农林问题导向的高等数学教学改革路径研究——知识图谱与人工智能赋能的差异化教学支持模式构建

Research on the Teaching Reform Path of Advanced Mathematics Oriented to Agricultural and Forestry Problems—Building a Personalized Learning Support Model Empowered by Knowledge Graphs and Artificial Intelligence

摘要: 针对农林院校高等数学课程中专业关联度不足、学生基础差异较大、智能技术应用浅层化、评价方式偏结果化等问题，本文以农林类专业人才培养需求为牵引，提出“问题链–知识链–能力链”三链融合的教学改革框架。研究从作物生长、森林资源测算、病虫害传播、生态碳汇评估等农林典型问题出发，梳理高等数学核心知识点与专业应用场景之间的内在关联，构建“数学知识–专业情境–项目任务–能力目标”四层知识图谱；在此基础上引入AI学情诊断、资源推荐、智能答疑、案例匹配与学习路径推送等功能，形成课前预诊断、课中问题驱动、课后个性化巩固的差异化教学支持路径。本文进一步设计了涵盖知识达成、数学应用、学习投入、专业认同和课程满意度的多维评价体系，为农林院校公共数学课程实现专业化、智能化和育人化转型提供可复制的实践方案。

Abstract: To address the weak connection between advanced mathematics and agricultural and forestry disciplines, the diverse mathematical backgrounds of students, the limited integration of intelligent technologies, and the predominance of outcome-oriented assessment, this study proposes a teaching reform framework integrating problem chains, knowledge chains, and competency chains. Starting from typical agricultural and forestry problems such as crop growth analysis, forest resource estimation, pest diffusion prediction, and ecological carbon sequestration assessment, a four-layer knowledge graph linking mathematical knowledge, disciplinary contexts, project tasks, and competency objectives is constructed. On this basis, AI-supported functions including learning diagnosis, resource recommendation, intelligent tutoring, case matching, and personalized learning path guidance are introduced to support differentiated instruction before, during, and after class. Furthermore, a multidimensional evaluation system covering knowledge acquisition, mathematical application, learning engagement, disciplinary identity, and course satisfaction is developed. The proposed framework provides a practical pathway for promoting disciplinary relevance, intelligent instructional support, and personalized learning in public mathematics courses at agricultural and forestry universities.