电信运营商AI客服平台技术研究与应用分析

doi:10.11959/j.issn.1000-0801.2023167

Abstract

Abstract:

The evolution of customer service platforms was reviewed systematically, covering the first generation of interactive voice response (IVR) customer service, the second generation of multimedia online customer service, and the third generation of artificial intelligence (AI) customer service.The functional characteristics of each generation of customer service platforms were elaborated in depth.Additionally, the functional construction of customer service systems in various industries was introduced in detail, such as manufacturing, finance, transportation, and telecommunications.Based on this, the application components of AI customer service platforms for operators were further depicted, including intelligent dispatching, voice transcription, knowledge recommendation, intelligent quality inspection, and intelligent liability determination.Currently, the adoption of AI customer service platforms by operators has become a development trend.Looking forward, customer service platforms will integrate various intelligent technologies such as large-scale models, natural language processing (NLP), and knowledge graphs to meet customer service demands.

Key words: AI customer service, customer service system, AI

CLC Number:

TP393

Xiaoliang MA, Ying LIU, Dequan DU, Guoxin ZHANG. Research and application analysis of artificial intelligence-based customer service platform technologies for telecom operators[J]. Telecommunications Science, 2023, 39(9): 141-152.

Figures/Tables 9

References 44

[1]	陈朝飞 . 大数据背景下的人工智能客服系统研究[J]. 信息与电脑, 2021(8): 180-182.
	CHEN C F . Research on artificial intelligence customer service system under the background of big data[J]. China Computer ＆Communication, 2021(8): 180-182.
[2]	李丹 . 人工智能在联通客服系统中的应用和关键技术研究[J]. 电脑知识与技术, 2020,16(26): 176-177.
	LI D . Research on the application and key technologies of artificial intelligence in Unicom customer service system[J]. Computer Knowledge and Technology, 2020,16(26): 176-177.
[3]	谭蓉 . 智能机器人在生产调度中的应用分析[J]. 信息系统工程, 2020(7): 82-83.
	TAN R . Application analysis of intelligent robot in production scheduling[J]. China CIO News, 2020(7): 82-83.
[4]	杨金峰, 陶以政, 梁燕 ,等. 面向知识管理的推荐算法研究[J]. 电脑知识与技术, 2020,16(26): 217-220.
	YANG J F , TAO Y Z , LIANG Y ,et al. Research on recommendation algorithm for knowledge management[J]. Computer Knowledge and Technology, 2020,16(26): 217-220.
[5]	张筱丹 . 铁路客服智能质检系统及其在客服中心的应用[J]. 铁路计算机应用, 2023,32(3): 64-67.
	ZHANG X D . Intelligent quality inspection system for railway customer service and its application in customer service center[J]. Railway Computer Application, 2023,32(3): 64-67.
[6]	王成胜 . 呼叫中心技术演进研究[J]. 电信网技术, 2014(4): 13-16.
	WANG C S . Study on call center technology evolution[J]. Telecommunications Network Technology, 2014(4): 13-16.
[7]	王萌, 许学军 . 浅析银行业智能客服系统的应用和发展[J]. 经济研究导刊, 2021(1): 41-43.
	WANG M , XU X J . Analysis on the application and development of intelligent customer service system in banking industry[J]. Economic Research Guide, 2021(1): 41-43.
[8]	陈卫兵, 彭慧中, 段斌 ,等. 商业银行智能客服应用研究[J]. 金融科技时代, 2022,30(7): 53-55.
	CHEN W B , PENG H Z , DUAN B ,et al. Research on the application of intelligent customer service in commercial banks[J]. Financial Technology Time, 2022,30(7): 53-55.
[9]	潘建东, 徐政钧, 刘逸雄 ,等. 多模态智能金融客户服务体系建设研究[J]. 金融科技时代, 2022,30(11): 53-56.
	PAN J D , XU Z J , LIU Y X ,et al. Research on the construction of multi-modal intelligent financial customer service system[J]. Financial Technology Time, 2022,30(11): 53-56.
[10]	李西南, 李强, 张四海 . 铁路智能客服系统的设计及应用[J]. 铁路计算机应用, 2022,31(9): 29-32.
