CN117370905B - Method for classifying comprehensive passenger transport hubs facing abnormal events - Google Patents
Method for classifying comprehensive passenger transport hubs facing abnormal events Download PDFInfo
- Publication number
- CN117370905B CN117370905B CN202311657163.2A CN202311657163A CN117370905B CN 117370905 B CN117370905 B CN 117370905B CN 202311657163 A CN202311657163 A CN 202311657163A CN 117370905 B CN117370905 B CN 117370905B
- Authority
- CN
- China
- Prior art keywords
- comprehensive
- passenger transport
- comprehensive passenger
- hub
- hubs
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims abstract description 68
- 230000008569 process Effects 0.000 claims abstract description 7
- 230000005484 gravity Effects 0.000 claims description 14
- 238000010606 normalization Methods 0.000 claims description 9
- 230000005251 gamma ray Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000005180 public health Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 241000531116 Blitum bonus-henricus Species 0.000 description 1
- 235000008645 Chenopodium bonus henricus Nutrition 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000029305 taxis Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention belongs to the technical field of traffic planning, and discloses a classification method of an abnormal event-oriented comprehensive passenger transport hub. The classification includes the following steps: s1, acquiring the number of comprehensive passenger transport hubs and classification indexes of the comprehensive passenger transport hubs under abnormal events, and acquiring a comprehensive feature matrix of the comprehensive passenger transport hubs; s2, calculating the distance between comprehensive passenger transport hubs by using the comprehensive feature matrix, so that all the comprehensive passenger transport hubs are divided into P major classes; s3, determining influence factors of decision makers with different identities on classification of the comprehensive passenger transport hubs, constructing maximum characteristic values corresponding to the mutual influence of all influence factors in each comprehensive passenger transport hub, dividing each major class into a plurality of subdivision subclasses, so as to realize subdivision of each major class, and thus realizing the classification process of all the comprehensive passenger transport hubs. The invention solves the problem that the classification method of the comprehensive passenger transport hub facing the abnormal event lacks and considers different decision makers.
Description
Technical Field
The invention belongs to the technical field of traffic planning, and particularly relates to a classification method of an abnormal event-oriented comprehensive passenger transport hub.
Background
The comprehensive passenger transport hub is an important component of an urban traffic network, comprises a collection node of various traffic modes such as airports, subways, buses, trains and the like, and is a city traffic hub and a people stream collecting and distributing place. However, in the event of various abnormal events, such as weather disasters, large-scale activities, equipment failures, safety accidents, etc., problems may occur in the operation of the passenger transportation hub, and the passenger flow may fluctuate greatly. In this context, how to accurately predict and cope with the impact of these unusual events on passenger hubs becomes an important issue that operators and decision makers need to solve. One of the key challenges is that different passenger hubs may have different characteristics and passenger flow patterns, and the response to the same anomaly may also be different. For example, a passenger hub located in a business may experience a surge in traffic during holidays or activities, while a passenger hub located in a residential area may experience a decrease in traffic. Therefore, simply considering all passenger hubs as the same category, the ideal effect is often not achieved using the same predictive model.
Under the background of artificial intelligence and big data, a large amount of data is needed to improve the accurate analysis and prediction of the running state of the comprehensive passenger transportation hub under the abnormal event. Thereby helping the passenger transport hub to make countermeasures in advance, such as adjusting operation strategies, optimizing passenger flow management, and the like.
CN202010258094.8 discloses a method for predicting passenger demand of a railway junction based on travel space classification, which divides traffic demand into three parts of urban external traffic demand, urban internal traffic demand and transit traffic demand according to passenger travel space characteristics of the railway junction, and provides data support for junction platform layout, operation organization, station body design and the like, reduces operation cost and avoids excessive construction. However, the lack of a comprehensive passenger transportation hub classification index system and method facing the abnormal event at present leads to inaccurate evaluation of traffic flow change rules in the comprehensive passenger transportation hub under the abnormal event, undefined abnormal event response strategy and poor coping effectiveness, and even can negatively affect the travel decision of the public and the public image of the passenger transportation hub. Meanwhile, when different decision makers classify the comprehensive passenger transport hub, the factors considered are different.
Therefore, the invention provides a classification method of the comprehensive passenger transport hub facing the abnormal event.
Disclosure of Invention
Aiming at the defects or improvement demands of the prior art, the invention provides a classification method of the comprehensive passenger transport hub facing the abnormal event, which solves the problems that the classification method of the comprehensive passenger transport hub facing the abnormal event is lack and different decision makers are not considered.
