CN114723163B - Time-sharing time-space passenger flow distribution method and system, electronic equipment and storage medium - Google Patents
Time-sharing time-space passenger flow distribution method and system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114723163B CN114723163B CN202210441873.0A CN202210441873A CN114723163B CN 114723163 B CN114723163 B CN 114723163B CN 202210441873 A CN202210441873 A CN 202210441873A CN 114723163 B CN114723163 B CN 114723163B
- Authority
- CN
- China
- Prior art keywords
- time
- path
- space
- probability
- transfer
- 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 80
- 238000012546 transfer Methods 0.000 claims abstract description 85
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 27
- 238000010586 diagram Methods 0.000 claims abstract description 9
- 238000012216 screening Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 2
- 238000011160 research Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 4
- 238000010845 search algorithm Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000007429 general method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Algebra (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a time-interval passenger flow space-time distribution method, a time-interval passenger flow space-time distribution system, electronic equipment and a storage medium, and belongs to the technical field of passenger flow distribution. The method comprises the following steps: s1, searching a physical path through a K shortest path algorithm according to an urban rail transit network; s2, adding a space-time path searching method through the time of the shift of the train operation diagram and the time constraints of the arrival, transfer and departure of AFC data; s3, searching the space-time path at different time intervals based on different space-time path selection rules of passengers at different time intervals; s4, in the effective space-time path set, carrying out big data time calibration in different time periods; and S5, calculating the space-time path probability based on a Bayesian algorithm to complete the space-time distribution of the passenger flow. The invention well solves the technical problems that the specific space-time information cannot be acquired, the accuracy of the distribution algorithm is low and the information acquisition is incomplete in the prior art.
Description
Technical Field
The present invention relates to a method for time-space distribution of passenger flow, and more particularly, to a method, a system, an electronic device and a storage medium for time-share time-space distribution of passenger flow, which belong to the technical field of passenger flow distribution.
Background
A general urban rail transit passenger flow distribution algorithm usually adopts a balance theory and a Logit model. The general method comprises the following specific steps: the method mainly comprises the steps of considering main factors influencing passenger path selection in the urban rail transit network, including riding time, transfer times and transfer time, defining an effective path set between OD (traffic starting and stopping points) according to shortest path cost, searching K short paths among all the starting and stopping points of a model by using a Dijkstra method, determining time according to the complexity of a network felt by a passenger and a passenger trip plan, punishing the transfer time, constructing a path generalized cost model of the urban rail transit network including transfer according to the passenger path selection influencing factors, analyzing the passenger path selection behavior based on a random utility theory, and calculating the selection probability of each path by using a Logit function.
The defects of the prior art mainly comprise:
1. at present, the Logit model research for urban rail transit passenger path selection reflects population selection. Most of the related researches of the logic model focus on the travel path selection and the macroscopic passenger flow distribution of the passengers, the description of the microscopic passenger flow distribution of each passenger cannot be realized, and the precision are not enough.
2. The method relies on the construction of a utility function represented by a generalized cost function, and in fact, a lot of variables influencing passenger path selection are abstract and difficult to depict, and the missing or inaccurate depiction of some variables can result in the calculation of wrong passenger flow distribution proportion. The parameters in the model are calculated by adopting experience setting or a maximum likelihood estimation method based on questionnaire survey data, the experience setting is not scientific enough, the questionnaire mode is troublesome, and the authenticity of the questionnaire data, the representativeness of sample selection and the like have problems which influence the accuracy of the calibration of the model parameters.
3. The prior research mostly adopts a random utility theory to research the physical path selection behaviors of passengers, but relatively less research is carried out on the more microscopic passenger boarding selection behaviors. Secondly, most of the existing researches study the distribution state of the passenger flow among different paths from the viewpoint of observation based on a discrete selection model, but the distribution state of the passenger flow among different trains is less studied. In short, the prior art only realizes the acquisition of the physical path information, but cannot realize the acquisition of the spatio-temporal path information.
4. The travel time calibration problem is that the travel time (refer to figure 5) comprises inbound travel time, inbound waiting time, transfer travel time, transfer waiting time, outbound time and the like, and when the travel time calibration is carried out, inbound, transfer and outbound travel time tests need to be carried out on each station manually, so that a large amount of manpower, material resources and financial resources are consumed; in addition, it is difficult to obtain accurate waiting time for the arrival waiting time and the transfer waiting time manually.
