产业集群知识图谱构建方法研究  

Research on the Construction Method of Industrial Cluster Knowledge Graph

作　　者：范存庆 余军合[1] 战洪飞[1] 王瑞 FAN Cunqing;YU Junhe;ZHAN Hongfei;WANG Rui(Faculty of Mechanical Engineering and Mechanics,Ningbo University,Ningbo 315211,China)

机构地区：[1]宁波大学机械工程与力学学院,浙江宁波315211

出　　处：《科技与经济》2022年第3期56-60,共5页Science & Technology and Economy

基　　金：国家自然科学基金项目——“面向产业集群广义制造系统的知识模块化机理研究”(项目编号:71671097,项目负责人:战洪飞)成果之一;国家重点研发项目——“注塑机和模具产业网络协同制造发展模式及关键技术研究”(项目编号:2019YFB1707101,项目负责人:战洪飞)成果之一。

摘　　要：通过探索知识图谱在产业集群的应用,提出了产业集群知识图谱整体设计框架,设计了产业集群知识图谱中实体及其关系本体模型。选取宁波市注塑机产业集群为例,通过互联网平台获取企业数据,经过数据预处理、知识抽取和知识融合,依据本体模型构建了宁波市注塑机产业集群知识图谱,将所构建的所有三元组存储于Neo4j图数据库中。根据所构建的知识图谱,分析注塑机集群整体特性,通过分析发现产业集群在地理位置临近关系上和业务往来有着密切的关系,验证本文提出方法的可行性。This paper explores the application of knowledge graph in industrial clusters, and proposes the overall design framework of industrial cluster knowledge graph. The entities and their relation ontology model in industrial cluster knowledge graph are designed. Taking injection machine cluster in Ningbo as an example, the enterprise data is obtained through the Internet platform. After data preprocessing, knowledge extraction and knowledge fusion, the knowledge graph of Ningbo injection machine cluster is constructed according to the ontology model, and all triples constructed are stored in the Neo4 j graph database. According to the knowledge graph constructed, this paper analyzes the overall characteristics of the injection machine cluster, and it is found that the industrial cluster has a close relationship with business transactions in terms of geographical proximity, which verifies the feasibility of the proposed method.

关 键 词：知识图谱 产业集群 知识抽取 Neo4j 

分 类 号：F124[经济管理—世界经济]