基于矩阵分解和注意力多任务学习的客服投诉工单分类

doi:10.11959/j.issn.1000-0801.2022031

Abstract

Abstract:

The automatic classification of complaint work orders is the requirement of the digital and intelligent development of customer service of communication operators.The categories of customer service complaint work orders have multiple levels, each level has multiple labels, and the levels are related, which belongs to a typical hierarchical multi-label text classification (HMTC) problem.Most of the existing solutions are based on classifiers to process all classification labels at the same time, or use multiple classifiers for each level, ignoring the dependence between hierarchies.A matrix factorization and attention-based multi-task learning approach (MF-AMLA) to deal with hierarchical multi-label text classification tasks was proposed.Under the classification data of real complaint work orders in the customer service scenario of communication operators, the maximum Top1 F1 value of MF-AMLA is increased by 21.1% and 5.7% respectively compared with the commonly used machine learning algorithm and deep learning algorithm in this scenario.It has been launched in the customer service system of one mobile operator, the accuracy of model output is more than 97%, and the processing efficiency of customer service agent unit time has been improved by 22.1%.

Key words: hierarchical multi-label classification, attention mechanism, multi-task learning, customer service work order classification

CLC Number:

TP183

Yong SONG, Zhiwei YAN, Yukun QIN, Dongming ZHAO, Xiaozhou YE, Yuanyuan CHAI, Ye OUYANG. Customer service complaint work order classification based on matrix factorization and attention multi-task learning[J]. Telecommunications Science, 2022, 38(2): 103-110.

Figures/Tables 6

模型	Top 1		Top 5		Top 10
模型	P	R	P	R	P	R
Hierarchical SVM	0.413	0.507	0.642	0.681	0.733	0.759
Clus HMC	0.449	0.477	0.665	0.688	0.741	0.763
GRU	0.622	0.597	0.874	0.886	0.921	0.918
TextCNN	0.614	0.608	0.89	0.882	0.938	0.934
BERT	0.666	0.642	0.926	0.915	0.97	0.955
MF-AMLA	$0 . 671$	$0 . 662$	$0 . 938$	$0 . 921$	$0 . 971$	$0 . 964$

References 33

[1]	TUNG F C . Customer satisfaction,perceived value and customer loyalty:the mobile services industry in China[J]. African Journal of Business Management, 2013,7(18): 1730-1737.
[2]	LIN L , ZHU B , WANG Q ,et al. A novel 5G core network capability exposure method for telecom operator[C]// Proceedings of 2020 IEEE Intl Conf on Parallel ＆ Distributed Processing with Applications,Big Data ＆ Cloud Computing,Sustainable Computing ＆ Communications,Social Computing ＆ Networking. Piscataway:IEEE Press, 2020: 1450-1454.
[3]	WEHRMANN J , CERRI R , BARROS R . Hierarchical multi-label classification networks[C]// Proceedings of International Conference on Machine Learning.[S.l.:s.n.], 2018: 5075-5084.
[4]	KOWSARI , MEIMANDI J , HEIDARYSAFA ,et al. Text classification algorithms:a survey[J]. Information, 2019,10(4): 150.
[5]	MINAEE S , KALCHBRENNER N , CAMBRIA E ,et al. Deep learning:based text classification[J]. ACM Computing Surveys, 2021,54(3): 1-40.
[6]	ZHANG Y , WALLACE B . A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification[J]. arXiv preprint arXiv:1510.03820, 2015.
[7]	MIKOLOV T , KOMBRINK S , BURGET L ,et al. Extensions of recurrent neural network language model[C]// Proceedings of 2011 IEEE International Conference on Acoustics,Speech and Signal Processing. Piscataway:IEEE Press, 2011: 5528-5531.
[8]	SOCHER R , LIN C C-Y , NG A Y ,et al. Parsing natural scenes and natural language with recursive neural networks[C]// Proceedings of the 28th International Conference on Machine Learning.[S.l.:s.n.], 2011.
[9]	HOCHREITER S , SCHMIDHUBER J . Long short-term memory[J]. Neural Computation, 1997,9(8): 1735-1780.
[10]	DEY R , SALEM F M . Gate-variants of Gated Recurrent Unit (GRU) neural networks[C]// Proceedings of 2017 IEEE 60th International Midwest Symposium on Circuits and Systems. Piscataway:IEEE Press, 2017: 1597-1600.
[11]	VASWANI A , SHAZEER N , PARMAR N ,et al. Attention is all you need[C]// Advances in neural information processing systems.[S.l.:s.n.], 2017: 5998-6008.
[12]	RADFORD A , NARASIMHAN K , SALIMANS T ,et al. Improving language understanding with unsupervised learning[EB]. 2018.
[13]	DEVLIN J , CHANG M-W , LEE K ,et al. Bert:Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018.
[14]	TSOUMAKAS G , KATAKIS I , VLAHAVAS I . Mining multi-label data[M]// Data Mining and Knowledge Discovery Handbook. Boston,MA: Springer US, 2009: 667-685.
[15]	BOUTELL M R , LUO J B , SHEN X P ,et al. Learning multi-label scene classification[J]. Pattern Recognition, 2004,37(9): 1757-1771.
[16]	TSOUMAKAS G , VLAHAVAS I . Random k-labelsets:an ensemble method for multilabel classification[C]// Machine Learning:ECML.[S.l.:s.n.], 2007.
[17]	FüRNKRANZ J , HüLLERMEIER E , LOZA MENCíA E ,et al. Multilabel classification via calibrated label ranking[J]. Machine Learning, 2008,73(2): 133-153.
[18]	MADJAROV G , KOCEV D , GJORGJEVIKJ D ,et al. An extensive experimental comparison of methods for multi-label learning[J]. Pattern Recognition, 2012,45(9): 3084-3104.
[19]	ELISSEEFF A , WESTON J . A kernel method for multi-labelled classification[J]. Advances in neural information processing systems,s.l.:The MIT Press, 2001(14): 681-687.
[20]	ZHANG M L , ZHOU Z H . ML-KNN:a lazy learning approach to multi-label learning[J]. Pattern Recognition, 2007,40(7): 2038-2048.
[21]	BI W , KWOK J T . Multilabel classification on tree-and dag-structured hierarchies[C]// Proceedings of the 28th International Conference on Machine Learning,[S.l,:s.n. ], 2011.
[22]	GONG J B , TENG Z Y , TENG Q ,et al. Hierarchical graph transformer-based deep learning model for large-scale multi-label text classification[J]. IEEE Access, 2020(8): 30885-30896.
[23]	VENS C , STRUYF J , SCHIETGAT L ,et al. Decision trees for hierarchical multi-label classification[J]. Machine Learning, 2008,73(2): 185-214.
[24]	CESA-BIANCHI N , GENTILE C , ZANIBONI L . Incremental algorithms for hierarchical classification[J]. The Journal of Machine Learning Research, 2006(7): 31-54.
[25]	LEVATI? J , KOCEV D , D?EROSKI S , . The importance of the label hierarchy in hierarchical multi-label classification[J]. Journal of Intelligent Information Systems, 2015,45(2): 247-271.
[26]	BORGES H B , NIEVOLA J C . Multi-Label Hierarchical Classification using a Competitive Neural Network for protein function prediction[C]// Proceedings of 2012 International Joint Conference on Neural Networks (IJCNN). Piscataway:IEEE Press, 2012: 1-8.
[27]	CARUANA R . Multitask learning[J]. Machine learning, 1997,28(1): 41-75.
[28]	COLLOBERT R , WESTON J . A unified architecture for natural language processing:deep neural networks with multitask learning[C]// Proceedings of the 25th international conference on Machine learning-ICML '08. New York:ACM Press, 2008: 160-167.
[29]	LIU X D , HE P C , CHEN W Z ,et al. Multi-task deep neural networks for natural language understanding[C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg,PA,USA:Association for Computational Linguistics, 2019.
[30]	EATON E , DESJARDINS M , LANE T . Modeling transfer relationships between learning tasks for improved inductive transfer[C]// Machine Learning and Knowledge Discovery in Databases.[S.l.:s.n.], 2008.
[31]	DUONG L , COHN T , BIRD S ,et al. Low resource dependency parsing:cross-lingual parameter sharing in a neural network parser[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2:Short Papers). Stroudsburg,PA,USA:Association for Computational Linguistics, 2015.
[32]	YANG Y , HOSPEDALES T M . Trace norm regularised deep multi-task learning[J]. arXiv preprint arXiv:1606.04038, 2016.
[33]	BENNETT J , LANNING S . The netflix prize[C]// Proceedings of KDD Cup and Workshop. New York:ACM Press, 2007:35.