The method is characterized by comprising the following specific steps of adopting a Bayesian algorithm as a passenger flow distribution algorithm, which is closest to the method of the present application: estimating travel time parameters by using AFC data to obtain the mean value and variance of travel time of each path between ODs; taking AFC data of each passenger as a sample, taking travel time as a characteristic attribute, performing probability classification by using a naive Bayes classifier, and dividing each passenger into a certain path with the highest posterior probability; and obtaining passenger flow of each effective path among the rail transit OD.
The Bayesian algorithm adopted as the passenger flow distribution algorithm has certain problems, specific time-space information cannot be obtained, the selection of a physical path is only optimized through travel time, the time-space path is not determined through travel time calibration, the algorithm is not accurate enough, and the information acquisition is not comprehensive enough.
Disclosure of Invention
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to determine the key or critical elements of the present invention, nor is it intended to limit the scope of the present invention. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.
In view of this, in order to solve the technical problems in the prior art that specific spatio-temporal information cannot be acquired, the accuracy of the distribution algorithm is low, and the information acquisition is incomplete, the invention provides a time-phased passenger flow spatio-temporal distribution method, a time-phased passenger flow spatio-temporal distribution system, an electronic device, and a storage medium.
The first scheme is as follows: the time-sharing passenger flow space-time distribution method comprises the following steps:
s1, searching a physical path through a shortest path algorithm;
s2, adding a space-time path searching method;
s3, searching a space-time path at different time intervals;
s4, in the effective space-time path set, carrying out time calibration on big data at different time intervals;
and S5, calculating the space-time path probability to complete the passenger flow space-time distribution.
Preferably, the method for searching a physical path through a shortest path algorithm includes the following steps:
s11, searching a travel path from a place A to a place B according to an urban rail transit network;
s12, considering riding time, transfer times, transfer time and crowding degree factors, and constructing a path selection probability function according to the travel path based on the generalized cost function and the logit model;
and S13, calculating the selection probability of each physical path based on a logit model.
Preferably, the method for adding the spatio-temporal path search method includes the following steps:
s21, setting a time constraint threshold value to be 0s through the time of the shift of the train operation diagram and the time constraints of the arrival, transfer and departure of AFC data;
s22, the space-time path comprises physical path information and specific getting-on and getting-off time and shift information, the first earliest space-time path is derived from the station-entering time, and the last latest space-time path is derived from the station-exiting time;
s23, obtaining all space-time paths between the earliest space-time path and the latest space-time path through a depth map traversal method;
s24, deleting the space-time paths which do not accord with the time sequence based on the time sequence, and screening out all effective space-time paths;
and S25, screening the minimum station entering time and the minimum station exiting time, and taking the time as a new time constraint threshold value to obtain all the space-time path sets.
Preferably, the specific method for searching the spatiotemporal path by time intervals is to divide the train running time in one day into four time intervals of an early peak, a flat peak, a late peak and a holiday, and acquire an effective spatiotemporal path set of the four time intervals according to the method in S2.
Preferably, the specific method for time-calibrating the big data at different time intervals is a big data calibration method based on a unique space-time path at a peak-smoothing period, and the specific implementation process is as follows: screening the unique travel data of the spatio-temporal path to obtain the unique inbound time of each travel, and then calculating the probability distribution of the inbound time, the transfer time and the outbound time:
wherein,representing a probability in +>The number of people when the departure time, the arrival time and the transfer time are t is shown, N is the total number of people,represents the probability of arrival time, and->Represents the probability of transfer time, is>Representing the probability of the outbound time;
the big data calibration method based on no transfer and one transfer in the early peak, late peak and holiday periods comprises the following specific implementation processes: screening out unique travel data of a space-time path, and calculating the probability distribution of the outbound time:
based on the travel data without transfer, screening the space-time path with the maximum outbound time probability from the travel data without transfer:
obtaining the inbound time based on the space-time path data with the maximum outbound time probability, and further obtaining the inbound time probability distribution:
screening the travel data of one transfer, and screening out the space-time path with the maximum inbound and outbound probability from the travel data of one transfer:
obtaining transfer time based on the space-time path data with the maximum outbound and inbound time probability, and further obtaining the probability distribution of the transfer time:
preferably, the specific method for calculating the space-time path probability and completing the space-time distribution of the passenger flow is to calculate the space-time path probability based on a Bayesian algorithm, and the realization process is as follows:
calculating the probability of the time path without transfer:
wherein,represents a stroke>The probability of arrival time->Indicates a stroke>Probability of outbound time;
calculating the probability of the time path containing the transfer:
calculating the probability of the physical path:
based on generalized cost model, total cost of jth physical pathIncluding the travel time cost->The path distance pick>And the number of times of transfer->And other fees +>The total travel cost is as follows:
calculating the space-time path probability:
spatio-temporal path probabilities may be decomposed into effective physical path probabilitiesAnd effective time physical path>The probability of the space-time path is obtained under the condition of the prior probability of the physical path, and is as follows:
calculating the probability of the space-time path without transfer:
calculating the probability of the space-time path containing the transfer:
scheme II: a time-sharing passenger flow space-time distribution system is used for realizing the time-sharing passenger flow space-time distribution method of the scheme I, and comprises a path search module, a space-time path search module, an operation time division module and a time calibration module space-time path probability calculation module;
the path searching module is used for realizing physical path searching;
the space-time path searching module is used for realizing space-time path searching;
the running time division module is used for dividing the running time of the train into different time periods;
the time calibration module is used for carrying out time calibration on the segmented space-time path;
the space-time path probability calculation module is used for calculating the space-time path probability and completing the passenger flow space-time distribution.
