• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2013, Vol. 35 ›› Issue (4): 130-135.

• 论文 • 上一篇    下一篇

基于MapReduce的航空公司服务品质热点发现算法

丁建立1,2,杨博1,2,雷雄3   

  1. (1.中国民航大学计算机科学与技术学院,天津 300300;
    2.中国民航大学智能信号与图像处理天津市重点实验室,天津 300300;
    3.中国航空结算有限责任公司,北京 100028)
  • 收稿日期:2012-02-13 修回日期:2012-04-09 出版日期:2013-04-25 发布日期:2013-04-25
  • 基金资助:

    国家863高技术研究发展计划资助项目(2006AA12A106);国家自然科学基金资助项目(60879015);民航局科技项目资助项目(MHRD201013)

Algorithm of airline QoS hot topic
detection based on MapReduce 

DING Jianli1,2,YANG Bo1,2,LEI Xiong3   

  1. (1.College of Computer Science and Technology,Civil Aviation University of China,Tianjin 300300;
    2.Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China,Tianjin 300300;
    3.Accounting Centre of China Aviation,Beijing 100028,China)
  • Received:2012-02-13 Revised:2012-04-09 Online:2013-04-25 Published:2013-04-25

摘要:

服务品质已经成为提升航空公司核心竞争力的重要因素,用户的评价对改进服务品质具有重要的意义。网络已成为旅客对航空公司服务品质进行评价的最主要平台,为了能及时、有效地追踪到这些有价值的评价信息,提出了一种新的航空公司服务品质热点发现算法。通过对传统的Kmeans算法和MapReduce计算模型进行分析,并结合民航背景及网络上评价信息的特点,将二者有机地结合起来,并对算法实现中的关键问题进行了讨论。通过实验验证,表明了该方法的有效性,为更准确地获取航空公司服务品质热点问题提供了有力的方法支持。

关键词: 服务品质, 热点发现, MapReduce, 文本聚类, 航空公司

Abstract:

QoS(Quality of Service) becomes a very important factor of improving the core competence of airlines. The user evaluation is of great significance in improving the QoS. The network has become the most important platform for passengers to deliver their evaluation to airlines’ QoS. A novel airlines QoS hot topic detection algorithm (AQHTD) was proposed to detect the most valuable evaluation information timely and effectively. On the base of analyzing the traditional Kmeans algorithm and MapReduce computation model and considering the background of civil aviation and the features of evaluation information in the network, both of them were integrated together for our purpose. The key issues of AQHTD were discussed as well. Experiments show that the AQHTD algorithm is very effective. Moreover, it provides strong support in method for accessing the hot issues of airlines QoS timely.        

Key words: service quality;hot topic detection;MapReduce;text cluster;airlines