技术领域technical field
本发明属于城市建设与更新领域，涉及一种基于多源数据融合的城市建设与更新模式确定方法及系统。The invention belongs to the field of urban construction and renewal, and relates to a method and system for determining a mode of urban construction and renewal based on multi-source data fusion.
背景技术Background technique
城市更新是当今世界各国普遍面临的重大城市发展问题，城市更新主要是在基于对城市与社会经济发展现状认识、城市未来发展前景分析的基础上，解决城市发展根本矛盾。即，将老化的城市片区进行科学化的改善，使其成为设施全面功能完备的代化城市。城市更新工作，其实质是对城市功能的新陈代谢过程，，包含着城市保护、城市修复、老城改造、城市更新、新建等多项内容。现阶段而言，对于城市更新往往采用的方法有三种：清除危旧房的重建性开发、保护历史性建筑的商业性开发以及综合整治方式的旧区更新，总的来说是以市场推动的房地产开发模式。由于对城市综合结构与功能的关注，人本主义的思想在城市更新中也越发的重要，然而现阶段的城市更新实践并没有能跟上更新理念的转变。Urban renewal is a major urban development problem commonly faced by countries all over the world today. Urban renewal is mainly based on the understanding of the status quo of urban and social and economic development and the analysis of the future development prospects of cities to solve the fundamental contradictions of urban development. That is, to scientifically improve the aging urban area to make it a modern city with comprehensive facilities and functions. The essence of urban renewal work is the metabolic process of urban functions, including urban protection, urban restoration, old city reconstruction, urban renewal, and new construction. At the present stage, there are three methods commonly used for urban renewal: reconstructive development to remove dilapidated buildings, commercial development to protect historic buildings, and comprehensive renovation of old districts. Generally speaking, it is driven by the market Real estate development model. Due to the focus on the comprehensive structure and function of the city, the idea of humanism is becoming more and more important in urban renewal. However, the current urban renewal practice has not been able to keep up with the transformation of the renewal concept.
美国建筑设计师哈里森·弗雷克最早提出了一种以公共交通为中枢、综合发展的城市建设概念，即公共交通为导向的土地利用发展模式TOD(Transit OrientedDevelopment)。实际上，对于城市的更新，也可以基于TOD的思路开展，即通过系统地协调土地开发、城市建设和公共交通间的关系，引导居民的出行行为和交通方式选择，通过居民的出行及区域的城市建筑规划情况确定城市更新的策略。这种基于交通发展与出行需求的城市更新思路实质上反映了交通与城市的协同关系。American architect Harrison Fleck first proposed a concept of urban construction with public transportation as the center and comprehensive development, that is, the public transportation-oriented land use development model TOD (Transit Oriented Development). In fact, urban renewal can also be carried out based on the idea of TOD, that is, by systematically coordinating the relationship between land development, urban construction and public transportation, guiding residents' travel behavior and transportation mode selection, and The situation of urban architectural planning determines the strategy of urban renewal. This urban renewal idea based on transportation development and travel demand essentially reflects the synergistic relationship between transportation and cities.
但是，在实际当中，受限于传统的交通基础数据采集技术，城市交通发展与出行需求的确定工作具有如下的几点局限性：1)在基础数据的采集工作上，传统的方法需要借助大量的人力进行居民入户调查，一方面会消耗大量的人力、物力与财力，并且调查的前期准备时间、调查的进行时间、调查数据的处理时间都非常的长；另一方面调查的覆盖面也非常窄，往往只能覆盖不超过3％的城市人口；2)在需求分析确定方面，对于部分关键数据及参数的取值时采用了近似的处理，导致交通出行需求分析的结果并不准确。此外，由于数据的采集周期长，导致交通出行需求分析的结果存在一定的滞后性。由此确定的交通需求并不能很好的决定城市更新的策略，在交通需求偏差较大时，甚至会导致城市更新的重大决策失误。However, in reality, limited by the traditional traffic basic data collection technology, the determination of urban traffic development and travel demand has the following limitations: 1) In the collection of basic data, the traditional method needs to rely on a large number of On the one hand, it will consume a lot of manpower, material resources and financial resources, and the preparation time of the survey, the time of conducting the survey, and the processing time of the survey data are very long; on the other hand, the coverage of the survey is also very large. 2) In terms of demand analysis and determination, approximate processing is used for some key data and parameter values, resulting in inaccurate results of traffic travel demand analysis. In addition, due to the long period of data collection, there is a certain lag in the results of traffic travel demand analysis. The traffic demand determined in this way cannot well determine the strategy of urban renewal. When the deviation of traffic demand is large, it may even lead to major decision-making mistakes in urban renewal.
发明内容Contents of the invention
发明目的：为解决传统城市建设与更新时，需要耗时耗力，且城市建设与更新模式确定与城市交通系统间协调不够的实际问题，发明目的在于提供一种基于多源数据融合的城市建设与更新模式确定方法及系统，通过对包含房地产住宅数据、矢量化道路网数据、兴趣点数据、企业纳税数据、消费水平数据等多源数据的采集、融合与分析，获取城市交通系统交通负荷、交通需求以及建筑年份等数据，并基于数据确定城市建设与更新的模式，优化数据采集的时间消耗与采集难度，提升城市建设与更新模式的时效性与可靠程度。Purpose of the invention: In order to solve the practical problems of time-consuming and labor-intensive traditional urban construction and renewal, and insufficient coordination between the determination of the urban construction and renewal mode and the urban transportation system, the purpose of the invention is to provide a kind of urban construction based on multi-source data fusion and update mode determination method and system, through the collection, integration and analysis of multi-source data including real estate and residential data, vectorized road network data, point of interest data, corporate tax data, consumption level data, etc., to obtain traffic load, Traffic demand and construction year data, and based on the data to determine the mode of urban construction and renewal, optimize the time consumption and difficulty of data collection, and improve the timeliness and reliability of the urban construction and renewal mode.
