[1]刘俊岭,吴晴晴,董珊珊,等.支持灾难救援的在线空间众包匹配算法[J].南京师大学报(自然科学版),2024,(04):21-30.[doi:10.3969/j.issn.1001-4616.2024.04.003]
　Liu Junling,Wu Qingqing,Dong Shanshan,et al.Online Spatial Crowdsourcing Matching Algorithm for Disaster Relief[J].Journal of Nanjing Normal University(Natural Science Edition),2024,(04):21-30.[doi:10.3969/j.issn.1001-4616.2024.04.003]
点击复制

支持灾难救援的在线空间众包匹配算法()
分享到：

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

卷:
期数:
2024年04期
页码:
21-30
栏目:
空间数据智能研究
出版日期:
2024-12-15

文章信息/Info

Title:
Online Spatial Crowdsourcing Matching Algorithm for Disaster Relief
文章编号:
1001-4616(2024)04-0021-10
作者:
刘俊岭1; 2; 吴晴晴1; 2; 董珊珊1; 2; 孙焕良1; 2; 许景科1; 2; 3
(1.沈阳建筑大学计算机科学与工程学院,辽宁 沈阳 110168)
(2.辽宁省城市建设大数据管理与分析重点实验室,辽宁 沈阳 110168)
(3.国家特种计算机工程技术研究中心沈阳分中心,辽宁 沈阳 110168)
Author(s):
Liu Junling1; 2; Wu Qingqing1; 2; Dong Shanshan1; 2; Sun Huanliang1; 2; Xu Jingke1; 2; 3
(1.School of Computer Science and Engineering,Shenyang Jianzhu University,Shenyang 110168,China)
(2.Liaoning Province Big Data Management and Analysis Laboratory of Urban Construction,Shenyang 110168,China)
(3.Shenyang Branch of National Special Computer Engineering Technology Research Center,Shenyang 110168,China)
关键词:
空间众包; 灾难救援; 任务匹配; 任务等级; 最小损失
Keywords:
spatial crowdsourcing; disaster relief; task matching; task level; minimum loss
分类号:
TP399
DOI:
10.3969/j.issn.1001-4616.2024.04.003
文献标志码:
A
摘要:
灾难发生后人们常常通过社交媒体平台发布志愿者救援与受灾者求助信息,从这些数据中抽取求助任务与救援人员信息并对两者进行合理匹配可以为救助提供有效支持. 本文将空间众包技术引入灾难救援领域,提出支持灾难救援的在线空间众包匹配问题. 利用深度学习分类方法与大规模语言模型构建灾难事件信息抽取模型,实现了救援和求助信息的准确抽取; 设计了任务等级评定方法与动态损失度量,以反映任务的紧急性和损失的动态变化; 基于动态损失度量提出了一种综合抢占与延迟策略的贪心算法. 通过真实数据集及合成数据集进行详细的实验分析,与现有算法相比,提出的综合抢占与延迟的贪心算法总损失至少减少35%,验证了所提算法的有效性.
Abstract:
After disasters,people often post information about volunteer rescue efforts and requests for help from the affected on social media platforms. Extracting the information of help task and rescue personnel from these data and making a reasonable match between them can provide effective support for rescue. In this paper,spatial crowdsourcing technology is introduced into the field of disaster relief,and online spatial crowdsourcing matching problem for disaster relief is proposed. The disaster event information extraction model is constructed by using deep learning classification method and large-scale language model to realize the accurate extraction of rescue and help information. The task rating method and dynamic loss measurement are designed to reflect the urgency of the task and the dynamic change of the loss. A greedy algorithm combining preempt and delay strategies is proposed based on dynamic loss measurement. Through detailed experimental analysis of real data sets and synthetic data sets,the total loss of the greedy algorithm combining preempt and delay strategies is reduced by at least 35% compared with the existing algorithm,and the effectiveness of the proposed algorithm is verified.

参考文献/References:

[1]ZHENG Y J,LING H F,XU X L,et al. Emergency scheduling of engineering rescue tasks in disaster relief operations and its application in China[J]. International transactions in operational research,2015,22(3):503-518.
[2]MOLLAH A K,SADHUKHAN S,DAS P,et al. A cost optimization model and solutions for shelter allocation and relief distribution in flood scenario[J]. International journal of disaster risk reduction,2018,31:1187-1198.
[3]BEIGI G,HU X,MACIEJEWSKI R,et al. An overview of sentiment analysis in social media and its applications in disaster relief[M]//PEDRYCZ W,CHEN S. Sentiment Analysis and Ontology Engineering. Cham:Springer,2016.
[4]GAO H,BARBIER G,GOOLSBY R. Harnessing the crowdsourcing power of social media for disaster relief[J]. IEEE intelligent systems,2011,26(3):10-14.
[5]KAZEMI L,SHAHABI C. Geocrowd:enabling query answering with spatial crowdsourcing[C]//Proceedings of the 20th International Conference on Advances in Geographic Information Systems. Redondo Beach:Association for Computing Machinery,2012:189-198.
[6]WU B,HAN K,ZHANG E. On the task assignment with group fairness for spatial crowdsourcing[J]. Information processing & management,2023,60(2):103175-103187.
[7]GUO X Y,HE T T. Survey about research on information extraction[J]. Computer science,2015,42(2):14-17.
[8]王剑,彭雨琦,赵宇斐,等. 基于深度学习的社交网络舆情信息抽取方法综述[J]. 计算机科学,2022,49(8):279-293.
[9]张仰森,刘帅康,刘洋,等. 基于深度学习的实体关系联合抽取研究综述[J]. 电子学报,2023,51(4):1093-1116.
[10]王浩畅,周郴莲,MARIUS G P. 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.
[11]车万翔,窦志成,冯岩松,等. 大模型时代的自然语言处理:挑战、机遇与发展[J]. 中国科学:信息科学,2023,53(9):1645-1687.
[12]邓成汝,凌捷. 融合预训练模型与神经网络的实体关系抽取[J]. 计算机工程与设计,2023,44(7):2023-2029.
[13]TONG Y,ZHOU Z,ZENG Y,et al. Spatial crowd-sourcing:a survey[J]. The VLDB journal,2020,29:217-250.
[14]CHENG P,JIAN X,CHEN L. An experimental evaluation of task assignment in spatial crowdsourcing[J]. Proceedings of the VLDB endowment,2018,11(11):1428-1440.
[15]DENG D,SHAHABI C,DEMIRYUREK U. Maximizing the number of worker's self-selected tasks in spatial crowdsourcing[C]//Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Orlando:Association for Computing Machinery,2013:314-323.
[16]DANIEL F,KUCHERBAEV P,CAPPIELLO C,et al. Quality control in crowdsourcing:a survey of quality attributes,assessment techniques,and assurance actions[J]. ACM computing surveys,2018,51(1):1-40.
[17]DENG D,SHAHABI C,ZHU L. Task matching and scheduling for multiple workers in spatial crowdsourcing[C]//Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. Seattle:Association of Computing Machinery,2015:1-10.
[18]陶阳阳. 众包模式下志愿者参与应急管理的意愿及影响因素研究[D]. 成都:四川大学,2021.
[19]朱国齐,郑乾,赵雨晴. 众包视角下救灾减灾的社会参与系统运行机制研究[J]. 价值工程,2018,37(33):286-289.
[20]HUTAGALUNG S,INDRAJAT H. Developing a crowdsourcing-based disaster relief model based on public participation[J]. International journal of safety and security engineering,2023,13(1):115-120.
[21]刘胜枝. 媒介向善中的“救命文档”共享型媒介的特征与启示[J]. 人民论坛,2022(9):86-89.
[22]ZOOK M,GRAHAM M,SHELTON T,et al. Volunteered geographic information and crowdsourcing disaster relief:a case study of the Haitian earthquake[J]. World medical & health policy,2010,2(2):7-33.
[23]孙焕良,王思懿,刘俊岭,等. 社交媒体数据中水灾事件求助信息提取模型[J]. 计算机应用,2024,44(8):2437-2445.
[24]陈报章,仲崇庆. 自然灾害风险损失等级评估的初步研究[J]. 灾害学,2010,25(3):1-5.
[25]SARMA D,DAS A,DUTTA P,et al. A cost minimization resource allocation model for disaster relief operations with an information crowdsourcing-based MCDM approach[J]. IEEE transactions on engineering management,2020,69(5):2454-2474.
[26]李超超,程晓陶,王艳艳,等. 洪涝灾害三参数损失函数的构建Ⅰ:基本原理[J]. 水利学报,2020,51(3):349-357.
[27]PARADILAGA S N,SULISTYONINGSIH M,LESTARI R K,et al. Flood prediction using inverse distance weighted interpolation of k-nearest neighbor points[C]//2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. Brussels:IEEE,2021:4616-4619.
[28]CHENG P,JIAN X,CHEN L. Task assignment on spatial crowdsourcing(Technical Report)[J]. arXiv:1605.09675,2016.

备注/Memo

备注/Memo:
收稿日期:2024-05-30.
基金项目:国家自然科学基金项目(62073227)、国家重点研发计划课题(2021YFF0306303)、辽宁省教育厅资助项目(JYTMS20231596、LJZ2021008).
通讯作者:孙焕良,博士,教授,博士生导师,研究方向:空间数据管理、数据挖掘等. E-mail:sunhl@sjzu.edu.cn
更新日期/Last Update: 2024-12-15