The third scheme is as follows: an electronic device comprising a memory storing a computer program and a processor implementing the steps of the time-share passenger flow space-time allocation method of aspect one when executing the computer program.
And the scheme is as follows: a computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the time-phased passenger flow spatiotemporal allocation method of aspect one.
The invention has the following beneficial effects: according to the method, effective space-time paths are determined through space-time path searching based on time constraint and depth map traversal, and space-time path selection probability is determined through a time calibration method based on time-share data of big data and a Bayesian algorithm, so that passenger flow distribution is completed, and the technical problems that specific space-time information cannot be obtained, the distribution algorithm is low in accuracy and information acquisition is incomplete in the prior art are solved;
1. according to the invention, by adopting a time-division method, the time-space path selection rules of passengers in different time periods are more comprehensively and finely embodied, and more accurate and more scientific passenger flow distribution results are obtained;
2. according to the invention, all effective spatio-temporal path sets are acquired through a spatio-temporal path search algorithm based on time constraint and depth map traversal and a method based on time constraint and depth map traversal, more scientifically and tightly constrained, and no possible spatio-temporal path is omitted;
3. the passenger flow distribution method based on double verification of the physical path and the space-time path is adopted, so that the defects of inaccurate model depiction, unscientific parameter calibration setting and inaccurate and incomplete distribution result of a general method can be overcome, more microscopic passenger boarding selection behaviors can be researched, the individual selection of each passenger can be reflected, and more, more comprehensive and more accurate information can be obtained;
4. the time calibration method of the time-sharing data based on the big data is adopted, the calibration is directly completed by the big data, manual walking calibration is not needed, different rules can be obtained in time sharing, and accurate calibration results are obtained in a targeted mode. The method is time-saving, labor-saving and financial-saving, results are accurate, and important data such as total inbound time (inbound running time plus waiting time), total transfer time (transfer running time plus waiting time), outbound time and the like can be acquired. And further supports path selection probability calculation based on a Bayesian algorithm, and can support time calibration and other researches.
5. The passenger flow distribution algorithm based on the double calibration of the physical path and the space-time path has the advantages that the acquired information is more comprehensive and the algorithm is more accurate.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a schematic diagram of the physical path of the present invention;
FIG. 4 is a schematic diagram of a spatio-temporal path search algorithm according to the present invention;
fig. 5 is a schematic diagram of the travel time in the background art.
Detailed Description
In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the following description of the exemplary embodiments of the present application with reference to the accompanying drawings is made in further detail, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all the embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example 1, the present embodiment is described with reference to fig. 1 to 4, and the method for time-share passenger flow space-time distribution includes the following steps:
s1, searching a physical path through a shortest path algorithm, comprising the following steps:
s11, searching a physical path through a K shortest path algorithm according to an urban rail transit network, and searching a travel path from a place A to a place B;
s12, considering riding time, transfer times, transfer time and congestion degree factors, and constructing a path selection probability function according to the travel path based on a generalized cost function and a logit model;
and S13, calculating the selection probability of each physical path based on a logit model.
Specifically, taking Shenzhen city subway as an example, OD is west beautiful subway station — citizen center subway station, and k shortest path algorithm can obtain three physical paths: physical path 1: getting on a Xili subway station, getting off the Xili subway station through a No. 7 line, transferring to a No. 2 line, and arriving at a citizen central subway station; physical path 2: getting on a Xili subway station, getting off the Xili subway station through a No. 7 line, and transferring the Xili subway station to a No. 4 line to reach a citizen central subway station; physical path 3: getting on the train at the Xili subway station, getting off the train at the Shenzhen north subway station through the line No. 5, transferring the train to the line No. 4, and arriving at the citizen center subway station; and then, based on the generalized cost function and the logit model, the cost function is constructed by fully considering factors such as riding time, transfer times, transfer time, crowding degree and the like, and the selection probability of each physical path is calculated based on the logit model.