In order to achieve the above object, according to the present invention, there is provided a classification method of an integrated passenger transportation hub for an abnormal event, the classification comprising the steps of:
s1, acquiring the number of comprehensive passenger transport hubs and classification indexes of the comprehensive passenger transport hubs under abnormal events, constructing a feature matrix relation of each classification index, calculating a feature matrix normalization value corresponding to each classification index of each comprehensive passenger transport hub, and taking a matrix formed by the feature matrix normalization values of all the classification indexes as a comprehensive feature matrix of the comprehensive passenger transport hubs;
s2, calculating the distance between comprehensive passenger transport hubs by using the comprehensive feature matrix, so that all the comprehensive passenger transport hubs are divided into P major classes;
s3, determining influence factors of decision makers with different identities on classification of the comprehensive passenger transport hubs, constructing maximum characteristic values corresponding to the mutual influence of all influence factors in each comprehensive passenger transport hub, arranging the maximum characteristic values in each class in sequence, and equally dividing the arranged comprehensive passenger transport hubs into a plurality of subdivision subclasses, so that subdivision of each major class is realized, and the classification process of all the comprehensive passenger transport hubs is realized.
Further preferably, in step S2, all the comprehensive passenger hubs are divided into P major classes, specifically according to the following steps:
s21, selecting initial P comprehensive passenger transport hubs from all the comprehensive passenger transport hubs as central points of classes;
s22, calculating the distance between each comprehensive passenger transportation junction distance and each central point by utilizing the comprehensive feature matrix, and dividing the current comprehensive passenger transportation junction into the class of the central point corresponding to the minimum distance value;
s23, repeating the step S22 until the classification of all the comprehensive passenger transport hubs is completed, dividing all the comprehensive passenger transport hubs into P classes, and calculating the sum of the distances from each comprehensive passenger transport hub to the center point of the class to which each comprehensive passenger transport hub belongs to obtain the sum of the distances.
Further preferably, after step S23, further optimization of the divided P-class is further required, which specifically includes the following steps:
s24, calculating the average value of all comprehensive passenger transport hub comprehensive feature matrixes in each class, and taking the average value as a new central point;
s25, returning to the step S22 until the preset iteration times are reached, comparing the distance sum obtained in all the iteration times, wherein the center point corresponding to the minimum value of the distance sum and the divided class are taken as the final required divided class.
Further preferably, in step S1, the classification index includes a geographical location, a surrounding environment, line information, average passenger flow volume, service time, number of stations, historical event, facility service, and special date passenger flow volume.
Further preferably, in step S22, the distance between each comprehensive passenger junction distance and each central point is calculated according to the following formula:
wherein,representing the distance between the ith center point in the ith comprehensive passenger junction distance P class; />The weight coefficient corresponding to the ia index; />、/>、/>、/>、/>、/>、/>、/>、/>The normalized values of 9 indexes of the ith comprehensive passenger transport hub are respectively represented, and are sequentially geographic position, surrounding environment, line information, average passenger flow, service time, station number, historical event, facility service and special-date passenger flow; />、/>、、/>、/>、/>、/>、/>、/>The normalized values of 9 indexes corresponding to the s-th central point in the P-type comprehensive passenger transport hub are sequentially geographic position, surrounding environment, line information, average passenger flow, service time, station number, historical event, facility service and special date passenger flow.
Further preferably, in step S3, the influencing factors are economic status, population structure, travel habits and city planning.
Further preferably, in step S3, the maximum feature value is obtained according to the following steps:
s31, constructing a correlation matrix of influence factors corresponding to a comprehensive passenger transportation hub for the comprehensive passenger transportation hub, and then normalizing the correlation matrix to obtain a normalized correlation matrix;
s32, calculating a weight vector by using the standardized relation matrix;
s33, calculating the maximum eigenvector of the interrelation matrix;
s34, calculating a corresponding maximum characteristic value by using the maximum characteristic vector.
Further preferably, in step S31, the normalized relationship matrix is performed as follows:
；
；
；
；
；
wherein,is a standardized relationship matrix; />Representing the specific gravity of the mth element relative to the nth element, wherein the economic status, the population structure, the travel habit and the city plan correspond to 1,2,3 and 4 respectively; />Is the sum of the specific gravities of all elements relative to element 1; />Is the sum of the specific gravities of all elements relative to the 2 nd element; />Is the sum of the specific gravities of all elements relative to the 3 rd element; />Is the sum of the specific gravities of all elements relative to the 4 th element.
Further preferably, in step S32, the weight vector is performed as follows:
；
the maximum eigenvector is performed as follows:
wherein,is->Is a weight vector of (2); />Is the maximum feature vector.
Further preferably, in step S34, the maximum feature value is calculated according to the following relation:
wherein,representation->Summing all elements in the list; />Summing all elements in the representation; />Is the maximum eigenvalue.
