浏览全部资源
扫码关注微信
国网山东省电力公司东营供电公司,山东 东营 257100
丁鹏程(1992-),男,国网山东省电力公司东营供电公司中级工程师,研究方向为工程投资审计管理、研究型审计以及工程投资审计数智化
韩琪(1980-),男,硕士,国网山东省电力公司东营供电公司高级工程师,研究方向为电气工程及自动化、新型电力系统。
收稿日期:2024-03-06,
纸质出版日期:2024-10-15
移动端阅览
丁鹏程,韩琪.基于事件抽取与核查预警的电力工程项目审计方法[J].软件导刊,2024,23(10):40-47.
DING Pengcheng,HAN Qi.Audit Method for Power Engineering Projects Based on Event Extraction and Verification Warning[J].Software Guide,2024,23(10):40-47.
丁鹏程,韩琪.基于事件抽取与核查预警的电力工程项目审计方法[J].软件导刊,2024,23(10):40-47. DOI: 10.11907/rjdk.241208.
DING Pengcheng,HAN Qi.Audit Method for Power Engineering Projects Based on Event Extraction and Verification Warning[J].Software Guide,2024,23(10):40-47. DOI: 10.11907/rjdk.241208.
针对电网工程项目业务范畴广、审计环节多、事件关联复杂,导致审计管理与数字化作业融合困难的问题,提出一种基于事件抽取与核查预警的电力工程项目审计方法。该方法首先构建基于事件框架的审计业务过程,减轻建模人员的工作量与业务扩展压力;其次采用模板匹配结合Transformer的方式,将固定格式文本识别后的审计事件作为远程学习知识,生成具有明确提示知识的触发词模板,并根据不同项目主题按需补充知识,从而提升非固定格式文本的事件抽取准确率;最后将识别出的各类审计事件匹配至不同审计阶段及事件框架中,以支持跟随项目进度对相关审计事件进行核查与预警。验证实验表明,在低人工标记文本中,该审计方法事件抽取准确率不低于93%,且提取事件可准确嵌入审计业务过程中,支持对关联审计事件的异常核查预警。
A power engineering project audit method based on event extraction and verification warning is proposed to address the difficulties in integrating audit management and digital operations caused by the wide scope of business, multiple audit processes, and complex event correlations in power grid engineering projects. This method first constructs an audit business process based on an event framework to reduce the workload and business expansion pressure of modeling personnel;Then, using template matching combined with Transformer, the audit events recognized from fixed format text are used as remote learning knowledge to generate trigger word templates with clear prompt knowledge, and knowledge is supplemented as needed according to different project topics, thereby improving the accuracy of event extraction from non fixed format text; Finally, the identified audit events will be matched to different audit stages and event frameworks to support the verification and early warning of relevant audit events in accordance with project progress. The verification experiment shows that in low manually annotated text, the accuracy of event extraction using this audit method is not less than 93%, and the extracted events can be accurately embedded into the audit business process, supporting abnormal verification and early warning of related audit events.
HUANG W J , CAI J J , XIONG C H . Application of earned value analysis to electric power construction schedule control——taking a 1000 kV substation as an example [J]. Engineering Journal of Wuhan University , 2018 , 51 ( S1 ): 387 - 392 .
黄伟杰 , 蔡军君 , 熊翠红 . 挣值分析在电力工程进度控制中的应用——以某1000 kV变电站为例 [J]. 武汉大学学报(工学版) , 2018 , 51 ( S1 ): 387 - 392 .
WANG X R , HOU W L , HU Y X . Construction of big data smart engineering audit platform-a data-based audit model based on the "point-line-surface" thinking [J]. Finance and Accounting Monthly , 2021 ( 17 ): 92 - 97 .
王雪荣 , 侯伟龙 , 虎祎笑 . 大数据智慧工程审计平台构建——基于“点—线—面”思维的数据式审计模式 [J]. 财会月刊 , 2021 ( 17 ): 92 - 97 .
ZHANG Z G , KANG C Q . Challenges and prospects for constructing the new-type power system towards a carbon neutrality future [J]. Proceedings of the CSEE , 2022 , 42 ( 8 ): 2806 - 2819 .
张智刚 , 康重庆 . 碳中和目标下构建新型电力系统的挑战与展望 [J]. 中国电机工程学报 , 2022 , 42 ( 8 ): 2806 - 2819 .
ZHAO X H , ZHANG H L . Capacity optimization of wind/pv hybrid power generation considering output correlation of wind turbines and photovoltaic units [J]. Software Guide , 2021 , 20 ( 5 ): 82 - 85 .
赵星虎 , 张会林 . 计及风光出力相关性的风光互补发电系统优化 [J]. 软件导刊 , 2021 , 20 ( 5 ): 82 - 85 .
HU J Y , KUANG Y , ZHANG L L . Analysis on the construction of digital audit platform for power grid enterprises [J]. Finance & Accounting , 2021 ( 4 ): 85 .
胡璟懿 , 匡尧 , 张兰澜 . 电网企业数字化审计平台构建浅析 [J]. 财务与会计 , 2021 ( 4 ): 85 .
WU J , CAO L X , WANG X J , et al . Risk identification and application of engineering project audit based on causal network learning [J]. Communication of Finance and Accounting , 2023 ( 5 ): 129 - 134,176 .
