WO2022041262A1 - 一种基于大数据的城市轨交用户锚点计算方法 - Google Patents

一种基于大数据的城市轨交用户锚点计算方法 Download PDF

Info

Publication number
WO2022041262A1
WO2022041262A1 PCT/CN2020/112708 CN2020112708W WO2022041262A1 WO 2022041262 A1 WO2022041262 A1 WO 2022041262A1 CN 2020112708 W CN2020112708 W CN 2020112708W WO 2022041262 A1 WO2022041262 A1 WO 2022041262A1
Authority
WO
WIPO (PCT)
Prior art keywords
anchor point
rail transit
positioning
data
residence
Prior art date
Application number
PCT/CN2020/112708
Other languages
English (en)
French (fr)
Inventor
夏钢
夏泽宇
方芳
Original Assignee
苏州大成电子科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 苏州大成电子科技有限公司 filed Critical 苏州大成电子科技有限公司
Priority to PCT/CN2020/112708 priority Critical patent/WO2022041262A1/zh
Publication of WO2022041262A1 publication Critical patent/WO2022041262A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/26Government or public services
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • H04W4/029Location-based management or tracking services

Definitions

  • the invention relates to a method for calculating an urban rail transit user anchor point based on big data, and belongs to the technical field of computers.
  • the present invention provides a method for calculating the anchor point of urban rail transit users based on big data.
  • a method for calculating user anchor points of urban rail transit based on big data comprising the following steps:
  • the step 1 includes: based on a weekly credit card record, firstly identify the daily job and housing anchor points in the way of a one day credit card record; then by setting a threshold, the threshold is set to 500m for clustering, and it is obtained that the user has multiple The residence or employment anchor point, the one with the most positioning times is selected as the residence or employment anchor point.
  • the step 2 includes: data based on mobile phone call base station positioning, and data based on mobile phone signaling position positioning.
  • the data based on mobile phone call base station positioning includes the following steps:
  • the first step is to convert the call records of individual residents into an activity sequence, and use the "activity location-activity room” data model to process the mobile phone call location data, where L represents the location of the base station where the data is moving, and T represents the activity time;
  • the second step is to identify the location of the base station used by individual residents during living and working hours. First, set the working period and nighttime sleep period. Select the base stations whose positioning times exceed the threshold in two time periods, set the working threshold of 6 hours and the residential threshold of 4 hours;
  • the third step is to simulate the location of the job and residence, use the Voronoi polygon to represent the service range of the base station, and use the random point simulation method to generate the coordinates of the job and residence in combination with the nature and structure of the land within the scope.
  • the data based on mobile phone signaling location positioning includes the following steps:
  • the first step is to extract the individual activity sequence of residents from the rule positioning data
  • the second step is to use cluster analysis to identify the location of the base station corresponding to the place of residence;
  • the third step is to use the Voronoi polygon and the property structure of the land within the range to simulate the location of the job and residence.
  • the step 3 includes the following steps:
  • the second step, density-based clustering determine the basic input parameters of DBSCAN: 1. E neighborhood, given the area within the radius of the object, in the anchor point calculation, the positioning point within the radius of E can be regarded as One cluster is an anchor point; two, the core object, the core object or the threshold represents the minimum number of occurrences. In the calculation of the anchor point, if the number of days of the anchor points in a cluster exceeds the threshold, the cluster can be called an anchor point; in addition, On the basis of DBSCAN, a qualification is added, that is, the time span of the positioning point must exceed a certain threshold, and the behavior of ensuring "residence" or "work” is long-term, not generated by short-term behavior.
  • the present invention provides a method for calculating urban rail transit user anchor points based on big data.
  • the data source of residents' job and residence anchor points determined by the present invention reflects citizens' long-term job and residence behavior. Connecting with the rail transit space unit, it can calculate the number of living and working population, job-housing ratio, internal, inward and outward commuting ratio, commuting distance and other indicators.
  • urban rail transit planning and management it can be applied in the fields of urban new urban rail transit planning, old urban rail transit reconstruction, and urban rail transit renewal.
  • the anchor point calculation result determined by the invention has strong linear correlation and high reliability, and is suitable for various statistical analysis.
  • a method for calculating user anchor points of urban rail transit based on big data comprising the following steps:
  • the described data based on mobile phone call base station positioning includes the following steps:
  • the first step is to convert the call records of individual residents into an activity sequence, and use the "Activity-Location Time” data model (Activity-Location Time,) to process the location data of mobile phone calls, where L represents the location of the base station where the data is moving, and T represents Activity time;
  • the second step is to identify the location of the base station used by individual residents during living and working hours. First, set the working period and nighttime sleep period. Select the base stations whose positioning times exceed the threshold in two time periods, set the working threshold of 6 hours and the residential threshold of 4 hours;
  • the third step is to simulate the location of the job and residence, use the Voronoi polygon to represent the service range of the base station, and use the random point simulation method to generate the coordinates of the job and residence in combination with the nature and structure of the land within the scope.
  • the described data based on mobile phone signaling location positioning includes the following steps:
  • the first step is to extract the individual activity sequence of residents from the rule positioning data
  • the second step is to use cluster analysis to identify the location of the base station corresponding to the place of residence;
  • the third step is to use the Voronoi polygon and the property structure of the land within the range to simulate the location of the job and residence.
  • DBSCAN Density-Based Spatial Clustering of Applications with Noise
  • DBSCAN has the following obvious advantages: no need to input clustering in advance The number of clusters; suitable for cases where there are multiple residences (or jobs) in the anchor calculation; clusters of arbitrary shapes can be found; noise points can be identified.
  • E neighborhood The given object radius is the area within E.
  • anchor points the anchor points within the radius of E can be regarded as a cluster, that is, an anchor point.
  • the core object represents the minimum number of occurrences. In the calculation of anchor points, if the number of days of anchor points in a cluster exceeds the threshold, the cluster can be called an anchor point.
  • a restriction is added, that is, the time span of the positioning point must exceed a certain threshold, and the behavior of ensuring "residence" or "work” is long-term, not caused by short-term behavior (such as business trip).

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Educational Administration (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种基于大数据的城市轨交用户锚点计算方法,包括步骤:1、获取轨交线路标定的数据;2、获取居民手机定位的数据;3、采用聚类分析确定居民锚点。该基于大数据的城市轨交用户锚点计算方法,确定居民职住锚点的数据源,反映市民长期职住行为,与轨交空间单元进行联系,能够计算居住与工作人口数量,职住比,内部、内向、外向通勤比,通勤距离等指标。在城市轨交规划管理中,可以在城市新城轨交规划、旧城轨交改造、城市轨交更新等领域得到应用。该基于大数据的城市轨交用户锚点计算方法确定的锚点计算结果线性相关性较强,可信度高,适用于各类统计分析。

Description

一种基于大数据的城市轨交用户锚点计算方法 技术领域
本发明涉及一种基于大数据的城市轨交用户锚点计算方法,属于计算机技术领域。
背景技术
目前,随着近年来城市经济的发展,城市轨道交通的物质环境和空间结构都经历着巨大演变,城市轨道交通的研究领域内新手段新方法层出不穷。在对城市轨交空间结构的研究中,学者开始更多地从人类空间行为的视角来解读城市空间格局;并从制度变化的视角来挖掘空间转型背后的深层机制。居住和就业是两个重要的居民时空行为要素。城市居民的通勤行为是指居民离开居住地前往工作地的出行。它受城市中居住与就业空间分布方式的影响,发生于工作人口中。城市轨交研究中,提取居住与就业锚点可以描述居民的时空行为,统计空间单元的通勤属性,并由此反映城市轨交的空间结构。
与此同时,通信技术的发展使得大数据越来越多的被用于城市轨交研究中。如何基于大数据取得比传统的问卷调查方式成本低、定位与时间精度高、覆盖人群广,善于描绘居民时空行为的方法,是本领域获取本市居民锚点重要研究问题。
发明内容
目的:为了克服现有技术中存在的不足,本发明提供一种基于大数据的城市轨交用户锚点计算方法。
技术方案:为解决上述技术问题,本发明采用的技术方案为:
一种基于大数据的城市轨交用户锚点计算方法,包括如下步骤:
1、获取居民轨交交通站点刷卡的数据;
2、获取居民手机定位的数据;
3、采用聚类分析确定居民锚点。
作为优选方案,所述步骤1包括:基于一周刷卡记录,首先按照一日刷卡记录的方式识别每日职住锚点;然后通过设置阈值,阈值设置为500m进行聚类,得出该用户多个居住或就业锚点,选取定位次数最多的视为居住或就业锚点。
作为优选方案,所述步骤2包括:基于手机通话基站定位的数据,基于手机信令位置定位的数据。
作为优选方案,所述基于手机通话基站定位的数据,包括如下步骤:
第一步,将居民个体的通话记录转换为个活动序列,使用“活动地点—活动间”数据模型,处理手机通话位置数据,L代表数据动的基站位置,T代表活动时间;
第二步,识别居住与工作时间居民个体通话使用的基站位置,首先设置工作段与夜间睡眠时段,设置工时段09:00-18:00,夜间睡眠时段为00:00-06:00,然后选取两个时段内定位次超过阈值的基站,设置工作阈值6小时,居住阈值4小时;
第三步,模拟职住地位置,使用Voronoi多边形表示基站服务范围,结合范内用地性质结构,使用随机点模拟法生成职住地的坐标。
作为优选方案,所述基于手机信令位置定位的数据,包括如下步骤:
第一步,从规则定位数据中提取出居民个体活动序列;
第二步,利用聚类分析识别职住地对应的基站位置;
第三步,最后利用Voronoi多边形与范围内用地性质结构,模拟职住地位置。
作为优选方案,所述步骤3包括如下步骤:
第一步,K-means聚类:选取Python程序包中K-means++的算法进行锚点计算;首先,需要确定分组个数K值,设置不同K值比较数据处理用时和轮廓系数指标;选择使轮廓系数结果最接近于1的K值;选定用户工作时间定位点的轮廓系数指标,当K=3时,用时最短;对所有工作时段定位点进行分组并求各个分组的中心点,按照组内定位点数量排序,取最高者作为第一就业锚点,第二位作为第二就业锚点;将同样的步骤用于所有夜间睡眠时段,计算出第一与第二居住锚点;
第二步,基于密度的聚类:确定DBSCAN基本的输入参数:一、E邻域,给定对象半径为Ε内的区域,在锚点计算中,半径为E的范围内定位点可以视为一簇,即一个锚点;二、核心对象,核心对象或阈值代表最少出现次数,在锚点计算中,若一簇里面定位点天数超过该阈值,则该簇可以称为锚点;另外,在DBSCAN的基础上增加了限定条件,即定位点的时间跨度要超过某阈值,保障“居住”或“工作”的行为是长期的,不是由短时间行为产生。
有益效果:本发明提供的一种基于大数据的城市轨交用户锚点计算方 法,综上,本发明确定的居民职住锚点的数据源,反映市民长期职住行为。与轨交空间单元进行联系,能够计算居住与工作人口数量,职住比,内部、内向、外向通勤比,通勤距离等指标。在城市轨交规划管理案例中,可以在城市的新城轨交规划、旧城轨交改造、城市轨交更新等领域得到应用。本发明确定的锚点计算结果线性相关性较强,可信度高,适用于各类统计分析。
具体实施方式
一种基于大数据的城市轨交用户锚点计算方法,包括如下步骤:
1、获取居民轨交站点刷卡的数据;基于一周刷卡记录,首先按照一日刷卡记录的方式识别每日职住锚点;然后通过设置阈值,阈值设置为500m进行聚类,得出该用户多个居住或就业锚点,选取定位次数最多的视为居住或就业锚点;
2、获取居民手机定位的数据;包括:基于手机通话基站定位的数据,基于手机信令位置定位的数据;
所述基于手机通话基站定位的数据,包括如下步骤:
第一步,将居民个体的通话记录转换为个活动序列,使用“活动地点—活动间”数据模型(Activity-Location Time,),处理手机通话位置数据,L代表数据动的基站位置,T代表活动时间;
第二步,识别居住与工作时间居民个体通话使用的基站位置,首先设置工作段与夜间睡眠时段,设置工时段09:00-18:00,夜间睡眠时段为00:00-06:00,然后选取两个时段内定位次超过阈值的基站,设置工作阈值6 小时,居住阈值4小时;
第三步,模拟职住地位置,使用Voronoi多边形表示基站服务范围,结合范内用地性质结构,使用随机点模拟法生成职住地的坐标。
所述基于手机信令位置定位的数据,包括如下步骤:
第一步,从规则定位数据中提取出居民个体活动序列;
第二步,利用聚类分析识别职住地对应的基站位置;
第三步,最后利用Voronoi多边形与范围内用地性质结构,模拟职住地位置。
3、采用聚类分析确定居民锚点,包括如下步骤:
第一步,K-means聚类:选取Python程序包中K-means++的算法进行锚点计算;首先,需要确定分组个数K值,设置不同K值比较数据处理用时和轮廓系数指标;选择使轮廓系数结果最接近于1的K值;选定用户工作时间定位点的轮廓系数指标,当K=3时,用时最短;对所有工作时段定位点进行分组并求各个分组的中心点,按照组内定位点数量排序,取最高者作为第一就业锚点,第二位作为第二就业锚点;将同样的步骤用于所有夜间睡眠时段,计算出第一与第二居住锚点;
第二步,基于密度的聚类:DBSCAN(Density-Based Spatial Clustering of Applications with Noise)是基于密度的聚类算法,相比于其他聚类算法,DBSCAN具有以下明显优势:不需要提前输入聚类簇的数量;适合锚点计算中有多个居住地(或工作地)的情况;可以发现任意形状的簇类;可以识别噪声点。
DBSCAN基本的输入参数有两个:一、E邻域。给定对象半径为Ε内的区域。在锚点计算中,半径为E的范围内定位点可以视为一簇,即一个锚点。二、核心对象。核心对象(或阈值)代表最少出现次数。在锚点计算中,若一簇里面定位点天数超过该阈值,则该簇可以称为锚点。另外,在DBSCAN的基础上增加了限定条件,即定位点的时间跨度要超过某阈值,保障“居住”或“工作”的行为是长期的,不是由短时间行为(如出差)产生。
以上所述仅是本发明的优选实施方式,应当指出:对于本技术领域的普通技术人员来说,在不脱离本发明原理的前提下,还可以做出若干改进和润饰,这些改进和润饰也应视为本发明的保护范围。

Claims (6)

  1. 一种基于大数据的城市轨交用户锚点计算方法,其特征在于:包括如下步骤:
    1、获取居民公交轨交站点刷卡的数据;
    2、获取居民手机定位的数据;
    3、采用聚类分析确定居民锚点。
  2. 根据权利要求1所述的一种基于大数据的城市轨用户路锚点计算方法,其特征在于:所述步骤1包括:基于一周刷卡记录,首先按照一日刷卡记录的方式识别每日职住锚点;然后通过设置阈值,阈值设置为500m进行聚类,得出该用户多个居住或就业锚点,选取定位次数最多的视为居住或就业锚点。
  3. 根据权利要求1所述的一种基于大数据的城市轨交用户锚点计算方法,其特征在于:所述步骤2包括:基于手机通话基站定位的数据,基于手机信令位置定位的数据。
  4. 根据权利要求3所述的一种基于大数据的城市轨用户路锚点计算方法,其特征在于:所述基于手机通话基站定位的数据,包括如下步骤:
    第一步,将居民个体的通话记录转换为个活动序列,使用″活动地点一活动间″数据模型,处理手机通话位置数据,L代表数据动的基站位置,T代表活动时间;
    第二步,识别居住与工作时间居民个体通话使用的基站位置,首先设置工作段与夜间睡眠时段,设置工时段09:00-18:00,夜间睡眠时段为00:00-06:00,然后选取两个时段内定位次超过阈值的基站,设置工作阈值6 小时,居住阈值4小时;
    第三步,模拟职住地位置,使用Voronoi多边形表示基站服务范围,结合范内用地性质结构,使用随机点模拟法生成职住地的坐标。
  5. 根据权利要求3所述的一种基于大数据的城市轨交用户锚点计算方法,其特征在于:所述基于手机信令位置定位的数据,包括如下步骤:
    第一步,从规则定位数据中提取出居民个体活动序列;
    第二步,利用聚类分析识别职住地对应的基站位置;
    第三步,最后利用Voronoi多边形与范围内用地性质结构,模拟职住地位置。
  6. 根据权利要求1所述的一种基于大数据的城市轨交线路锚点计算方法,其特征在于:所述步骤3包括如下步骤:
    第一步,K-means聚类:选取Python程序包中K-means++的算法进行锚点计算;首先,需要确定分组个数K值,设置不同K值比较数据处理用时和轮廓系数指标;选择使轮廓系数结果最接近于1的K值;选定用户工作时间定位点的轮廓系数指标,当K=3时,用时最短;对所有工作时段定位点进行分组并求各个分组的中心点,按照组内定位点数量排序,取最高者作为第一就业锚点,第二位作为第二就业锚点;将同样的步骤用于所有夜间睡眠时段,计算出第一与第二居住锚点;
    第二步,基于密度的聚类:确定DBSCAN基本的输入参数:一、E邻域,给定对象半径为E内的区域,在锚点计算中,半径为E的范围内定位点可以视为一簇,即一个锚点;二、核心对象,核心对象或阈值代表最少出 现次数,在锚点计算中,若一簇里面定位点天数超过该阈值,则该簇可以称为锚点;另外,在DBSCAN的基础上增加了限定条件,即定位点的时间跨度要超过某阈值,保障″居住″或″工作″的行为是长期的,不是由短时间行为产生。
PCT/CN2020/112708 2020-08-31 2020-08-31 一种基于大数据的城市轨交用户锚点计算方法 WO2022041262A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/112708 WO2022041262A1 (zh) 2020-08-31 2020-08-31 一种基于大数据的城市轨交用户锚点计算方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/112708 WO2022041262A1 (zh) 2020-08-31 2020-08-31 一种基于大数据的城市轨交用户锚点计算方法

Publications (1)

Publication Number Publication Date
WO2022041262A1 true WO2022041262A1 (zh) 2022-03-03

Family

ID=80354394

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/112708 WO2022041262A1 (zh) 2020-08-31 2020-08-31 一种基于大数据的城市轨交用户锚点计算方法

Country Status (1)

Country Link
WO (1) WO2022041262A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115002680A (zh) * 2022-07-28 2022-09-02 北京融信数联科技有限公司 基于手机信令的人群职业类型获取方法、系统和存储介质
CN115186049A (zh) * 2022-09-06 2022-10-14 深圳市城市交通规划设计研究中心股份有限公司 一种智能公交备选站点选址方法、电子设备及存储介质
CN115587657A (zh) * 2022-10-19 2023-01-10 华中科技大学 一种夜间定制公交的站点确定及线路优化方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013107669A1 (en) * 2012-01-20 2013-07-25 Telefónica, S.A. A method for the automatic detection and labelling of user point of interest
CN106951549A (zh) * 2017-03-27 2017-07-14 重庆邮电大学 一种基于轨道ic卡和手机信令数据的乘客出行路线识别方法
CN107038168A (zh) * 2016-02-03 2017-08-11 中兴通讯股份有限公司 一种用户通勤轨迹管理方法、装置及系统
CN107909098A (zh) * 2017-11-09 2018-04-13 苏州大成电子科技有限公司 一种基于大数据的城市居民锚点计算方法
CN111582948A (zh) * 2020-05-25 2020-08-25 北京航空航天大学 一种基于手机信令数据与poi兴趣点的个体行为分析方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013107669A1 (en) * 2012-01-20 2013-07-25 Telefónica, S.A. A method for the automatic detection and labelling of user point of interest
CN107038168A (zh) * 2016-02-03 2017-08-11 中兴通讯股份有限公司 一种用户通勤轨迹管理方法、装置及系统
CN106951549A (zh) * 2017-03-27 2017-07-14 重庆邮电大学 一种基于轨道ic卡和手机信令数据的乘客出行路线识别方法
CN107909098A (zh) * 2017-11-09 2018-04-13 苏州大成电子科技有限公司 一种基于大数据的城市居民锚点计算方法
CN111582948A (zh) * 2020-05-25 2020-08-25 北京航空航天大学 一种基于手机信令数据与poi兴趣点的个体行为分析方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
GAO SHUO, WANG MINGYANG;LU XU;MAO MINGRUI: "Research on Residence-and-Work Anchor Points Algorithm with Big Data in Urban Research", JOURNAL OF HUMAN SETTLEMENTS IN WEST CHINA, vol. 32, no. 1, 28 February 2017 (2017-02-28), pages 31 - 37, XP055904289, ISSN: 1006-2181, DOI: 10.13791/j.cnki.hsfwest.20170105 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115002680A (zh) * 2022-07-28 2022-09-02 北京融信数联科技有限公司 基于手机信令的人群职业类型获取方法、系统和存储介质
CN115002680B (zh) * 2022-07-28 2022-12-27 北京融信数联科技有限公司 基于手机信令的人群职业类型获取方法、系统和存储介质
CN115186049A (zh) * 2022-09-06 2022-10-14 深圳市城市交通规划设计研究中心股份有限公司 一种智能公交备选站点选址方法、电子设备及存储介质
CN115186049B (zh) * 2022-09-06 2023-02-03 深圳市城市交通规划设计研究中心股份有限公司 一种智能公交备选站点选址方法、电子设备及存储介质
CN115587657A (zh) * 2022-10-19 2023-01-10 华中科技大学 一种夜间定制公交的站点确定及线路优化方法

Similar Documents

Publication Publication Date Title
WO2022041262A1 (zh) 一种基于大数据的城市轨交用户锚点计算方法
CN111932036B (zh) 基于位置大数据的精细时空尺度动态人口预测方法及系统
Liu et al. How urban land use influences commuting flows in Wuhan, Central China: A mobile phone signaling data perspective
AU2019100989A4 (en) Global dynamic travel demand estimation method based on multi-source traffic data
CN110418287B (zh) 基于手机信令的人口居住地迁徙识别方法
CN106931974B (zh) 基于移动终端gps定位数据记录计算个人通勤距离的方法
Kim et al. Ridership patterns at subway stations of Seoul capital area and characteristics of station influence area
Kim Exploring the difference between ridership patterns of subway and taxi: Case study in Seoul
CN107909098A (zh) 一种基于大数据的城市居民锚点计算方法
CN111582948A (zh) 一种基于手机信令数据与poi兴趣点的个体行为分析方法
CN115512216A (zh) 耦合街区时空特征和集成学习的城市功能区精细化识别方法
Aubrecht et al. Exploring the potential of volunteered geographic information for modeling spatio-temporal characteristics of urban population: a case study for Lisbon Metro using foursquare check-in data
Qian et al. Quantify city-level dynamic functions across China using social media and POIs data
CN109189949A (zh) 一种人口分布计算方法
CN115034524A (zh) 基于手机信令的工作居住人口预测方法、系统和存储介质
CN110956188A (zh) 基于移动通信信令数据的人口行为轨迹数字化编码方法
Yuan et al. Recognition of functional areas based on call detail records and point of interest data
CN111242352A (zh) 基于车辆轨迹的停等聚集效应预测方法
Chen et al. An analysis of movement patterns between zones using taxi GPS data
CN113573238B (zh) 一种基于手机信令的联程旅客出行链识别方法
CN117114210B (zh) 无障碍公共设施布局优化方法、装置、设备及存储介质
Shad et al. Cell oscillation resolution in mobility profile building
Verdini The costs of urban growth at the fringe of a Chinese city: evidence from Jinshi Village in Suzhou
CN112364776A (zh) 一种城市功能区识别模型建立、分类方法及装置
Wang et al. Identifying the service areas and travel demand of the commuter customized bus based on mobile phone signaling data

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20950931

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20950931

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20950931

Country of ref document: EP

Kind code of ref document: A1