In general, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects:
1. the invention provides an abnormal event-oriented comprehensive passenger transportation hub classification index system, which simultaneously considers geographic positions, surrounding environments, line information, average passenger flow, service time, the number of stations, historical events, facility services and special-date passenger flow, has strong comprehensiveness, can provide method support for comprehensive passenger transportation hub characteristic analysis under abnormal events, and can comprehensively evaluate and predict traffic flow and operation state of the passenger transportation hub under abnormal events;
2. the invention provides a classification method of an abnormal event-oriented comprehensive passenger transport hub, which adopts the comprehensive passenger transport hub classification index system, quantifies the difference of various classification results and is more scientific; meanwhile, the method has small calculated amount, is easy to operate, and is convenient for non-professional personnel participating in comprehensive passenger transport junction management to use and popularize, the comprehensive passenger transport junctions are classified, and analysis results of different comprehensive passenger transport junctions of the same class under abnormal events can be popularized to other comprehensive passenger transport junctions, so that the effectiveness and rationality of decision making are improved;
3. the invention provides a comprehensive passenger transportation hub classification method suitable for abnormal events of different identity decision makers, which is based on technical angle analysis of comprehensive passenger transportation hub classification results, and is characterized in that four factors including economic conditions, population structures, travel habits and city planning are considered, a correlation matrix formed by the four factors is constructed, the maximum eigenvector and the maximum eigenvalue of the correlation matrix are calculated, and consistency evaluation of the results is carried out to realize refinement classification of the comprehensive passenger transportation hub. The method comprehensively considers the attention indexes of different decision makers to the comprehensive passenger transport hub classification, improves the rationality of the decision process, and improves the application range of the comprehensive passenger transport hub classification method.
Drawings
FIG. 1 is a flow chart of an integrated passenger hub classification method for exception oriented events constructed in accordance with a preferred embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
As shown in fig. 1, a classification method of an integrated passenger transportation hub facing to an abnormal event includes the following steps:
in the invention, the comprehensive passenger transport hub is various in types, and specifically comprises:
(1) Can provide an integrated passenger transport hub for various traffic modes such as airports, high-speed or common-speed train stations, bus stations and the like which are communicated with an international airline. Such as Beijing capital International airport, shanghai Pudong International airport, etc.
(2) The comprehensive passenger transport hub is mainly used for long-distance travel in China and can provide comprehensive passenger transport hubs for transportation modes such as planes, trains, coaches and the like. Such as major airports and train stations in each province city.
(3) Comprehensive passenger hubs, which primarily serve travel needs in and around provinces, typically include train stations and bus stops.
(4) The comprehensive passenger transport hub mainly serves the urban internal traffic demand and comprises subway stations, urban bus stations, taxis and the like. Such as Beijing, guangzhou, east, shenzhen north, etc.
(5) Typically located in suburban areas or at the edges of cities, and primarily serve comprehensive passenger transport hubs of urban and suburban area commuting needs, including railway stations, subway stations, bus stations, and the like.
(6) Usually located in villages and towns, and mainly serve comprehensive passenger transport hubs, including bus stops and bus stops, for towns and regional travel needs.
(7) Comprehensive passenger hubs that serve a particular need, such as docking stations for tourist attractions, large-scale, mobile temporary passenger hubs, etc.
In the comprehensive passenger transport hub, when an abnormal event occurs, mutual reference possibility exists among different types of comprehensive passenger transport hubs. Therefore, the comprehensive passenger transport hub is required to be faced, a hub classification index system is provided, and when abnormal events occur, data among hubs can be used for revealing the passenger flow evolution rule of the target comprehensive passenger transport hub in a quantitative evaluation mode.
In the present invention, the abnormal event includes: weather factors, public health events, traffic accidents, equipment failures, policy factors, social events, and the like.
Weather factors: severe weather conditions, such as storms, haze, snow storms, typhoons, etc., may lead to flight cancellation, train outages, road closure;
public health event: such as epidemic diseases, etc., can lead to people reducing travel;
traffic accident: accidents with vehicles such as trains, airplanes, etc. may cause temporary disruption of the traffic route;
equipment failure: failure of equipment such as radar systems at airports, signaling systems at train stations, etc. may cause temporary interruption of traffic services;
policy factors: policies such as traffic restriction and adjustment of bus routes may affect the travel habits of people, thereby affecting the passenger flow;
social events: large sporting events, music knots, concerts, etc. may cause significant amounts of people to rush to or avoid certain areas.
S1, acquiring comprehensive feature matrixes corresponding to all comprehensive passenger transport hubs
1. The method for determining the comprehensive passenger transportation hub classification index under the abnormal event comprises the following steps of: geographic location, ambient environment, line information, average traffic, time of service, number of stations, historical events, facility services, special date traffic.
