CN108428024B - Emergency resource allocation decision optimization method for irregular emergency under uncertain information - Google Patents

Emergency resource allocation decision optimization method for irregular emergency under uncertain information Download PDF

Info

Publication number
CN108428024B
CN108428024B CN201810589712.XA CN201810589712A CN108428024B CN 108428024 B CN108428024 B CN 108428024B CN 201810589712 A CN201810589712 A CN 201810589712A CN 108428024 B CN108428024 B CN 108428024B
Authority
CN
China
Prior art keywords
emergency
disaster
rescue
resource allocation
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810589712.XA
Other languages
Chinese (zh)
Other versions
CN108428024A (en
Inventor
刘晋
韩琦
吴政阳
翁腾飞
邓世琴
谯自强
邹瑞
齐东川
庞峥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing University of Science and Technology
Original Assignee
Chongqing University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chongqing University of Science and Technology filed Critical Chongqing University of Science and Technology
Priority to CN201810589712.XA priority Critical patent/CN108428024B/en
Publication of CN108428024A publication Critical patent/CN108428024A/en
Application granted granted Critical
Publication of CN108428024B publication Critical patent/CN108428024B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Computer Security & Cryptography (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to an emergency resource allocation decision optimization method for an unconventional emergency under uncertain information, and belongs to the field of emergency resource management. The method specifically comprises the following steps: acquiring situation factors reflecting the disaster severity of the disaster area and uncertain information data thereof from the actual emergency management application of the unconventional emergency; preprocessing the data and converting the preprocessed data into data information in a unified form; solving the weight value of the considered situation factor by using a guest observation weight determination method; grading the disaster severity of each rescue point in the disaster area by using an improved fuzzy C-means clustering algorithm; under the condition of considering subjective factors that an emergency decision maker recognizes the overall disaster severity of the disaster and recognizes the disaster severity of each rescue point of the disaster, establishing an emergency resource allocation decision optimization model; and determining an emergency resource allocation scheme of each rescue point through a decision optimization model. The invention can establish a reasonable, efficient and fair emergency resource allocation decision scheme through uncertain information data.

