in Psychology.2025, (16).

文章被引用时，请邮件提醒。

Submit

Methods for AIGC-Assisted Generation of Teaching Resources in the Education Sector

Integration and Practical Application of AI Technology in Classroom Teaching for Film and Television Post-production in Higher Education Institutions

EEG Emotion Recognition Using Multi-Feature DNN with PCA and Multi-Seed Training

Research on the Social Coordination Path of AI Robot Replacing high-risk Occupations

Simulation and Comparative Study of FOC Control Algorithms for Permanent Magnet Synchronous Motors

Related Author

Xiaomei Zhou Nanjing University of Communication

Qingzhong Feng School of Broadcasting and Television, Communication University of China Nanjing

Lingzi Li School of Broadcasting and Television, Communication University of China Nanjing

Baoxiang Xu School of Broadcasting and Television, Communication University of China Nanjing

Related Institution

Nanjing University of Communication

School of Broadcasting and Television, Communication University of China Nanjing

⁰