2. For each comprehensive passenger transportation hub classification index, a corresponding feature matrix needs to be established so as to conduct quantitative calculation analysis. The construction process of the feature matrix corresponding to each index is as follows:
2.1 geographic location
Taking the distance between the comprehensive passenger transport hub and the city center into consideration, and establishing all N geographic position feature matrices of the comprehensive passenger transport hubs，/>，dl i Representing the distance of the ith integrated passenger hub from the center of the city;
will bePerforming normalization operation to obtain a normalized geographic position feature matrix:
；
a normalized value representing the distance of the ith integrated passenger hub from the center of the city;
2.2 ambient environment
Taking the distance between the comprehensive passenger transport hub and the commercial area into consideration, and establishing all N geographic position feature matrices of the comprehensive passenger transport hubs，/>，/>Representing the distance of the ith integrated passenger hub from the business district;
will bePerforming normalization operation to obtain a normalized geographic position feature matrix:
；
；
a normalized value representing an ith integrated passenger hub distance from the business district distance;
2.3 Circuit information
Considering the type of traffic mode of the comprehensive passenger transport hub, and establishing all N comprehensive passenger transport hub line information feature matrixes，/>，/>Representing the type of transportation mode of the ith comprehensive passenger transport hub;
will beCarrying out normalization operation to obtain a normalized line information feature matrix:
;
;
a normalized value representing an ith integrated passenger hub transportation means type;
2.4 average passenger flow volume
Considering the average passenger flow volume of the comprehensive passenger transport hubs, and establishing an average passenger flow volume characteristic matrix of all N comprehensive passenger transport hubs，/>，/>Representing the average passenger flow volume of the ith integrated passenger hub;
will beCarrying out normalization operation to obtain a normalized average passenger flow characteristic matrix:
；
；
a normalized value representing the average passenger flow of the ith integrated passenger hub.
2.5 service time
Taking the operation time of the comprehensive passenger transport hub into consideration, and establishing all N comprehensive passenger transport hub service time feature matrixes，/>，/>Representing the service time of the ith integrated passenger transport hub;
will bePerforming normalization operation to obtain a normalized service time feature matrix:
；
；
a normalized value representing the ith integrated passenger hub service time.
2.6 number of stations
Considering the number of stations of the comprehensive passenger transport hub, and establishing a total N number of comprehensive passenger transport hub station number feature matrices，/>，/>Indicating the number of stations of the ith integrated passenger transport hub;
；
；
a normalized value representing the number of ith integrated passenger hub stations.
2.7 historical events
Considering the historical events of the comprehensive passenger transport hub, mainly referring to the types and the quantity of the emergent events, and establishing all N historical event feature matrixes of the comprehensive passenger transport hub，/>，/>Representing historical events of an ith integrated passenger hub;
；
；
a normalized value representing an ith integrated passenger hub historical event.
2.8 facility services
Considering the type and quantity of facility services of the comprehensive passenger transport hub, and establishing all N comprehensive passenger transport hub facility service feature matrixes，/>，/>Facility representing an ith integrated passenger transport hubA service;
；
；
representing a normalized value for the ith integrated passenger hub facility service.
2.9 special date passenger flow volume
Taking actual passenger flow of comprehensive passenger transport hubs under sudden events into consideration, and establishing special-date passenger flow characteristic matrices of all N comprehensive passenger transport hubs，/>，/>Representing special date traffic for an ith integrated passenger hub;
；
；
a normalized value representing the special date passenger flow of the ith integrated passenger hub.
S2, dividing all comprehensive passenger transport hubs into P major classes
In the following, all N comprehensive passenger transport hubs are divided into P major classes according to the 9 indexes, and the 9 indexes corresponding to the comprehensive passenger transport hubs in each major class have higher similarity, namely the data in the plurality of comprehensive passenger transport hubs corresponding to each class can be used for common analysis, so that the purpose of expanding the data of a single comprehensive passenger transport hub is achieved. The classification of the comprehensive passenger transport hubs of P major classes can be based on the following table:
；
the specific partitioning method of the comprehensive passenger transport hub under the abnormal event is as follows:
3. randomly selecting P comprehensive passenger transport hubs as the dividing standard of P major classes; clustering by distance
4. Taking the 1 st P1 in the P-class comprehensive passenger transport hub as an example,
the comprehensive matrix formed by 9 indexes corresponding to P1 is as follows:
the comprehensive feature matrix of the 9 indexes corresponding to the 1 st comprehensive passenger transport hub is as follows:
the distance between the 1 st comprehensive passenger transport hub and P1 is calculated as follows:
；
the weight coefficient corresponding to the ia index.