Description

Emergency resource allocation decision optimization method for irregular emergency under uncertain information
Technical Field
The invention belongs to the field of emergency resource management, relates to the technical fields of uncertain information processing, decision psychological influence, emergency resource management and the like, and particularly relates to an emergency resource allocation decision optimization method for an unconventional emergency under uncertain information.
Background
Emergency resource management has been one of the research hotspots in the field of emergency management. In the emergency resource allocation method for the unconventional emergency, emergency resources and wounded rescue characteristics of various unconventional emergency are considered, and emergency material allocation methods suitable for different response situations, such as minimum emergency time, minimum transportation cost and corresponding multi-objective allocation optimization methods, are provided. However, in the actual emergency resource allocation process, the information provided by each disaster-suffering point and reflecting the severity of the disaster is often uncertain information data, and the above method lacks consideration of the uncertain information data. Meanwhile, in the emergency resource allocation process, the subjective factors of the emergency decision maker also influence the final emergency resource allocation scheme.
On the basis of considering emergency resource allocation fairness in actual unconventional emergencies, by considering the situation factors of the severity of each disaster-affected point and aiming at uncertain information data of each situation factor, the invention provides an emergency resource allocation decision optimization method based on subjective factors of decision makers, and finally establishes a reasonable, efficient and fair emergency resource allocation decision scheme.
Disclosure of Invention
In view of the above, the present invention provides an unconventional emergency resource allocation decision optimization method under uncertain information, which solves the weight of each situation factor through a passenger weight determination method on the basis of uncertain information data of the considered situation factor, improves the fuzzy C-means clustering analysis method, and classifies the disaster severity of each disaster-affected point. According to the obtained situation factor weights and disaster-affected points grading conditions, an emergency resource allocation decision optimization method based on the overall emergency resource allocation preference of the emergency decision maker to the overall disaster-affected degree and the directional allocation preference of the emergency decision maker to the disaster-affected severity of each disaster-affected point is provided, and finally a reasonable, efficient and fair emergency resource allocation decision scheme is established.
In order to achieve the purpose, the invention provides the following technical scheme:
an emergency resource allocation decision optimization method for an unconventional emergency under uncertain information specifically comprises the following steps:
s1: acquiring situation factors reflecting the disaster severity of the disaster area and uncertain information data thereof from the actual emergency management application of the unconventional emergency;
s2: preprocessing the acquired information data and converting the preprocessed information data into data information in a unified form;
s3: solving the weight value of the considered situation factor by using a guest observation weight determination method;
s4: grading the disaster severity of each rescue point in the disaster area by using an improved fuzzy C-means clustering algorithm;
s5: under the condition of considering subjective factors that an emergency decision maker recognizes the overall disaster severity of the disaster and recognizes the disaster severity of each rescue point of the disaster, establishing an emergency resource allocation decision optimization model;
s6: and determining an emergency resource allocation scheme of each rescue point through a decision optimization model.
Further, in step S2, the preprocessing of the information data is: the method comprises the steps of uniformly converting a determined number, an interval number and a fuzzy value in uncertain information data into a fuzzy form, and converting numerical values of all situation factors into a uniform dimension form through preprocessing; the method specifically comprises the following steps:
s21: if the jth situation factor value of the ith rescue point
Figure BDA00016902533900000221
Is a determined number, which is converted into a fuzzy form
Figure BDA0001690253390000021
Wherein
Figure BDA0001690253390000022
i∈{1,2,…,NEDPs}，j∈{1,2,…,MSFs}，NEDPsNumber of emergency rescue points, MSFsRepresenting the number of selected situation factors;
s22: if the jth of the ith rescue pointValue of situational factor
Figure BDA0001690253390000023
Is a number of intervals
Figure BDA0001690253390000024
Convert it to a blurred form
Figure BDA0001690253390000025
Wherein
Figure BDA0001690253390000026
Figure BDA0001690253390000027
Respectively representing the minimum value and the maximum value of the corresponding interval number;
s23: if the jth situation factor value of the ith rescue point
Figure BDA0001690253390000028
Is a fuzzy number
Figure BDA0001690253390000029
Keeping its blurred form unchanged;
s24: through the steps, unified fuzzy form data of uncertain information data are obtained
Figure BDA00016902533900000210
Wherein
Figure BDA00016902533900000211
Figure BDA00016902533900000212
Figure BDA00016902533900000213
Respectively representing the minimum value, the middle value and the maximum value of a fuzzy number;
s25: obtaining the optimal situation value of each situation factor
Figure BDA00016902533900000214
And worst case value
Figure BDA00016902533900000215
Figure BDA00016902533900000216
Where j ∈ {1,2, …, MSFs}；
S26: converting the data into unified dimensional data by using a normalization formula (1):
Figure BDA00016902533900000217
where k is {1,2,3}, i is {1,2, …, N ∈EDPs}，j∈{1,2,…,MSFs}，
Figure BDA00016902533900000218
Respectively representing the minimum value, the middle value and the maximum value of the fuzzy form of the jth situation factor value of the ith rescue point after normalization;
s27: the preprocessed uncertain information data is
Figure BDA00016902533900000219
Wherein
Figure BDA00016902533900000220
Further, the step S3 specifically includes the following steps:
s31: selecting the jth (j epsilon {1,2, …, M) of each rescue pointSFs}) the context factor feature sets are:
Figure BDA0001690253390000031
calculating the weight value by using the formulas (2) and (3),
Figure BDA0001690253390000032
Figure BDA0001690253390000033
wherein the content of the first and second substances,
Figure BDA0001690253390000034
l∈{1,2,…,MSFs}；
s32: the weight w of each situation factor is obtained through a formula (4) by comprehensively considering the variance and the variation coefficientj
Figure BDA0001690253390000035
Further, the step S4 specifically includes the following steps:
s41: initializing membership matrices
Figure BDA0001690253390000036
Wherein u isk,i∈[0,1]The emergency rescue points are random numbers, wherein c represents that the emergency rescue points are divided into c types according to the disaster severity, namely the number of clustering centers; n is a radical ofEDPsThe number of emergency rescue points satisfies the constraint condition in the formula
Figure BDA0001690253390000037
i＝1,2,...,NEDPs(ii) a Classifying objects
Figure BDA0001690253390000038
Wherein
Figure BDA0001690253390000039
i∈{1,2,…,NEDPs}，
Figure BDA00016902533900000310
Is shown as MSFsColumn essenceA number vector;
s42: calculation of the clustering center by equation (5)
Figure BDA00016902533900000311
k∈{1,2,…,c}；
Figure BDA00016902533900000312
Wherein m is uk,iThe power of (d), representing a ambiguity parameter, m ∈ [1,. varies);
Figure BDA00016902533900000313
representing a membership matrix; i iskRepresenting a k-th cluster center vector;
s43: the clustering center is transformed by equation (6), where k ∈ {1,2, …, c }, j, j' ∈ {1,2, …, M ∈ {1,2, … }SFs}；
Figure BDA0001690253390000041
Then the transformed cluster center
Figure BDA0001690253390000042
k∈{1,2,…,c}；
S44: calculating the objective function according to the formula (7), if the objective function is smaller than a certain artificially set threshold value, or the change amount of the objective function relative to the last objective function value is smaller than a certain artificially set threshold value, stopping the algorithm, and keeping the membership matrix U and the clustering center Ik(ii) a Otherwise, returning to the steps S42 and S43 to obtain a new cluster center
Figure BDA0001690253390000043
k ∈ {1,2, …, c }, and recalculates the new U matrix using equation (8) until the algorithm stops;
Figure BDA0001690253390000044
Figure BDA0001690253390000045
wherein the content of the first and second substances,
Figure BDA0001690253390000046
is the euclidean distance between the kth class center and the ith data point,
Figure BDA0001690253390000047
represents the k-th cluster center vector,
Figure BDA0001690253390000048
represents the t-th cluster center vector,
Figure BDA0001690253390000049
data vector, k, t ∈ 1,2, …, c, i ∈ 1,2, …, N, representing the ith emergency rescue pointEDPs。
Further, the step S5 specifically includes the following steps:
s51: establishing an emergency resource distribution model based on the subjective factors of decision makers according to the relative demand gain of the best and worst situations of the distance between the rescue points
Figure BDA00016902533900000410
Figure BDA00016902533900000411
Figure BDA00016902533900000412
Figure BDA00016902533900000413
Figure BDA00016902533900000414
Figure BDA0001690253390000051
Figure BDA0001690253390000052
Figure BDA0001690253390000053
Wherein the content of the first and second substances,
Figure BDA0001690253390000054
representing the euclidean distance of the ith rescue point from the good situation,
Figure BDA0001690253390000055
representing the worst case distance the Euclidean distance of the best case, α ∈ [0,1 ]]Represents a cutoff factor, gamma represents a global cognitive index of the emergency decision maker for the disaster,
Figure BDA0001690253390000056
the emergency decision maker can recognize the directional cognitive index of the category where the ith rescue point is located,
Figure BDA0001690253390000057
the directional cognitive index k representing the category of the q-th rescue point of the emergency decision makeri,kq∈{1,2},i,q∈{1,2,...,NEDPs}；
S52: according to the emergency resource allocation decision optimization model established in the step S51, the preprocessed uncertain information data V obtained in the step S2 and the weights w of the various situation factors obtained in the step S3 arej(j∈{1,2,…,MSFs}) and grading the disaster severity of each rescue point according to the disaster severity obtained in the step S4Situation determination emergency decision maker global cognition index gamma for disasters and directional cognition index of category where disaster severity of each disaster rescue point is
Figure BDA0001690253390000058
The emergency resource distribution proportion of each rescue point is obtained by inputting a formula (9)
Figure BDA0001690253390000059
RiThe emergency resource distribution proportion of the ith rescue point is shown, i belongs to 1,2, … and NEDPs。
Further, the step S6 specifically includes:
according to the emergency resource allocation decision proportion R of each rescue point obtained in the step S5i(i＝1,...,NEDPs) Determining the emergency resource quantity T allocated to each rescue by using a formula (10)i：
Figure BDA00016902533900000510
Wherein, TCDHFor the total amount of allocable emergency resources, k is equal to 1,2, …, NEDPs，RkAnd distributing proportion of emergency resources of the kth rescue point.
