基于WLAN移动定位的个性化商品信息推荐平台

J4 ›› 2014, Vol. 36 ›› Issue (10): 1925-1931.

基于WLAN移动定位的个性化商品信息推荐平台

冯锦海1，杨连贺1，刘军发2，忽丽莎2

(1.天津工业大学计算机科学与软件学院，天津 300387;2.中国科学院计算技术研究所，北京 100190)

收稿日期:2014-06-11 修回日期:2014-08-16 出版日期:2014-10-25 发布日期:2014-10-25
基金资助:
国家自然科学基金资助项目（61173066）；国家青年科学基金资助项目（41201410）；广东省战略性新兴产业发展专项资金资助项目（2011912030）

Personalized WeChat recommendation system
based on indoor WLAN localization

FENG Jinhai1,YANG Lianhe1,LIU Junfa2,HU Lisha2

(1.School of Computer Science & Software Engineering,Tianjin Polytechnic University,Tianjin 300387;
2.Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China)

Received:2014-06-11 Revised:2014-08-16 Online:2014-10-25 Published:2014-10-25

摘要/Abstract

摘要：

随着WLAN在室内环境的日益普及，基于现代的移动设备可以方便实时地获取各种有价值的WLAN数据，这对我们识别个体日常生活中的多样化行为提供了前所未有的机会。近年来，用户的兴趣点与行为模式挖掘等领域日益引起各界的广泛关注，设计了一套基于室内定位的推荐系统，基于用户的历史访问记录，实现从过载的信息中识别出用户感兴趣的内容。现有的位置服务通常只针对用户的室外位置数据，缺乏对室内数据的挖掘分析，忽略了室内位置数据中蕴含的大量语义信息。利用室内定位技术获取用户在商场中的活动轨迹，根据用户去过的店铺和浏览过的商品等历史信息，估算用户的兴趣爱好并进而向用户个性化地推荐感兴趣的商品，基于以上思路设计实现了一套基于室内定位和微信平台的个性化商品推荐系统。

关键词: 兴趣点发现, k近邻, 微信, 室内定位, 推荐系统

Abstract:

With the popularity of WLAN(Wireless Local Area Networks) indoors, mobile devices can easily get real-time access to it, which provides us an unprecedented opportunity to understand individual behavior in everyday life. Recently, mining persons’ point of interest and behaviors attracts more attentions. A WeChat recommendation system based on indoor WLAN localization is proposed, which uses users’ historical information to obtain users’ interest from the overload information. Existing location services usually aim for users’ outdoor location data, lack analyzing indoor data through mining, and ignore an amount of semantic information in users’ location data. The users’ activities are traced by the indoor positioning technology. According to the shops which users visited and the products users saw, users’ interest is estimated so as to recommend users for personalized products that may interest them. Based on the above work, we design a personalized product recommendation system based on indoor WLAN localization and the WeChat platform.

Key words: point of interest;k-nearest neighbor algorithm;Wechat;indoor location;recommended system

冯锦海1，杨连贺1，刘军发2，忽丽莎2. 基于WLAN移动定位的个性化商品信息推荐平台[J]. J4, 2014, 36(10): 1925-1931.

FENG Jinhai1,YANG Lianhe1,LIU Junfa2,HU Lisha2. Personalized WeChat recommendation system
based on indoor WLAN localization [J]. J4, 2014, 36(10): 1925-1931.