5. Repeating the step 4, and calculating the distance between the 1 st comprehensive passenger transportation junction and all P-type comprehensive passenger transportation junctions to obtain a distance matrix corresponding to the 1 st comprehensive passenger transportation junction:
；
in the method, in the process of the invention,refers to the distance between the 1 st comprehensive passenger transportation hub and the i-th comprehensive passenger transportation hub in the P-type comprehensive passenger transportation hubs;
comparison ofFinding out the minimum value in all elements and the pk value corresponding to the minimum value, namely indicating that the 1 st comprehensive passenger transport hub needs to be divided into the k-th class;
6. calculating the distance between the comprehensive passenger transport hub and the center of the comprehensive passenger transport hub of all P classes，
Wherein,representing the distance between the ith center point in the ith comprehensive passenger junction distance P class; />The weight coefficient corresponding to the ia index; />、/>、/>、/>、/>、/>、/>、/>、/>The normalized values of 9 indexes of the ith comprehensive passenger transport hub are respectively represented, and are sequentially geographic position, surrounding environment, line information, average passenger flow, service time, station number, historical event, facility service and special-date passenger flow; />、/>、、/>、/>、/>、/>、/>、/>The normalized values of 9 indexes corresponding to the s-th central point in the P-type comprehensive passenger transport hub are sequentially geographic position, surrounding environment, line information, average passenger flow, service time, station number, historical event, facility service and special date passenger flow.
And 5, repeating the step, and calculating to obtain the minimum value of the distance between all passenger transport hubs and all P-class comprehensive passenger transport hubs, so that all comprehensive passenger transport hubs can be divided into P-class.
7. Calculating a distance matrix between all comprehensive passenger transportation hub distance matrices and the first class comprehensive passenger transportation hub center P1:
；
NA1 represents the number of class 1 integrated passenger hubs;
calculating a distance matrix between all comprehensive passenger transportation hub distance matrices and all P-type comprehensive passenger transportation hub centers Pi:
；
ib=1，2，…，NAci。
NAci represents the number of c class i integrated passenger hubs.
Calculating the sum of all distances:
the method for adjusting the central position of the P1 type comprehensive passenger transportation hub comprises the following steps:
in the P1 type comprehensive passenger transport hubs, the number of the comprehensive passenger transport hubs is NP1, and index feature matrixes corresponding to the comprehensive passenger transport hubs are sequentially as follows:，/>an index feature matrix of the id-th comprehensive passenger transport hub belonging to the P1 class comprehensive passenger transport hub is represented;
calculating the center of the P1 type comprehensive passenger transport hub, namely a P1 index matrix after position adjustment and update:
similarly, calculating an updated position index matrix of the P2-PP comprehensive passenger transportation hub center, namely, an index matrix after position adjustment and update:
。
9. sequentially calculating index feature matrix of 1 st comprehensive passenger transport hubAnd index matrixForming a distance matrix:
；
comparison ofFind the minimum value, the corresponding +.>A value indicating that the 1 st integrated passenger hub needs to be divided into +.>Class;
10. repeating the above steps to obtain the index feature matrix and index feature matrix of all comprehensive passenger transport hubsThe distance matrix is formed, the minimum value of the distance corresponding to all the comprehensive passenger transport hubs is calculated, and all the comprehensive passenger transport hubs are divided into P major classes;
11. calculating the distance matrix between the index feature matrix of all the comprehensive passenger transport hubs belonging to the class 1 and the class 1 comprehensive passenger transport hub center P1,
；
NN1 represents the number of class 1 integrated passenger hubs;
12. calculating a distance matrix between all comprehensive passenger transportation hub index feature matrices belonging to Pi types and a Pi center of an ei type comprehensive passenger transportation hub in all P type comprehensive passenger transportation hubs:，ei=1,2，…,NNei，
NNei is the number of class ei comprehensive passenger hubs;
calculating the sum of all distances:
13. repeating the steps 8-12, continuously updating the positions of all P-type comprehensive passenger transport hub centers, and calculating the sum of all distances。/>Refers to the sum of all distances corresponding to the positions of all P-class comprehensive passenger transportation hub centers after the fi-th update,
on the basis, a total distance matrix is established:
NUM represents the total number of Pi updates.
14. The minimum value of the elements in the search is found, the P-type comprehensive passenger transportation hub division result corresponding to the minimum value is the final result, and all P-type comprehensive passenger transportation hub center position index feature matrices are marked as follows:。
S3P major class further refined classification
15. The comprehensive passenger transportation hub classification considering the direct traffic flow influence factors is realized, and the classification method is mainly suitable for technicians from the technical point of view. However, in the decision-making process in the comprehensive passenger transportation hub under the abnormal event, besides technical personnel, decision-makers also comprise industry master personnel, operation scheduling personnel, maintenance personnel, traffic engineers, city planners and the like, so that when the comprehensive passenger transportation hub is classified, the difference of attention factors of different types of decision-makers needs to be considered, and further, the comprehensive passenger transportation hub is further classified in a refined manner on the basis of the steps.
In this section, on the basis of classifying the comprehensive passenger transport hubs into the P-class, four factors including economic status, population structure, travel habit and city planning are considered to refine and classify the comprehensive passenger transport hubs.
15.1 economic conditions
The market value of all goods and services produced in the region, and the income situation and the job position situation of people are mainly considered.
15.2 population structure
Mainly consider population count, age structure, sex ratio and education level.
