1.College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, Hubei, China
2.Key Laboratory of Intelligent Information Processing and Real-Time Industrial System in Hubei Province, Wuhan University of Science and Technology, Wuhan 430065, Hubei, China
Cardiovascular disease has been the leading cause of mortality in China for a long time, and its mortality rate is still rising year by year. Under the background of the scarcity of Chinese open source medical datasets, we combine top-down and bottom-up approaches to construct Chinese knowledge graph of heart disease in a semi-automatic way to provide strong data support and guidance for medical artificial intelligence. First, we construct the heart disease ontology by referring high-quality encyclopedia data and medical literatures, and the cardiovascular disease data have been gathered from heterogeneous data sources, such as encyclopedia websites and medical websites, using a predefined disease dictionary to get the data closed to the specific domain. And then, we adapt the entity similarity calculation for better knowledge fusion, add the data schema by discovering new schema upon the data of the graph, and iterate the schema layer together with the data layer in the graph. Finally, the graph data are visualized in the graph database and several promising applications of the heart disease knowledge graph are explored based on current research trends.
YANGC. Automatic Construction of Financial Domain Knowledge Graph with Template Induced Method[D]. Wuhan: Wuhan University of Science and Technology, 2018(Ch).
[3]
孙驰. 基于微博的知识图谱的构建与研究[D].成都:西华大学, 2015.
[4]
SUNC. The Construction Method of Knowledge Graph in Micro⁃Blog [D]. Chengdu: Xihua University, 2015(Ch).
CHENY D, XIANG J, KOUY T, et al. Study on construction of knowledge graph of apple industry in China[J]. Chinese Journal of Agricultural Resources and Regional Planning,2017,38(11):40-45. DOI:10.7621/cjarrp.1055-9121.20171106(Ch).
JIAL R, LIUJ, YUT, et al. Construction of traditional Chinese medicine knowledge graph [J]. Journal of Medical Informatics,2015,36(8):51-53. DOI:10.3969/j.issn.1673-6036.2015.08.012(Ch).
LIX L, LIUY, HEL Y, et al. Research review of knowledge graph and its application in TCM field [J]. Chinese Journal of Information on Traditional Chinese Medicine, 2017, 24(7):129-132. DOI:10.3969/j.issn.1005-5304.2017.07.033(Ch).
LIUQ, LIY, DUANH, et al. Knowledge graph construction techniques[J]. Journal of Computer Research and Development, 2016,53(3):582-600. DOI:10.7544/issn1000-1239.2016.20148228(Ch).
[13]
胡芳槐. 基于多种数据源的中文知识图谱构建方法研究[D]. 上海: 华东理工大学, 2015.
[14]
HUF H. Chinese Knowledge Graph Construction Method Based on Multiple Data Sources [D]. Shanghai: East China University of Science and Technology, 2015(Ch).
XUZ L, SHENGY P, HEL R, et al. Review on knowledge graph techniques [J]. Journal of University of Electronics Science and Technology of China,2016,45(4):589-606. DOI:10.3969/j.issn.1001-0548.2016.04.012(Ch).
[17]
BORDESA, USUNIERN, GARCIA-DURANA, et al. Translating Embeddings for Modeling Multi-Relational Data[DB/OL]. [2019-01-10]. ta.pdf.
[18]
WANGZ, ZHANGJ W, FENGJ L, et al. Knowledge graph embedding by translating on hyperplanes [C]// 28th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2014:1112-1119.
[19]
JIG L, HES Z, XUL H, et al. Knowledge Graph Embedding via Dynamic Mapping Matrix[DB/OL].[2019-02-20].
[20]
LINY K, LIUZ Y, LUANH B, et al. Modeling Relation Paths for Representation Learning of Knowledge Bases [DB/OL]. [2019-03-02].
[21]
YAOX C, Durme BVAN. Information Extraction over Structured Data: Question Answering with Freebase [DB/OL]. [2019-03-02]. 965907073.html.
[22]
BERANTJ, CHOUA, FROSTIGR, et al. Semantic Parsing on Freebase from Question-Answer Pair[DB/OL]. [2019-03-02].
[23]
BORDESA, WESTONJ, USUNIERN. Open question answering with weakly supervised embedding models[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases(LNCS 8724).Berlin: Springer, 2014: 165-180. DOI:10.1007/978-3-662-44848-9_11 .
[24]
YIH W T, CHANGM W, HEX D, et al. Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base[DB/OL].[2019-01-02].