基于图嵌入技术的产业集群分析方法研究
PDF下载 (275)牛士银,余军合,战洪飞,王 瑞,刘东洋.基于图嵌入技术的产业集群分析方法研究[J].宁波大学学报(理工版),2023,36(5):29-36.DOI:10.20098/j.cnki.1001-5132.2022.1211
NIU Shiyin,YU Junhe,ZHAN Hongfei,WANG Rui,LIU Dongyang.Industrial cluster analysis method based on graph embedding technology[J].Journal of Ningbo University(Natural Science & Engineering Edition),2023,36(5):29-36.DOI:10.20098/j.cnki.1001-5132.2022.1211
| Title: | Industrial cluster analysis method based on graph embedding technology |
| 作者: | 牛士银, 余军合, 战洪飞, 王 瑞, 刘东洋 |
| Author(s): | NIU Shiyin, YU Junhe, ZHAN Hongfei, WANG Rui, LIU Dongyang |
| 关键词: | 产业集群; 关联网络; 关系型图卷积网络; 区域特性 |
| Keywords: | industrial cluster; associated network; relational graph convolutional networks; regional characteristics |
| 分类号: | F276; T-9 |
| DOI: | 10.20098/j.cnki.1001-5132.2022.1211 |
| 文献标识码: | A |
| 摘要: | 以往对产业集群的相关实证研究存在数据获取困难、数据维度片面、传统复杂网络理论分析方法可拓展性差等问题. 针对以上问题, 本文以互联网上的大量非结构化数据为基础, 采用图嵌入模型提取集群网络特征的向量空间分析方法, 利用互联网公开数据构建产业集群关联网络, 结合企业行业分类标准与分析目的设计部分节点标签, 使用关系型图卷积神经网络模型(R-GCNs), 从产品关联层面进行产业集群特征学习. 根据产业集群内企业的嵌入表示和地理位置信息, 提出了集群网络嵌入应用分析方法. 通过对宁波地区制造业集群相关数据进行实验分析和论证, 验证了图嵌入分析方法在量化分析产业集群关联网络特征上的有效性. |
| Abstract: | Previous research on industrial clusters has problems such as the difficulty in data acquisition or one-sidedness of data dimensions, and poor scalability of analysis method in traditional complex network theory. To address these problems, a vector space analysis method is proposed, which is based on a large amount of unstructured data on the Internet, and employs a graph embedding model to extract the features of cluster associated network. The public data from Internet are used to construct industrial cluster associated network, and part of node labels are designed based on standards of industry classification and purposes of analysis, with which the model of relational graph convolutional networks (R-GCNs) is used to learn the characteristics of industrial clusters from the level of product association. According to the embedding and geographic location information of enterprises in the industrial cluster, the application method of cluster network embedding is also proposed. Through the experimental analysis and demonstration of the relevant data of the manufacturing industry cluster in Ningbo, the effectiveness of the graph embedding analysis method in the quantitative analysis of the characteristics of the industrial cluster associated network is verified. |
| 参考文献 /References: | [1] 赵炳新, 杜培林, 肖雯雯, 等. 产业集群的核结构与指标体系[J]. 系统工程理论与实践, 2016, 36(1):55-62. [2] 吴宇, 余军合, 战洪飞, 等. 数据驱动的产业集群辨识及空间关联性分析[J]. 科技与经济, 2020, 33(4):51-55. [3] Sozinova A A, Okhrimenko O I, Goloshchapova L V, et al. Industrial and innovation clusters: Development in Russia[J]. International Journal of Applied Business and Economic Research, 2017, 15(11):111-118. [4] Brachert M, Titze M, Kubis A. Identifying industrial clusters from a multidimensional perspective: Methodical aspects with an application to Germany[J]. Papers in Regional Science, 2011, 90(2):419-439. [5] Papagiannidis S, See-To E W K, Assimakopoulos D G, et al. Identifying industrial clusters with a novel big-data methodology: Are SIC codes (not) fit for purpose in the internet age?