技术方案：为实现上述发明目的，本发明采用的技术方案为：Technical scheme: in order to realize the above-mentioned purpose of the invention, the technical scheme adopted in the present invention is:
一种基于多源数据融合的城市建设与更新模式确定方法，该方法包括如下步骤：A method for determining an urban construction and renewal model based on multi-source data fusion, the method comprising the following steps:
(1)多源数据采集，所述多源数据包括房地产住宅数据、兴趣点数据、企业纳税数据、消费水平数据和道路网络数据；所述房地产住宅数据包括城市的住宅区数量以及各住宅区的名称、房屋总数、房屋总使用面积、人均居住面积和建筑年份；所述兴趣点数据包括兴趣点总数量以及各兴趣点的名称、行业分类和坐标；所述企业纳税数据包括城市的企业数量以及各企业的名称和年营业额；所述消费水平数据包括城市的店铺数量以及各店铺的名称和人均消费金额；(1) Multi-source data collection, the multi-source data includes real estate residential data, point of interest data, enterprise tax data, consumption level data and road network data; the real estate residential data includes the number of residential areas in the city and the number of each residential area Name, total number of houses, total usable area of houses, per capita living area and construction year; the POI data includes the total number of POIs and the names, industry classifications and coordinates of each POI; the enterprise tax data includes the number of enterprises in the city and The name and annual turnover of each enterprise; the consumption level data includes the number of stores in the city, the name of each store and the per capita consumption amount;
(2)多源数据融合，包括：将行业分类为写字楼或住宅区的兴趣点分类为交通发生类兴趣点，其他兴趣点分类为交通吸引类兴趣点；将兴趣点名称分别与住宅区名称、企业名称、店铺名称匹配，得到匹配成功的兴趣点的房屋总使用面积、人均居住面积、企业年营业额和人均消费金额；将兴趣点的房屋总使用面积与人均居住面积相除计算交通发生类兴趣点交通发生人数；将兴趣点的企业年营业额与人均消费金额相除计算交通吸引类兴趣点的交通吸引人数；(2) Multi-source data fusion, including: classify POIs classified as office buildings or residential areas as traffic occurrence POIs, and classify other POIs as traffic attraction POIs; Match the name of the enterprise and the name of the store, and get the total usable area of the house, the per capita living area, the annual turnover of the enterprise and the per capita consumption amount of the successfully matched point of interest; divide the total usable area of the house and the per capita living area of the point of interest to calculate the traffic occurrence The number of people who have traffic at the point of interest; divide the annual turnover of the company at the point of interest by the per capita consumption amount to calculate the number of traffic attracting traffic at the point of interest;
(3)城市交通出行需求及负荷确定，包括：将各交通小区内的所有的兴趣点的交通发生人数和通吸引人数对应的累加作为交通小区的交通发生人数和交通吸引人数；将各交通小区的交通发生人数与人均出行次数相乘得到交通小区的交通发生量，各交通小区的交通吸引人数为交通吸引量；根据交通出行需求和依据道路网络数据计算的道路阻抗，采用双约束重力模型计算确定交通分布矩阵；将交通分布矩阵在道路网络上进行交通分配，根据分配结果计算各交通小区的交通负荷，其中第n个交通小区内的交通负荷Jn为第n个交通小区内的道路总条数，分别为第n个交通小区内第j条道路的长度和交通负荷；(3) Determination of urban traffic travel demand and load, including: the cumulative number of traffic occurrences and traffic attraction numbers of all points of interest in each traffic area is used as the number of traffic occurrences and traffic attraction numbers in the traffic area; Multiply the number of traffic occurrences and the number of trips per capita to obtain the traffic occurrence of the traffic area, and the traffic attraction number of each traffic area is the traffic attraction; according to the traffic travel demand and the road impedance calculated based on the road network data, the double-constraint gravity model is used to calculate Determine the traffic distribution matrix; distribute the traffic distribution matrix on the road network, calculate the traffic load of each traffic area according to the distribution results, and the traffic load in the nth traffic area Jn is the total number of roads in the nth traffic area, are the length and traffic load of the jth road in the nth traffic area, respectively;
(4)根据各交通小区的建筑年份、交通负荷及交通需求排序情况确定城市建设及更新模式。(4) Determine the urban construction and renewal mode according to the construction year, traffic load and traffic demand ranking of each traffic district.
作为优选，所述步骤(1)中采用网络爬虫技术，在互联网上爬取城市的房地产住宅数据。As preferably, web crawler technology is adopted in the step (1) to crawl the real estate and residential data of cities on the Internet.
作为优选，所述步骤(1)中采用百度地图API，在百度地图网页采集城市的兴趣点数据。As a preference, in the step (1), Baidu map API is used to collect the point-of-interest data of the city on the Baidu map web page.
作为优选，所述步骤(1)中采用大众点评API，在大众点评网页采集消费水平数据。Preferably, the Dianping API is used in the step (1) to collect consumption level data on the Dianping webpage.
作为优选，所述步骤(1)中采用QGIS软件下载城市的全部道路网络数据，并计算道路在自由流的情况下的道路阻抗。As preferably, adopt QGIS software to download all road network data of city in the described step (1), and calculate the road impedance of road under the situation of free flow.
作为优选，所述步骤(2)中，采用KMP算法将兴趣点名称NBmb分别与住宅区名称NAma、企业名称NCmc、店铺名称NDmd进行匹配；按照名称NBmb、NAma进行匹配时：若名称NBmb、NAma采用KMP算法计算得到的数值大于或者等于名称NBmb与任何一个NAma采用KMP算法计算得到数值，且KMP算法计算得到的数值大于或者等于min(NBmb、NAma)的0.85倍，则匹配成功；否则匹配失败；按照名称NBmb、NCmc进行匹配时：若名称NBmb、NCmc采用KMP算法计算得到的数值大于或者等于名称NBmb与任何一个NCmc采用KMP算法计算得到数值，且KMP算法计算得到的数值大于或者等于min(NBmb、NCmc)的0.85倍，则匹配成功；否则匹配失败；按照名称NBmb、NDmd进行匹配时：若名称NBmb、NDmd采用KMP算法计算得到的数值大于或者等于名称NBmb与任何一个NDmd采用KMP算法计算得到数值，且KMP算法计算得到的数值大于或者等于min(NBmb、NDmd)的0.85倍，则匹配成功；否则匹配失败；其中，ma、mb、mc、md分别表示住宅区的序号、兴趣点的序号、企业的序号、店铺的序号；min(NBmb、NAma)、min(NBmb、NCmc)、min(NBmb、NDmd)分别表示名称NBmb和NAma的字符串长度的较小值、名称NBmb和NCmc的字符串长度的较小值、名称NBmb和NDmd的字符串长度的较小值。Preferably, in the step (2), the KMP algorithm is used to match the name of the point of interest NBmb with the name of the residential area NAma , the name of the enterprise NCmc , and the name of the shop NDmd ; when matching according to the names NBmb and NAma : If the value calculated by the KMP algorithm for the name NBmb and NAma is greater than or equal to the value calculated by the KMP algorithm for the name NBmb and any NAma , and the value calculated by the KMP algorithm is greater than or equal to min(NBmb , NAma ) of 0.85 times, the matching is successful; otherwise, the matching fails; when matching according to the name NBmb and NCmc : if the value calculated by the KMP algorithm for the name NBmb and NCmc is greater than or equal to the name NBmb and any NCmc If the value calculated by the KMP algorithm is greater than or equal to 0.85 times of min(NBmb , NCmc ), the matching is successful; otherwise, the matching fails; when matching according to the names NBmb and NDmd : if the name NB The value calculated by KMP algorithm formb and NDmd is greater than or equal to the value calculated by KMP algorithm for the name NBmb and any NDmd , and the value calculated by KMP algorithm is greater than or equal to 0.85 times of min(NBmb , NDmd ) , the matching is successful; otherwise, the matching fails; among them, ma, mb, mc, md represent the serial number of the residential area, the serial number of the point of interest, the serial number of the enterprise, and the serial number of the store respectively; min(NBmb , NAma ), min(NBmb , NCmc ), min(NBmb , NDmd ) represent the smaller value of the string lengths of the names NBmb and NAma , the smaller value of the string lengths of the names NBmb and NCmc , the names NBmb and Smaller value for the string length of NDmd .
