多轮对话技术及其在电网数据查询中的应用

doi:10.11896/jsjkx.200600078

计算机科学 ›› 2022, Vol. 49 ›› Issue (10): 265-271.doi: 10.11896/jsjkx.200600078

多轮对话技术及其在电网数据查询中的应用

王凯¹, 李舟军², 盛文博², 陈舒玮², 王明轩¹, 刘剑青¹, 蓝海波¹, 张锐¹

1 国网冀北电力有限公司北京 100053
2 北京航空航天大学计算机学院北京 100191

收稿日期:2020-06-15 修回日期:2021-12-24 出版日期:2022-10-15 发布日期:2022-10-13
通讯作者: 李舟军(lizj@buaa.edu.cn)
作者简介:(wang.kai.h@jibei.sgcc.com.cn)
基金资助:
国家自然科学基金(U1636211,61672081);软件开发环境国家重点实验室课题(SKLSDE-2019ZX-17);国网人工智能技术在调控运行全过程安全管控中的应用研究(520101180044)

Multi-turn Dialogue Technology and Its Application in Power Grid Data Query

WANG Kai¹, LI Zhou-jun², SHENG Wen-bo², CHEN Shu-wei², WANG Ming-xuan¹, LIU Jian-qing¹, LAN Hai-bo¹, ZHANG Rui¹

1 State Grid Jibei Electric Company Limited,Beijing 100053,China
2 School of Computer Science and Engineering,Beihang University,Beijing 100191,China

Received:2020-06-15 Revised:2021-12-24 Online:2022-10-15 Published:2022-10-13
About author:WANG Kai,born in 1990,postgra-duate.His main research interests include power system operational optimization and control and application of artificial intelligence in power system operation.
LI Zhou-jun,born in 1963,Ph.D,professor,is a member of China Computer Federation.His main research interests include data mining,natural language processing,network and information security.
Supported by:
National Natural Science Foundation of China(U1636211,61672081),Fund of the State Key Laboraty of Software Development Environment(SKLSDE-2019ZX-17) and Research on the Application of Artificial Intelligence in the Safety Control of the Whole Process of Regulation and Operation in State Grid(520101180044).

摘要/Abstract

摘要： 随着信息技术与传统行业的相互融合,使用计算机控制的机器替代人类进行一系列重复、枯燥甚至危险的工作已成为一大趋势。为利用自然语言与计算机进行有效的交互,基于多轮对话技术的人机交互与对话系统应运而生,并已成为当前人工智能与自然语言处理领域的研究热点。电网调控系统中存在大量查询操作,需要调度员手动操作数据管理系统。利用多轮对话技术实现电网数据的智能化查询,可解决现有调度系统操作流程复杂低效的问题,大大提高了调度员对紧急情况的处理速度。文中首先阐述了任务导向型多轮对话系统的基本架构,以及自然语言理解、对话管理、自然语言生成3个模块的功能与相关算法。然后,为满足电网公司对数据智能查询等特定场景的需求,设计并实现了一个多模块级联式的任务导向型多轮对话系统。该系统主要由自然语言理解模块、对话管理模块、自然语言生成模块和知识库4个核心部分组成。电网调度员可使用自然语言的形式向该系统询问其所希望获得的信息,并得到相应的回复。该过程无需键盘和鼠标的操作,大大提高了电网信息查询的快捷性与便利性。

关键词: 对话系统, 意图识别, 槽填充, 对话管理, 自然语言生成

Abstract: With the integration of information technology and traditional industries,it has become a trend to use computer-controlled machines instead of humans to perform repetitive,boring and even dangerous tasks.In order to effectively interact with computers in natural language,human-computer interaction and dialogue systems based on multi-turn dialogue technology have become a research hotspot in the field of artificial intelligence and natural language processing.In the grid control system,the dispatcher needs to do a large number of query operations manually.To reduce the complexity of existing dispatching system and improve the speed of emergency handling of dispatchers,multi-turn dialogue technology can be applied to realize intelligent voice query of power grid data.This paper first describes the basic architecture of the task-oriented multi-turn dialogue system,including functions and related algorithms of its three modules:natural language understanding,dialogue management,and natural language generation.Next,in order to meet the demand of power grid companies for specific scenarios such as intelligent data queries,this paper designs and implements a multi-module task-oriented multi-turn dialogue system which consists of natural language understanding module,dialogue management module,natural language generation module and knowledge base as core mo-dules.The grid dispatcher can ask the system questions and get answers in the form of natural language.This process does not require keyboard or mouse operations,which greatly improves the rapidity and convenience of the grid information query.

Key words: Dialogue system, Intention recognition, Slot filling, Dialogue management, Natural language generation

中图分类号:

TP391

王凯, 李舟军, 盛文博, 陈舒玮, 王明轩, 刘剑青, 蓝海波, 张锐. 多轮对话技术及其在电网数据查询中的应用[J]. 计算机科学, 2022, 49(10): 265-271. https://doi.org/10.11896/jsjkx.200600078

WANG Kai, LI Zhou-jun, SHENG Wen-bo, CHEN Shu-wei, WANG Ming-xuan, LIU Jian-qing, LAN Hai-bo, ZHANG Rui. Multi-turn Dialogue Technology and Its Application in Power Grid Data Query[J]. Computer Science, 2022, 49(10): 265-271. https://doi.org/10.11896/jsjkx.200600078

参考文献

[1]TURING A M.Computing machinery and intelligence[J].Mind,1950,59(236):433-460.
[2]WEIZENBAUM J.ELIZA—A Computer Program for theStudy of Natural Language Communication Between Man and Machine[J].Communications of the ACM,1983,9(1):36-45.
[3]WALLACE R S.The Anatomy of A.L.I.C.E[EB/OL].https://link.springer.com/chapter/10.1007/978-1-4020-6710-5_13.
[4]YAN Z.Research on the Key Technologies of CustomizableKnowledge-Based Chatbots [D].Beijing:Beihang University,2018.
[5]GALE W A,CHURCH K W,YAROWSKY D.One sense per discourse[C]//Proceedings of the workshop on Speech and Na-tural Language.1992:233-237.
[6]ZUE V,GLASS J,GOODINE D,et al.Preliminary Evaluation of the VOYAGER Spoken Language System[C]//Workshop on Speech & Natural Language.Association for Computational Linguistics,1989:160-167.
[7]FERRUCCI D,BROWN E,CHU-CARROLL J,et al.BuildingWatson:An overview of the DeepQA project[J].AI Magazine,2010,31(3):59-79.
[8]LI R.Research of natural dialogue system for smart internet[D].Beijing:Beijing University of Technology,2017.
[9]LUONG M T,LE Q V,SUTSKEVER I,et al.Multi-task Sequence to Sequence Learning[J].arXiv:1511.06114,2015.
[10]AUST H,OERDER M,SEIDE F,et al.A spoken language inquiry system for automatic train timetable information[J].Phi-lips Journal of Research,1995,49(4):399-418.
[11]WARD W,ISSAR S.Recent Improvements in the CMU Spoken Language Understanding System[C]//Proceedings of the Workshop on Human Language Technology.New Jerey,USA,1994:213-216.
[12]KIM Y.Convolutional Neural Networks for Sentence Classification[J].arXiv:1408.5882,2014.
[13]HASHEMI H B,ASIAEE A,KRAFT R.Query intent detection using convolutional neural networks[C]//International Confe-rence on Web Search and Data Mining,Workshop on Query Understanding.2016.
[14]TUR G,DENG L,HAKKANITÜR D,et al.Towards deeperunderstanding:Deep convex networks for semantic utterance classification[C]//IEEE International Conference on Acoustics.IEEE,2012:5045-5048.
[15]LIU P,QIU X,HUANG X.Recurrent Neural Network for Text Classification with Multi-Task Learning[J].arXiv:1605.05101,2016.
[16]GRAVES A,MOHAMED A R,HINTON G.Speech Recognition with Deep Recurrent Neural Networks[J/OL].ICASSP,2013:6645-6649.https://ieeexplore.ieee.org/abstract/document/6638947/.
[17]HUANG Z,XU W,YU K.Bidirectional LSTM-CRF Models for Sequence Tagging[J].arXiv:.1508.01991,2015.
[18]LIU B,LANE I.Attention-Based Recurrent Neural NetworkModels for Joint Intent Detection and Slot Filling[J].arXiv:1609.01454,2016.
[19]XU P,SARIKAYA R.Convolutional neural network basedtriangular CRF for joint intent detection and slot filling[C]//2013 IEEE Workshop on Automatic Speech Recognition and Understanding.IEEE,2014:78-83.
[20]GUO D Z,TUR G,YIH W T,et al.Joint semantic utterance classification and slot filling with recursive neural networks[C]//2014 IEEE Spoken Language Technology Workshop(SLT).IEEE,2015:554-559.
[21]BELLIK Y,TEIL D.A multimodal dialogue controller for multimodal user interface management system application:a multimodal window manager[C]//Interact 93 & Chi 93 Conference Companion on Human Factors in Computing Systems.ACM,1993:93-94.
[22]GODDEAU D,MENG H M,POLIFRONI J,et al.A form-based dialogue manager for spoken language applications[C]//International Conference on Spoken Language.IEEE,1996:701-704.
[23]TURUNEN M,HAKULINEN J.Agent-based adaptive interaction and dialogue management architecture for speech applications[J].Lecture Notes in Computer Science,2001,2166:357-364.
[24]ARDISSONO L,BOELLA G,LESMO L.A plan-based agent architecture for interpreting natural language dialogue[J].International Journal of Human-Computer Studies,2000,52(4):583-635.
[25]YAN Y,TIAN H F,BO D,et al.Research and Implementation of the Frame-based Dialogue Management Model[J].Computer Engineering,2005,31(13):212-214.
[26]ZHANG J H,CHEN J J.Summarization of natural language generation[J/OL].Application Research of Computers.http://en.cnki.com.cn/Article_en/CJFDTOTAL-JSYJ200608000.htm.
[27]MIRKOVIC D,CAVEDON L.DialogueManagement UsingScripts:US,EP1891625B1[P].2011-02-16[2022-07-22].https://www.freepatentsonline.com/8041570.html.
[28]ALICE H,RUDNICKY,ALEXANDER I.Stochastic naturallanguage generation for spoken dialog systems[J].Comport Speech Lang,2002,16(3):387-407.
[29]WEN T H,GASIC M,MRKš IĆ N,et al.Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.2015:1711-1721.
[30]TANG J,YANG Y,CARTON S,et al.Context-aware Natural Language Generation with Recurrent Neural Networks[J].ar-Xiv:1611.0900,2016.
[31]HOCHREITER S,SCHMIDHUBER J.Long Short-Term Me-mory[J].Neural Computation,1997,9(8):1735-1780.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

