铁路智能客服关键技术研究被引量：2

Key technologies of railway intelligent customer service

下载PDF

导出

摘要提出铁路智能客服总体框架,研究铁路客运服务专业的语义理解与处理,深度学习模型和用户画像等关键技术,解决铁路12306互联网售票系统(简称:12306系统)客服维护成本高、服务时间受限、培训成本高、线路忙、人为错误不利于控制等问题。研究表明,铁路智能客服可有效提高铁路12306系统客服接通率和客户满意度,提升铁路用户体验,树立铁路良好社会形象。 This paper proposed the overall framework of railway intelligent customer service,researched on key technologies of railway passenger service professional semantic understanding and processing,deep learning model and user portrait,solved the problems of high maintenance cost,limited service time,high training cost,busy line,human errors which were not conducive to control of railway 12306 Internet ticketing and reservation system.Research results show that the railway intelligent customer service can effectively improve the connection rate and customer satisfaction of the railway 12306 system,enhance railway user experience,establish a good social image of railway.

作者张志强汪健雄靳超 ZHANG Zhiqiang;WANG Jianxiong;JIN Chao(Institute of Computing Technologies,China Academy of Railway Sciences Corporation Limited,Beijing 100081,China)

机构地区中国铁道科学研究院集团有限公司电子计算技术研究所

出处《铁路计算机应用》 2019年第9期1-5,共5页 Railway Computer Application

基金中国铁路总公司科技研究开发计划重点课题(Z2017-X004)

关键词 12306互联网售票系统智能客服接通率满意度 12306 Internet ticketing and reservation system intelligent customer service connection rate satisfaction

分类号 U293.22 [交通运输工程—交通运输规划与管理] TP39 [自动化与计算机技术—计算机应用技术]

引文网络
相关文献

参考文献3

1崔悦,宋齐军.智能语音技术发展趋势及电信运营商应用浅析[J].邮电设计技术,2016(12):6-11. 被引量：12
2刘文举,聂帅,梁山,张学良.基于深度学习语音分离技术的研究现状与进展[J].自动化学报,2016,42(6):819-833. 被引量：70
3王斌,朱建军,谭雪.智能推荐系统在铁路客运延伸服务中应用研究[J].铁路计算机应用,2019,28(3):33-36. 被引量：7

二级参考文献82

1Kim G, Lu Y, Hu Y, Loizou P C. An algorithm that im- proves speech intelligibility in noise for normal-hearing lis- teners. The Journal of the Acoustical Society of America, 2009, 126(3): 1486-1494.
2Dillon H. Hearing Aids. New York: Thieme, 2001.
3Allen J B. Articulation and intelligibility. Synthesis Lectures on Speech and Audio Processing, 2005, 1(1): 1-124.
4Seltzer M L, Raj B, Stern R M. A Bayesian classifier for spectrographic mask estimation for missing feature speech recognition. Speech Communication, 2004, 43(4): 379-393.
5Weninger F, Erdogan H, Watanabe S, Vincent E, Le Roux J, Hershey J R, Schuller B. Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR. In: Proceedings of the 12th International Conference on Latent Variable Analysis and Signal Separation. Liberec, Czech Republic: Springer International Publishing, 2015.91 -99.
6Weng C, Yu D, Seltzer M L, Droppo J. Deep neural networks for single-channel multi-talker speech recognition. IEEE/ ACM Transactions on Audio, Speech, and Language Pro- cessing, 2015, 23(10): 1670-1679.
7Boll S F. Suppression of acoustic noise in speech using spec- tral subtraction. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1979, 27(2): 113-120.
8Chen J D, Benesty J, Huang Y T, Doclo S. New insights into the noise reduction wiener filter. IEEE Transactions on Audio, Speech, and Language Processing, 2006, 14(4): 1218 -1234.
9Loizou P C. Speech Enhancement: Theory and Practice. New York: CRC Press, 2007.
10Liang S, Liu W J, Jiang W. A new Bayesian method incor- porating with local correlation for IBM estimation. IEEE Transactions on Audio, Speech, and Language Processing, 2013, 21(3): 476-487.