| 基于多数据源融合的医疗知识图谱框架构建研究 |
| |
| 引用本文： | 韩普,马健,张嘉明,刘亦卓.基于多数据源融合的医疗知识图谱框架构建研究[J].现代情报,2019,39(6):81-90. |
| |
| 作者姓名： | 韩普 马健 张嘉明 刘亦卓 |
| |
| 作者单位： | 1. 南京邮电大学管理学院, 江苏 南京 210003;2. 江苏省数据工程与知识服务重点实验室, 江苏 南京 210023 |
| |
| 基金项目： | 国家社会科学基金项目"大数据环境下健康领域实体语义挖掘研究"（项目编号：17CTQ022）；江苏高校哲学社会科学项目"大数据环境下科技词汇语义知识挖掘研究"（项目编号：TJS216035）；2018年南京邮电大学大学生创新训练计划项目"基于多数据源的医疗健康领域知识图谱构建与应用研究"（省级）（项目编号：SZD2018022）。 |
| |
| 摘 要： | 目的/意义]随着大数据和人工智能时代的来临，基于数据驱动的医疗辅助决策以及医疗健康知识挖掘受到人们的极大关注。医疗知识图谱是医疗信息分析和知识服务的基础，在医疗人工智能和医疗信息检索中发挥着重要作用。方法/过程]本文以医疗领域的实际应用需求为出发点，从医疗大数据获取、医疗实体及关系标注、医疗实体识别、医疗实体链接、医疗实体关系挖掘、中文医疗知识图谱表示和存储等关键技术入手，提出了多数据源融合的医疗知识图谱构建的理论框架。结果/结论]面向医疗领域的知识图谱构建是一项非常重要的基础任务，同时也是人工智能领域的重要发展方向。
|
| 关 键 词： | 医疗知识图谱 多源数据融合 实体识别 实体链接 实体关系 |
The Framework Construction of Medical Knowledge Graph Based on Multi-data Source Fusion |
| |
| Authors: | Han Pu Ma Jian Zhang Jiaming Liu Yizhuo |
| |
| Institution: | 1. School of Management, Nanjing University of Posts & Telecommunications, Nanjing 210023, China;2. Jiangsu Provincial Key Laboratory of Data Engineering and Knowledge Service, Nanjing 210023, China |
| |
| Abstract: | Purpose/Significance]With the approaching of the big data and artificial intelligence age,people have been paying great attention to the medical-assisted decision making and mining for the medical health knowledge based on the data driving.As the basis of medical information analysis and medical knowledge services,medical health knowledge graphs play a significant role in the medical artificial intelligence and medical information retrieval.Method/Process]Therefore,based on the actual application demand in medical field and proceeded with such key technologies as acquisition of medical big data,annotation of medical entities and their relations,identification of medical entities,linkage of medical entities,mining for relations of medical entities,as well as expression and storage of Chinese medical health knowledge graphs,this paper put forward a theoretical framework regarding construction of the medical health knowledge graph integrated with multi-data sources.Result/Conclusion]The construction of knowledge maps for the medical field was a very important basic task,and it is also an important development direction in the field of artificial intelligence. |
| |
| Keywords: | medical knowledge graph multi-data source fusion entity recognition entity linking entity relationship |
|
| 点击此处可从《现代情报》浏览原始摘要信息 |
| 点击此处可从《现代情报》下载免费的PDF全文 |