	LI X N , LI Q , ZHANG S H . Railway intelligent customer service system[J]. Railway Computer Application, 2022,31(9): 29-32.
[11]	孙杰贤 . 智能客服成为企业数字化转型突破口[J]. 中国信息化, 2022(2): 35.
	SUN J X . Intelligent customer service becomes a breakthrough in enterprise digital transformation[J]. China Informatization, 2022(2): 35.
[12]	MAKKI M , VAN LANDUYT D , JOOSEN W. . Automated regression testing of BPMN 2.0 processes:a capture and replay framework for continuous delivery[C]// Proceedings of the 2016 ACM SIGPLAN International Conference on Generative Programming:Concepts and Experiences. New York:ACM Press, 2016.
[13]	李颢, 张吉皓 . 基于文本挖掘技术的客服投诉工单自动分类探讨[J]. 移动通信, 2017,41(23): 66-72.
	LI H , ZHANG J H . Discussion of automatic classification of customer service complaints based on text mining[J]. Mobile Communications, 2017,41(23): 66-72.
[14]	任华, 王铮, 汪少敏 . 多种因素向量化的客服工单智能排序应用[J]. 电信科学, 2018,34(12): 125-131.
	REN H , WANG Z , WANG S M . Application of intelligent sorting of customer service work orders with multiple factors vectorization[J]. Telecommunications Science, 2018,34(12): 125-131.
[15]	黄峰, 王定军 . 基于文本相似度的智能工单分析系统解决方案研究[J]. 电子技术与软件工程, 2018(19): 206-207.
	HUANG F , WANG D . Research on intelligent work order analysis system solution based on text similarity[J]. Electronic Technology ＆ Software Engineering, 2018(19): 206-207.
[16]	薛巍 . 基于人工智能技术实现银行工单智能派单[J]. 金融电子化, 2019(4): 56-57.
	XUE W . Realization of intelligent dispatch of bank work orders based on artificial intelligence technology[J]. Financial Electrification, 2019(4): 56-57.
[17]	HIRAYAMA N , YOSHINO K , ITOYAMA K ,et al. Automatic speech recognition for mixed dialect utterances by mixing dialect language models[J]. ACM Transactions on Audio,Speech,and Language Processing, 2015,23(2): 373-382.
[18]	MUKHAMADIYEV A , KHUJAYAROV I , DJURAEV O ,et al. Automatic speech recognition method based on deep learning approaches for Uzbek language[J]. Sensors, 2022,22(10): 3683.
[19]	CHEN T G , PENG L J , YANG J J ,et al. Analysis of user needs on downloading behavior of English vocabulary Apps based on data mining for online comments[J]. Mathematics, 2021,9(12): 1341.
[20]	WU Y Z , LU X G , YAMAMOTO H ,et al. Factored language model based on recurrent neural network[C]// Proceedings of COLING 2012.[S.l.:s.n.], 2012: 2835-2850.
[21]	杭婷婷, 冯钧, 陆佳民 . 知识图谱构建技术:分类、调查和未来方向[J]. 计算机科学, 2021,48(2): 175-189.
	HANG T T , FENG J , LU J M . Knowledge graph construction techniques:taxonomy,survey and future directions[J]. Computer Science, 2021,48(2): 175-189.
[22]	周晶, 孙喜民, 于晓昆 ,等. 知识图谱与数据应用:智能推荐[J]. 电信科学, 2019,35(8): 165-172.
	ZHOU J , SUN X M , YU X K ,et al. Knowledge graph and data application:intelligent recommendation[J]. Telecommunications Science, 2019,35(8): 165-172.
[23]	刘烨宸, 李华昱 . 领域知识图谱研究综述[J]. 计算机系统应用, 2020,29(6): 1-12.
	LIU Y C , LI H Y . Survey on domain knowledge graph research[J]. Computer Systems ＆ Applications, 2020,29(6): 1-12.
[24]	SULTAN N . Knowledge management in the age of cloud computing and Web 2.0:experiencing the power of disruptive innovations[J]. International Journal of Information Management, 2013,33(1): 160-165.
[25]	YIN J , ZHAO W X , LI X M . Type-aware question answering over knowledge base with attention-based tree-structured neural networks[J]. Journal of Computer Science and Technology, 2017,32(4): 805-813.
[26]	徐鑫, 杜剑, 雯聂淼 . 客户服务应用知识库体系的运用与深化[J]. 现代信息科技, 2017,1(3): 63-64,67.
	XU X , DU J , WEN N M . Application and deepening of customer service application knowledge base system[J]. Modern Information Technology, 2017,1(3): 63-64,67.
[27]	赵畅, 李慧颖 . 面向知识库问答的实体链接方法[J]. 中文信息学报, 2019,33(11): 125-133.