作为优选，所述步骤(4)中，确定城市建设及更新模式的规则包括如下一种或多种：若某交通小区的建筑年份排序后a％且交通负荷排序前a％，则判定该小区应当进行功能疏解型城市更新；若某交通小区的建筑年份排序后a％且交通负荷排序后a％，则判定该小区应当进行功能提升型城市更新；若某交通小区的建筑年份排序前a％且交通负荷排序前a％，则判定该小区应当进行交通基础设施建设及优化；若某交通小区的建筑年份排序前a％且交通负荷排序后a％，则判定该小区应当进行城市配套设施完善；若某交通小区的交通需求排序后a％，则判定该小区应当进行城市配套设施完善；若某交通小区的交通需求排序前a％，则判定该小区应当进行城市交通系统优化；其中a为设定阈值。As preferably, in the step (4), the rules for determining the urban construction and renewal mode include one or more of the following: if the building year of a certain traffic district is sorted by a% and the traffic load is sorted by a% before, then it is determined that the district Urban renewal based on function deconstruction should be carried out; if a% of the construction years of a certain traffic district are sorted and a% of traffic loads are ranked behind, it is determined that the district should undergo urban renewal of function enhancement; And the traffic load ranks a% before, then it is determined that the community should carry out the construction and optimization of traffic infrastructure; if the construction year of a traffic community is ranked a% before and the traffic load is ranked a%, then it is determined that the community should improve urban supporting facilities ; If the traffic demand of a certain traffic area is sorted by a%, then it is judged that the urban supporting facilities should be improved in this community; Set the threshold.
本发明另一方面提供的一种基于多源数据融合的城市建设与更新模式确定系统，包括：Another aspect of the present invention provides an urban construction and renewal mode determination system based on multi-source data fusion, including:
多源数据采集模块，包括房地产住宅数据采集单元、兴趣点数据采集单元、企业纳税数据采集单元、消费水平数据采集单元和道路网络数据采集单元分别用于采集房地产住宅数据、兴趣点数据、企业纳税数据、消费水平数据和道路网络数据；所述房地产住宅数据包括城市的住宅区数量以及各住宅区的名称、房屋总数、房屋总使用面积、人均居住面积和建筑年份；所述兴趣点数据包括兴趣点总数量以及各兴趣点的名称、行业分类和坐标；所述企业纳税数据包括城市的企业数量以及各企业的名称和年营业额；所述消费水平数据包括城市的店铺数量以及各店铺的名称和人均消费金额；Multi-source data acquisition module, including real estate and residential data acquisition unit, point of interest data acquisition unit, enterprise tax data acquisition unit, consumption level data acquisition unit and road network data acquisition unit are used to collect real estate residential data, interest point data, enterprise tax payment data, consumption level data, and road network data; the real estate residential data includes the number of residential areas in the city and the names of each residential area, the total number of houses, the total usable area of houses, the per capita living area, and the year of construction; the data of interest points includes interest The total number of points and the name, industry classification and coordinates of each point of interest; the enterprise tax data includes the number of enterprises in the city, the name and annual turnover of each enterprise; the consumption level data includes the number of shops in the city and the name of each shop and per capita consumption;
多源数据融合模块，包括：兴趣点分类单元，用于将行业分类为写字楼或住宅区的兴趣点分类为交通发生类兴趣点，其他兴趣点分类为交通吸引类兴趣点；多源数据匹配单元，用于将兴趣点名称分别与住宅区名称、企业名称、店铺名称匹配，得到匹配成功的兴趣点的房屋总使用面积、人均居住面积、企业年营业额和人均消费金额；交通发生人数计算单元，用于将兴趣点的房屋总使用面积与人均居住面积相除计算交通发生类兴趣点交通发生人数；以及，交通吸引人数计算单元，将兴趣点的企业年营业额与人均消费金额相除计算交通吸引类兴趣点的交通吸引人数；Multi-source data fusion module, including: POI classification unit, which is used to classify POIs whose industries are classified as office buildings or residential areas into traffic occurrence POIs, and other POIs into traffic attraction POIs; multi-source data matching unit , used to match the name of the point of interest with the name of the residential area, the name of the enterprise, and the name of the store, and obtain the total usable area of the house, the per capita living area, the annual turnover of the enterprise, and the per capita consumption amount of the successfully matched points of interest; the calculation unit for the number of traffic occurrences , which is used to divide the total housing area of the POI by the per capita living area to calculate the number of traffic occurrences of the POI; and, the calculation unit for the number of people attracted by traffic, divide the annual turnover of the POI by the per capita consumption amount to calculate The number of traffic attractors of traffic attracting POIs;
城市交通出行需求及负荷确定模块，用于根据兴趣点的交通发生人数和通吸引人数计算交通小区的交通发生量和交通吸引量；以及根据交通出行需求和依据道路网络数据计算的道路阻抗，采用双约束重力模型计算确定交通分布矩阵；将交通分布矩阵在道路网络上进行交通分配，根据分配结果计算各交通小区的交通负荷，其中第n个交通小区内的交通负荷Jn为第n个交通小区内的道路总条数，分别为第n个交通小区内第j条道路的长度和交通负荷；The urban traffic travel demand and load determination module is used to calculate the traffic generation and traffic attraction of the traffic area according to the number of traffic occurrences and traffic attraction of points of interest; and the road impedance calculated according to the traffic travel demand and road network data, using The double-constraint gravity model calculates and determines the traffic distribution matrix; distributes the traffic distribution matrix on the road network, and calculates the traffic load of each traffic area according to the distribution results, among which the traffic load in the nth traffic area Jn is the total number of roads in the nth traffic area, are the length and traffic load of the jth road in the nth traffic area, respectively;
以及，城市建设及更新模式确定模块，用于根据各交通小区的建筑年份、交通负荷及交通需求排序情况确定城市建设及更新模式。And, the urban construction and renewal mode determination module is used to determine the urban construction and renewal mode according to the construction year, traffic load and traffic demand ranking of each traffic district.
