CHKD期刊全文数据库

节点文献

基于专家生成内容的领域知识图谱构建

Domain Knowledge Graph Construction Based on Expert Generated Content

优先出版版本

【作者】 李保珍苏菁

【Author】 LI Bao-zhen;SU Jing;Government Audit Big Data Research Centre, Nanjing Audit University;School of Economics and Management, Jiangsu University of Science and Technology;

【通讯作者】 李保珍;

【机构】 南京审计大学国家审计大数据研究中心江苏科技大学经济管理学院

【摘要】 【目的/意义】基于专业性多源网络数据,构建同质性或异质性领域知识图谱。【方法/过程】基于场景性关键词相似度计算进行同质网络层次聚类,揭示症状的同质性网络层次以及治疗方案的同质性网络层次;基于2-mode共现矩阵进行异质网络聚类,兼顾症状及治疗方案的关联关系,通过设置不同阈值揭示其异质关联性网络层次。【结果/结论】基于聚类纯度及熵值评价指标,实验结果显示:就纯度评价指标而言,进行同质性网络知识图谱分析较为合理;就熵值指标而言,进行异质性网络知识图谱分析较为合理。

【Abstract】 【Purpose/significance】Based on professional multi-source network data to construct homogeneous or heterogeneous networks domain knowledge graph.【Method/process】Hierarchical clustering of homogeneous networks based on similarity computation of scene keywords was conduct, the homogeneity network of symptom and treatment plan were revealed; Heterogeneous network clustering based on 2-mode co-occurrence matrix was condect, association between symptoms and treatment options was considered, setting different thresholds to reveal the hierarchy of heterogeneous networks.【Result/conclusion】Based on the clustering purity and entropy evaluation index, the experimental results show that: in terms of the purity evaluation index, the construction of homogeneous network knowledge map is more reasonable; in terms of entropy index, it is reasonable to build heterogeneous network knowledge graph.

【关键词】 知识图谱; 同质网络; 异质网络; 聚类;

【Key words】 knowledge graph; homogeneous network; heterogeneous network; clustering;

【基金】 国家自然科学基金项目(71673122;71273121)

  • 【网络出版时间】2018-10-11 13:40
  • 【下载频次】266
节点文献中: