摘要
目前普遍的知识图谱构建思路是图谱中的关系标签采用文字描述,这样很难对图谱中的关系进行计算。针对这个问题,提出了关系方向、强度因子和时态因子的概念,关系的正负、强度和时态可以通过有监督机器学习的方法形成自动模型,从而在领域知识图谱中实现关系的量化计算。这种知识图谱构建方法在计算事件舆情走向、计算企业合作与竞争情况变化、分析销售人员市场拓展情况等领域,形成了一种新的数据分析模式,对人工智能在具体行业的落地应用很有意义。
In current popular ideas for knowledge graph construction,the relations in graphs were described by words,it is difficult to calculate the relations in graphs.To this issue,concepts of the direction,intensive factors,temporal factors of relations were proposed.Automatic models of positive,negative,intensive and temporal relations can be formed through supervised machine learning,so that the quantitative calculation of the relations can be implemented in the domain knowledge graph.This method forms a new idea in many areas such as calculating the trend of incidents,calculating the change of cooperation and competition between enterprises,and analyzing the market expansion of sales people.It is meaningful for artificial intelligence to be applied in specific industries.
作者
臧根林
王亚强
吴庆蓉
占春丽
谢新扬
ZANG Genlin;WANG Yaqiang;WU Qingrong;ZHAN Chunli;XIE Xinyang(TRS Knowledge Graph Research Institute,Guangzhou 510665,China;Guangzhou TRS Big Data Co.,Ltd.,Guangzhou 510665,China)
出处
《大数据》
2019年第3期96-103,共8页
Big Data Research
关键词
知识图谱
关系方向
关系强度
负关系
时态关系
knowledge graph
direction of relation
strength of relation
negative relation
temporal relation