The invention has the beneficial effects that: on the basis of considering uncertain information data of situation factors reflecting disaster severity, the invention establishes an emergency resource allocation decision optimization method based on subjective factors of decision makers, and can establish a reasonable, efficient and fair emergency resource allocation decision scheme through the uncertain information data.
Drawings
In order to make the object, technical scheme and beneficial effect of the invention more clear, the invention provides the following drawings for explanation:
FIG. 1 is a flow chart of a resource allocation decision optimization method according to the present invention;
FIG. 2 is a diagram illustrating a comparison of emergency resource allocation differences of different directional preference indexes of a decision maker.
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The emergency resource allocation decision optimization scheme is used for emergency resource allocation of unconventional emergencies, for example, an infectious disease event occurs in a certain area, limited 10000 vaccines need to be efficiently, reasonably and fairly allocated to 30 emergency points, and uncertain information data of the existing 30 rescue points are shown in table 1.
TABLE 1. uncertain information raw data
Figure BDA0001690253390000061
The advantages of the present invention will be described below with reference to specific embodiments.
As shown in fig. 1, the method for optimizing emergency resource allocation decision of an irregular emergency under uncertain information specifically includes the following steps:
s1: acquiring situation factors reflecting the disaster severity of a disaster area and uncertain information data thereof from an actual emergency management application of an unconventional emergency, wherein the situation factors and the uncertain information data are shown in a table 1;
s2: preprocessing the acquired information data, and converting the preprocessed information data into data information in a unified form, wherein the method specifically comprises the following steps:
s21: if the jth situation factor value of the ith rescue point
Figure BDA0001690253390000071
Is a determined number, which is converted into a fuzzy form
Figure BDA0001690253390000072
Wherein
Figure BDA0001690253390000073
i∈{1,2,…,NEDPs}，j∈{1,2,…,MSFs}，NEDPsNumber of emergency rescue points, MSFsRepresenting the number of selected situation factors;
s22: if the jth situation factor of the ith rescue pointValue of
Figure BDA0001690253390000074
Is a number of intervals
Figure BDA0001690253390000075
Convert it to a blurred form
Figure BDA0001690253390000076
Wherein
Figure BDA0001690253390000077
Figure BDA0001690253390000078
Respectively representing the minimum value and the maximum value of the corresponding interval number;
s23: if the jth situation factor value of the ith rescue point
Figure BDA0001690253390000079
Is a fuzzy number
Figure BDA00016902533900000710
Keeping its blurred form unchanged;
s24: through the steps, unified fuzzy form data of uncertain information data are obtained
Figure BDA00016902533900000711
Wherein
Figure BDA00016902533900000712
Figure BDA00016902533900000713
Respectively representing the minimum value, the middle value and the maximum value of a fuzzy number;
s25: obtaining the optimal situation value of each situation factor
Figure BDA00016902533900000714
And worst case value
Figure BDA00016902533900000715
Figure BDA00016902533900000716
Where j ∈ {1,2, …, MSFs}；
S26: converting the data into unified dimensional data by using a normalization formula (1):
Figure BDA00016902533900000717
where k is {1,2,3}, i is {1,2, …, N ∈EDPs}，j∈{1,2,…,MSFs}，
Figure BDA00016902533900000718
Respectively representing the minimum value, the middle value and the maximum value of the fuzzy form of the jth situation factor value of the ith rescue point after normalization;
s27: the preprocessed uncertain information data is
Figure BDA00016902533900000719
Wherein
Figure BDA00016902533900000720
After step S2 is completed, the converted uncertain information is shown in table 2:
TABLE 2 processed uncertain information data
Figure BDA00016902533900000721
Figure BDA0001690253390000081
S3: solving the weight of the considered situation factor by using a guest observation weight method, which specifically comprises the following steps:
s31: selecting the jth (j epsilon {1,2, …, M) of each rescue pointSFs}) the context factor feature sets are:
Figure BDA0001690253390000082
calculating the weight value by using the formulas (2) and (3),
Figure BDA0001690253390000083
Figure BDA0001690253390000084
wherein the content of the first and second substances,
Figure BDA0001690253390000085
l∈{1,2,…,MSFs}；
s32: the weight w of each situation factor is obtained through a formula (4) by comprehensively considering the variance and the variation coefficientj
Figure BDA0001690253390000091
After step S3 is completed, the weight of each context factor is:
w＝[w1；w2；w3；w4]＝[0.26386；0.25576；0.21237；0.26801]。
s4: the method comprises the following steps of classifying the disaster severity of each rescue point in a disaster area by using an improved fuzzy C-means clustering algorithm, and further comprising the following steps:
s41: initializing membership matrices
Figure BDA0001690253390000092
Wherein u isk,i∈[0,1]Is a random number, NEDPsThe number of emergency rescue points satisfies the constraint condition in the formula
Figure BDA0001690253390000093
i＝1,2,...,NEDPs(ii) a Classifying objects
Figure BDA0001690253390000094
Wherein
Figure BDA0001690253390000095
i∈{1,2,…,NEDPs}，
Figure BDA0001690253390000096
Is shown as MSFsA real number vector of a column;
s42: calculation of the clustering center by equation (5)
Figure BDA0001690253390000097
k ∈ {1,2, …, c }, where c ═ 2;
Figure BDA0001690253390000098
wherein m is uk,iThe power of (d), representing a ambiguity parameter, m ∈ [1,. varies);
Figure BDA0001690253390000099
representing a membership matrix; i iskRepresenting a k-th cluster center vector;
s43: the clustering center is transformed by equation (6), where k ∈ {1,2}, j, j' ∈ {1,2, …, MSFs}；
Figure BDA00016902533900000910
Then the transformed cluster center
Figure BDA00016902533900000911
k∈{1,2}；
