面向案例消耗推理的应急物资预测

doi:10.3778/j.issn.1002-8331.2007-0036

摘要/Abstract

摘要：

面向案例推理（Case-Based Reasoning，CBR）的应急物资需求预测中，针对老旧案例影响推理结果精确度的问题进行了研究，给出了一种基于消耗策略的案例推理的应急物资预测方法。通过粗糙集属性依赖度的计算确定了案例属性之间的权重系数；针对地震应急数据特征提出了一种消耗策略的定义，确定消耗函数、消耗参数和消耗区间参数，采用消耗策略对各案例间的相似度进行优化调整，减小老旧案例的权重，进而不同程度地削弱老旧案例对案例匹配结果的影响，再从案例库中检索到与目标案例匹配的最佳源案例，从而决策出目标案例的处理方案；通过进行地震实例分析，验证了参数调节后的案例消耗推理的预测结果精度更高。该方法在应急救援的物资预测中有一定的借鉴意义。

关键词: 应急物资, 案例推理（CBR）, 粗糙集, 消耗策略

Abstract:

In the Case-Based Reasoning（CBR） of emergency supplies demand forecasting, aiming at the problem that the old cases affect the accuracy of reasoning results, this paper proposes a method of emergency supplies forecasting based on a case-based reasoning with consumption strategy. Firstly, through the calculation of attribute dependency of rough set, the weight coefficient between case attributes is determined. Secondly, according to the characteristics of earthquake emergency data, a definition of consumption strategy is proposed, the consumption function, consumption parameters and consumption interval parameters are determined, the consumption strategy is used to optimize and adjust the similarity of each cases, weaken the weight of old cases, weaken the influence of old cases on case matching results in varying degrees, and then retrieve the best matching with the target case from the case database and get the processing scheme of the target case. Finally, through the analysis of an earthquake case, it is proved that the prediction result accuracy of case consumption inference after parameter adjustment is higher. Therefore, this method can be used for reference in the supplies forecast of emergency rescue.

Key words: emergency supplies, Case-Based Reasoning（CBR）, rough set, consumption strategy

王庆荣，马辰坤. 面向案例消耗推理的应急物资预测[J]. 计算机工程与应用, 2021, 57(22): 281-287.

WANG Qingrong, MA Chenkun. Forecast of Emergency Supplies for Case Consumption Reasoning[J]. Computer Engineering and Applications, 2021, 57(22): 281-287.

参考文献

[1] 张磊.面向地震灾情时序变化的应急救援物资需求动态预测研究[J].灾害学，2018，33（3）：161-164.
ZHANG L.Research on dynamic demand prediction of emergency relief materials oriented to the temporal and spatial change of earthquake disaster losses[J].Journal of Catastrophology，2018，33（3）：161-164.
[2] 吴雪莲，孙丙宇，李文波，等.基于粗糙集和CBR的救灾口粮需求预测[J].计算机工程，2012，38（9）：158-161.
WU X L，SUN B Y，LI W B，et al.Relief food demand forecast based on rough set and case-based reasoning[J].Computer Engineering，2012，38（9）：158-161.
[3] 郭子雪，韩瑞，齐美然.基于多元模糊回归的应急物资需求预测模型[J].河北大学学报（自然科学版），2017，37（4）：337-342.
GUO Z X，HAN R，QI M R.Predictive method of emer-gency supplies demand based on multiple fuzzy linear regression model[J].Journal of Hebei University（Natura Science Edition），2017，37（4）：337-342.
[4] SPENCER S，EVANS R，ALLEN T，et al.A multivariate time series approach to modeling and forecasting demand in the emergency department[J].Journal of Biomedical Informatics，2009，42（1）：123-139.
[5] MOHAMMADI R，GHOMI S M T F，ZEINALI F.A new hybrid evolutionary based RBF networks method for forecasting time series：a case study of forecasting emergency supply demand time series[J].Engineering Applications of Artificial Intelligence，2014，36：204-214.
[6] 胡忠君，刘艳秋，李佳.基于改进GM（1，1）的洪涝灾害应急物资动态需求预测[J].系统仿真学报，2019，31（4）：702-709.
HU Z J，LIU Y Q，LI J.Dynamic demand forecast of emergency materials for flood disasters based on improved GM（1，1） model[J].Journal of System Simulation，2019，31（4）：702-709.
[7] 程琼琼.基于GA的BP神经网络的地震应急物资需求预测[D].成都：西南财经大学，2016.
CHENG Q Q.The forecast of earthquake emergency material demand based on GA optimization BP neural network[D].Chengdu：Southwestern University of Finance and Economics，2016.
[8] 刘德元，朱昌锋，丁伟.基于相似案例推理的应急物资需求预测方法研究[J].兰州交通大学学报，2013，32（4）：119-123.
LIU D Y，ZHU C F，DING W.Research on emergency supply demand forecast methods based on case reasoning[J].Journal of Lanzhou Jiaotong University，2013，32（4）：119-123.
[9] 郭继东，杨月巧.地震应急物资需求预测的模糊案例推理技术[J].中国安全生产科学技术，2017，13（2）：176-180.
GUO J D，YANG Y Q.Study on fuzzy case-based reaso-ning（FCBR） for demand forecast of emergency material in earthquake[J].Journal of Safety Science and Technology，2017，13（2）：176-180.
[10] SCHANK R C.Dynamic memory：a theory of reminding and learning in computers and people[M].New York：Cambridge University Press，1982.
[11] 邹鑫，李远富，邵晨超，等.基于CBR的山区铁路桥梁大高差桥墩设计研究[J].铁道标准设计，2020，64（6）：83-87.
ZOU X，LI Y F，SHAO C C，et al.Research on design of large height difference bridge pier of mountain railway bridge based on CBR[J].Railway Standard Design，2020，64（6）：83-87.
[12] SHEN Y Y，YAN Y，WANG H Z.Recent advances on supervised distance metric learning algorithms[J].Acta Automatica Sinica，2014，40（12）：2673-2686.
[13] 钱静，刘奕，刘呈，等.案例分析的多维情景空间方法及其在情景推演中的应用[J].系统工程理论与实践，2015，35（10）：2588-2595.
QIAN J，LIU Y，LIU C，et al.Study on case analysis and scenario deduction based on multi-dimensional scenario space method[J].Systems Engineering Theory & Practice，2015，35（10）：2588-2595.
[14] 梁曼，徐肖豪，周建，等.基于粗糙集的航路飞行冲突能解脱系统案例检索方法[J].科学技术与工程，2015，15（3）：289-294.
LIANG M，XU X H，ZHOU J，et al.Fuzzy rough set based case retrieval in automated enroute flights conflict resolution CBR system[J].Science Technology and Engineering，2015，15（3）：289-294.
[15] 高天宇，王庆荣，杨磊.粗糙集属性依赖度强化的应急数据挖掘模型[J].计算机工程与应用，2021，57（3）：87-93.
GAO T Y，WANG Q R，YANG L.Data mining model based on attribute dependability enhancement of rough set[J].Computer Engineering and Application，2021，57（3）：87-93.
[16] 王浩玮，陈旭.基于案例推理的旧工业区再生利用方案优选[J].土木工程与管理学报，2019，36（2）：173-178.
WANG H W，CHEN X.Scheme optimization selection of old industrial area recycling based on case reasoning[J].Journal of Civil Engineering and Management，2019，36（2）：173-178.