健康评估课程知识图谱的构建及初步应用研究

doi:10.3761/j.issn.1672-9234.2024.09.001

摘要/Abstract

摘要：

目的构建健康评估课程知识图谱，并了解学生的使用感受。方法采用Neo4j图数据库构建健康评估课程知识图谱；2023年5月—7月，将其初步应用于某医科大学2021级83名未使用过知识图谱的护理本科二年级学生的健康评估课程教学中。教学结束后，评估学生的知识点学习时长、知识点练习次数、对知识图谱使用的整体满意度、继续使用知识图谱进行学习的意愿，并采用目的抽样法，抽取17名学生作为访谈对象，对其进行半结构化访谈，了解其使用健康评估课程知识图谱的感受。结果课程知识图谱共包含199个知识点，2 890个节点，2 628个属性，在节点间建立了168次包含性关系、97次顺序性关系、37次相关性关系。83名学生的知识点学习时长为0.17（0.17，3.37） h，知识点练习次数为1（1，33）次；对知识图谱使用的整体满意度得分为8.00（7.00，9.00）分，99%（82/83）的学生表示愿意继续使用知识图谱进行学习。通过访谈发现，学生表示健康评估课程知识图谱的运用有助于提高学习投入度、减轻应试焦虑感、形成清晰的学习思路、保障知识学习内容的全面性、加深对知识的理解和记忆，但在使用知识图谱的过程中存在未被满足的学习需求。结论学生对健康评估课程知识图谱的使用反馈良好，健康评估课程知识图谱的运用有助于学生高效、系统化学习，提高其学习效果。

关键词: 知识图谱, 健康评估, 教育, 护理

Abstract:

Objective To construct a knowledge graph for the Health Assessment Course and investigate students’ usage experiences. Methods The Neo4j graph database was utilized to construct a knowledge graph for the Health Assessment Course. From May to July 2023，the knowledge graph was implemented in the Health Assessment Course for 83 second-year nursing undergraduate students from the Grade 2021 of a medical university who had not used a knowledge graph previously. After the course，students’ practice duration and frequency on knowledge points，overall satisfaction with the knowledge graph platform，and willingness to continue using it for learning were evaluated. Additionally，17 students were purposively sampled for semi-structured interview to collect their feedback. Results The constructed knowledge graph consisted of 199 knowledge points，2 890 nodes，and 2 628 attributes，with 168 types of inclusion relationships，97 types of sequential relationships，and 37 types of correlation relationships established among the nodes. The average learning duration for knowledge points among the 83 students was 0.17（0.17，3.37） hours，with an average practice frequency of 1（1，33） times. The overall satisfaction with the knowledge graph platform was 8.00（7.00，9.00） out of 10，and 99%（82/83） of students expressed willingness to continue using the knowledge graph for learning. Interviews revealed that students believed the application of the knowledge graph for the Health Assessment Course enhanced their learning engagement，alleviated exam anxiety，facilitated clearer learning paths，ensured comprehensive content coverage，and deepened understanding and memory of knowledge. However，there were still some unmet learning needs. Conclusion Positive feedback is got for using the knowledge graph in the Health Assessment Course，which can facilitate the efficient and systematic learning，and ultimately improving their learning effects.

Key words: Knowledge Graph, Health Assessment, Education, Nursing

杨智慧, 李兴雯, 闭晓君, 林劲秋, 赵倩倩, 刘素婷, 罗园园, 张立力. 健康评估课程知识图谱的构建及初步应用研究[J]. 中华护理教育, 2024, 21(9): 1035-1040.

YANG Zhihui, LI Xingwen, BI Xiaojun, LIN Jinqiu, ZHAO Qianqian, LIU Suting, LUO Yuanyuan, ZHANG Lili. Construction and application of knowledge graph in Health Assessment Course[J]. Chinese Journal of Nursing Education, 2024, 21(9): 1035-1040.