S44: according to the formula (7) Calculating an objective function, if the objective function is smaller than a certain artificially set threshold value or the change amount of the objective function relative to the last objective function value is smaller than a certain artificially set threshold value, stopping the algorithm, and keeping the membership degree matrix U and the clustering center I thereofk(ii) a Otherwise, returning to the steps S42 and S43 to obtain a new cluster center
Figure BDA00016902533900000912
k belongs to {1,2}, and a new U matrix is recalculated by using a formula (8) until the algorithm stops;
Figure BDA00016902533900000913
Figure BDA00016902533900000914
wherein d isi,k＝||Ik-ViI is the Euclidean distance between the kth class center and the ith data point, IkDenotes the k-th cluster center vector, ItRepresenting the t-th cluster center vector, ViData vector, k, t ∈ 1,2, …, c, i ∈ 1,2, …, N, representing the ith emergency rescue pointEDPs(ii) a m ∈ 1, and ∞ is a weighting index; and c is the number of cluster centers 2.
After step S4 is completed, the disaster severity level of each rescue point is classified into 2 types, and the less-disaster type defines the directional preference index as
Figure BDA0001690253390000101
The preference index of the serious disaster is defined as
Figure BDA0001690253390000102
And i ≠ j.
S5: under the condition of considering subjective factors of an emergency decision maker for recognizing the overall disaster severity of the disaster and recognizing the disaster severity of each rescue point of the disaster, an emergency resource allocation decision optimization model is established, and the method specifically comprises the following steps:
s51: according to the formula (9), an emergency resource allocation model based on the subjective factors of the decision maker is established according to the relative demand gain of the best and worst situations of the distance between the rescue points, and alpha is made to be 0.4,
Figure BDA0001690253390000103
Figure BDA0001690253390000104
Figure BDA0001690253390000105
Figure BDA0001690253390000106
Figure BDA0001690253390000107
Figure BDA0001690253390000108
Figure BDA0001690253390000109
Figure BDA00016902533900001010
wherein the content of the first and second substances,
Figure BDA00016902533900001011
representing the euclidean distance of the ith rescue point from the good situation,
Figure BDA00016902533900001012
representing the worst case distance the Euclidean distance of the best case, α ∈ [0,1 ]]Representing a cutoff factor, gamma representing a global cognitive index of the emergency decision maker for the disaster, dkiThe emergency decision maker can recognize the directional cognitive index of the category where the ith rescue point is located,
Figure BDA0001690253390000111
the directional cognitive index k representing the category of the q-th rescue point of the emergency decision makeri,kq∈{1,2},i,q∈{1,2,...,NEDPs}；
S52: according to the emergency resource allocation decision optimization model established in the step S51, the preprocessed uncertain information data V obtained in the step S2 and the weights w of the various situation factors obtained in the step S3 arej(j∈{1,2,…,MSFs}) and determining the cognitive index gamma of the decision maker to the overall disaster-suffered severity degree to be 0.5 and the directional cognitive index of the category of the disaster-suffered severity degree of each disaster rescue point according to the disaster-suffered severity degree grading conditions of each disaster rescue point obtained in the step S4
Figure BDA0001690253390000112
[0.9,0.1]，[0.7,0.3]Or [0.5,0.5 ]](kq∈{1,2},q∈{1,2,…,NEDPs}) inputting a formula (9) to obtain the emergency resource distribution proportion of each rescue point
Figure BDA0001690253390000113
RiThe emergency resource distribution proportion of the ith rescue point is shown, i belongs to 1,2, … and NEDPs。
S52: according to the emergency resource allocation decision optimization model established in the step S51, the preprocessed uncertain information data V obtained in the step S2 and the weights w of the various situation factors obtained in the step S3 arej(j∈{1,2,…,MSFs}) and determining the global cognitive index gamma of the emergency decision maker for the disaster and the disaster severity directional cognitive index gamma of the class in which each disaster rescue point is located according to the disaster severity grading conditions of each rescue point obtained in the step S4
Figure BDA0001690253390000114
The emergency resource distribution proportion of each rescue point is obtained by inputting a formula (9)
Figure BDA0001690253390000115
RiThe emergency resource distribution proportion of the ith rescue point is shown, i belongs to 1,2, … and NEDPs。
S6: the decision optimization model is used to obtain a comparison schematic diagram of the emergency resource allocation differences under different directional preference indexes of the decision maker shown in fig. 2 and an emergency resource allocation scheme under different directional preference indexes of the decision maker shown in table 3.
TABLE 3 Emergency resource Allocation schemes under different Directional preference indicators for the decision maker
Figure BDA0001690253390000116
As can be seen in fig. 2: if the rescue points are classified into two types of serious disaster and non-serious disaster according to the disaster severity of the disaster, the larger the difference of the directional cognition indexes of the disaster severity between the two types is, the larger the emergency resource proportion allocated to each rescue point is, so that the emergency decision maker has certain influence on the allocation of the emergency resource proportion corresponding to the difference of the directional cognition indexes of the disaster severity between the different types.
Finally, it is noted that the above-mentioned preferred embodiments illustrate rather than limit the invention, and that, although the invention has been described in detail with reference to the above-mentioned preferred embodiments, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the invention as defined by the appended claims.