Metrics

Recommended 0

No Suggested Reading articles found!

文本	客户来电反映本机预约了宽带安装，但是装维人员电话：1xxxxxxxxxx，服务态度非常不好，一直没有帮客户安装，而且讲话非常不耐烦。客户对此不满，来电投诉。请查询处理，谢谢，随时联系1xxxxxxxxxx
标签	（一级）家庭业务→（二级）服务触点→（三级）装维人员→（四级）全局流转→（五级）售后服务→（六级）装维人员服务态度差→（七级）解释差错
文本	客户反映：于 2019 年开始在昆明龙泉路，某小区无法使用移动数据，已补换卡均无法使用，提示网络错误！强烈要求我方工作人员上门处理，并赔偿（未详细说明赔偿事宜），解释无效，请老师帮忙处理
标签	（一级）移动业务→（二级）网络质量→（三级）手机上网（4G）→（四级）有信号无法使用→（五级）功能使用→（六级）有信号无法浏览网页→（七级）室外

占比	70%	80%	90%	100%
标签数	73	186	889	3 692

层级	原始	一级	二级	三级	四级	五级	六级	七级
数量	186	4	5	45	49	6	83	64

Customer service complaint work order classification based on matrix factorization and attention multi-task learning

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References 33

Related Articles 7

Metrics

Recommended 0

[1]	Yong ZHANG, Jikui LIU, Wenlong KE. EEG emotion recognition based on parallel separable convolution and label smoothing regularization [J]. Telecommunications Science, 2023, 39(5): 116-128.
[2]	Jianfeng DAI, Xingyu CHEN, Ligang DONG, Xian JIANG. A triple joint extraction method combining hybrid embedding and relational label embedding [J]. Telecommunications Science, 2023, 39(2): 132-144.
[3]	Nan JIN, Ruiqin WANG, Yuecong LU. Ebbinghaus forgetting curve and attention mechanism based recommendation algorithm [J]. Telecommunications Science, 2022, 38(10): 89-97.
[4]	Jinyang SUN, Baisong LIU, Hao REN, Jiangbo QIAN. TAGAN: an academic paper adversarial recommendation algorithm incorporating fine-grained semantic features [J]. Telecommunications Science, 2021, 37(8): 57-65.
[5]	Jinhua WANG,Na YING,Chendu ZHU,Zhaosen LIU,Zhedong CAI. Speech emotion recognition algorithm based on spectrogram feature extraction of deep space attention feature [J]. Telecommunications Science, 2019, 35(7): 100-108.
[6]	Yiming WANG,Ken CHEN,Aihaiti ABUDUSALAMU. End-to-end audiovisual speech recognition based on attention fusion of SDBN and BLSTM [J]. Telecommunications Science, 2019, 35(12): 79-89.
[7]	Jingming XIA,Lingling TANG,Ling TAN,Han ZHENG. Biometric monitoring system based on K-means ＆MTLS-SVM algorithm [J]. Telecommunications Science, 2017, 33(10): 43-49.