S2, adding a space-time path searching method, comprising the following steps:
s21, setting a time constraint threshold value to be 0s through the time of the shift of the train operation diagram and the time constraints of the arrival, transfer and departure of AFC data, wherein the time constraint threshold value is used for the time constraints of the arrival, the transfer and the time constraints of the departure, and the arrival time constraint threshold value represents the minimum time difference between the time of the passenger swiping the card and the time of the departure of the nearest departure train; the transfer time constraint threshold value represents the minimum time difference between the train getting-off time of the passengers on the line 1 and the train getting-on time of the nearest line 2; the outbound time constraint threshold value represents the minimum time difference between the time when the passenger punches the card to outbound and the time when the nearest arriving train arrives at the station;
and S22, the space-time path comprises physical path information and specific getting-on and getting-off time and shift information. The first earliest spatiotemporal path is pushed backwards from the arrival time (which can be simply regarded as a first ride plan, i.e. the first train meeting the journey condition on every boarding or transfer), and the last latest spatiotemporal path is pushed forwards from the arrival time (which can be simply regarded as a last ride plan, i.e. the last train meeting the journey condition on every boarding or transfer).
S23, obtaining all space-time paths between the earliest space-time path and the latest space-time path through a depth map traversal method;
s24, deleting the space-time paths which do not accord with the time sequence based on the time sequence, and screening out all effective space-time paths;
specifically, taking a Shenzhen city subway as an example, suppose that a Xili subway station (inbound time 08). Taking the above physical path 1 as an example, there are two spatio-temporal paths on the physical path 1 according to the spatio-temporal path search algorithm: spatio-temporal path 1: west (boarding 08) — An Tuoshan (alighting: 08, boarding 08; spatio-temporal path 2: west (boarding 08).
S25, screening the minimum station entering time and the minimum station exiting time, and taking the time as a new time constraint threshold value to obtain all space-time path sets. And the time constraint threshold is reset, and the time-space path search is more accurate through time constraint threshold calibration.
The method based on the time constraint can specifically allocate the passengers in terms of time;
the depth-based graph traversal method can ensure that any possibility is not missed and all possible sets are obtained;
and screening out the space-time sets which do not accord with the time sequence based on the time sequence to obtain an effective space-time path set.
S3, searching a space-time path in time segments;
because the passenger has different space-time path selection rules in different time periods, the space-time path search in different time periods is more accurate,
the specific method for searching the space-time path in different time periods is to divide the running time of the train in one day into four time periods of an early peak, a flat peak, a late peak and a holiday, and obtain an effective space-time path set of the four time periods according to the method S2.
Specifically, the early peak is 7 to 10 o 'clock of the working day, the late peak is 17 to 20 o' clock of the working day, the average peak is other time except the early and late peak of the working day, and the holiday is weekend and legal holiday.
In order to prepare data for time calibration and space-time path selection probability, the AFC data quantity which is as large as possible needs to be operated in the four periods, for example, the data of the latest month is operated, and effective space-time path sets of the four periods of early peak, flat peak, late peak and holiday can be obtained.
Specifically, the early peak and the late peak time can be determined according to local conditions, and the early peak can be from 7 to 9 points of a working day, or from 7 to half to 9 points; the late peak may be 17 o 'clock to 19 o' clock of the working day, and may be 18 o 'clock to 20 o' clock.
Specifically, the amount of AFC data that is run. The operation can be carried out for the last 1 month or 2 months, and the data volume is ensured to be large enough.
Specifically, the time constrains the threshold. The time constraint threshold value can be set to be 0s, 3s or 5s, and the time constraint threshold value is ensured to be smaller than the shortest inbound time and the shortest outbound time of all stations. The strategy of time division is adopted, namely the four categories of early peak, average peak, late peak and holiday are mainly adopted. Different from the common method, the passenger flow distribution is carried out by taking all time data together, or the congestion judgment is carried out by experience in a general way, so that the method is not accurate enough. The space-time path selection rule of passengers at different time intervals is not explored, so that space-time path searching through AFC (automatic frequency control) big data at different time intervals is more accurate.