武健 , 曹丽霞 , 王晓军 , 等 . 基于因果网络学习的工程项目审计风险识别与应用 [J]. 财会通讯 , 2023 ( 5 ): 129 - 134,176 .
WANG Z Y , ZHOU J Y , WANG Y . Research on audit methods for electric power construction enterprises under digital traction [J]. Electrical Equipment and Economy , 2023 ( 8 ): 201 - 203 .
王震宇 , 周嘉宇 , 王苑 . 数字化牵引下的电力施工企业审计方法研究 [J]. 电气技术与经济 , 2023 ( 8 ): 201 - 203 .
DONG M L , ZHOU L Z , ZHANG Z , et al . Research and application of cloud audit for electric power big data [J]. Power Systems and Big Data , 2023 , 26 ( 4 ): 90 - 96 .
董美玲 , 周榴照 , 章桢 , 等 . 面向电力大数据的云审计研究与应用 [J]. 电力大数据 , 2023 , 26 ( 4 ): 90 - 96 .
YAN H N , YU Z T , HUANG Y X , et al . Fusing the extended semantic information of part-of-speech for event detection [J]. Computer Engineering , 2024 , 50 ( 3 ): 89 - 97 .
严海宁 , 余正涛 , 黄于欣 , 等 . 融合词性语义扩展信息的事件检测方法 [J]. 计算机工程 , 2024 , 50 ( 3 ): 89 - 97 .
WANG H H , ZHOU C L , MARIUS G P . Survey on event extraction based on deep learning [J]. Journal of Software , 2023 , 34 ( 8 ): 3905 - 3923 .
王浩畅 , 周郴莲 , Marius Gabriel Petrescu . 基于深度学习的事件抽取研究综述 [J]. 软件学报 , 2023 , 34 ( 8 ): 3905 - 3923 .
ZHANG J M , HARMAN M , GUEDJ B , et al . Model validation using mutated training labels: an exploratory study [J]. Neurocomputing , 2023 , 539 : 126116 .
LI W S , GUAN P . News commentary sentiment analysis method based on BE-MCNN model [J]. Software Guide , 2024 , 23 ( 3 ): 1 - 7 .
李文书 , 管平 . 基于BE-MCNN模型的新闻评论情感分析方法 [J]. 软件导刊 , 2024 , 23 ( 3 ): 1 - 7 .
GUO W Q , ZHANG T , LYU Y , et al . Power system transient fault event diagnosis method based on knowledge base and rule base [J]. Microcomputer Applications , 2023 , 39 ( 11 ): 103 - 105,125 .
郭伟琪 , 张婷 , 吕艺 , 等 . 基于知识库与规则库的电力系统暂态故障事件诊断方法 [J]. 微型电脑应用 , 2023 , 39 ( 11 ): 103 - 105,125 .
WANG S J , CHANG X , CAO S , et al . Host baseline checking algorithm of power monitoring system based on association rules [J]. Electrical Automation , 2023 , 45 ( 6 ): 17 - 19,23 .
王树军 , 常星 , 曹帅 , 等 . 基于关联规则的电力监控系统主机基线核查算法 [J]. 电气自动化 , 2023 , 45 ( 6 ): 17 - 19,23 .
XIANG W , WANG B . Survey of Chinese event extraction research [J]. Computer Technology and Development , 2020 , 30 ( 2 ) : 1 - 6 .
ZENG G Y , ZHANG Y , ZHOU Y , et al . Beyond OCR + VQA: towards end-to-end reading and reasoning for robust and accurate textvqa [J]. Pattern Recognition , 2023 , 138 : 109337 .
GE Y M , QIU C G , XIE L R , et al . Research on multi-energy coupled power load prediction based on K-means clustering and LSTM model [J/OL]. Modern Electric Power , 2024 , 1 - 8 [ 2024-08-30 ]. https://doi.org/10.19725/j.cnki.1007-2322.2023.0110 https://doi.org/10.19725/j.cnki.1007-2322.2023.0110 .
葛亚明 , 仇晨光 , 谢丽荣 , 等 . 基于K-means聚类与LSTM模型的多能源耦合电力负荷预测 [J/OL]. 现代电力 , 2024 , 1 - 8 [ 2024-08-30 ]. https://doi.org/10.19725/j.cnki.1007-2322.2023.0110. https://doi.org/10.19725/j.cnki.1007-2322.2023.0110. .
CHEN P , TAI B , SHI Y , et al . Text entity extraction of power equipment defects based on BERT-BI-LSTM-CRF algorithm [J]. Power System Technology , 2023 , 47 ( 10 ): 4367 - 4376 .
陈鹏 , 邰彬 , 石英 , 等 . 融合BERT、双向长短记忆网络和条件随机场的电力设备缺陷文本实体抽取 [J]. 电网技术 , 2023 , 47 ( 10 ): 4367 - 4376 .
WAN Y P , YAN S C , YU H K , et al . A text classification model based on semi-supervised generative adversarial networks and BERT [J]. Computer Technology and Development , 2023 , 33 ( 2 ): 187 - 194 .
宛艳萍 , 闫思聪 , 于海阔 , 等 . 结合SS-GAN和BERT的文本分类模型 [J]. 计算机技术与发展 , 2023 , 33 ( 2 ): 187 - 194 .
SHUN Z , WEI C , WEI X , et al . Doc2EDAG: an end-to-end document-level framework for Chinese financial event extraction [C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) , 2019 : 337 - 346 .
0
浏览量
131
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构