|本期目录/Table of Contents|

[1]孔胜利,杜崇瀚,钱继发.提示路径对ChatGPT辅助应急预案编制效果的影响作用*[J].中国安全生产科学技术,2024,20(8):27-32.[doi:10.11731/j.issn.1673-193x.2024.08.004]
　KONG Shengli,DU Chonghan,QIAN Jifa.Influence of prompt paths on effect of ChatGPT aided emergency plan formulation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(8):27-32.[doi:10.11731/j.issn.1673-193x.2024.08.004]
点击复制

提示路径对ChatGPT辅助应急预案编制效果的影响作用*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
20
期数:
2024年8期
页码:
27-32
栏目:
学术论著
出版日期:
2024-08-30

文章信息/Info

Title:
Influence of prompt paths on effect of ChatGPT aided emergency plan formulation
文章编号:
1673-193X(2024)-08-0027-06
作者:
孔胜利; 杜崇瀚; 钱继发
（上海应用技术大学 城市建设与安全工程学院，上海 201418）
Author(s):
KONG Shengli;  DU Chonghan;  QIAN Jifa
(School of Urban Construction and Safety Engineering,Shanghai Institute of Technology,Shanghai 201418,China)
关键词:
ChatGPT; 应急预案; 文本精确度; ROUGE评估
Keywords:
ChatGPT;  emergency plan;  text accuracy;  ROUGE evaluation
分类号:
X913.2
DOI:
10.11731/j.issn.1673-193x.2024.08.004
文献标志码:
A
摘要:
为探索人工智能辅助应急预案编制的可行性，有效提升预案编制效率，基于ChatGPT文本投喂，采用案例提示和规则提示2种方式对大语言模型辅助预案编制技术进行探索和尝试，并通过ROUGE方法对不同提示路径下应急预案的文本性能进行评估。研究结果表明：2种路径下均能形成相关预案的内容文本，在文本性能上，案例提示法整体优于规则提示法，特别的对于结构性较强的文本内容，单案例提示明显优于多案例提示；但对于内容灵活性较强的部分，多案例提示的文本性能能够明显提升。研究结果可为采用类似技术开展应急预案智能辅助编制时的提示路径选择提供数据支持和实践参考。
Abstract:
In order to explore the feasibility of artificial intelligence aided emergency plan formulation and effectively improve the efficiency of plan formulation,based on ChatGPT text feeding,two methods of case prompt and rule prompt were used to explore and try the large language model aided plan formulation technology,and the ROUGE method was used to evaluate the text performance of emergency plans under different prompt paths.The results show that the content text of relevant plans can be formed under the two paths.In terms of text performance,the case prompt method is superior to the rule prompt method as a whole,especially for the text content with strong structure,and the single case prompt is obviously superior to the multi-case prompt.However,the text performance of partial multi-case prompt with strong content flexibility can be significantly improved.The research results can provide data support and practical reference for the selection of prompt path when using similar technologies to carry out the intelligence aided formulation of emergency plans.

参考文献/References:

［1］李峰,张超,张正辉.中国石油数字化应急预案系统研究［J］.中国安全生产科学技术,2013,9(9):142-147. LI Feng,ZHANG Chao,ZHANG Zhenghui.Research on digital emergency plan system of CNPC［J］.Journal of Safety Science and Technology,2013,9(9):142-147.
［2］张超,裴玉起,邱华.国内外数字化应急预案技术发展现状与趋势［J］.中国安全生产科学技术,2010,6(5):154-158. ZHANG Chao,PEI Yuqi,QIU Hua.Current status and development trend of digital emergency plan at home and abroad［J］.Journal of Safety Science and Technology,2010,6(5):154-158.
［3］李迎顺,任晶,王晶晶.应急预案数字化发展方向及路径探讨［J］.中国应急管理,2022(9):20-31.
［4］王晶晶,朱伟,高玉坤.数字化视角下的应急预案结构化及流程化技术方案研究［J］.中国安全生产科学技术,2018,14(12):164-168. WANG Jingjing,ZHU Wei,GAO Yukun.Study on technical schemes for structured and processed emergency plan from digital perspective［J］.Journal of Safety Science and Technology,2018,14(12):164-168.
［5］李娜,李娇,孙青峰.突发事件数字化应急预案综述及研究［J］.油气田环境保护,2019,29(5):71-74,78.
［6］刘铁民.突发事件应急预案体系概念设计研究［J］.中国安全生产科学技术,2011,7(8):5-13. LIU Tiemin.Design of the emergency plan system’s concept［J］.Journal of Safety Science and Technology,2011,7(8):5-13.
［7］BROWN T,MANN B,RYDER N,et al.Language models are few-shot learners［J］.Advances in Neural Information Processing Systems,2020,33:1877-1901.
［8］赵朝阳,朱贵波,王金桥.ChatGPT给语言大模型带来的启示和多模态大模型新的发展思路［J］.数据分析与知识发现,2023,7(3):26-35. ZHAO Chaoyang,ZHU Guibo,WANG Jinqiao.The inspiration brought by ChatGPT to LLM and the new development ideas of multi-modal large model［J］.Data Analysis and Knowledge Discovery,2023,7(3):26-35.
［9］宋时磊,杨逸云.应用场景、风险与前景：ChatGPT类大语言模型时代的学术出版［J］.出版科学,2023,31(5):76-84. SONG Shilei,YANG Yiyun.Application scenarios,risks and prospects:academic publishing in the ChatGPT era ［J］.Publishing Journal,2023,31(5):76-84.
［10］NI X F,LI P J.A systematic evaluation of large language models for natural language generation tasks［C］//Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 2:Frontier Forum)，2023:40-56.
［11］张华平,李林翰,李春锦.ChatGPT中文性能测评与风险应对［J］.数据分析与知识发现,2023,7(3):16-25. ZHANG Huaping,LI Linhan,LI Chunjin.ChatGPT performance evaluation on Chinese language and risk measures［J］.Data Analysis and Knowledge Discovery,2023,7(3):16-25.
［12］钱力,刘熠,张智雄,等.ChatGPT的技术基础分析［J］.数据分析与知识发现,2023,7(3):6-15. QIAN Li,LIU Yi,ZHANG Zixiong,et al.Technical basic analysis of ChatGPT ［J］.Data Analysis and Knowledge Discovery,2023,7(3):6-15.
［13］LECLER A,DURON L,SOYER P.Revolutionizing radiology with GPT-based models:current applications,future possibilities and limitations of ChatGPT［J］.Diagnostic and Interventional Imaging,2023,104(6):269-274.
［14］QIU X H,HAO T Q,TAN X Y,et al,Chain-of-loRA:enhancing the instruction fine-tuning performance of low-rank adaptation on diverse instruction set［J］.IEEE Signal Processing Letters,2024,31:875-879.
［15］秦涛,杜尚恒,常元元,等.ChatGPT的工作原理、关键技术及未来发展趋势［J］.西安交通大学学报,2024,58(1):1-12. QIN Tao,DU Shangheng,CHANG Yuanyuan,et al.Principles,key technologies and emerging rends of ChatGPT［J］.Journal of Xi’an Jiaotong University,2024,58(1):1-12.
［16］鲍彤,章成志.ChatGPT中文信息抽取能力测评——以三种典型的抽取任务为例［J］.数据分析与知识发现,2023,7(9):1-11. BAO Tong,ZHANG Chengzhi.Performance evaluation of ChatGPT on Chinese information extraction-an empirical study by three typical extraction tasks ［J］.Data Analysis and Knowledge Discovery,2023,7(9):1-11.