参考文献［11］

［1］	Cacheda F, Carneiro V, Fernández D, et al. Comparison of collaborative filtering algorithms:Limitations of current techniques and proposals for scalable, highperformance recommender systems［J］. ACM Transactions on the Web (TWEB), 2011, 5(1):2.
［2］	Liu Junfa, Gu Yang, Chen YiQiang. Incremental wireless location method is aging mechanism［J］. Chinese Journal of Computers, 2013, 36(7):14481455. (in Chinese)
［3］	Zhao Mi, Liu Junfa, Chen Yiqiang, et al. Calibrationfree indoor location method based on directional signal compensation［J］. Computer Engineering, 2012, 38(1):276278.(in Chinese)
［4］	Luo Junzhou,Wu Wujia,Yang Ming.Mobile Internet:Terminal devices, networks and services［J］. Chinese Journal of Computers, 2011, 34(11):20292051.(in Chinese)
［5］	Chen X, Liu X, Huang Z, et al. Regionknn:A scalable hybrid collaborative filtering algorithm for personalized web service recommendation［C］∥Proc of 2010 IEEE International Conference on Web Services (ICWS), 2010:916.
［6］	Zhou Aoying, Yang Bin, Jin Cheqing. Location based services:Architecture and development［J］. Chinese Journal of Computers, 2011, 34(7):11551171. (in Chinese)
［7］	Kwon J, Dundar B, Varaiya P. Hybrid algorithm for indoor positioning using wireless LAN［C］∥Proc of 2004 IEEE the 60th Vehicular Technology Conference, 2004:46254629.
［8］	Zheng Y, Xie X, Ma W Y. GeoLife:A collaborative social networking service among user, location and trajectory［J］. IEEE Data Eng Bull, 2010, 33(2):3239.
［9］	Do T M T, GaticaPerez D. The places of our lives:Visiting patterns and automatic labeling from longitudinal smartphone data［J］. IEEE Transactions on Mobile Computing, 2014,13(3):638648.
［10］	Xiao H, Wang W J, Zhang X. Identifying the stay point using GPS trajectory of taxis［J］. Applied Mechanics and Materials, 2013(353356):35113515.
［11］	Hu Li, Chen Jian, Shen Shuyi. Recommendation algorithm research based on user trajectory clustering analysis［J］. Journal of Computer Research and Development, 2012, 49(10 Suppl):250256. (in Chinese)
［12］	Pham M C, Cao Yiwei, Klamma R, et al. A clustering approach for collaborative filtering recommendation using social network analysis［J］. Journal of Universal Computer Science, 2010,17(4):121.
［13］	Ricci F.Mobile recommender systems［J］. International Journal of Information Technology and Tourism, 2011,12(3):205231.
［14］	Koren Y, Sill J. Collaborative filtering on ordinal user feedback［C］∥Proc of the 23rd International Joint Conference on Artificial Intelligence, 2013:30223026.
［15］	Yu C, Luo Y, Liu K. A multiattribute collaborative filtering recommendation algorithm based on improved group decisionmaking［C］∥Proc of International Federation for Information Processing,2014:320330.
	附中文参考文献：
［2］	刘军发, 谷洋, 陈益强, 等. 具有时效机制的增量式无线定位方法［J］. 计算机学报, 2013, 36(7):14481455.
［3］	赵咪，刘军发，陈益强，等.基于定向信号补偿的免标定室内定位方法［J］.计算机工程，2012，38（1）：276278.
［4］	罗军舟，吴文甲，杨明.移动互联网：终端、网络与服务［J］.计算机学报，2011，34（11）：20292051.
［6］	周傲英, 杨彬, 金澈清, 等. 基于位置的服务:架构与进展［J］. 计算机学报, 2011, 34(7):11551171.
［11］	胡立, 陈健, 沈书毅. 基于用户轨迹聚类分析的推荐算法研究［J］. 计算机研究与发展, 2012, 49(10 Suppl.):250256.

[1]	高玮蔚, 刘杨, 马慧芳, 唐月晨. 基于增强偏好影响力的图注意力网络推荐算法[J]. 计算机工程与科学, 2023, 45(07): 1300-1307.
[2]	王玫申, 张鹏, 薛乐洋, . 基于二分网络的长期推荐[J]. 计算机工程与科学, 2023, 45(04): 691-700.
[3]	罗可劲, 刘广聪, 杨文浩. 基于多任务学习的图神经网络推荐模型研究[J]. 计算机工程与科学, 2023, 45(04): 726-733.
[4]	张若一, 金柳, 马慧芳, 王亦可, 李清风. 融合相似用户影响效应的知识图谱推荐模型[J]. 计算机工程与科学, 2023, 45(03): 520-527.
[5]	邹程辉, 李卫疆, . 融合知识图谱和评论文本的个性化推荐模型[J]. 计算机工程与科学, 2023, 45(01): 181-190.
[6]	仲臣, 余学祥, 邰晓曼, 韩雨辰, 肖星星, 刘清华, . 萤火虫算法优化支持向量机室内定位研究[J]. 计算机工程与科学, 2022, 44(11): 1968-1975.
[7]	贾俊杰, 姚叶旺, 陈旺虎. 基于非负矩阵分解的群组推荐算法[J]. 计算机工程与科学, 2022, 44(05): 933-943.
[8]	贾俊杰, 段超强. 基于评分离散度的托攻击检测算法[J]. 计算机工程与科学, 2022, 44(03): 554-562.
[9]	刘颜星, 郝占军, 田冉. 基于CSI信号的被动式室内指纹定位算法研究[J]. 计算机工程与科学, 2021, 43(08): 1398-1404.
[10]	党小超, 汝春瑞, 郝占军, . 基于CSI与SVM回归的室内定位方法[J]. 计算机工程与科学, 2021, 43(05): 853-861.
[11]	顾军华, 佘士耀, 樊帅, 张素琪. 基于用户长短期兴趣与知识图卷积网络的推荐[J]. 计算机工程与科学, 2021, 43(03): 511-517.
[12]	陈海涵, 吴国栋, 李景霞, 王静雅, 陶鸿. 基于注意力机制的深度学习推荐研究进展[J]. 计算机工程与科学, 2021, 43(02): 370-380.
[13]	杨丰瑞, 李前洋, 罗思烦, . 一种基于降噪自编码器的隐式反馈推荐算法[J]. 计算机工程与科学, 2020, 42(08): 1500-1505.
[14]	杨丰瑞, 李前洋, 罗思烦, . 基于降噪自编码器的社会化推荐算法[J]. 计算机工程与科学, 2020, 42(05): 944-950.
[15]	贾玉福1，刘文平1，胡胜红2. 一种基于多模数据的室内定位算法[J]. 计算机工程与科学, 2020, 42(02): 229-235.