	ZHAO C , LI H Y . An entity linking approach for knowledge base question answering[J]. Journal of Chinese Information Processing, 2019,33(11): 125-133.
[28]	袁满, 褚冰, 陈萍 . 知识图谱构建中的语义标准问题研究[J]. 情报理论与实践, 2020,43(3): 131-137.
	YUAN M , CHU B , CHEN P . Research on issues of semantic standard in knowledge graph construction[J]. Information Studies:Theory ＆ Application, 2020,43(3): 131-137.
[29]	李智敏 . 探究 AVAYA 呼叫中心服务器的日常维护[J]. 信息与电脑, 2017(8): 31-32.
	LI Z M . Exploring the daily maintenance of the AVAYA call center server[J]. China Computer ＆ Communication, 2017(8): 31-32.
[30]	WANG C B , MA X G , CHEN J G ,et al. Information extraction and knowledge graph construction from geoscience literature[J]. Computers ＆ Geosciences, 2018(112): 112-120.
[31]	刘建, 赵加奎, 杨维 ,等. 电力95598客户服务质检抽样算法研究[J]. 电网技术, 2015,39(11): 3163-3168.
	LIU J , ZHAO J K , YANG W ,et al. Research on quality inspection sampling algorithm of electric 95598 customer service[J]. Power System Technology, 2015,39(11): 3163-3168.
[32]	苏立伟, 刘振华, 陈海燕 . 95598电力客服智能质检系统问题语音检出方法研究[J]. 微型电脑应用, 2019,35(8): 98-100,108.
	SU L W , LIU Z H , CHEN H Y . Research on voice detection method of intelligent customer service quality inspection system of 95598[J]. Microcomputer Applications, 2019,35(8): 98-100,108.
[33]	关浩华 . 基于语音分析的智能质检关键词提取方法设计[J]. 自动化与仪器仪表, 2017(7): 106-108.
	GUAN H H . Design of intelligent quality inspection keyword extraction method based on speech analysis[J]. Automation ＆Instrumentation, 2017(7): 106-108.
[34]	武尧亮, 殷慧, 张炜 . 内蒙古广电网络呼叫中心智能化探讨[J]. 数字传媒研究, 2019,36(8): 37-41.
	WU Y L , YIN H , ZHANG W . Discussion on call center intelligence of Inner Mongolia radio and television networks[J]. Digital Media Studies, 2019,36(8): 37-41.
[35]	KIM Y . Convolutional neural networks for sentence classification[J]. arXiv preprint, 2014,arXiv:1408.5882.
[36]	YANG Z C , YANG D Y , DYER C ,et al. Hierarchical attention networks for document classification[C]// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Stroudsburg:Association for Computational Linguistics, 2016: 1480-1489.
[37]	LAMPLE G , BALLESTEROS M , SUBRAMANIAN S ,et al. Neural architectures for named entity recognition[J]. arXiv preprint, 2016,arXiv:1603.01360.
[38]	DEVLIN J , CHANG M , LEE K ,et al. BERT:pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint, 2018,arXiv:1810.04805.
[39]	PANG B , LEE L , VAITHYANATHAN S . Thumbs up:sentiment classification using machine learning techniques[C]// Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing – EMNLP’02. Morristown:Association for Computational Linguistics, 2002: 79-86.
[40]	SOCHER R , PERELYGIN A , WU J Y ,et al. Recursive deep models for semantic compositionality over a sentiment treebank[C]// Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Stroudsburg:Association for Computational Linguistics, 2013: 1631-1642.
[41]	MIKOLOV T , SUTSKEVER I , CHEN K ,et al. Distributed representations of words and phrases and their compositionality[C]// Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2. New York:ACM Press, 2013: 3111-3119.
[42]	VASWANI A , SHAZEER N , PARMAR N ,et al. Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems.Red Hook:Curran Associates Inc. , 2017: 5998-6008.
[43]	NGIAM J , KHOSLA A , KIM M ,et al. Multimodal deep learning[C]// Proceedings of the 28th International Conference on Machine Learning.[S.l.:s.n.], 2011: 689-696.
[44]	SRIVASTAVA N , SALAKHUTDINOV R . Multimodal learning with deep Boltzmann machines[C]// Proceedings of the 25th International Conference on Neural Information Processing Systems.Red Hook:Curran Associates Inc. , 2012: 2222-2230.