有益效果：本发明提出的基于多源数据融合的城市建设与更新模式确定方法，该方法充分考虑了城市土地开发、城市建设与更新和曾是交通间的互动及关联变化关系，通过本发明方法获得的城市建设与更新模式，一方面优化了相关数据采集的时间消耗与采集难度，更重要的是提升了城市建设与更新模式的时效性与可靠程度。Beneficial effects: the method for determining the urban construction and renewal mode based on multi-source data fusion proposed by the present invention fully considers the interaction and correlation between urban land development, urban construction and renewal, and former traffic, and through the method of the present invention The obtained urban construction and renewal model, on the one hand, optimizes the time consumption and difficulty of collecting relevant data, and more importantly, improves the timeliness and reliability of the urban construction and renewal model.
附图说明Description of drawings
图1为本发明的流程框图。Fig. 1 is a flowchart of the present invention.
具体实施方式Detailed ways
下面结合附图和具体实施例，对本发明作更进一步的说明。The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
如图1所示，本发明实施例公开的一种基于多源数据融合的城市建设与更新模式确定方法，通过对包含房地产住宅数据、矢量化道路网数据、兴趣点数据、企业纳税数据、消费水平数据等多源数据的采集、融合与分析，获取城市交通系统出行负荷，并基于交通的负荷确定城市建设与更新的模式。该方法主要包含以下步骤：As shown in Figure 1, a method for determining urban construction and renewal modes based on multi-source data fusion disclosed in the embodiment of the present invention, through real estate housing data, vectorized road network data, point of interest data, corporate tax data, consumption The collection, integration and analysis of multi-source data such as horizontal data, obtain the travel load of the urban traffic system, and determine the mode of urban construction and renewal based on the traffic load. The method mainly includes the following steps:
步骤S1：多源数据采集。具体包括如下方面数据的采集：Step S1: Multi-source data collection. Specifically, the collection of data includes the following aspects:
步骤1A)房地产住宅数据数据采集。采用网络爬虫技术，在互联网上(如链家(https://www.lianjia.com/)、我爱我家(https://www.5i5j.com/)，或者城市房管部门主管的房产登记网站等)爬取城市的房地产住宅数据。采集的数据包含：城市的住宅区数量MA，第ma个住宅区名称NAma，第ma个住宅区的房屋总数TAma，第ma个住宅区的房屋总使用面积AAma，第ma个住宅区的人均居住面积ABma，第ma个住宅区的建筑年份YEARma。其中，ma为住宅区的序号，ma为自然数，且MA≥ma≥1；Step 1A) Real estate housing data data collection. Using web crawler technology, on the Internet (such as Lianjia (https://www.lianjia.com/), I love my home (https://www.5i5j.com/), or the real estate registration website headed by the urban housing management department, etc. ) to crawl the city's real estate housing data. The collected data includes: the number of residential areas MA in the city, the name of the ma-th residential area NAma , the total number of houses in the ma-th residential area TAma , the total usable area of houses in the ma-th residential area AAma , the ma-th residential area The per capita living area ABma , the construction year YEARma of the ma-th residential area. Among them, ma is the serial number of the residential area, ma is a natural number, and MA≥ma≥1;
步骤1B)兴趣点数据采集。采用百度地图API(如http://api.map.baidu.com/lbsapi/接口)，在百度地图网页采集城市的兴趣点数据。采集的数据包含：兴趣点的总数量MB，第mb个兴趣点的名称NBmb，第mb个兴趣点的行业分类TBmb，第mb个兴趣点的坐标(xmb,ymb)。其中，mb为兴趣点的序号，mb为自然数，且MB≥mb≥1；Step 1B) Data collection of points of interest. Use the Baidu map API (such as http://api.map.baidu.com/lbsapi/ interface) to collect the city's POI data on the Baidu map web page. The collected data includes: the total number MB of POIs, the name NBmb of the mbth POI, the industry classification TBmb of the mbth POI, and the coordinates (xmb , ymb ) of the mbth POI. Among them, mb is the serial number of the interest point, mb is a natural number, and MB≥mb≥1;
步骤1C)企业纳税数据采集。通过企查查(https://www.qichacha.com/)或天眼查(https://www.tianyancha.com/)提供的企业经营状况信息直接获取，或者计算得到。采集的数据包含：城市的企业数量MC，第mc个企业的名称NCmc，第mc个企业的年营业额TCmc。其中，mc为企业的序号，mc为自然数，且MC≥mc≥1；Step 1C) Collection of enterprise tax payment data. It can be directly obtained or calculated from the business status information provided by Qichacha (https://www.qichacha.com/) or Tianyancha (https://www.tianyancha.com/). The collected data includes: the number MC of enterprises in the city, the name NCmc of the mcth enterprise, and the annual turnover TCmc of the mcth enterprise. Among them, mc is the serial number of the enterprise, mc is a natural number, and MC≥mc≥1;
步骤1D)消费水平数据采集。采用大众点评API，在大众点评网页采集消费水平数据。采集的数据包含：城市的店铺数量MD，第md个店铺的名称NDmd，第md个店铺的人均消费金额TDmd。其中，md为店铺的序号，md为自然数，且MD≥md≥1；Step 1D) Consumption level data collection. Dianping API is used to collect consumption level data on the Dianping webpage. The collected data includes: the number of stores in the city MD, the name of the md store NDmd , and the per capita consumption amount TDmd of the md store. Among them, md is the serial number of the store, md is a natural number, and MD≥md≥1;
步骤1E)道路网络数据采集。采用QGIS软件内置的“Openstreetmap-DownloadData”功能，手动选定城市的范围，并下载城市的全部道路网络数据，随后采用美国公路局BPR函数计算道路在自由流的情况下的道路阻抗；Step 1E) road network data collection. Use the built-in "Openstreetmap-DownloadData" function of QGIS software to manually select the range of the city and download all the road network data of the city, and then use the BPR function of the U.S. Highway Bureau to calculate the road impedance of the road in the case of free flow;
步骤S2：多源数据融合，包含如下步骤：Step S2: multi-source data fusion, including the following steps:
步骤2A)：兴趣点分类。将步骤1B)中采集得到的兴趣点数据根据行业分类TBmb进行分类：若TBmb为写字楼、住宅区的兴趣点，则第mb个兴趣点为交通发生类兴趣点；否则，若TBmb为除了写字楼、住宅区以外的兴趣点，则第mb个兴趣点为交通吸引类兴趣点；Step 2A): POI classification. The point of interest data collected in step 1B) is classified according to the industry classification TBmb : if TBmb is a point of interest in office buildings and residential areas, then the mbth point of interest is a traffic occurrence class of interest; otherwise, if TBmb is For POIs other than office buildings and residential areas, the mbth POI is a traffic-attracting POI;
步骤2B)：多源数据匹配。将步骤1B)采集得到的兴趣点数据，和步骤1A)房地产住宅数据数据，按照名称NBmb、NAma进行匹配：对于第mb个兴趣点，若名称NBmb、NAma采用KMP算法计算得到的数值大于或者等于名称NBmb与任何一个NAma采用KMP算法计算得到数值，且KMP算法计算得到的数值大于或者等于min(NBmb、NAma)的0.85倍，则匹配成功，此时匹配后第mb个兴趣点的房屋总使用面积为匹配后的人均居住面积为将步骤1B)采集得到的兴趣点数据，和步骤1C)采集得到的企业纳税数据，按照名称NBmb、NCmc进行匹配：对于第mb个兴趣点，若名称NBmb、NCmc采用KMP算法计算得到的数值大于或者等于名称NBmb与任何一个NCmc采用KMP算法计算得到数值，且KMP算法计算得到的数值大于或者等于min(NBmb、NCmc)的0.85倍，则匹配成功，此时，匹配后第mb个兴趣点的企业的年营业额为将步骤1B)采集得到的兴趣点数据，和步骤1D)采集得到的消费水平数据，按照名称NBmb、NDmd进行匹配：对于第mb个兴趣点，若名称NBmb、NDmd采用KMP算法计算得到的数值大于或者等于名称NBmb与任何一个NDmd采用KMP算法计算得到数值，且KMP算法计算得到的数值大于或者等于min(NBmb、NDmd)的0.85倍，则匹配成功，此时匹配后第mb个兴趣点的人均消费金额其中，下标MAmb为与第mb个兴趣点匹配的房地产住宅数据的序号，下标MCmb为与第mb个兴趣点匹配的企业纳税数据的序号，下标MDmb为与第mb个兴趣点匹配的消费水平数据的序号；min(NBmb、NAma)、min(NBmb、NCmc)、min(NBmb、NDmd)分别表示名称NBmb和NAma的字符串长度的较小值、名称NBmb和NCmc的字符串长度的较小值、名称NBmb和NDmd的字符串长度的较小值；Step 2B): Multi-source data matching. Match the point of interest data collected in step 1B) with the real estate and residential data in step 1A) according to the name NBmb and NAma : for the mbth point of interest, if the name NBmb and NAma are calculated using the KMP algorithm If the value is greater than or equal to the value calculated by the KMP algorithm between the name NBmb and any NAma , and the value calculated by the KMP algorithm is greater than or equal to 0.85 times min(NBmb , NAma ), the match is successful. The total usable area of houses for mb POIs is The per capita living area after matching is Match the POI data collected in step 1B) with the enterprise tax data collected in step 1C) according to the name NBmb and NCmc : for the mbth POI, if the name NBmb and NCmc are calculated using the KMP algorithm If the value obtained is greater than or equal to the value calculated by the KMP algorithm between the name NBmb and any NCmc , and the value calculated by the KMP algorithm is greater than or equal to 0.85 times of min(NBmb , NCmc ), the match is successful. At this time, The annual turnover of the enterprise of the mbth interest point after matching is Match the POI data collected in step 1B) with the consumption level data collected in step 1D) according to the names NBmb and NDmd : for the mbth POI, if the names NBmb and NDmd are calculated using the KMP algorithm If the value obtained is greater than or equal to the value calculated by the KMP algorithm between the name NBmb and any NDmd , and the value calculated by the KMP algorithm is greater than or equal to 0.85 times of min(NBmb , NDmd ), the match is successful. The per capita consumption amount of the next mbth point of interest Among them, the subscript MAmb is the serial number of the real estate housing data matching the mbth POI, the subscript MCmb is the serial number of the corporate tax payment data matching the mbth POI, and the subscript MDmb is the serial number matching the mbth POI The serial number of the consumption level data matched by the point; min(NBmb , NAma ), min(NBmb , NCmc ), min(NBmb , NDmd ) represent the smaller of the string lengths of the names NBmb and NAma respectively value, the smaller of the string lengths of names NBmb and NCmc , the smaller of the string lengths of names NBmb and NDmd ;
步骤2C)：交通发生类兴趣点交通发生人数计算。若第mb个兴趣点在步骤2A)中分类为交通吸引类兴趣点，则第mb个兴趣点的交通发生人数Pmb＝0；若第mb个兴趣点在步骤2A)中分类为交通发生类兴趣点，则计算交通发生人数：若该兴趣点在步骤2B)中匹配成功，则第mb个兴趣点的交通发生人数若该兴趣点在步骤2B)中匹配不成功，则第mb个兴趣点的交通发生人数Pmb为其他所有匹配成功的交通发生类兴趣点的交通发生人数的平均值；Step 2C): Calculation of the number of traffic occurrences in traffic occurrence POIs. If the mbth interest point is classified as a traffic attraction class interest point in step 2A), then the traffic occurrence number Pmb of the mbth interest point =0; if the mbth interest point is classified as a traffic occurrence class in step 2A) point of interest, the number of traffic occurrences is calculated: if the point of interest is successfully matched in step 2B), the number of traffic occurrences of the mbth point of interest If the point of interest is unsuccessfully matched in step 2B), the number of traffic occurrences Pmb of the mb point of interest is the average value of the number of traffic occurrences of all other traffic generation class points of interest that match successfully;
步骤2D)：交通吸引类兴趣点交通吸引人数计算。若第mb个兴趣点在步骤2A)中分类为交通发生类兴趣点，则第mb个兴趣点的交通吸引人数Amb＝0；若第mb个兴趣点在步骤2A)中分类为交通吸引类兴趣点，则计算交通吸引人数：若该兴趣点在步骤2B)中匹配成功，则第mb个兴趣点的交通吸引人数若该兴趣点在步骤2B)中匹配不成功，则第mb个兴趣点的交通吸引人数Amb为其他所有匹配成功的交通吸引类兴趣点的交通吸引人数的平均值；Step 2D): Calculation of the number of traffic attractors of traffic attracting POIs. If the mbth interest point is classified as the traffic generation class interest point in step 2A), then the traffic attracting numberAmb =0 of the mbth interest point; if the mbth interest point is classified as the traffic attraction class in step 2A) point of interest, then calculate the number of traffic attractors: if the point of interest is successfully matched in step 2B), the number of traffic attractors of the mbth point of interest If the point of interest is unsuccessfully matched in step 2B), the number of traffic attractors Amb of the mb point of interest is the average value of the number of traffic attractors of all other traffic attraction points of interest that match successfully;
步骤S3：城市交通出行需求及负荷确定，包含如下步骤：Step S3: Determination of urban traffic travel demand and load, including the following steps:
步骤3A)交通出行需求初始化。设置第n个交通小区的初始交通发生人数为Pron＝0，初始交通吸引人数为Attn＝0。其中，n为交通小区的序号，n为自然数，且N≥n≥1。N为交通小区的总数；Step 3A) Traffic travel demand initialization. Set the initial traffic occurrence number of the nth traffic area as Pron =0, and the initial traffic attraction number as Attn =0. Among them, n is the serial number of the traffic area, n is a natural number, and N≥n≥1. N is the total number of traffic areas;
步骤3B)交通出行人数确定。依次处理每个兴趣点的交通发生人数与交通吸引人数：第mb个兴趣点在交通小区nmb内，则将第mb个兴趣点的交通发生人数Pmb、交通吸引人数Amb对应的累加至第nmb个交通小区的交通发生人数交通吸引人数之上；Step 3B) The number of traffic travelers is determined. Process the number of traffic occurrences and traffic attraction numbers of each POI in turn: when the mbth POI is within the traffic area nmb , the corresponding number of traffic occurrences Pmb and traffic attraction number Amb of the mbth POI is accumulated to The number of traffic occurrences in the nmb traffic district traffic attraction above;
步骤3C)交通出行需求确定。第n个交通小区的交通发生量为PPron＝Pron×time，交通吸引量为AAttn＝Attn，其中，time为人均出行次数；Step 3C) Determination of traffic travel demand. The traffic generation volume of the nth traffic area is PPron =Pron ×time, and the traffic attraction volume is AAttn =Attn , where time is the number of trips per capita;
步骤3D)交通分布矩阵确定。利用步骤3C)获取的交通出行需求，以及步骤1E)获取的道路阻抗，采用双约束重力模型，计算确定交通分布矩阵；具体的双约束重力模型的方法可参考王炜、陈学武主编的《交通规划》(人民交通出版社，2007年版)第66-70页中的内容。Step 3D) The traffic distribution matrix is determined. Using the traffic travel demand obtained in step 3C) and the road impedance obtained in step 1E), the double-constrained gravity model is used to calculate and determine the traffic distribution matrix; for the specific method of the double-constrained gravity model, please refer to "Traffic Planning" (People's Communications Publishing House, 2007 edition) on pages 66-70.
步骤3E)交通分配。将步骤1G4)获取的交通分布矩阵，在步骤1E)采集的道路网络上进行交通分配，分配方法采用容量限制-多路径分配法。记录交通分配的结果：第n个交通小区内，第j条道路的长度第j条道路的为交通负荷为其中，j为道路的序号，j为自然数，且Jn≥j≥1。Jn为第n个交通小区内的道路总条数；Step 3E) Traffic distribution. The traffic distribution matrix obtained in step 1G4) is allocated to the road network collected in step 1E), and the allocation method adopts the capacity limitation-multi-path allocation method. Record the result of traffic distribution: the length of the jth road in the nth traffic area The traffic load of the jth road is Wherein, j is the serial number of the road, j is a natural number, and Jn ≥ j ≥ 1. Jn is the total number of roads in the nth traffic area;
步骤3F)交通负荷计算。第n个交通小区内的交通负荷由下式确定Step 3F) Traffic load calculation. The traffic load in the nth traffic area is determined by the following formula
步骤S4：城市建设及更新模式确定，包含如下步骤：Step S4: Determine the urban construction and renewal mode, including the following steps:
步骤4A)交通负荷、需求与建筑年份排序。将交通小区按照交通负荷大小进行降序排列，排序后第n个交通小区的排序序号为nVOC；将交通小区按照交通发生量为PPron与交通吸引量AAttn的和进行降序排列，排序后第n个交通小区的排序序号为ndemand；将交通小区按照交通小区内住宅区的建筑年份平均值大小进行降序排序，排序后第n个交通小区的排序序号为nyear；Step 4A) Sort traffic load, demand and construction year. Arrange the traffic districts in descending order according to the size of the traffic load. After sorting, the sorting sequence number of the nth traffic district is nVOC ; arrange the traffic districts in descending order according to the sum of the traffic generation volume PPron and the traffic attraction AAttn , and the sorting number is n VOC . The sorting serial number of n traffic districts is ndemand ; the traffic district is sorted in descending order according to the building year average size of the residential area in the traffic district, and the sorting serial number of the nth traffic district after sorting is nyear ;
步骤4B)城市建设、更新模式确定。根据步骤4A)交通负荷、交通需求与建筑年份的排序结果，确定城市建设、更新模式：若第n个交通小区的建筑年份排序后10％且交通负荷排序前10％，则对该小区应当进行功能疏解型城市更新；若第n个交通小区的建筑年份排序后10％且交通负荷排序后10％，则对该小区应当进行功能提升型城市更新；若第n个交通小区的建筑年份排序前10％且交通负荷排序前10％，则对该小区应当进行交通基础设施建设及优化；若第n个交通小区的建筑年份排序前10％且交通负荷排序后10％，则对该小区应当进行城市配套设施完善；若第n个交通小区的交通需求(交通发生量与交通吸引量的和)排序后10％，则对该小区应当进行城市配套设施完善；若第n个交通小区的交通需求排序前10％，则对该小区应当进行城市交通系统优化。Step 4B) Urban construction and update mode determination. According to the sorting results of traffic load, traffic demand and construction year in step 4A), determine the urban construction and renewal mode: if the construction year of the nth traffic district is ranked 10% and the traffic load is ranked 10%, then the district should be Functional deconstruction urban renewal; if the construction year of the nth traffic district is ranked 10% and the traffic load is 10% behind, then the urban renewal of function improvement should be carried out for the district; if the construction year of the nth traffic district is ranked before 10% and the top 10% of the traffic load ranking, the traffic infrastructure construction and optimization should be carried out for the community; The urban supporting facilities are perfect; if the traffic demand (the sum of traffic occurrence and traffic attraction) of the nth traffic area is ranked 10%, then the urban supporting facilities should be improved for the area; if the traffic demand of the nth traffic area The top 10% in the ranking, the urban traffic system optimization should be carried out for the community.
本发明另一实施例提供的一种基于多源数据融合的城市建设与更新模式确定系统，包括多源数据采集模块、多源数据融合模块、城市交通出行需求及负荷确定模块以及城市建设及更新模式确定模块。其中多源数据采集模块，包括房地产住宅数据采集单元、兴趣点数据采集单元、企业纳税数据采集单元、消费水平数据采集单元和道路网络数据采集单元分别用于采集房地产住宅数据、兴趣点数据、企业纳税数据、消费水平数据和道路网络数据。多源数据融合模块，包括：兴趣点分类单元，用于将行业分类为写字楼或住宅区的兴趣点分类为交通发生类兴趣点，其他兴趣点分类为交通吸引类兴趣点；多源数据匹配单元，用于将兴趣点名称分别与住宅区名称、企业名称、店铺名称匹配，得到匹配成功的兴趣点的房屋总使用面积、人均居住面积、企业年营业额和人均消费金额；交通发生人数计算单元，用于将兴趣点的房屋总使用面积与人均居住面积相除计算交通发生类兴趣点交通发生人数；以及，交通吸引人数计算单元，将兴趣点的企业年营业额与人均消费金额相除计算交通吸引类兴趣点的交通吸引人数。城市交通出行需求及负荷确定模块，用于根据兴趣点的交通发生人数和通吸引人数计算交通小区的交通发生量和交通吸引量；以及根据交通出行需求和依据道路网络数据计算的道路阻抗，采用双约束重力模型计算确定交通分布矩阵；将交通分布矩阵在道路网络上进行交通分配，根据分配结果计算各交通小区的交通负荷；城市建设及更新模式确定模块，用于根据各交通小区的建筑年份、交通负荷及交通需求排序情况确定城市建设及更新模式。该基于多源数据融合的城市建设与更新模式确定系统实施例可以用于执行上述基于多源数据融合的城市建设与更新模式确定方法实施例，其技术原理、所解决的技术问题及产生的技术效果相似，具体实现细节参见上述方法实施例，此处不再赘述。Another embodiment of the present invention provides an urban construction and update mode determination system based on multi-source data fusion, including a multi-source data acquisition module, a multi-source data fusion module, an urban traffic travel demand and load determination module, and urban construction and update mode determination module. Among them, the multi-source data acquisition module, including real estate residential data acquisition unit, point of interest data acquisition unit, enterprise tax data acquisition unit, consumption level data acquisition unit and road network data acquisition unit, is used to collect real estate residential data, interest point data, enterprise Tax data, consumption level data and road network data. Multi-source data fusion module, including: POI classification unit, which is used to classify POIs whose industries are classified as office buildings or residential areas into traffic occurrence POIs, and other POIs into traffic attraction POIs; multi-source data matching unit , used to match the name of the point of interest with the name of the residential area, the name of the enterprise, and the name of the store, and obtain the total usable area of the house, the per capita living area, the annual turnover of the enterprise, and the per capita consumption amount of the successfully matched points of interest; the calculation unit for the number of traffic occurrences , which is used to divide the total housing area of the POI by the per capita living area to calculate the number of traffic occurrences of the POI; and, the calculation unit for the number of people attracted by traffic, divide the annual turnover of the POI by the per capita consumption amount to calculate The number of traffic attractors of the traffic attraction POI. The urban traffic travel demand and load determination module is used to calculate the traffic generation and traffic attraction of the traffic area according to the number of traffic occurrences and traffic attraction of points of interest; and the road impedance calculated according to the traffic travel demand and road network data, using The double-constraint gravity model calculates and determines the traffic distribution matrix; distributes the traffic distribution matrix on the road network, and calculates the traffic load of each traffic area according to the distribution results; the urban construction and renewal mode determination module is used to calculate the construction year of each traffic area , traffic load and traffic demand ranking to determine the urban construction and renewal model. The embodiment of the urban construction and renewal mode determination system based on multi-source data fusion can be used to implement the above-mentioned embodiment of the urban construction and renewal mode determination method based on multi-source data fusion, its technical principles, technical problems solved and generated technologies The effects are similar, and for specific implementation details, refer to the foregoing method embodiments, and details are not repeated here.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810868013.9ACN109035112B (en) | 2018-08-02 | 2018-08-02 | City construction and updating mode determining method and system based on multi-source data fusion |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810868013.9ACN109035112B (en) | 2018-08-02 | 2018-08-02 | City construction and updating mode determining method and system based on multi-source data fusion |
| Publication Number | Publication Date |
|---|---|
| CN109035112Atrue CN109035112A (en) | 2018-12-18 |
| CN109035112B CN109035112B (en) | 2021-01-26 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810868013.9AActiveCN109035112B (en) | 2018-08-02 | 2018-08-02 | City construction and updating mode determining method and system based on multi-source data fusion |
| Country | Link |
|---|---|
| CN (1) | CN109035112B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112199566A (en)* | 2020-09-27 | 2021-01-08 | 成都房联云码科技有限公司 | City update effect evaluation method and system based on real estate big data |
| CN112613662A (en)* | 2020-12-23 | 2021-04-06 | 北京恒达时讯科技股份有限公司 | Highway traffic volume analysis method and device, electronic equipment and storage medium |
| CN113192321A (en)* | 2021-03-17 | 2021-07-30 | 东南大学 | Traffic demand distribution extraction method for comprehensive land utilization |
| CN113611105A (en)* | 2021-07-09 | 2021-11-05 | 东南大学 | Urban traffic travel demand total quantity prediction method |
| CN120471310A (en)* | 2025-07-16 | 2025-08-12 | 海开智慧(北京)科技服务有限公司 | Urban updating multidimensional dynamic supervision and analysis system based on big data |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368309A (en)* | 2011-04-02 | 2012-03-07 | 复旦大学 | Method and system for supporting urban land utilization and traffic integrated planning policy |
| CN104809112A (en)* | 2014-01-23 | 2015-07-29 | 朱东霞 | Method for comprehensively evaluating urban public transportation development level based on multiple data |
| CN105070042A (en)* | 2015-07-22 | 2015-11-18 | 济南市市政工程设计研究院（集团）有限责任公司 | Modeling method of traffic prediction |
| CN106250540A (en)* | 2016-08-09 | 2016-12-21 | 大连理工大学 | Analysis method based on the region parking difficulty or ease index that the open data of Baidu's map are excavated with web data |
| CN106504535A (en)* | 2016-11-30 | 2017-03-15 | 东南大学 | A Traffic Distribution Prediction Method Combining Gravity Model and Fratar Model |
| CN106528611A (en)* | 2016-09-28 | 2017-03-22 | 西南交通大学 | Analysis method based on internet comment data |