Claims (5)

1. An emergency resource allocation decision optimization method for unconventional emergency under uncertain information is characterized by comprising the following steps: the method specifically comprises the following steps:
s1: acquiring situation factors reflecting the disaster severity of the disaster area and uncertain information data thereof from the actual emergency management application of the unconventional emergency;
s2: preprocessing the acquired information data and converting the preprocessed information data into data information in a unified form;
s3: solving the weight value of the considered situation factor by using a guest observation weight determination method;
s4: grading the disaster severity of each rescue point in the disaster area by using an improved fuzzy C-means clustering algorithm;
s5: under the condition of considering subjective factors of an emergency decision maker for recognizing the overall disaster severity of the disaster and recognizing the disaster severity of each rescue point of the disaster, an emergency resource allocation decision optimization model is established, and the method specifically comprises the following steps:
s51: relative demand gain R according to best and worst case distance of rescue pointsiEstablishing an emergency resource allocation model based on subjective factors of decision makers as follows:
Figure FDA0003037422690000011
Figure FDA0003037422690000012
Figure FDA0003037422690000013
Figure FDA0003037422690000014
Figure FDA0003037422690000015
Figure FDA0003037422690000016
Figure FDA0003037422690000017
Figure FDA0003037422690000018
wherein the content of the first and second substances,
Figure FDA0003037422690000019
representing the euclidean distance of the ith rescue point from the good situation,
Figure FDA00030374226900000110
representing the worst case distance the Euclidean distance of the best case, α ∈ [0,1 ]]Represents a cutoff factor, gamma represents a global cognitive index of the emergency decision maker for the disaster,
Figure FDA0003037422690000021
respectively representing the minimum value, the middle value and the maximum value of the fuzzy form of the jth situation factor value of the ith rescue point after normalization,
Figure FDA0003037422690000022
the directional cognitive index of the emergency decision maker to the category of the ith rescue point is represented,
Figure FDA0003037422690000023
the directional cognitive index k representing the category of the q-th rescue point of the emergency decision makeri,kq∈{1,2},i,q∈{1,2,...,NEDPs}；
S52: according to the emergency resource allocation decision optimization model established in the step S51, the preprocessed uncertain information data V obtained in the step S2 and the weights w of the situation factors obtained in the step S3 are usedj(j∈{1,2,…,MSFs}) and determining the cognitive index gamma of the decision maker for the overall disaster-suffered severity degree and the directional cognitive index of the category of the disaster-suffered severity degree of each disaster rescue point according to the disaster-suffered severity degree grading conditions of each disaster rescue point obtained in the step S4
Figure FDA0003037422690000024
And
Figure FDA0003037422690000025
inputting a formula (1) to obtain the relative demand gain of each rescue point;
s6: and determining an emergency resource allocation scheme of each rescue point through a decision optimization model.
2. The method for optimizing emergency resource allocation decision-making for irregular emergencies without information determination according to claim 1, wherein: in step S2, the preprocessing of the information data is: the method comprises the steps of uniformly converting a determined number, an interval number and a fuzzy value in uncertain information data into a fuzzy form, and converting numerical values of all situation factors into a uniform dimension form through preprocessing; the method specifically comprises the following steps:
s21: if the jth situation factor value of the ith rescue point
Figure FDA0003037422690000026
Is a determined number, which is converted into a fuzzy form
Figure FDA0003037422690000027
Wherein
Figure FDA0003037422690000028
NEDPsNumber of emergency rescue points, MSFsRepresenting the number of selected situation factors;
s22: if the jth situation factor value of the ith rescue point
Figure FDA0003037422690000029
Is a number of intervals
Figure FDA00030374226900000210
Convert it to a blurred form
Figure FDA00030374226900000211
Wherein
Figure FDA00030374226900000212
Figure FDA00030374226900000213
Respectively representing the minimum value and the maximum value of the corresponding interval number;
s23: if the jth situation factor value of the ith rescue point
Figure FDA00030374226900000214
Is a fuzzy number
Figure FDA00030374226900000215
Keeping its blurred form unchanged;
s24: through the steps, unified fuzzy form data of uncertain information data are obtained
Figure FDA00030374226900000216
Wherein
Figure FDA00030374226900000217
Figure FDA00030374226900000218
Figure FDA00030374226900000219