Metrics

Recommended 0

No Suggested Reading articles found!

优点	不足
● 提供24 h全天候的客户服务，方便用户随时获取服务	● 交互方式单一，用户通过语音与客服系统交互，操作复杂，降低了效率
● 自动处理一些常见问题，降低人工客服的工作量	● 服务内容仅限于语音
● 语音导航为用户提供自助服务	● 用户往往需要进行多次操作才能获得相应解答

优点	不足
● 用户通过文字、语音、图片、视频等与客服系统交互	● 上网环境影响客服质量
● 提供更实时客户服务	● 消耗较高算力和时间

优点	不足
● 根据用户的需求和情感进行智能化回答和处理	● 定制化模型质量和训练数据会影响智能化水平
● 可以通过数据分析和挖掘，为企业提供更为精准的客户服务和营销策略	● 系统消耗大量算力和时间
● 可以通过强化学习不断提升智能化水平	● 训练过拟合，系统会“变傻”

解决方案	优点	不足
基于混合语言模型的方言识别方法	结合标准普通话和方言的语言模型，提高方言识别准确性	可能无法完全捕捉方言的所有特点
基于深度学习的声学模型	引入方言语音特征，显著提高方言识别性能	需要大量标注数据进行训练
基于词频统计的行业词汇表构建方法	通过统计行业文本中的高频词汇，有效构建行业词汇表	可能无法涵盖所有行业专有词汇
基于循环神经网络的行业语言模型	引入行业专有词汇，提高行业用词识别准确性	训练过程可能较慢，需要较多计算资源

解决方案	优点	不足
知识管理系统	提出了知识库的新概念，为知识图谱的研究和应用奠定了基础	未针对具体应用场景进行深入研究
基于注意力的树状结构神经网络	通过卷积神经网络改善传统知识库问答质量，提高问答准确性	需要大规模语料训练词向量模型，计算资源和时间成本较高
改进问答标准处理方法	减少用户因得到不准确回答而产生的等待焦虑感，提高与用户交流的语言准确性	未详细介绍具体的技术实现方式
词汇训练和高频信息组合搜索方法	根据关键词相似性和高频信息组合搜索，提高问答准确性	需要大规模语料训练词向量模型，计算资源和时间成本较高
5层规则体系模型	为客服行业信息图谱的建立提供了指导性规则，有助于提高知识图谱的结构化程度	未针对实体消歧等具体问题进行深入研究

Research and application analysis of artificial intelligence-based customer service platform technologies for telecom operators