15.3 travel habit
The daily travel times, travel mode selection, travel time and travel distance are mainly considered.
15.4 urban planning
Mainly consider population density, land use type, traffic facility layout, and public transportation accessibility.
16. On the basis of dividing all comprehensive passenger transport hubs into P classes by adopting the comprehensive passenger transport hub classification method under abnormal events, four factors of economic conditions, population structures, travel habits and city planning are considered to refine and classify the comprehensive passenger transport hubs.
Taking all T comprehensive passenger transport hubs in the j-th class of comprehensive passenger transport hubs as an example, the all T comprehensive passenger transport hubs are further subdivided,
16.1 taking the kth comprehensive passenger hub of the jth class of comprehensive passenger hubs as an example, the baseEstablishing a correlation matrix based on four factors including economic status, population structure, travel habit and city planning：
Matrix of relationshipsPerforming standardization to obtain a standardized correlation matrix:
；
；
；
；
；
wherein,is a standardized relationship matrix; />Representing the specific gravity of the mth element relative to the nth element, wherein the economic status, the population structure, the travel habit and the city plan correspond to 1,2,3 and 4 respectively; />For the ratio of total elements to 1 st elementSum of weights; />Is the sum of the specific gravities of all elements relative to the 2 nd element; />Is the sum of the specific gravities of all elements relative to the 3 rd element; />Is the sum of the specific gravities of all elements relative to the 4 th element.
16.2 calculationWeight vector +.>：
16.3 calculating the maximum eigenvector of the correlation matrix:
wherein,is->Is a weight vector of (2); />Is the maximum feature vector.
Maximum eigenvalue corresponding to maximum eigenvectorThe calculation method is as follows:
wherein,representation->Summing all elements in the list; />Representation->Summing all elements in the list;is the maximum eigenvalue.
16.4 in order to ensure that the relative interrelationships of the four factors in the interrelationship matrix have consistency and rationality, the consistency of the elements of the interrelationship matrix needs to be analyzed.
The consistency index of the interrelationship matrix is：/>
Consistency ratioThe calculation method comprises the following steps: />
Is a random consistency index, and is inquired through a random consistency index RI value table;
by establishing a relationship between the consistency ratio and 0.1, consistency of the relative interrelationship of four factors can be judged:
when (when)When it is, it indicates that the consistency is acceptable;
when (when)When the consistency is unacceptable, the correlation matrix needs to be readjusted>：
16.5 repeating steps 16.1 to 16.4, and calculating the maximum characteristic values corresponding to all T comprehensive passenger transport hubs:
i=1, 2,3, …, T. And consistency analysis is performed.
Will all beOrdering from big to small.
The sub-class number of all T comprehensive passenger hubs is NT, the number of comprehensive passenger hubs of each class：
；
Representing a rounding function.
Will beOrdered in order of from big to small and sequentially selected +.>The quantity is that all T comprehensive passenger transport hubs corresponding to the j-th class of comprehensive passenger transport hubs are subdivided into NT subdivision subclasses。
16.6 repeating steps 16.1 to 16.5, the comprehensive passenger transport hubs in all P major categories can be further subdivided into subclasses by considering four factors, namely economic status, population structure, travel habits and city planning.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (6)
1. A method for classifying an exception-oriented comprehensive passenger transportation hub, the method comprising the steps of:
s1, acquiring the number of comprehensive passenger transport hubs and classification indexes of the comprehensive passenger transport hubs under abnormal events, constructing a feature matrix relation of each classification index, calculating a feature matrix normalization value corresponding to each classification index of each comprehensive passenger transport hub, and taking a matrix formed by the feature matrix normalization values of all the classification indexes as a comprehensive feature matrix of the comprehensive passenger transport hubs;
s2, calculating the distance between comprehensive passenger transport hubs by using the comprehensive feature matrix, so that all the comprehensive passenger transport hubs are divided into P major classes;
s3, determining influence factors of decision makers with different identities on classification of the comprehensive passenger transport hubs, constructing maximum characteristic values corresponding to the mutual influence of all influence factors in each comprehensive passenger transport hub, sequentially arranging the maximum characteristic values in each class, equally dividing the arranged comprehensive passenger transport hubs into a plurality of subdivision subclasses, so as to realize subdivision of each major class, and thus realizing the classification process of all the comprehensive passenger transport hubs;
in step S3, the maximum feature value is obtained according to the following steps:
s31, constructing a correlation matrix of influence factors corresponding to a comprehensive passenger transportation hub for the comprehensive passenger transportation hub, and then normalizing the correlation matrix to obtain a normalized correlation matrix;
s32, calculating a weight vector by using the standardized relation matrix;
s33, calculating the maximum eigenvector of the interrelation matrix;
s34, calculating a corresponding maximum characteristic value by using the maximum characteristic vector;
in step S31, the normalized relationship matrix proceeds as follows:
AA＝A 11 +A 21 +A 31 +A 41
AB＝A 12 +A 22 +A 32 +A 42
AC＝A 13 +A 23 +A 33 +A 43
AD＝A 14 +A 24 +A 34 +A 44
wherein,is a standardized relationship matrix; a is that mn Representing the specific gravity of the mth element relative to the nth element, wherein the economic status, the population structure, the travel habit and the city plan correspond to 1,2,3 and 4 respectively; AA is the sum of the specific gravities of all elements relative to element 1; AB is the sum of the specific gravities of all elements relative to the 2 nd element; AC is the sum of the specific gravities of all elements relative to the 3 rd element; AD is the sum of the specific gravities of all elements relative to the 4 th element;
in step S32, the weight vector is performed as follows:
the maximum eigenvector is performed as follows:
wherein JQ k Is thatIs a weight vector of (2); TZ (TZ) k Is the maximum feature vector;
in step S34, the maximum feature value is calculated according to the following relation:
wherein, sumTZ k Representing TZ k Summing all elements in the list; sumJQ k Representing JQ k Summing all elements in the list;is the maximum eigenvalue.