[J]. Computers & Operations Research, 2018, 98(10):355-366. [6] Kozonogova E V, Kurushin D S, Dubrovskaya J V. Computer visualization of the identify industrial clusters task using GVMap[J]. Scientific Visualization, 2019, 11(5):126-141. [7] 郑荣, 魏明珠, 高志豪, 等. 基于SCAN-CPM的产业新兴技术识别与演化路径分析: 以新能源汽车产业为例[J]. 图书情报工作, 2022, 66(11):100-109. [8] 张岩, 朱艳硕, 吴曼, 等. 中小企业智能制造产业集群创新扩散动力学复杂网络模型仿真[J]. 青岛科技大学学报(社会科学版), 2019, 35(1):35-40. [9] Lei H S, Huang C H. Geographic clustering, network relationships and competitive advantage two industrial clusters in Taiwan[J]. Management Decision, 2014, 52(5): 852-871. [10] 高菲, 俞竹超, 江山. 多核式中卫型产业集群的网络结构分析—–以沈阳装备制造业集群为例[J]. 产经评论, 2014, 5(5):63-77. [11] 关峻, 徐泽磊, 邢李志. 全球产业集群发展关联网络模型研究—–以汽车产业集群为例[J]. 科技进步与对策, 2017, 34(17):72-79. [12] Titze M, Brachert M, Kubis A. The identification of regional industrial clusters using qualitative input–output analysis (QIOA)[J]. Regional Studies, 2011, 45(1):89-102. [13] 李经成, 黄春晓. 创新型企业城市内部空间分布及组织逻辑—–以南京市为例[J]. 经济地理, 2022, 42(7):93-105. [14] 沈体雁, 李志斌, 凌英凯, 等. 中国国家标准产业集群的识别与特征分析[J]. 经济地理, 2021, 41(9):103-114. [15] Bordes A, Usunier N, Garcia-Durán A, et al. Translating embeddings for modeling multi-relational data[C]// Proceedings of the 26th International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada. New York: ACM, 2013:2787-2795. [16] Song D D, Zhang F, Lu M Y, et al. DTransE: Distributed translating embedding for knowledge graph[J]. IEEE Transactions on Parallel and Distributed Systems, 2021, 32(10):2509-2523. [17] Perozzi B, Al-Rfou R, Skiena S. DeepWalk: Online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, USA. New York: ACM, 2014:701-710. [18] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[EB/OL]. [2022-10-16]. https://arxiv.org/abs/1609.02907. [19] Schlichtkrull M, Kipf T N, Bloem P, et al. Modeling relational data with graph convolutional networks[C]// European Semantic Web Conference. Cham: Springer, 2018:593-607. [20] Nayak T, Majumder N, Goyal P, et al. Deep neural approaches to relation triplets extraction: A comprehen- sive survey[J]. Cognitive Computation, 2021, 13(5):1215-1232. [21] Devlin J, Chang M W, Lee K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding [C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019:4171-4186. [22] 童旭红. 从企业的进退机制看集群发展—–以高新技术企业为例[D]. 成都: 西南财经大学, 2005. |
| 备注/Memo: | 收稿日期: 2022－12－12. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/ 基金项目: 国家重点研发计划项目（2019YFB1707101, 2019YFB1707103）; 国家自然科学基金（71671097）; 浙江省省属高校基本科研项目（SJLZ2023001）; 浙江省公益技术应用研究计划项目（LGG20E050010, LGG18E050002）. 第一作者: 牛士银（1996－）, 男, 河南周口人, 在读硕士研究生, 主要研究方向: 知识管理、企业信息化. E-mail: niushiyin_nb@163.com *通信作者: 余军合（1971－）, 男, 湖北天门人, 博士/副教授, 主要研究方向: 知识管理、智能制造. E-mail: yujunhe@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