Respectively representing the minimum value, the middle value and the maximum value of a fuzzy number;
s25: obtaining the optimal situation value of each situation factor
Figure FDA00030374226900000220
And worst case value
Figure FDA00030374226900000221
Figure FDA0003037422690000031
Where j ∈ {1,2, …, MSFs}；
S26: converting the data into unified dimensional data by using a normalization formula (2):
Figure FDA0003037422690000032
where k is {1,2,3}, i is {1,2, …, N ∈EDPs}，j∈{1,2,…,MSFs}，
Figure FDA0003037422690000033
Respectively representing the minimum value, the middle value and the maximum value of the fuzzy form of the jth situation factor value of the ith rescue point after normalization;
s27: the preprocessed uncertain information data is
Figure FDA0003037422690000034
Wherein
Figure FDA0003037422690000035
3. The method for optimizing emergency resource allocation decision-making for irregular emergencies without information determination according to claim 2, wherein: the step S3 specifically includes the following steps:
s31: selecting the jth (j epsilon {1,2, …, M) of each rescue pointSFs}) the context factor feature sets are:
Figure FDA0003037422690000036
calculating the weight value by using the formulas (3) and (4),
Figure FDA0003037422690000037
Figure FDA0003037422690000038
wherein the content of the first and second substances,
Figure FDA0003037422690000039
s32: the weight w of each situation factor is obtained through a formula (5) by comprehensively considering the variance and the variation coefficientj
Figure FDA00030374226900000310
4. The method for optimizing emergency resource allocation decision-making for irregular emergencies without information determination according to claim 3, wherein: the step S4 specifically includes the following steps:
s41: initializing membership matrices
Figure FDA00030374226900000311
Wherein u isk,i∈[0,1]The emergency rescue points are random numbers, wherein c represents that the emergency rescue points are divided into c types according to the disaster severity, namely the number of clustering centers; n is a radical ofEDPsThe number of emergency rescue points satisfies the constraint condition in the formula
Figure FDA0003037422690000041
Classifying objects
Figure FDA0003037422690000042
Wherein
Figure FDA0003037422690000043
Figure FDA0003037422690000044
Is shown as MSFsA real number vector of a column;
s42: calculation of clustering center by equation (6)
Figure FDA0003037422690000045
Figure FDA0003037422690000046
Wherein m is uk,iThe power of (d), representing the ambiguity parameter, m ∈ [1, ∞);
Figure FDA0003037422690000047
representing a membership matrix; i iskRepresenting a k-th cluster center vector;
s43: the clustering center is transformed by equation (7), where k ∈ {1,2, …, c }, j, j' ∈ {1,2, …, M ∈ {1,2, … }SFs}；
Figure FDA0003037422690000048
Then the transformed cluster center
Figure FDA0003037422690000049
S44: calculating the objective function according to the formula (8), if the objective function is smaller than a certain artificially set threshold value, or the change amount of the objective function relative to the last objective function value is smaller than a certain artificially set threshold value, stopping the algorithm, and keeping the membership matrix U and the clustering center Ik(ii) a Otherwise, returning to the steps S42 and S43 to obtain a new cluster center
Figure FDA00030374226900000410
And recalculate the new U matrix with equation (9) until the algorithm stops;
Figure FDA00030374226900000411
Figure FDA00030374226900000412
wherein the content of the first and second substances,
Figure FDA00030374226900000413
is the euclidean distance between the kth class center and the ith data point,
Figure FDA00030374226900000414
represents the k-th cluster center vector,
Figure FDA00030374226900000415
represents the t-th cluster center vector,
Figure FDA00030374226900000416
data vector representing the ith emergency rescue point, k, te {1,2, …, c }, i e {1,2, …, N }EDPs}。
5. The method for optimizing emergency resource allocation decision-making for irregular emergencies without information determination according to claim 4, wherein: the step S6 specifically includes:
according to the relative demand gain R of each rescue point obtained in the step S5i(i＝1,...,NEDPs) Determining the emergency resource quantity T allocated to each rescue by using a formula (10)i：
Figure FDA0003037422690000051
Wherein, TCDHFor the total amount of allocable emergency resources, k ∈ {1,2, …, NEDPs}，RkThe relative demand gain for the kth rescue point.
CN201810589712.XA 2018-06-08 2018-06-08 Emergency resource allocation decision optimization method for irregular emergency under uncertain information Active CN108428024B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810589712.XA CN108428024B (en) 2018-06-08 2018-06-08 Emergency resource allocation decision optimization method for irregular emergency under uncertain information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810589712.XA CN108428024B (en) 2018-06-08 2018-06-08 Emergency resource allocation decision optimization method for irregular emergency under uncertain information