图/表 2

参考文献 16

[1]	徐增林, 盛泳潘, 贺丽荣, 等. 知识图谱技术综述[J]. 电子科技大学学报, 2016, 45(4):589-606.
	Xu ZL, Sheng YP, He LR, et al. Review on knowledge graph techniques[J]. J Univ Electron Sci Technol China, 2016, 45(4):589-606.
[2]	张山, 吴瑛. 支气管哮喘患者护理教学内容知识图谱的构建[J]. 中华护理教育, 2024, 21(3):269-275.
	Zhang S, Wu Y. Construction of nursing teaching content for patients with bronchial asthma based on knowledge graph[J]. Chin J Nurs Educ, 2024, 21(3):269-275.
[3]	张宁豫, 谢辛, 陈想, 等. 基于知识协同微调的低资源知识图谱补全方法[J]. 软件学报, 2022, 33(10):3531-3545.
	Zhang NY, Xie X, Chen X, et al. Knowledge collaborative fine-tuning for low-resource knowledge graph completion[J]. J Softw, 2022, 33(10):3531-3545.
[4]	王雅琳, 邹江枫, 王凯, 等. 基于本体引导的注塑知识图谱构建及缺陷溯因应用[J]. 电子与信息学报, 2022, 44(5):1521-1529.
[5]	聂同攀, 曾继炎, 程玉杰, 等. 面向飞机电源系统故障诊断的知识图谱构建技术及应用[J]. 航空学报, 2022, 43(8):40-56.
	Nie TP, Zeng JY, Cheng YJ, et al. Knowledge graph construction technology and its application in aircraft power system fault diagnosis[J]. Acta Aeronaut Astronaut Sin, 2022, 43(8):40-56.
[6]	周俊, 郑彭元, 袁立存, 等. 基于改进CASREL的水稻施肥知识图谱信息抽取研究[J]. 农业机械学报, 2022, 53(11):314-322.
	Zhou J, Zheng PY, Yuan LC, et al. Knowledge graph information extraction for rice fertilization based on improved CASREL[J]. Trans Chin Soc Agric Mach, 2022, 53(11):314-322.
[7]	郭宏伟. 基于智能教育的高校在线课程知识图谱构建研究:以中国医学史为例[J]. 中国电化教育, 2021(2):123-130.
	Guo HW. Construction of knowledge graph for the online course in colleges and universities based on intelligent education—a case study on Chinese medical history[J]. China Educ Technol, 2021(2):123-130.
[8]	孙锡波, 谢晓尧, 郑欣. 融合多源数据的学科知识图谱构建与应用[J]. 福建电脑, 2023, 39(11):6-13.
[9]	高雅, 陈宁, 袁玲, 等. 精准健康管理视角下高血压健康干预知识图谱的构建[J]. 中华全科医学, 2023, 21(12):2068-2073.
	Gao Y, Chen N, Yuan L, et al. Constructing a knowledge graph for health intervention in hypertension from the perspective of precise health management[J]. Chin J Gen Pract, 2023, 21(12):2068-2073.
[10]	胡雁, 王志稳. 护理研究[M]. 5版. 北京: 人民卫生出版社,2017:290-291.
[11]	赵宇博, 张丽萍, 闫盛, 等. 个性化学习中学科知识图谱构建与应用综述[J]. 计算机工程与应用, 2023, 59(10):1-21. doi: 10.3778/j.issn.1002-8331.2209-0345
	Zhao YB, Zhang LP, Yan S, et al. Construction and application of discipline knowledge graph in personalized learning[J]. Comput Eng Appl, 2023, 59(10):1-21. doi: 10.3778/j.issn.1002-8331.2209-0345
[12]	张忻忻, 牟智佳. 数据化学习环境下面向个性化学习的精准教学模式设计研究[J]. 现代远距离教育, 2018(5):65-72.
	Zhang XX, Mou ZJ. The research on the design of precise instruction model facing personalized learning under the data learning environment[J]. Mod Distance Educ, 2018(5):65-72.
[13]	木本荣, 李丽群, 刘文雯, 等. 后疫情时代大学生期末复习影响因素及有效复习实现路径[J]. 创新教育研究, 2022(4):605-610.
	Mu BR, Li LQ, Liu WW, et al. Influencing factors of college students’ final review in the post-epidemic era and the path to effective review[J]. Creat Educ Stud, 2022(4):605-610.
[14]	程时伟, 沈泽鹏, 张章伟. 基于眼动跟踪的移动智慧课堂可视交互系统[J]. 浙江工业大学学报, 2023, 51(4):362-371.
	Cheng SW, Shen ZP, Zhang ZW. Visual interaction system of mobile intelligent classroom based on eye tracking[J]. J Zhejiang Univ Technol, 2023, 51(4):362-371.
[15]	徐瑶怡, 王依洁, 张梦男, 等. 微信小程序用户持续使用意愿的影响因素实证研究:基于用户体验视角[J]. 中国商论, 2022(7):52-56.
[16]	石雪, 杨晓娟. 混合式学习中大学生在线学习力影响因素研究[J]. 现代教育技术, 2020, 30(4):95-100.
	Shi X, Yang XJ. Research on the influencing factors of college students’ online learning power in blended learning[J]. Mod Educ Technol, 2020, 30(4):95-100.