知识图谱中的关系方向与强度研究
|
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.
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.
引文
[1]赵军,刘康,何世柱,等.知识图谱[M].北京:高等教育出版社,2018.ZHAO J,LIU K,HE S Z,et al.Knowledge graph[M].Beijing:Higher Education Press,2018.
[2]陈秀娟,冷德荣.面向语言信息处理的语义研究--合著者的社会网络分析[J].情报科学,2013(7):126-129.CHEN X J,LENG D R.Semantic study in language and information processing based on social network analysis[J].Information Science,2013(7):126-129.
[3]秦长江,侯汉清.知识图谱--信息管理与知识管理的新领域[J].大学图书馆学报,2009(1):30-37,96.QIN C J,HOU H Q.Knowledge graph:a new area of information management and knowledge management[J].Journal of Academic Libraries,2009(1):30-37,96.
[4]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(4):589-606.XU Z L,SHENG Y P,HE L R,et al.Review on knowledge graph techniques[J].Journal of University of Electronic Science and Technology of China,2016(4):589-606.
[5]李涓子,侯磊.知识图谱研究综述[J].山西大学学报(自然科学版),2017,40(3):454-459.L I J Z,HOU L.Reviews on knowledge graphre search[J].Journal of Shanxi University(Natural Science Edition),2017,40(3):454-459.
[6]朱木易洁,鲍秉坤,徐常胜.知识图谱发展与构建的研究进展[J].南京信息工程大学学报(自然科学版),2017,9(6):575-582.ZHU M Y J,BAO B K,XU C S.Research progress on development and construction of knowledge graph[J].Journal of Nanjing Univrsity of Information Science&Technology(Natural Science Edition),2017,9(6):575-582.
[7]SOWA J F.Principles of semantic networks:exploration in the representation of knowledge[J].Frame Problem in Artificial Intelligence,1991(2-3):135-157.
[8]STAAB S,STUDER R,SCHNURR H.Knowledge processes and ontologies[J].IEEE Intelligent Systems,Special Issue on Knowledge Management,2001,16(1):26-34.
[9]HENDRICKX I,KIM S N,KOZAREVA Z,et al.SemEval-2010 task 8:multi-way classification of sema nt ic relat ions bet ween pa ir s of nominals[C]//The Workshop on Semantic Evaluations:Recent Achievements and Future Directions,June 4,2009,Boulder,USA.[S.l.]:Association for Computational Linguistics,2009:94-99.
[10]HASHIMOTO K,STENETORP P,MIWA M,et al.Task-oriented learning of word embeddings for semantic relation classification[J].Computer Science,2015:268-278.
[11]ZHOU ZQ,QIG L,GLIM M B.Exploring parallel tractability of ontology materialization[C]//European Conference on Artificial Intelligence,Hague,Netherlands,August 29-September 2,2016.[S.l:s.n.],2016:73-81.
[2]陈秀娟,冷德荣.面向语言信息处理的语义研究--合著者的社会网络分析[J].情报科学,2013(7):126-129.CHEN X J,LENG D R.Semantic study in language and information processing based on social network analysis[J].Information Science,2013(7):126-129.
[3]秦长江,侯汉清.知识图谱--信息管理与知识管理的新领域[J].大学图书馆学报,2009(1):30-37,96.QIN C J,HOU H Q.Knowledge graph:a new area of information management and knowledge management[J].Journal of Academic Libraries,2009(1):30-37,96.
[4]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(4):589-606.XU Z L,SHENG Y P,HE L R,et al.Review on knowledge graph techniques[J].Journal of University of Electronic Science and Technology of China,2016(4):589-606.
[5]李涓子,侯磊.知识图谱研究综述[J].山西大学学报(自然科学版),2017,40(3):454-459.L I J Z,HOU L.Reviews on knowledge graphre search[J].Journal of Shanxi University(Natural Science Edition),2017,40(3):454-459.
[6]朱木易洁,鲍秉坤,徐常胜.知识图谱发展与构建的研究进展[J].南京信息工程大学学报(自然科学版),2017,9(6):575-582.ZHU M Y J,BAO B K,XU C S.Research progress on development and construction of knowledge graph[J].Journal of Nanjing Univrsity of Information Science&Technology(Natural Science Edition),2017,9(6):575-582.
[7]SOWA J F.Principles of semantic networks:exploration in the representation of knowledge[J].Frame Problem in Artificial Intelligence,1991(2-3):135-157.
[8]STAAB S,STUDER R,SCHNURR H.Knowledge processes and ontologies[J].IEEE Intelligent Systems,Special Issue on Knowledge Management,2001,16(1):26-34.
[9]HENDRICKX I,KIM S N,KOZAREVA Z,et al.SemEval-2010 task 8:multi-way classification of sema nt ic relat ions bet ween pa ir s of nominals[C]//The Workshop on Semantic Evaluations:Recent Achievements and Future Directions,June 4,2009,Boulder,USA.[S.l.]:Association for Computational Linguistics,2009:94-99.
[10]HASHIMOTO K,STENETORP P,MIWA M,et al.Task-oriented learning of word embeddings for semantic relation classification[J].Computer Science,2015:268-278.
[11]ZHOU ZQ,QIG L,GLIM M B.Exploring parallel tractability of ontology materialization[C]//European Conference on Artificial Intelligence,Hague,Netherlands,August 29-September 2,2016.[S.l:s.n.],2016:73-81.