一种用于供电服务评估的多模态多任务框架

doi:10.3969/j.issn.1006-2475.2018.12.010

计算机与现代化

一种用于供电服务评估的多模态多任务框架

(国网浙江省电力公司,浙江杭州310007)

收稿日期:2018-05-07 出版日期:2019-01-03 发布日期:2019-01-04
作者简介:沈然(1984-),男,浙江杭州人,国网浙江省电力公司高级工程师，硕士，研究方向:电力营销信息化; 林恺丰(1983-),男,高级工程师,硕士,研究方向:信息与自动化；吴慧(1984-),女,高级工程师,硕士,研究方向:电力信息。

A Multi-modal and Multi-task Framework for Power Supply Service Evaluation

(State Grid Zhejiang Electric Power Corporation, Hangzhou 310007, China)

Received:2018-05-07 Online:2019-01-03 Published:2019-01-04

摘要/Abstract

摘要： 应用神经网络进行电力服务中的语音情感分析和文本诉求分类是一种新颖的算法。相比于传统的方法，它避免了特征工程的做法，不需要人为进行特征选择，同时可以学习到更鲁棒的特征。受多任务学习的启发，本文设计一种多模态多任务的模型，可对语音和文本2种不同模态的数据进行处理，一方面使用情感分析来进行供电服务评估，另一方面引入用户诉求分类，用相似的任务提高单一任务的性能。实验表明，本文模型在单个任务上的结果与目前最好的模型结果接近。

关键词: 多模态, 多任务, 情感分析, 诉求分类, 神经网络

Abstract: The application of neural network into speech emotion analysis and text appeal classification in power service is a novel algorithm. Compared with the traditional method, the method of feature engineering is avoided, no human feature selection is needed, and more robust features can be learned. Inspired by the multi-task learning, this paper designs a multi-modal multi-task model, which can manage two different modes data of voice and text, on the one hand, it uses emotional analysis to evaluate the power supplying service, on the other hand, it introduces the classification of user demands, using similar tasks to improve the performance of a single task. The experiments show that the result in the single task of the model in this paper is close to the result of the best model.

Key words: multi-model, multi-task, sentiment analysis, appeal classification, neural network

中图分类号:

TP391.1

沈然，林恺丰，吴慧. 一种用于供电服务评估的多模态多任务框架[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2018.12.010.

SHEN Ran, LIN Kai-feng, WU Hui. A Multi-modal and Multi-task Framework for Power Supply Service Evaluation[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.12.010.

参考文献

［1］ GERS F A, SCHMIDHUBER J, CUMMINS F. Learning to forget: Continual prediction with LSTM［J］. Neural Computation, 2000,12(10):2451-2471.
［2］张冬雯,杨鹏飞,许云峰. 基于word2vec和SVMperf的中文评论情感分类研究［J］. 计算机科学, 2016,43(6A):418-421.
［3］梁军,柴玉梅,原慧斌,等. 基于极性转移和LSTM递归网络的情感分析［J］. 中文信息学报, 2015,29(5):152-159.
［4］ QIAN Q, HUANG M, LEI J, et al. Linguistically regularized LSTMs for sentiment classification［C］// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 2017:1679-1689.
［5］ 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. 2008:160-167.
［6］ DENG L, HINTON G, KINGSBURY B. New types of deep neural network learning for speech recognition and related applications: An overview［C］// 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 2013:8599-8603.
［7］ GIRSHICK R B. Fast R-CNN［C］// 2015 IEEE International Conference on Computer Vision. 2015:1440-1448.
［8］ RAMSUNDAR B, KEARNES S , RILEY P, et al. Massively multitask networks for drug discovery［C］// The International Conference on Machine Learning. 2015: arXiv:1502.02072.
［9］ LONG M, WANG J, et al. Learning multiple tasks with deep relationship networks［C］// The International Conference on Machine Learning. 2015: arXiv:1506.02117.
［10］LU Y, KUMAR A, ZHAI S, et al. Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification［C］// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2016: arXiv:1611.05377.
［11］MISRA I, SHRIVASTAVA A, GUPTA A, et al. Cross-stitch networks for multi-task learning［C］// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:3994-4003.
［12］HASHIMOTO K, XIONG C, TSURUOKA Y, et al. A joint many-task model: Growing a neural network for multiple NLP tasks［C］// 2017 Conference on ICLR. 2016:arXiv:1611.01587.
［13］SGAARD A, GOLDBERG Y. Deep multi-task learning with low level tasks supervised at lower layers［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2016,2:231-235.
［14］KENDALL A, GAL Y, CIPOLLA R. Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics［EB/OL］. http://cn.arxiv.org/abs/1705.07115, 2017-03-19.
［15］YANG Y, HOSPEDALES T M. Deepmulti-task Representation Learning: A Tensor Cactorisation Approach［EB/OL］. http://cn.arxiv.org/abs/1605.06391, 2016-05-20.
［16］韩敏捷. 基于深度学习框架的多模态动作识别［J］. 计算机与现代化, 2017(7): 48-52.
［17］李飞,李晗静,姚登峰,等. WAPM：基于改进层次分析法的网站无障碍评估指标［J］. 计算机与现代化, 2018(1): 78-83.
［18］卜庆伟,陈雄,柴金宝,等. 基于模糊神经网络PID的舵机控制系统［J］. 计算机与现代化, 2018(3):1-5.

[1]	宋涛涛, 李艳萍, 李洪港, 韩春雪. 基于改进变结构趋近律的机械臂滑模控制系统[J]. 计算机与现代化, 2023, 0(12): 14-18.
[2]	周成诚, 曾庆军, 杨康, 胡家铭, 韩春伟. 基于高效通道注意力模块的运动想象脑电识别[J]. 计算机与现代化, 2023, 0(12): 19-23.
[3]	王宇航, 董宝良, 公超, 尚真真, 姚康宁. 基于意图识别的空中群目标动态威胁评估[J]. 计算机与现代化, 2023, 0(12): 100-104.
[4]	李诗月, 孟佳娜, 于玉海, 李雪莹, 许英傲. 基于知识增强的方面级情感分析方法[J]. 计算机与现代化, 2023, 0(10): 1-8.
[5]	谷明轩, 范冰冰. 基于多模态特征融合的抑郁症识别[J]. 计算机与现代化, 2023, 0(10): 17-22.
[6]	陈俊义. 基于图节点动静态特征的健康事件预测模型[J]. 计算机与现代化, 2023, 0(10): 39-44.
[7]	黎世达, 项剑文. 一种提高图像识别模型鲁棒性的弱化强化方法[J]. 计算机与现代化, 2023, 0(10): 70-76.
[8]	陈子健, 段春红. 面向在线学习情境的认知情绪面部表情识别[J]. 计算机与现代化, 2023, 0(10): 92-98.
[9]	刘付琪, 张达, 宋建华, 王海东. 基于CNN-BiLSTM的液压系统故障诊断[J]. 计算机与现代化, 2023, 0(09): 10-19.
[10]	吴甜, 刘海华, 童顺延. 基于深度反馈的卷积神经网络的图像分类[J]. 计算机与现代化, 2023, 0(09): 82-86.
[11]	毛明扬, 徐胜超. 面向粒子群优化BP神经网络的粗糙集连续属性离散化算法[J]. 计算机与现代化, 2023, 0(09): 115-119.
[12]	孙子雨, 任燃, 魏曦哲. 基于DTW-TCN的股票分类及预测研究[J]. 计算机与现代化, 2023, 0(08): 31-37.
[13]	曾丽丽, 汤华贝, 牛艺晓, 孟凡月. 基于LSTM堆叠残差网络的岩相识别方法[J]. 计算机与现代化, 2023, 0(08): 38-43.
[14]	江蕾, 唐建, 杨超越, 吕婷婷. 基于CWGAN-GP与CNN的轴承故障诊断方法[J]. 计算机与现代化, 2023, 0(07): 1-6.
[15]	崔少国, 张岗, 王奥迪. 基于感知注意力的深度交叉网络推荐模型[J]. 计算机与现代化, 2023, 0(07): 54-60.

一种用于供电服务评估的多模态多任务框架

A Multi-modal and Multi-task Framework for Power Supply Service Evaluation

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价