多轮对话技术及其在电网数据查询中的应用

Multi-turn Dialogue Technology and Its Application in Power Grid Data Query

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

Metrics

本文评价

推荐阅读 0

[1]	钟将, 尹红, 张剑. 基于学术知识图谱的辅助创新技术研究 Academic Knowledge Graph-based Research for Auxiliary Innovation Technology 计算机科学, 2022, 49(5): 194-199. https://doi.org/10.11896/jsjkx.210400195
[2]	杨慧敏, 马廷淮. 融合检索与生成的复合对话模型 Compound Conversation Model Combining Retrieval and Generation 计算机科学, 2021, 48(8): 234-239. https://doi.org/10.11896/jsjkx.200700162
[3]	姚冬, 李舟军, 陈舒玮, 季震, 张锐, 宋磊, 蓝海波. 面向任务的基于深度学习的多轮对话系统与技术 Task-oriented Dialogue System and Technology Based on Deep Learning 计算机科学, 2021, 48(5): 232-238. https://doi.org/10.11896/jsjkx.200600092
[4]	张玉帅, 赵欢, 李博. 基于BERT和BiLSTM的语义槽填充 Semantic Slot Filling Based on BERT and BiLSTM 计算机科学, 2021, 48(1): 247-252. https://doi.org/10.11896/jsjkx.191200088
[5]	王玉,任福继,全昌勤. 口语对话系统中对话管理方法研究综述 Review of Dialogue Management Methods in Spoken Dialogue System 计算机科学, 2015, 42(6): 1-7. https://doi.org/10.11896/j.issn.1002-137X.2015.06.001
[6]	杨明浩,陶建华,李昊,巢林林. 面向自然交互的多通道人机对话系统 Nature Multimodal Human-Computer-Interaction Dialog System 计算机科学, 2014, 41(10): 12-18. https://doi.org/10.11896/j.issn.1002-137X.2014.10.003
[7]	杨艺,周元. 基于用户查询意图识别的Web搜索优化模型 Web Retrieval Optimization Model Based on User's Query Intention Identification 计算机科学, 2012, 39(1): 264-267.
[8]	伏晓,谢立. 安全报警关联技术研究 Security Alert Correlation: A Survey 计算机科学, 2010, 37(5): 9-14.
[9]	彭武,姚淑萍. 基于概率推理的入侵意图识别研究 Study on Intrusion Intention Recognition Based on the Probabilistic Inference 计算机科学, 2010, 37(1): 79-82.
[10]	曾鹏吴玲达陈文伟. 多Agent战术意图识别的知识组织与问题求解计算机科学, 2007, 34(7): 181-183.
[11]	宁卓龚俭. 网络入侵意图识别方法综述计算机科学, 2006, 33(9): 4-7.
[12]	. 一个基于文本输入的口语对话系统的新的实现策略计算机科学, 2006, 33(11): 205-209.