基于机器学习的涉海企业类型识别及其空间组织特征的城市比较研究  

A Comparative Study on the Type Recognition and Spatial Organization Characteristics of Sea-Related Enterprises Based on Machine Learning in Cities

作　　者：刘天宝[1,2] 马广鹏 张海瑜 张贵祥 Liu Tianbao;Ma Guangpeng;Zhang Haiyu;Zhang Guixiang(Center for Studies of Marine Economy and Sustainable Development,Liaoning Normal University,Dalian 116029,China;University Collaborative Innovation Center of Marine Economy High-Quality Development of Liaoning Province,Dalian 116029,China;School of Urban Economics and Public Administration,Capital University of Economics and Business,Beijing 100070,China;Faculty of Geography,Tianjin Normal University,Tianjin 300387,China)

机构地区：[1]辽宁师范大学海洋经济与可持续发展研究中心,辽宁大连116029 [2]辽宁省“海洋经济高质量发展”高校协同创新中心,辽宁大连116029 [3]首都经济贸易大学城市经济与公共管理学院,北京100070 [4]天津师范大学地理学部,天津300387

出　　处：《热带地理》2024年第8期1460-1474,共15页Tropical Geography

基　　金：国家社会科学基金项目(21BJL005);教育部人文社会科学重点研究基地重大项目(22JJD790031)。

摘　　要：在推进海洋强国建设的进程中,海洋产业是海洋经济增长的最直接对象,而其空间布局与产业组织特征的研究是最具基础性的工作之一。选取4个代表性城市为研究区,基于海洋企业的工商登记信息,爬取空间坐标构建POI产业信息数据库。使用人工神经网络等机器学习算法识别各企业所属的行业,综合运用GIS空间分析方法,分析海洋产业集群的空间分异性规律。结果表明:1)从空间格局特征看,总体呈“大分散、小集聚”的均衡格局,多类别对比显示企业选址存在行业集聚性,同时具有空间极化特征,陆海关系上体现为海岸带高密度单峰或“海岸带-市中心”双峰分布格局。2)从空间组织模式看,产业集群存在与人口规模、行政等级相对应的多层次等级位序特征;除单核心结构外,多核心结构中一般表现为“主-次双核心”或者“一主多次放射状”,核心区间产生空间联系形成多节点的轴线或网络结构。3)从空间匹配关系看,椭圆面积与城市面积呈正相关,椭圆长轴方向与海岸线延伸方向相近,产业分布与城市行政中心、港口等交通枢纽、海湾地形、海岸线等空间要素存在明确的匹配关系。Maritime Power has gradually increased as a national strategy.In this process,gross marine products continue to grow,and the marine industry has become the most fundamental and critical object.The spatial layout and industrial organization of maritime enterprises are fundamental related tasks.Domestic research can be divided into two main categories,based on the data used.One is to use economic and social statistical data,which have a large spatial scope but large granularity and cannot reflect the details of the industrial layout.The other is to use point-of-interest data,which are often not fully mined owing to the heavy workload of data processing.Therefore,there is little relevant content on departmental and urban comparisons in the existing research.Four representative cities-Dalian,Qingdao,Ningbo,and Xiamen-were selected as the research areas.According to the Industrial Classification for Ocean Industries and Their Related Activities,the research objects were identified as the marine core layer,marine support layer,and marine peripheral layer industries and further refined into eight subcategories.This study is based on the information of maritime enterprises registered for business registration,and uses Python to crawl geographic coordinates to improve the spatial information of enterprises.An innovative task is to identify the industry categories of enterprises.This task was performed using fastText,Convolutional Neural Networks,and Recurrent Neural Network.Thus,a spatial enterprise information database,including multiple marine industry departments,was established.Kernel density analysis,standard deviational ellipse analysis,buffer analysis,and other methods were used.Finally,by comparing the visualization results of the marine industrial spatial layout in the four cities,we delved into the marine industrial spatial differentiation patterns.In the experiment,machine learning models,such as artificial neural networks,exhibited high accuracy and recall when completing human recognition tasks,and these meth

关 键 词：机器学习 自然语言处理 核密度分析 海洋企业 产业集聚 空间布局特征 产业空间组织 沿海城市 

分 类 号：F129.9[经济管理—世界经济] K902[历史地理—人文地理学] TP3[自动化与计算机技术—计算机科学与技术]