基于矩阵分解和注意力多任务学习的客服投诉工单分类

宋勇; 严志伟; 秦玉坤; 赵东明; 叶晓舟; 柴园园; 欧阳晔

doi:10.11959/j.issn.1000-0801.2022031

您当前的位置：

首页 >

文章列表页 >

基于矩阵分解和注意力多任务学习的客服投诉工单分类

研究与开发 | 更新时间：2024-06-05

- 基于矩阵分解和注意力多任务学习的客服投诉工单分类
- Customer service complaint work order classification based on matrix factorization and attention multi-task learning
- 电信科学 2022年38卷第2期页码：103-110
- 作者机构：
  
  1. 亚信科技（中国）有限公司，北京 100193
  2. 亚信科技（南京）有限公司，江苏南京 210013
  3. 中国移动通信集团天津有限公司，天津 300020
- 作者简介：
  
  [ "宋勇（1989- ），男，亚信科技（中国）有限公司通信人工智能实验室通信业务与应用算法研究部负责人，主要研究方向为NLP、知识图谱、AIOps、推荐等" ]
  [ "严志伟（1994- ），男，博士，亚信科技（南京）有限公司通信人工智能实验室算法工程师，主要研究方向为NLP、AIOps" ]
  [ "秦玉坤（1987- ），男，亚信科技（南京）有限公司通信人工智能实验室算法工程师，主要研究方向为NLP、AIOps、知识图谱" ]
  [ "赵东明（1984- ），男，博士，中国移动通信集团天津有限公司技术专家，天津移动 AI 实验室/天津移动博士后科研工作站负责人，主要研究方向为知识图谱、智能语音情感、认知概念网络" ]
  [ "叶晓舟（1980- ），男，博士，亚信科技（中国）有限公司通信人工智能实验室资深总监、首席科学家，主要研究方向为通信网络与人工智能" ]
  [ "柴园园（1980- ），女，博士，亚信科技（中国）有限公司通信人工智能实验室首席算法科学家，主要研究方向为深度学习、人工智能、数据科学及管理" ]
  [ "欧阳晔（1981- ），男，博士，亚信科技（中国）有限公司首席技术官、高级副总裁，主要研究方向为移动通信、人工智能、数据科学、科技研发创新与管理" ]
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2022031
  中图分类号： TP183
- 网络出版日期：2022-02，
  
  纸质出版日期：2022-02-20
- 稿件说明：
移动端阅览
宋勇, 严志伟, 秦玉坤, 等. 基于矩阵分解和注意力多任务学习的客服投诉工单分类[J]. 电信科学, 2022,38(2):103-110.

Yong SONG, Zhiwei YAN, Yukun QIN, et al. Customer service complaint work order classification based on matrix factorization and attention multi-task learning[J]. Telecommunications science, 2022, 38(2): 103-110.
宋勇, 严志伟, 秦玉坤, 等. 基于矩阵分解和注意力多任务学习的客服投诉工单分类[J]. 电信科学, 2022,38(2):103-110. DOI： 10.11959/j.issn.1000-0801.2022031.

Yong SONG, Zhiwei YAN, Yukun QIN, et al. Customer service complaint work order classification based on matrix factorization and attention multi-task learning[J]. Telecommunications science, 2022, 38(2): 103-110. DOI： 10.11959/j.issn.1000-0801.2022031.

摘要

投诉工单自动分类是通信运营商客服数字化、智能化发展的要求。客服投诉工单的类别有多层，每一层有多个标签，层级之间有所关联，属于典型的层次多标签文本分类问题，现有解决方法大多数基于分类器同时处理所有的分类标签，或者对每一层级分别使用多个分类器进行处理，忽略了层次结构之间的依赖。提出了一种基于矩阵分解和注意力的多任务学习的方法（MF-AMLA），处理层次多标签文本分类任务。在通信运营商客服场景真实投诉工单分类数据下，与该场景常用的机器学习算法和深度学习算法的 Top1 F1 值相比分别最大提高了21.1%和5.7%。已在某移动运营商客服系统上线，模型输出的正确率97%以上，对客服坐席单位时间的处理效率提升22.1%。

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%.

关键词

Keywords

references

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 .

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 .

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 .

KOWSARI , MEIMANDI J , HEIDARYSAFA , et al . Text classification algorithms:a survey [J ] . Information , 2019 , 10 ( 4 ): 150 .

MINAEE S , KALCHBRENNER N , CAMBRIA E , et al . Deep learning:based text classification [J ] . ACM Computing Surveys , 2021 , 54 ( 3 ): 1 - 40 .

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 .

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 .

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 .

HOCHREITER S , SCHMIDHUBER J . Long short-term memory [J ] . Neural Computation , 1997 , 9 ( 8 ): 1735 - 1780 .

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 .

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 .

RADFORD A , NARASIMHAN K , SALIMANS T , et al . Improving language understanding with unsupervised learning [EB ] . 2018 .

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 .

TSOUMAKAS G , KATAKIS I , VLAHAVAS I . Mining multi-label data [M ] // Data Mining and Knowledge Discovery Handbook . Boston,MA : Springer US , 2009 : 667 - 685 .

BOUTELL M R , LUO J B , SHEN X P , et al . Learning multi-label scene classification [J ] . Pattern Recognition , 2004 , 37 ( 9 ): 1757 - 1771 .

TSOUMAKAS G , VLAHAVAS I . Random k-labelsets:an ensemble method for multilabel classification [C ] // Machine Learning:ECML .[S.l.:s.n. ] , 2007 .

FÜRNKRANZ J , HÜLLERMEIER E , LOZA MENCÍA E , et al . Multilabel classification via calibrated label ranking [J ] . Machine Learning , 2008 , 73 ( 2 ): 133 - 153 .

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 .

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 .

ZHANG M L , ZHOU Z H . ML-KNN:a lazy learning approach to multi-label learning [J ] . Pattern Recognition , 2007 , 40 ( 7 ): 2038 - 2048 .

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 .

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 .

VENS C , STRUYF J , SCHIETGAT L , et al . Decision trees for hierarchical multi-label classification [J ] . Machine Learning , 2008 , 73 ( 2 ): 185 - 214 .

CESA-BIANCHI N , GENTILE C , ZANIBONI L . Incremental algorithms for hierarchical classification [J ] . The Journal of Machine Learning Research , 2006 ( 7 ): 31 - 54 .

LEVATIĆ J , KOCEV D , DŽEROSKI S , . The importance of the label hierarchy in hierarchical multi-label classification [J ] . Journal of Intelligent Information Systems , 2015 , 45 ( 2 ): 247 - 271 .

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 .

CARUANA R . Multitask learning [J ] . Machine learning , 1997 , 28 ( 1 ): 41 - 75 .

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 .

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 .

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 .

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 .

YANG Y , HOSPEDALES T M . Trace norm regularised deep multi-task learning [J ] . arXiv preprint arXiv:1606.04038 , 2016 .

BENNETT J , LANNING S . The netflix prize [C ] // Proceedings of KDD Cup and Workshop . New York:ACM Press , 2007 :35.

浏览量

234

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

GMTBLC：基于深度学习的双模态网络流量分类

基于改进长短期记忆网络的新能源场站网络安全评估方法研究

基于霍克斯过程的动态异质网络表征学习方法

基于多任务学习的行人重识别算法研究

信号增强网络驱动的调制识别