安徽农学通报 >
2025 , Vol. 31 >Issue 14: 129 - 133
DOI: https://doi.org/10.16377/j.cnki.issn1007-7731.2025.14.030
人工智能(AI)赋能普通植物病理学创新实验课程教学改革探索
|
赵志博(1989—),男,河南周口人,博士,副教授,从事植物病理学研究。 |
Copy editor: 杨欢
收稿日期: 2025-03-25
网络出版日期: 2025-07-31
基金资助
贵州省级“金课”一流本科课程(2024JKHH0032)
贵州大学本科教改项目(XJG2023090)
贵州大学首批AI课程建设项目(XJG2024106)
Exploration of teaching reform in Innovative Experimental of General Plant Pathology course empowered by artificial intelligence
Received date: 2025-03-25
Online published: 2025-07-31
为探索生成式人工智能(AI)在实验实践教学中的创新应用,本文以普通植物病理学创新实验课程为实践场域,探索AI赋能实验实践教学“师—机—生”协同应用的具体路径。通过案例对比分析与系统设计,构建了涵盖AI互动教学平台、知识引擎、创新设计助手及个性化评估的“四维”应用模式框架,并实施了AI赋能实验教学活动。具体路径包括打造基于AI的互动教学平台,使用DeepSeek R1大模型,经过层层调试,开发了基于Python的植物叶片病害严重度计量软件,准确率达97%;发挥AI知识引擎和创新设计助手功能,开发了涵盖病害调查抽样图示、基因组序列提取、猕猴桃病害图像识别小程序等具体应用场景的小工具;利用AI完善反馈与全过程评估机制,对学生实验完成度、创新作品设计等进行全过程考核,并提供针对性辅导。实践表明,AI辅助教学班级的学生活跃度、学习成绩和创新成果产出均明显增加,且开发的工具被应用于科研实践,可有效提升实验实践教学效果。本文为农科及其他实验性学科的AI赋能教学改革提供参考。
赵志博 , 王勇 , 丁海霞 , 陈相儒 , 韦珊 . 人工智能(AI)赋能普通植物病理学创新实验课程教学改革探索[J]. 安徽农学通报, 2025 , 31(14) : 129 -133 . DOI: 10.16377/j.cnki.issn1007-7731.2025.14.030
To explore the innovative application of generative artificial intelligence in experimental practice teaching, the Innovative Experimental of General Plant Pathology course was taken as the practical field, and the specific path of AI empowering the collaborative application of “teacher-machine-student” in experimental practice teaching was explored. Through case comparison analysis and system design (AI), a “four-dimensional” application model framework covering AI interactive teaching platform, knowledge engine, innovative design assistant, and personalized evaluation was constructed, and multiple AI empowered experimental teaching activities were implemented. The specific path includes building an AI based interactive teaching platform, use the DeepSeek R1 model, and after layer by layer debugging, developing a Python based software for measuring the severity of plant leaf diseases, with an accuracy rate of 97%; utilize the functions of AI knowledge engine and innovative design assistant, it have developed small tools covering specific application scenarios such as disease investigation sampling diagrams, genome sequence extraction, kiwifruit disease image recognition mini programs, etc.; utilize AI to improve the feedback and full process evaluation mechanism, conduct full process assessment on students' experimental completion, innovative work design additional scores, and provide targeted guidance. Practice has shown that the activity level, academic performance, and innovative output of students in AI assisted teaching classes have significantly increased, and the developed tools have been applied to scientific research practice. It can effectively improve the effectiveness of experimental practice teaching. This article provides references for AI empowered teaching reform in agricultural science and other experimental disciplines.
| [1] |
王繁,刘永强,周天华. 人工智能引领高等教育数字化创新发展[J]. 中国高等教育,2024(增刊1):9-12.
|
| [2] |
郭蕾蕾. 生成式人工智能驱动教育变革:机制、风险及应对:以DeepSeek为例[J]. 重庆高教研究,2025,13(3):38-47.
|
| [3] |
|
| [4] |
刘邦奇,聂小林,王亚飞,等. 生成式AI赋能教育:技术框架、应用场域及价值:2024智能教育发展研究报告[J]. 中国电化教育,2025(3):61-70.
|
| [5] |
张立新,檀根甲,汪章勋,等. 植物病理学实验教学改革与质量标准的探索实践[J]. 内蒙古农业大学学报(社会科学版),2017,19(2):47-51.
|
| [6] |
张娜,杨文香,闫红飞,等. 新农科背景下植物病理学实验实践教学改革[J]. 智慧农业导刊,2023,3(19):143-146.
|
| [7] |
尹良芬,罗朝喜. 农业高校植物病理虚拟仿真实践教学改革探究[J]. 智慧农业导刊,2024,4(9):151-154.
|
| [8] |
秦磊,郭凯. 生成式人工智能在酸碱中和滴定图像模拟中的应用[J/OL]. 大学化学,2025:1-8. (2025-01-27)[2025-07-30]. http://kns.cnki.net/kcms/detail/11.1815.O6.20250126.1703.012.html.
|
| [9] |
蒋倩,王红丽,王海光. 基于图像处理技术的小麦条锈病严重度自动分级系统构建[J]. 植物病理学报,2024,54(2):385-397.
|
| [10] |
王海光. 普通植物病理学实验:农学专业用书[M]. 北京:中国农业大学出版社,2024.
|
| [11] |
高岩,林颖,苏淑文,等. 实践创新能力导向下的人工智能类实践课程教学体系探索[J]. 计算机教育,2025(3):240-246.
|
| [12] |
谢武桃,金盛辉,毕朝虎,等. AI背景下影像学专业实习教学模式的探讨[J]. 医学理论与实践,2023,36(8):1426-1429.
|
| [13] |
张建华,陈申宽,张晓振,等. 人工智能技术在植物叶片病虫害识别中的研究进展[J]. 种子科技,2023,41(16):124-126.
|
| [14] |
王金辉,赵冬梅,王逍冬. R语言在植物病理学专业教学中的应用[J]. 安徽农学通报,2024,30(1):123-126.
|
| [15] |
饶泓,吴佳跃,樊莉莉,等. 基于AI Studio平台的机器学习课程实践教学[J]. 计算机教育,2021(6):115-119.
|
| [16] |
郭壬癸,谢佳眉. 论DeepSeek类人工智能模型训练的著作权侵权责任认定[J/OL]. 电子科技大学学报(社科版),2025:1-8. (2025-03-20)[2025-07-20]. https://link.cnki.net/doi/10.14071/j.1008-8105(2025)-5009.
|
| [17] |
翟依晨,张林,祝佳佳,等. 猕猴桃软腐病无损高光谱诊断技术研究[J]. 山地农业生物学报,2025,44(2):78-86.
|
/
| 〈 |
|
〉 |