2. The method for classifying an integrated passenger transportation hub for an abnormal event according to claim 1, wherein in step S2, all the integrated passenger transportation hubs are classified into P major classes, specifically according to the following steps:
s21, selecting initial P comprehensive passenger transport hubs from all the comprehensive passenger transport hubs as central points of classes;
s22, calculating the distance between each comprehensive passenger transportation junction distance and each central point by utilizing the comprehensive feature matrix, and dividing the current comprehensive passenger transportation junction into the class of the central point corresponding to the minimum distance value;
s23, repeating the step S22 until the classification of all the comprehensive passenger transport hubs is completed, dividing all the comprehensive passenger transport hubs into P classes, and calculating the sum of the distances from each comprehensive passenger transport hub to the center point of the class to which each comprehensive passenger transport hub belongs to obtain the sum of the distances.
3. The method for classifying an abnormal event-oriented comprehensive passenger transportation hub according to claim 2, further comprising the step of optimizing progress of the classified P-type after step S23, wherein the method comprises the steps of:
s24, calculating the average value of all comprehensive passenger transport hub comprehensive feature matrixes in each class, and taking the average value as a new central point;
s25, returning to the step S22 until the preset iteration times are reached, comparing the distance sum obtained in all the iteration times, wherein the center point corresponding to the minimum value of the distance sum and the divided class are taken as the final required divided class.
4. The method of classifying an integrated passenger transportation hub for an abnormal event according to claim 2, wherein in step S1, the classification index includes geographical location, surrounding environment, line information, average passenger flow, service time, number of stations, historical event, facility service and special date passenger flow.
5. The method for classifying an abnormal event-oriented comprehensive passenger transportation hub according to claim 4, wherein in step S22, the distance between each comprehensive passenger transportation hub and each center point is calculated according to the following formula:
wherein JL i-Ps Representing the distance between the ith center point in the ith comprehensive passenger junction distance P class; gamma ray ia The weight coefficient corresponding to the ia index; dlg (dlg) i 、zbg i 、xlg i 、pjg i 、fwg i 、ztg i 、lsg i 、ssg i 、tsg i The normalized values of 9 indexes of the ith comprehensive passenger transport hub are respectively represented, and are sequentially geographic position, surrounding environment, line information, average passenger flow, service time, station number, historical event, facility service and special-date passenger flow; dlg (dlg) Ps 、zbg Ps 、xlg Ps 、pjg Ps 、fwg Ps 、ztg Ps 、lsg Ps 、ssg Ps 、tsg Ps The normalized values of 9 indexes corresponding to the s-th central point in the P-type comprehensive passenger transport hub are sequentially geographic position, surrounding environment, line information, average passenger flow, service time, station number, historical event, facility service and special date passenger flow.
