Research on Text Classification of Power Work Orders Based on RoBERTa-RCNN and Channel Attention Mechanism

[1] Zhao Junnan. Discussion on the existing problems and solutions in electric power marketing audit management [J]. Modern State-owned Enterprise Research, 2018(06):141. Search in Google Scholar

[2] Xie Xiao. Research and Application of Rough Set attribute Reduction Algorithm in Power Market [D]. North China Electric Power University, 2011. Search in Google Scholar

[3] Ren Runhu. Power System Data Warehouse Technology and its Application [D]. Tianjin University, 2010. Search in Google Scholar

[4] Ge Shaoyun, YUE Shunmin, Wu Qi, Liu Hong, WANG Shaomian, BU Xiangzhi. Power market analysis Decision support System [J]. Electric Power Informatization, 2005(11):83-84+88. Search in Google Scholar

[5] Li Bo. Application Research of Power Consumption Information Acquisition System Based on Carrier Technology [D]. Dalian University of Technology, 2014. Search in Google Scholar

[6] Huang Yafen. Discussion on application of power consumption information acquisition system (negative control terminal) in smart grid [D]. Zhejiang University, 2012. Search in Google Scholar

[7] Qiu J. Research on Power Chinese text data Mining technology and its application in reliability [D]. Zhejiang University, 2016. Search in Google Scholar

[8] Expert view of China Electric Power Research Institute “2018 Scientific Conference” -- Basic theory, key technology and development trend of large power grid security and operation in the era of big Data [J]. Electric Power Information and Communication Technology, 2016, 14(07):1-5. Search in Google Scholar

[9] LI Tingshun, Tan Wen, Liu Zesan. Research on Key Technologies of Smart Grid based on Big Data [J]. Power Supply Technology, 2017, 41(08):1195-1197. Search in Google Scholar

[10] PENG Xiaosheng, DENG Diyuan, CHENG Shijie, Wen Jinyu, LI Zhaohui, Niu Lin. Key Technologies of Power Big Data for Smart Grid Applications [J]. Proceedings of the CSEE, 2015, 35(03): 503-511. Search in Google Scholar

[11] ZHANG Dongxia, Miao Xin, Liu Liping, Zhang Yan, LIU Zhi-Ren. Research on the development of Smart Grid Big Data Technology [J]. Proceedings of the CSEE, 2015, 35(01):2-12. Search in Google Scholar

[12] Liu Haifeng, Liu Zongqi. Research on Further Application of Power Consumption Information Acquisition System [J]. Power Supply and Electricity, 2012, 29(06):40-42. Search in Google Scholar

[13] Zhu Longzhu, Xu Hong, Liu Lili. 95598 major service event recognition based on deep learning study [J]. Electric power information and communication technology, 2018, 16 (11): 5. DOI: CNKI: SUN: DXXH. 0.2018-11-004. Search in Google Scholar

[14] Chen Hao. Research on Marketing Strategy based on Power Customer Behavior Data Mining [D]. North China Electric Power University (Beijing), 2017. Search in Google Scholar

[15] TAO Yongcai, Wu Wenle, Shi Lei et al. Multi-channel RCNN and ON-LSTM models based ON attention mechanism and emotion [J/OL]. Miniature Microcomputer System, 202:1-9. (2021-05-10). Search in Google Scholar

[16] Feng Bin, Zhang Youwen, Tang Xin, et al. Power equipment defect text mining based on BiLSTM-Attention neural network [J]. Proceedings of the CSEE, 20, 40(1):1-10. Search in Google Scholar

[17] Chen Xiaona, Gao Pengfei, Liang Yue, et al. Hierarchical classification of power text based on category hybrid embedding [J]. Journal of Peking University: Natural Science, 2022, 58(1):77-82. (in Chinese) Search in Google Scholar

[18] Liu Z Q, Wang H F, Cao J, et al. Research on defect text classification model of Power equipment based on Convolutional neural network [J]. Power Grid Technology, 2018, 42(2):644-651. Search in Google Scholar

[19] Wang Yixing. Research on Power data Mining technology based on deep learning and transfer learning [D]. Hangzhou, Zhejiang University, 2019. Search in Google Scholar

[20] Wang Jundong, Yang Jun, Pei Yangzhou, et al. Research on fault aided decision of distribution network based on Knowledge graph [J]. Power Grid Technology, 2021, 45(6):2101-2112. Search in Google Scholar

[21] Yang Fan, Huang He, Li Haiying, et al. Defect text mining method of Power Equipment based on ERNIE pre-training [J]. Electric Transmission, 2022, 52(14):7. Search in Google Scholar

[22] CAI Yingkai, Cao Shilong, Zhang Ye, et al. Application of BERT and BiGRU-AT to Power marketing customer service job order classification model [J]. Microcomputer Applications, 2019, 39(4):6-9. Search in Google Scholar

[23] Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J].Computer engineering and applications,2020,56(23):12-22. Search in Google Scholar

[24] Liu Y, Ott M, Goyal N, et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach[J]. 2019. DOI:10.48550/arXiv.1907.11692. Search in Google Scholar

[25] Müller, Rafael, Kornblith S, Hinton G.When Does Label Smoothing Help?[J]. 2020. DOI: 10.48550/arXiv.1906.02629. Search in Google Scholar