基于微博位置签到数据的POI更新方法

摘要

POI的现势性对于位置服务至关重要,但传统人工实地调查效率低,现势性无法满足需求.以当前用户参与数众多的微博社交网络为数据平台,提出了一种基于微博位置签到数据的POI更新方法.首先,对微博位置签到数据进行预处理,剔除语义与空间位置不一致的噪声点,在此基础上提出一种基于RANSAC算法的位置签到数据集地理配准方法,实现位置签到数据与已有地理数据库的可靠配准;然后,将位置签到数据集与已有POI数据库进行空间分析与匹配建模,对匹配不成功的位置签到数据进行有效性验证,提取有效新增数据入库用以更新POI;最后,以武汉市的街旁网位置签到数据进行POI更新实验,能够有效地发现新增POI和消失POI,为POI快速高效更新提供了全新的方式.%The latest tendency of POI is critical for location-based services. The traditional POIs collecting based on on-the-spot investigation is inefficient. However, the fact is that it is unable to meet the demands of the location-based service applications. In this paper, a POIs update approach based on Weibo that involved the largest number users was proposed. Firstly, by preprocessing Weibo check-in data, coarse error points that were semantically and spatially inconsistent were removed, on the basis of which, a geo-referencing method based on Weibo check-in data in RANSAC algorithm was proposed for the purpose of fulfilling reliability of Weibo position check-in data with existing geo-database. Secondly, spatial analysis and matching modeling of check-in data set and the existing POIs database was implemented. After validation of unmatched data, extraction of valid new data as an updated POI into database was implemented. Finally, a POIs update experiment of Wuhan Jiepang position check-in data was implemented with the proposed approach. The experiment results show that the proposed approach can meet the requirements and effectively find new POIs and disappeared POIs. It provides a new way to update POIs quickly and efficiently and has a good prospect of application.