城市街区和签到数据结合的个性化城市兴趣区域推荐方法  

Personalized city region of interests recommendation method based on city block and check-in data

作　　者：刘纪平[1] 张志然[1,2] 杨超伟 徐胜华[1] 陈才[4] 仇阿根 张福浩[1] LIU Jiping;ZHANG Zhiran;YANG Chaowei;XU Shenghua;CHEN Cai;QIU Agen;ZHANG Fuhao(Chinese Academy of Surveying and Mapping,Beijing 100830,China;School of Earth Sciences and Engineering,Xi'an Shiyou University,Xi'an 710065,China;NSF Spatiotemporal Innovation Center,George Mason University,Fairfax Virglnia 22030,USA;School of Marine Technology and Geomatics,Jiangsu Ocean University,Lianyungang 222005,China)

机构地区：[1]中国测绘科学研究院,北京100830 [2]西安石油大学地球科学与工程学院,陕西西安710065 [3]乔治梅森大学时空创新中心,弗吉尼亚费尔法克斯22030 [4]江苏海洋大学海洋技术与测绘学院,江苏连云港222005

出　　处：《测绘学报》2022年第8期1797-1806,共10页Acta Geodaetica et Cartographica Sinica

基　　金：地理信息工程国家重点实验室、自然资源部测绘科学与地球空间信息技术重点实验室联合资助基金项目(2021-04-13);国家自然科学基金(42071384);国家重点研发计划(2019YFB2102503)。

摘　　要：利用社交媒体用户的历史签到数据分析用户空间活动偏好实现用户兴趣区域推荐,在城市商业规划中起着重要作用,也为了解人们的城市生活和需求提供帮助。已有方法获得的ROI具有模糊性和多样性,无法给ROI赋予准确的地理描述信息,对用户来说可解释性不强。因此,本文提出了一种结合城市街区和签到数据的个性化兴趣区域推荐方法(CBCD),引入城市街区概念解决ROI边界模糊问题。首先,通过城市道路网生成城市街区,并将大规模签到数据映射到城市街区转换为区域签到;然后,基于区域签到对用户空间活动偏好和类别偏好分别进行个性化建模;最后,融合空间和类别活动偏好,向用户推荐其可能感兴趣的区域。在真实的数据集上进行试验,结果表明该方法具有较高的推荐精度,对用户感兴趣城市街区的挖掘和推荐具有一定的价值。Using the historical user data of social media to analyze the preferences of users'spatial activities and region of interest(ROI)is of great value for city commercial planning,people's urban life and needs.The ROI obtained by existing methods has big ambiguity and vague in content,and lack actual geographical scope and accurate geographical description for users.We propose a personalized ROI mining and recommendation method combing city block and check-in data(CBCD)that introduces the concept of city blocks to solve the problem of vague ROI boundaries.Specifically,the large number of check-in points are mapped into city blocks generated by the road network,followed by modeling of user geographical and categorical preference.Finally,we integrate geographical and categorical activity preference models to recommend ROIs to users.Experiments on real datasets show that this method has high recommendation accuracy and is of great value for mining and recommending city blocks of interest to users.

关 键 词：兴趣区域 推荐 城市街区 基于位置的社交网络 

分 类 号：P227[天文地球—大地测量学与测量工程]