相似文献/References:

[1]杨芳,储胜利.企业应急预案编制的难点及对策研究[J].中国安全生产科学技术,2011,7(1):127.
　YANG Fang,CHU Sheng-li.Research on difficulties and countermeasures in the compilation of emergency plan of enterprises[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(8):127.
[2]朱中华,王则胜.港口水域突发事件应急预案存在的问题与对策分析[J].中国安全生产科学技术,2011,7(3):123.
　ZHU Zhong-hua,WANG Ze-sheng.Analysis and Countermeasure to Problems of Port Waters Emergency Response Plan[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(8):123.
[3]贾海江,刘双跃,姜传胜,等.基层应急体系现状调查分析[J].中国安全生产科学技术,2011,7(6):38.
　Jia Hai-jiang,Liu Shuang-yue,Jiang Chuan-sheng,et al.Investigation of emergency system at grassroots level[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(8):38.
[4]王善文.国内外含硫气田应急预案编制对比分析研究[J].中国安全生产科学技术,2011,7(10):46.
　WANG Shan-wen.Comparison study on emergency planning of nature gas well involving hydrogen sulfide[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(8):46.
[5]邢娟娟.危险化学品中毒事故应急预案编制与响应关注要点[J].中国安全生产科学技术,2011,7(10):75.
　XING Juan-juan.Compilation and response key points of emergency plan for dangerous chemical poisoning accident and response points[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(8):75.
[6]刘铁民.应急预案重大突发事件情景构建* ——基于“情景-任务-能力”应急预案编制技术研究之一[J].中国安全生产科学技术,2012,8(4):5.
　LIU Tie min.Studies on scenes’ construction of emergency planning ——part I of emergency planning technology based on “scenetaskability”[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(8):5.
[7]蒋白桦,刘海龙.应急预案建模方法及其在石油化工行业的应用研究[J].中国安全生产科学技术,2012,8(5):69.
　JIANG Bai hua,LIU Hai long.Emergency schema modeling method and application in petrochemical industry[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(8):69.
[8]王晋刚,唐雪娇 ,付军凤,等.石化企业的环境污染事故应急预案分析与建议[J].中国安全生产科学技术,2012,8(6):148.
　WANG Jin gang,TANG Xue jiao,FU Jun feng,et al.Analysis and advices on emergency plan of environmental pollution accident  for petrochemical enterprise[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(8):148.
[9]杨力,邢娟娟.学校突发事件应急管理与预案模式探讨[J].中国安全生产科学技术,2010,6(1):139.
　YANG Li,XING Juan-juan.Study on emergency management and plan mode of incident in school[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(8):139.
[10]马巧焕,禇 洪.我国应急预案研究文献的定量分析[J].中国安全生产科学技术,2009,5(4):202.
　MA Qiao huan,CHU Hong.Quantitative analysis of domestic articles on emergency plan[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2009,5(8):202.

备注/Memo

备注/Memo:
收稿日期： 2024-03-04
* 基金项目： 上海应用技术大学中青年教师科技人才发展基金项目（ZQ2022-8）
作者简介： 孔胜利，博士，副教授，主要研究方向为城市安全与智慧应急、工业安全与矿井瓦斯防治。
更新日期/Last Update: 2024-08-26