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 44

Related Articles 15

Metrics

Recommended 0

[1]	Fei XUE, Bin CHEN, Jing LIU, Xiaoyang LIANG, Lin ZHU, Feng WANG, Tian LI, Liang ZHANG, Zhenzhen CHEN, Xiao LI. Research and practice on technologies for full stack deployment of autonomous networks [J]. Telecommunications Science, 2023, 39(9): 63-75.
[2]	Jun ZHOU, Keqing LIU, Shikui WANG, Ling YANG. Research on intelligent modeling and policy making of CNC brain [J]. Telecommunications Science, 2023, 39(9): 54-62.
[3]	Minglu LIU, Yan ZHENG, Xue HAN, Xiangyang YUAN, Chao DENG. Watermark embedding and detection based on generative causal language model [J]. Telecommunications Science, 2023, 39(9): 32-42.
[4]	Jie PAN, Lan YE, Pengfei ZHANG, Zhonggui BU. Research on the security of national secret algorithm based compute first networking [J]. Telecommunications Science, 2023, 39(8): 157-166.
[5]	Ting ZHOU. An adaptive unscented Kalman filter algorithm for electronic archives information data denoising [J]. Telecommunications Science, 2023, 39(8): 102-108.
[6]	Chengyu ZHENG, Yiting YAO, Hongbin LIANG, Lei WANG. Review of optimal resource allocation scheme for 5G Internet of vehicles [J]. Telecommunications Science, 2023, 39(7): 124-138.
[7]	Ting ZHOU. Blockchain and credibility function based chain storage method of electronic encrypted information [J]. Telecommunications Science, 2023, 39(7): 116-123.
[8]	Yaoyu HE, Chao ZHANG. Airworthiness analysis of low earth orbit satellite communication technology for UAV application [J]. Telecommunications Science, 2023, 39(6): 96-104.
[9]	Zehua GUO, Haowen ZHU, Tongwen XU. Network modal innovation for distributed machine learning [J]. Telecommunications Science, 2023, 39(6): 44-51.
[10]	Kaihui GAO, Dan LI. Data center networks with performance guarantee: a survey [J]. Telecommunications Science, 2023, 39(6): 1-21.
[11]	Xiaoliang MA, Ying LIU, Dequan DU, Lingling AN. Key technologies and development trends of intelligent customer service for operators [J]. Telecommunications Science, 2023, 39(5): 76-89.
[12]	Sihong ZHANG, Jian ZHANG. Impact and countermeasures of generative AI represented by ChatGPT on the telecom industry [J]. Telecommunications Science, 2023, 39(5): 67-75.
[13]	Liang XU, Ye WANG, Ran ZHENG, Jiheng ZHANG, Ping YUAN, Xinyang LI, Yu TIAN. Design and application of multi-dimensional evaluation model of telecommunication network operations and maintenance [J]. Telecommunications Science, 2023, 39(4): 142-151.
[14]	Xiaoyun WANG, Wei DENG, Long ZHANG, Qi SUN. Research on multi-domain collaboration based method of TDD large-scale networking [J]. Telecommunications Science, 2023, 39(4): 43-51.
[15]	Qingfeng DING, Song WANG. Distributed IOS-SM transmission scheme with joint antenna and IOS unit selection for high-speed railway scenario [J]. Telecommunications Science, 2023, 39(4): 31-42.

解决方案	优点	不足
AVAYA的质量管理体系	涵盖完整的质检过程，针对具体情况使用功效明显	费用较高，不适宜在经营方式不同的企业中应用
利用因子分析处理信道失配问题	为智能数据搜索、分类及识别奠定技术基础	未针对具体应用场景进行深入研究
升级C4.5算法分类问题录音和工单	提高质检效率，有效降低漏检概率	可能存在过拟合问题，对噪声敏感
问题语音质量检验技术	自动甄别出问题通话录音，提升质检效率	受限于设备性能和算法复杂度
将语音转化为文字后进行关键词挖掘、对比	获取更高频率信息，提高质检准确性	转换过程可能存在误差，关键词挖掘效果受限于预设关键字
智慧机器人和智能质检系统	提升企业服务水平，降低人力成本	面临技术成熟度和推广难题