Publications (2)

Publication Number Publication Date
CN108428024A CN108428024A (en) 2018-08-21
CN108428024B true CN108428024B (en) 2021-06-15

Family

ID=63164781

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810589712.XA Active CN108428024B (en) 2018-06-08 2018-06-08 Emergency resource allocation decision optimization method for irregular emergency under uncertain information

Country Status (1)

Country Link
CN (1) CN108428024B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110046760B (en) * 2019-04-10 2022-06-14 武汉理工大学 Medical rescue point addressing method considering urgency of disaster-affected point demand
CN110120150B (en) * 2019-04-16 2021-05-11 东南大学 Configuration method of obstacle removing mechanical equipment of expressway network
CN110503320B (en) * 2019-08-07 2023-04-07 卓尔智联(武汉)研究院有限公司 Vaccine resource allocation method, device and storage medium
CN111275327B (en) * 2020-01-19 2024-06-07 深圳前海微众银行股份有限公司 Resource allocation method, device, equipment and storage medium
CN111582595B (en) * 2020-05-13 2023-09-26 内蒙古工业大学 Emergency decision method and device for natural disasters and electronic equipment
CN112633718A (en) * 2020-12-28 2021-04-09 航天科工网络信息发展有限公司 Emergency material grading method for public health emergency based on evidence reasoning

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5011408B2 (en) * 2010-02-22 2012-08-29 株式会社日立製作所 Communication apparatus and communication system
CN104504544A (en) * 2014-11-26 2015-04-08 沈阳建筑大学 Decision-making method of uncertain emergency material distribution
CN107193990A (en) * 2017-05-31 2017-09-22 民政部国家减灾中心 The dead population estimation method and apparatus of earthquake disaster based on history case information

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5011408B2 (en) * 2010-02-22 2012-08-29 株式会社日立製作所 Communication apparatus and communication system
CN104504544A (en) * 2014-11-26 2015-04-08 沈阳建筑大学 Decision-making method of uncertain emergency material distribution
CN107193990A (en) * 2017-05-31 2017-09-22 民政部国家减灾中心 The dead population estimation method and apparatus of earthquake disaster based on history case information

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于区间情境理论的军民联合救援应急物资分配方法;庞国楹等;《军事交通学院学报》;20180531;第20卷(第5期);全文 *
应急医疗物资直升机与车辆联合运送优化;阮俊虎;《中国博士学位论文全文数据库》;20151015(第10期);全文 *

Also Published As

Publication number Publication date
CN108428024A (en) 2018-08-21

Similar Documents

Publication Publication Date Title
CN108428024B (en) Emergency resource allocation decision optimization method for irregular emergency under uncertain information
CN106923846B (en) Psychological stress assessment and feedback system
CN109684922A (en) A kind of recognition methods based on the multi-model of convolutional neural networks to finished product dish
CN110245783B (en) Short-term load prediction method based on C-means clustering fuzzy rough set
CN111046926B (en) Computer vision image classification integrated learning method
CN114203284A (en) Emergency blood dispatching method
CN110930030B (en) Doctor skill level rating method
CN109377064B (en) Urban multi-reservoir water source water quantity distribution method based on comprehensive evaluation information
CN114219228A (en) Stadium evacuation evaluation method based on EM clustering algorithm
CN111914900B (en) User electricity utilization mode classification method
CN108898271A (en) A kind of non-base price commercial bid evaluation method based on TOPSIS method
CN116933139A (en) Village classification method integrating membership value, grade and sequence
CN116433679A (en) Inner ear labyrinth multi-level labeling pseudo tag generation and segmentation method based on spatial position structure priori
CN110009024A (en) A kind of data classification method based on ID3 algorithm
CN115392582A (en) Crop yield prediction method based on incremental fuzzy rough set attribute reduction
TWI599896B (en) Multiple decision attribute selection and data discretization classification method
CN110097126B (en) Method for checking important personnel and house missing registration based on DBSCAN clustering algorithm
CN111933226A (en) Artificial intelligence material screening method based on classification model
CN113128789A (en) Urban road surface collapse prevention method and system based on probability prediction and storage medium
CN112785004A (en) Greenhouse intelligent decision-making method based on rough set theory and D-S evidence theory
CN111563665A (en) Voltage quality management method
CN109214459A (en) A kind of clustering method of geography suitability
CN109145967B (en) Diagnosis method for flood full-factor variation
CN115859223A (en) Multi-source data industry fusion analysis method and system
CN107330442A (en) In a kind of combination class between compactness and class separation property increment fuzzy clustering method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant