摘要
城市休闲相关产业的高质量发展对当前我国城市消费升级以及人居环境质量提升具有重要现实意义。但是,现有研究未能精准地捕捉海量广域分布的城市休闲产业的基本空间分布规律与结构,而已有的空间聚类算法较多适用于城市用地分析,未能很好地适用于离散分布的城市休闲产业研究。为此,文章基于空间兴趣点数据,开发距离通达值及空间集群中心点等算法,构建城市休闲旅游产业聚类模式空间算法模型(APM)。在以广州为例的研究中,APM模型捕捉出3170个以500 m步行生活圈为范围的城市休闲产业集群,校验了APM模型的科学性与应用价值。整体上,APM算法可以较好地捕捉城市休闲业态集群的空间结构,清晰识别城市休闲产业空间冷、热点分布的基本结构,由其捕捉行程的聚类边界与实际道路和建筑走向、水系边界、区域范围等重合度高,聚类集群符合实际情况,具备可信度与有效性。该研究是休闲产业集聚机制研究的一次方法创新,在算法精度、实际应用、可视化效率上均做出了创新性推进。与Fishnet方法相比,可以更科学精准地识别城市内部多个休闲消费商圈的边界,实现了高效率的城市休闲产业集群捕捉;与同位模型相比,可以呈现多类别的城市休闲业态结构,突破了现有研究只能捕捉两类业态组团的局限。
The efficient development of the leisure industry is increasingly important for the upgrading of the urban consumer economy and the improvement of human environment quality,but existing research has not been able to accurately capture the basic spatial distribution pattern and structure of the urban leisure industry.Most of the existing spatial clustering algorithms are applied to urban land use analysis,and there are fewer algorithms for the characteristics of urban leisure industry data.At the same time,existing algorithms have problems such as strong subjectivity in methodology and the inability to accurately identify the internal situation of the city,so they cannot be well-adapted to the characteristics of the sea quantization and fragmentation of urban leisure industry data.Now that points of interest(POI) have become a very important data source in urban leisure industry research,spatial clustering algorithms for POI data needs to be developed to provide more effective support for subsequent in-depth research.To this end,this paper develops an APM(agglomeration pattern mining)model for urban leisure industry clustering based on the leisure point of interest data of Guangzhou city,using algorithms such as effective accessibility of amenities and peak value,and also verifies the scientific validity and application value of the APM model.The final APM model captures 3170 urban leisure industry clusters within a 500-meter walking life circle and confirms that it can accurately obtain the spatial distribution and structural characteristics of urban leisure industry clusters through a two-fold verification.Generally,the APM algorithm can better identify the spatial cold and hot spot distribution of the urban leisure industry;locally,the APM algorithm can more scientifically identify the boundary conditions of multiple leisure consumption business circles within the city.In multiple inner-city representative areas,the clustering boundaries formed by APM algorithm have a greater overlap with the actual road and bu
作者
刘逸
吴雪涵
许汀汀
LIU Yi;WU Xuehan;XU Tingting(School of Tourism Management,Sun Yat-sen University,Guangzhou 510275,China;Key Laboratory of Sustainable Tourism Smart Assessment Technology,Ministry of Culture and Tourism of China,Zhuhai 519080,China;School of Software Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400000,China)
出处
《旅游学刊》
北大核心
2024年第4期40-52,共13页
Tourism Tribune
基金
广东省科技创新战略专项资金(粤港澳联合实验室)项目“数据时空颗粒度对深度学习智慧城市发展模拟模型精度影响研究”(2020B1212030009)资助。
关键词
城市旅游休闲
产业集聚模式
空间数据挖掘
聚类算法
POI
广州市
unban tourism and leisure
industry clustering pattern
spatial data mining
clustering algorithm
point of interest
Guangzhou city
