高中生物学混合式组卷路径探索
Exploration of Hybrid Test Paper Composition Pathways for High School Biology
DOI: 10.12677/ae.2025.15112185, PDF,    科研立项经费支持
作者: 蒯 龙, 田慧敏, 徐立新, 李长远, 郭 成*:赤峰学院化学与生命科学学院,内蒙古 赤峰;韩殿国:赤峰学院附属中学,内蒙古 赤峰
关键词: 传统人工组卷试题库组卷AIGC组卷混合模式高中生物学Traditional Manual Test Paper Composition Question Bank-Based Test Paper Composition AIGC Test Paper Composition Hybrid Model High School Biology
摘要: 随着教育信息化的深入发展,组卷方式呈现多元化趋势。本文通过对人工组卷、高中生物题库组卷和AIGC智能组卷三种模式的深入分析,比较了各自的优势与不足,并探讨了混合组卷模式的优势与发展,并以生成式人工智能软件Claude组卷为例进行实践。认为,传统人工组卷在个性化和教学针对性方面不可替代,题库组卷在标准化和资源共享方面具有优势,AI组卷在效率和客观性方面表现突出。基于IAGC高中生物学混合组卷模式能够有效整合三种方式的优势,提高组卷效率及质量,为一线教师进行教育评价提供更高效的解决方案。
Abstract: With the deepening development of educational informatization, test paper composition approaches exhibit diversified trends. This paper conducts an in-depth analysis of three modalities: manual test paper composition, high school biology question bank-based composition, and AIGC intelligent test paper composition. The study compares their respective advantages and limitations, explores the merits and development of hybrid composition models, and provides practical implementation using the generative artificial intelligence software Claude as an exemplar for test paper composition. The findings indicate that traditional manual composition remains irreplaceable in terms of personalization and pedagogical targeting, question bank-based composition demonstrates advantages in standardization and resource sharing, while AI-based composition exhibits outstanding performance in efficiency and objectivity. The AIGC-based hybrid test paper composition model for high school biology can effectively integrate the advantages of all three approaches, enhancing both the efficiency and quality of test paper composition, thereby providing frontline educators with more efficient solutions for educational assessment.
文章引用:蒯龙, 田慧敏, 韩殿国, 徐立新, 李长远, 郭成. 高中生物学混合式组卷路径探索[J]. 教育进展, 2025, 15(11): 1431-1440. https://doi.org/10.12677/ae.2025.15112185

参考文献

[1] 柳博. 考试命题制度研究[M]. 北京: 高等教育出版社, 2017.
[2] 骆方, 田雪涛, 屠焯然, 等. 教育评价新趋向: 智能化测评研究综述[J]. 现代远程教育研究, 2021, 33(5): 42-52.
[3] Huang, R. and Song, H. (2025) Comment On: “ChatGPT 35 Better Improves Comprehensibility of English, than Spanish, Generated Responses to Osteosarcoma Questions”. Journal of Surgical Oncology, 131, 1491-1492. [Google Scholar] [CrossRef] [PubMed]
[4] 管宝云. 基于混合智能算法的高校时间表及自动组卷问题研究[D]: [博士学位论文]. 天津: 天津大学, 2005.
[5] 张玉强, 李年琪, 尹学慧. 中小学教师命题能力: 现状剖析、提升路径与整体支持[J]. 华东师范大学学报(教育科学版), 2025, 43(6): 81-98.
[6] 全惠云, 范国闯, 赵霆雷. 基于遗传算法的试题库智能组卷系统研究[J]. 武汉大学学报(自然科学版), 1999(5): 758-760.
[7] 王友仁, 张砦, 施玉霞, 等. 题库系统智能成卷理论和组卷方法研究[J]. 电子科技大学学报, 2006(3): 363-366.
[8] Lei, W. (2023) Automatic Test Paper Generation Technology for Mandarin Based on Hilbert Huang Algorithm. Procedia Computer Science, 228, 808-816.
[9] 聂慧超. 学术出版交手AIGC产生“双重魔法” [N]. 中国出版传媒商报, 2024-04-05(001).
[10] 邱元阳. AI的幻觉[J]. 中国信息技术教育, 2025(9): 22.
[11] 任少铎. 基于项目命题落实立德树人考察核心素养培养关键能力——以2024年福建中考“项目式试题”为例[J]. 物理教学, 2025, 47(9): 34-37.
[12] 蔡悦琪, 肖安庆. 生成式人工智能在高中生物学考试评价中的实践与探索[J]. 生物学教学, 2025, 50(7): 41-43.
[13] Ngo, A., Gupta, S., Perrine, O., Reddy, R., Ershadi, S. and Remick, D. (2024) ChatGPT 3.5 Fails to Write Appropriate Multiple Choice Practice Exam Questions. Academic Pathology, 11, Article 100099. [Google Scholar] [CrossRef] [PubMed]
[14] 闫白洋, 佘建云. 生成式人工智能在高中生物学教学领域中的问答测试与使用建议[J]. 生物学教学, 2023, 48(9): 34-36.