6. A method of classifying an exception oriented complex passenger transportation hub according to claim 1, wherein in step S3, the influencing factors are economy, demographics, travel habits and city planning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657163.2A CN117370905B (en) | 2023-12-06 | 2023-12-06 | Method for classifying comprehensive passenger transport hubs facing abnormal events |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657163.2A CN117370905B (en) | 2023-12-06 | 2023-12-06 | Method for classifying comprehensive passenger transport hubs facing abnormal events |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117370905A CN117370905A (en) | 2024-01-09 |
| CN117370905B true CN117370905B (en) | 2024-02-20 |
Family
ID=89398787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311657163.2A Active CN117370905B (en) | 2023-12-06 | 2023-12-06 | Method for classifying comprehensive passenger transport hubs facing abnormal events |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117370905B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408234A (en) * | 2014-11-03 | 2015-03-11 | 北京交通大学 | Railway traffic hub facility design method based on in-line analysis |
| WO2018113787A1 (en) * | 2016-12-23 | 2018-06-28 | 中兴通讯股份有限公司 | Region division method and device, and storage medium |
| CN110852650A (en) * | 2019-11-19 | 2020-02-28 | 交通运输部公路科学研究所 | Comprehensive passenger transport hub group network modeling method based on dynamic graph hybrid automaton |
| CN113343400A (en) * | 2021-06-23 | 2021-09-03 | 北京航空航天大学 | Cooperative layout optimization method and system for urban group comprehensive passenger transport hub |
| CN114707709A (en) * | 2022-03-21 | 2022-07-05 | 重庆城市综合交通枢纽（集团）有限公司 | Safety early warning method and system for comprehensive passenger transport hub of railway |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160335534A1 (en) * | 2015-05-14 | 2016-11-17 | Thalchemy Corporation | Neural sensor hub system |
-
2023
- 2023-12-06 CN CN202311657163.2A patent/CN117370905B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408234A (en) * | 2014-11-03 | 2015-03-11 | 北京交通大学 | Railway traffic hub facility design method based on in-line analysis |
| WO2018113787A1 (en) * | 2016-12-23 | 2018-06-28 | 中兴通讯股份有限公司 | Region division method and device, and storage medium |
| CN110852650A (en) * | 2019-11-19 | 2020-02-28 | 交通运输部公路科学研究所 | Comprehensive passenger transport hub group network modeling method based on dynamic graph hybrid automaton |
| CN113343400A (en) * | 2021-06-23 | 2021-09-03 | 北京航空航天大学 | Cooperative layout optimization method and system for urban group comprehensive passenger transport hub |
| CN114707709A (en) * | 2022-03-21 | 2022-07-05 | 重庆城市综合交通枢纽（集团）有限公司 | Safety early warning method and system for comprehensive passenger transport hub of railway |
Non-Patent Citations (2)
| Title |
|---|
| Analysis on evolving model with modular growth of urban roadway network topology structure;Zhi-yun ZOU.et.;《Kybernetes》;第44卷(第4期);505-517 * |
| 基于多源数据的枢纽间异常状态及受影响换乘客流识别研究;杨涛;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第3期);C034-1859 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117370905A (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108053062B (en) | Customized bus route generation method based on multi-source data | |
| CN108596727B (en) | Management and decision-making method for shared bicycle | |
| CN104809112B (en) | A kind of city bus development level integrated evaluating method based on multi-source data | |
| CN113902011A (en) | Urban rail transit short-time passenger flow prediction method based on cyclic neural network | |
| Pan et al. | Deploying public charging stations for electric taxis: A charging demand simulation embedded approach | |
| He et al. | Walking access distance of metro passengers and relationship with demographic characteristics: A case study of Nanjing metro | |
| CN110555544A (en) | traffic demand estimation method based on GPS navigation data | |
| CN111581325B (en) | K-means station area division method based on space-time influence distance | |
| Kato et al. | Latest urban rail demand forecast model system in the Tokyo Metropolitan Area | |
| Zou et al. | Research on assessment methods for urban public transport development in China | |
| CN117370905B (en) | Method for classifying comprehensive passenger transport hubs facing abnormal events | |
| Lin et al. | Passenger flow scale prediction of urban rail transit stations based on multilayer perceptron (MLP) | |
| CN116796904A (en) | Method, system, electronic equipment and medium for predicting new line passenger flow of rail transit | |
| Suh et al. | A large neighborhood search heuristic to establish an optimal ad-hoc hubbing strategy in the wake of a large-scale airport outage | |
| CN117408393B (en) | Prediction method and system for comprehensive passenger transportation hub traffic flow under abnormal event | |
| Zhang et al. | Discovering station patterns of urban transit network with multisource data: empirical evidence in Jinan, China | |
| CN113554221B (en) | Method for simulating and predicting town development boundary under view angle of' flow space | |
| Bo et al. | Commuting in the Storm: Adaptation of Transit Riders and Measures for Transit Operator—A Case in Shanghai | |
| CN111429166B (en) | Electric vehicle charging demand spatial distribution prediction method based on maximum contour clustering | |
| Lee et al. | Ensemble-based methodology to identify optimal personal mobility service areas using public data | |
| CN114154393A (en) | Method for predicting passenger throughput of target ground airport group based on abdominal theory | |
| Yang et al. | The application of venue-side location-based social networking (VS-LBSN) data in dynamic origin-destination estimation | |
| Mamdoohi et al. | An Analysis of Public Transit Connectivity Index in Tehran. The Case Study: Tehran Multi-Modal Transit Network | |
| Fitrada | Investigating the Impact of Airport Relocation on the Transport Network in Special Region of Yogyakarta, Indonesia | |
| Wang et al. | Development of location method for urban public transit networks based on hub-and-spoke network structure |
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 |