基于手机信令数据的城市小活动空间人群空间分布特征

Spatial Distribution Characteristics of People with Small Activity Space in Urban based on Mobile Phone Signaling Data

小活动空间人群是指日常活动范围较小的居民群体,他们对城市公共资源的需求主要集中在家庭位置附近的区域,分析其活动的时空规律特征,有助于更好地实现城市公共资源的均等化和精准化配置。然而目前研究中对此类人群关注较少,为此,本文提出一种基于手机信令数据的小活动空间人群识别及其空间分布的研究方法。首先识别用户家庭位置和停留点位置,构建基家最大距离指标,度量用户以家庭位置为中心的活动空间范围,并据此筛选小活动空间人群;其次根据用户与家庭位置间的距离信息构建"时间-距离"框架下的用户轨迹,在此基础上构建基于面积的轨迹相似性方法;然后利用逐级合并的层次聚类算法,根据用户轨迹的相似性对其进行聚类,挖掘小活动空间人群中典型活动模式;最后根据用户的家庭位置,进一步分析不同活动模式人群的时空分布特征。本文以上海市手机信令数据为例对该方法进行了测试,结果表明:(1)"时间-距离"框架下构建的基于面积的轨迹相似性方法,可反映用户基于家庭位置进行活动的时空特征,而逐级合并的层次聚类算法对典型活动模式挖掘的效率有明显提高,有助于研究城市居民的移动模式;(2)上海市小活动空间人群分布呈现出圈层结构,主要分布在中心城区,郊区的工厂和大学城以及各区的商业中心附近,在郊区过渡区相对较少。本文提出的方法能够用于分析城市小活动空间人群的时空分布特征,可以为目前各大城市提出建设社区生活圈的决策提供方法支撑。

The People with Small Activity Space(PwSAS) refers to the residents with a small range of daily activity locations. Their demand for urban public resources is mainly concentrated in the area around their home.Analyzing the spatial and temporal characteristics of their activities can help to better realize the equalization and precise allocation of urban public resources. However, little attention has been paid to this kind of people in current researches. This study proposed a research method to identify the spatial distribution of PwSAS based on mobile phone signaling data. Firstly, we identified each user’s home location and stay location. An indicator of HmaxD, the maximum distance from the home location, was proposed to measure the activity space range centered on the home location. This indicator was also used to filter the PwSAS. Secondly, we transformed the traditional trajectory into a new form in a "time-distance" coordinate based on the distance between the location of each record and the home location. An area-based approach was constructed to measure the similarity between different trajectories. Then an optimized hierarchical clustering algorithm was applied to identify typical activity patterns of PwSAS based on the similarity approach. Finally, the spatial distribution patterns were analyzed based on the home locations of the users belonging to each pattern. A signaling dataset, a typical type of mobile phone location data of Shanghai, was used to test the effectiveness of the method. We found that:(1) the areabased trajectory similarity method constructed based on "time-distance" framework can reflect the spatiotemporal characteristics of users’ activities based on home location, and the hierarchical clustering algorithm merged level by level can significantly improve the efficiency of mining typical activity patterns. This means that the proposed method can effectively support the mining of the mobility patterns of urban residents;and(2) in the suburbs, the commercial centers and places with many factories or universities tended to have more PwSAS;While, the transition area in the suburban had less PwSAS. Therefore, the method proposed in this paper can be used to analyze the temporal and spatial distribution characteristics of people in a small activity area in a city and can provide support for the current large cities’ decision to build community life circles.