教育数智化背景下知识图谱赋能高校医学免疫学教学的实践路径研究

    Research on the practical path of knowledge graph empowering medical immunology teaching in colleges and universities under the background of educational digitalization and Intelligence

    • 摘要:
      目的: 在教育数智化背景下,探索将人工智能领域的知识图谱技术融入医学免疫学教学的实践路径,设计并构建智慧教学优化方案。
      方法: 选取临床医学专业2个教学班共61名大二学生分为2组,观察组31人采用基于知识图谱的智慧教学模式,对照组30人采用传统教学模式。比较2组学生的理论考试成绩、学习行为数据以及问卷访谈结果,并评估课堂教学质量和效率。
      结果: 观察组学生的学习路径完成质量评分为4.27 ± 0.53(满分5分),该评分与其平台使用频次呈显著正相关关系(r = 0.63,P < 0.01),该组学生在情境任务中的自主拓展行为(如查阅跨模块文献或提出创新性问题)、在平台上的主动检索行为和非指定资源的阅读量均高于对照组(P < 0.01)。观察组学生对智慧教学平台的访问频次高于对照组,在知识图谱上单次学习时长亦高于对照组复习讲义、完成作业的用时(P < 0.01)。观察组教学质量总评分高于对照组(P < 0.01)。87.10%(27/31名)观察组学生认为将知识图谱引入智慧教学这一模式在提高课堂效率、优化教学结构和促进知识内化方面具有积极作用。
      结论: >在教育数智化背景下,将人工智能知识图谱技术引入医学免疫学教学,有助于优化学生知识获取路径,提高教学质量与效率,值得在智慧医学教育中进一步推广应用。

       

      Abstract:
      Objective To explore the practical path of integrating the knowledge graph technology in the field of artificial intelligence into the teaching of medical immunology under the background of digital and intelligent education, and design and construct an intelligent teaching optimization plan.
      Methods A total of 61 sophomore students from two teaching classes of the Clinical Medicine major were selected, and divided into two groups. The observation group (31 cases) were given the intelligent teaching mode based on the knowledge graph, and the control group (30 cases) were given the traditional teaching mode. The theoretical examination scores, learning behavior data and questionnaire interview results between two groups were compared, and the quality and efficiency of classroom teaching were evaluated.
      Results The quality score of learning path completion in the observation group was 4.27 ± 0.53 (full score: 5 points), and this score was significantly positively correlated with the frequency of platform usage (r = 0.63, P < 0.01). The autonomous expansion behaviors in situational tasks (such as consulting cross-module literature or raising innovative questions), active search behaviors on the platform and reading volume of non-specified resources in the observation group were higher than those in control group (P < 0.01). The access frequency of intelligent teaching platform in the observation group was higher than that in control group, and the single learning duration on the knowledge graph was also higher than that of reviewing the lecture notes and completing the homework in control group (P < 0.01). The total score of teaching quality in the observation group was higher than that in control group (P < 0.01). The 87.10% of the students (27/31) in the observation group believed that introducing the knowledge graph into the smart teaching model had a positive effect in improving classroom efficiency, optimizing the teaching structure and promoting the internalization of knowledge.
      Conclusions Under the background of educational digitalization and intelligence, introducing artificial intelligence knowledge graph technology into the teaching of medical immunology is conducive to optimizing students' knowledge acquisition paths, improving teaching quality and efficiency, and is worthy of further promotion and application in smart medical education.

       

    /

    返回文章
    返回