| US20180011912A1 (en)* | 2016-07-11 | 2018-01-11 | Al-Elm Information Security Co. | Methods and systems for multi-dynamic data retrieval and data disbursement |
| CN107943936A (en)* | 2017-11-23 | 2018-04-20 | 烟台大学 | A kind of construction method of the city space holographic map based on the fusion of multi-source big data |
| CN108009972A (en)* | 2017-10-24 | 2018-05-08 | 北京交通大学 | A kind of multimode trip O-D needs estimate methods checked based on multi-source data |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368309A (en)* | 2011-04-02 | 2012-03-07 | 复旦大学 | Method and system for supporting urban land utilization and traffic integrated planning policy |
| CN104809112A (en)* | 2014-01-23 | 2015-07-29 | 朱东霞 | Method for comprehensively evaluating urban public transportation development level based on multiple data |
| CN105070042A (en)* | 2015-07-22 | 2015-11-18 | 济南市市政工程设计研究院（集团）有限责任公司 | Modeling method of traffic prediction |
| US20180011912A1 (en)* | 2016-07-11 | 2018-01-11 | Al-Elm Information Security Co. | Methods and systems for multi-dynamic data retrieval and data disbursement |
| CN106250540A (en)* | 2016-08-09 | 2016-12-21 | 大连理工大学 | Analysis method based on the region parking difficulty or ease index that the open data of Baidu's map are excavated with web data |
| CN106528611A (en)* | 2016-09-28 | 2017-03-22 | 西南交通大学 | Analysis method based on internet comment data |
| CN106504535A (en)* | 2016-11-30 | 2017-03-15 | 东南大学 | A Traffic Distribution Prediction Method Combining Gravity Model and Fratar Model |
| CN108009972A (en)* | 2017-10-24 | 2018-05-08 | 北京交通大学 | A kind of multimode trip O-D needs estimate methods checked based on multi-source data |
| CN107943936A (en)* | 2017-11-23 | 2018-04-20 | 烟台大学 | A kind of construction method of the city space holographic map based on the fusion of multi-source big data |
| Title |
|---|
| 任敏 等: ""基于新浪微博的公交系统数据采集及分析"", 《现代电子技术》* |
| 华雪东: ""基于供需平衡的多方式交通系统出行结构优化研究"", 《中国博士学位论文全文数据库(工程科技Ⅱ辑)》* |
| 崔真真 等: ""智慧城市建设中的多源开放数据获取对策"", 《2014（第九届）城市发展与规划大会论文集》* |
| 阳建强 等: ""城市更新与功能提升"", 《城市规划》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112199566A (en)* | 2020-09-27 | 2021-01-08 | 成都房联云码科技有限公司 | City update effect evaluation method and system based on real estate big data |
| CN112199566B (en)* | 2020-09-27 | 2021-07-30 | 成都房联云码科技有限公司 | City update effect evaluation method and system based on real estate big data |
| CN112613662A (en)* | 2020-12-23 | 2021-04-06 | 北京恒达时讯科技股份有限公司 | Highway traffic volume analysis method and device, electronic equipment and storage medium |
| CN112613662B (en)* | 2020-12-23 | 2023-11-17 | 北京恒达时讯科技股份有限公司 | Highway traffic volume analysis method, device, electronic equipment and storage medium |
| CN113192321A (en)* | 2021-03-17 | 2021-07-30 | 东南大学 | Traffic demand distribution extraction method for comprehensive land utilization |
| CN113611105A (en)* | 2021-07-09 | 2021-11-05 | 东南大学 | Urban traffic travel demand total quantity prediction method |
| CN120471310A (en)* | 2025-07-16 | 2025-08-12 | 海开智慧(北京)科技服务有限公司 | Urban updating multidimensional dynamic supervision and analysis system based on big data |
| Publication number | Publication date |
|---|---|
| CN109035112B (en) | 2021-01-26 |
| Publication | Publication Date | Title |
|---|---|---|
| CN109035112A (en) | Method and system are determined based on the urban construction and renewal model of multisource data fusion | |
| CN110428126B (en) | Urban population spatialization processing method and system based on multisource open data | |
| CN109146155B (en) | Method and system for determining urban traffic travel demand based on multi-source data fusion | |
| CN114925985A (en) | Municipal facility site selection planning method based on GIS decision | |
| CN112508332B (en) | Gradual rural settlement renovation partitioning method considering multidimensional characteristics | |
| CN116644886A (en) | Method, device, terminal and medium for evaluating transformation value of stock land | |
| CN117273476A (en) | Green road line selection method, device, electronic equipment and medium | |
| CN103971300A (en) | Geographic information system (GIS) space information-based substation site positioning method | |
| Akrivi | Second-home tourism present and future. The case of Greece | |
| Annamoradnejad et al. | Using web Mining in the analysis of housing prices: A case study of tehran | |
| Feng et al. | Study on Grey Correlation Degree Decision‐Making Model for Investment Scheme on High‐Grade Highways in Western China | |
| CN117078487A (en) | Emergency supplies site selection optimization method, electronic equipment and readable storage media | |
| CN110175199A (en) | Energy enterprise key user's identifying and analyzing method based on K mean cluster algorithm | |
| Gao | Sustainability assessment of maritime tourism industry based on uncertain evidential reasoning approach in the context of big data and internet | |
| Kumar et al. | Development of a Land Price Model for a Medium Sized Indian City. | |
| Narvaez et al. | Configurational economies: The value of accessibility in urban development | |
| Yeh | A land information system for the programming and monitoring of new town development | |
| KR102699099B1 (en) | Land Price Prediction System Converged with Big Data | |
| KR102699103B1 (en) | A system for preventing false sales through mapping of land research data | |
| Chakraborty et al. | A GIS Anchored system for selection of utility service stations through Hierarchical Clustering | |
| Boyko et al. | Land plot data usage for urban transect zones delimitation in case of Tula | |
| Hoang et al. | Green industrial buildings in Vietnam from experts’ point of view | |
| KR102699094B1 (en) | A system for predicting the location of underground water and sewage pipes using big data to provide real estate information | |
| CN111325647B (en) | Community public space updating design method based on social network analysis | |
| KR102699082B1 (en) | Real transaction price collection system using GIS |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | Effective date of registration:20220621 Address after:210018 No. four archway, 2, Jiangsu, Nanjing Patentee after:Nanjing Southeast University urban planning and Design Institute Co.,Ltd. Address before:211189 No. 2 Southeast University Road, Jiangning District, Nanjing, Jiangsu Patentee before:SOUTHEAST University | |
| TR01 | Transfer of patent right |