S4, in the effective space-time path set, carrying out time calibration on big data at different time intervals;
the specific method for carrying out big data time calibration in different time intervals is that,
the method for calibrating the only big data of the space-time path in the peak balancing period is based on the method for calibrating the only big data of the space-time path in the peak balancing period, because the pedestrian volume in the peak balancing period is small, queuing for getting on the bus is not needed in most cases, the only AFC data of the space-time path which is relatively fixed and accurate can be selected, and the specific implementation process is as follows:
screening the unique travel data of the spatio-temporal path to obtain the unique inbound time of each travel, and then calculating the probability distribution of the inbound time, the transfer time and the outbound time:
wherein,represents a probability, is>The number of people when the outbound, inbound and transfer time is t is shown, N is the total number of people,represents the probability of arrival time, and->Representing a probability of transfer time, in conjunction with a predetermined threshold value>Representing the probability of the outbound time;
because the flow of people is large in peak period, most of the cases are crowded, queue up is needed, and the like, the situation selection is needed, and the large data calibration method based on transfer-free and one-time transfer in early peak period, late peak period and holiday period has the following concrete implementation process: screening out unique travel data of a space-time path, and calculating the probability distribution of the outbound time:
based on the travel data without transfer, screening the space-time path with the maximum outbound time probability from the travel data without transfer:
obtaining the inbound time based on the space-time path data with the maximum outbound time probability, and further obtaining the inbound time probability distribution:
screening the travel data of one transfer, and screening out the space-time path with the maximum inbound and outbound probability from the travel data of one transfer:
obtaining transfer time based on the space-time path data with the maximum outbound and inbound time probability, and further obtaining the probability distribution of the transfer time:
s5, calculating the space-time path probability to complete the space-time distribution of the passenger flow, wherein the specific method is to calculate the space-time path probability based on a Bayes algorithm, and the realization process is as follows:
calculating the probability of the time path without transfer:
wherein,represents a stroke>The probability of arrival time->Indicates a stroke>Probability of outbound time;
calculating the probability of the time path containing the transfer:
calculating the probability of the physical path:
based on generalized cost model, total cost of jth physical pathIncluding the travel time cost->The path distance pick>And the number of times of transfer->And other fees->The total travel cost is as follows:
wherein,is a parameter of the logit model formula, the parameter->Representing a maximum likelihood estimate;
calculating the probability of the space-time path:
spatio-temporal path probabilities may be decomposed into effective physical path probabilitiesAnd effective time physical path>The probability of the space-time path is obtained under the condition of the prior probability of the physical path as follows:
calculating the probability of the space-time path without transfer:
calculating the probability of the space-time path containing the transfer:
specifically, taking Shenzhen city subway as an example, OD is a west beautiful subway station — a citizen center subway station, and three physical paths: physical path 1: getting on a Xili subway station, getting off the station at an Antuo mountain railway station through a No. 7 line, transferring the station to a No. 2 line, and arriving at a citizen central subway station; physical path 2: getting on a Xili subway station, getting off the Xili subway station through a No. 7 line, and transferring the Xili subway station to a No. 4 line to reach a citizen central subway station; physical path 3: and getting on the train at the Xili subway station, getting off the train at the Shenzhen north subway station through the line No. 5, transferring the train to the line No. 4, and arriving at the citizen center subway station. Assuming that a west subway station (arrival time 08) — a citizen center subway station (departure time 08). According to the space-time path search algorithm, two space-time paths are arranged on a physical path 1: spatio-temporal path 1: west (get-on 08) — An Tuoshan (get-off: 08; spatio-temporal path 2: west (getting-on 08). Then calculating the entering time, the transfer time, the exiting time, the traveling time and the waiting time: spatio-temporal path 1: the total time of the station entering, the walking and waiting is 2min, the total time of the transferring, the walking and waiting is 5min, and the total time of the station exiting and the walking is 3min; spatio-temporal path 2: the total time of the inbound walking and waiting is 6min, the total time of the transfer walking and waiting is 1min, and the total time of the outbound walking is 3min. According to the big data calibration algorithm, acquiring the probability distribution of the inbound, transfer, outbound traveling and waiting time of all the sites, wherein the probability distribution corresponds to the inbound, transfer and outbound probability of the two space-time paths: spatio-temporal path 1: the probability of the total time of the station entering, the walking and the waiting is 20 percent, the probability of the total time of the transfer walking and the waiting is 30 percent, and the probability of the total time of the station exiting and the walking is 25 percent; spatio-temporal path 2: the probability of the total time of the inbound walking and the waiting is 15 percent, the probability of the total time of the transfer walking and the waiting is 5 percent, and the probability of the total time of the outbound walking is 25 percent. According to the probability calculation formula, the specific space-time path probability is obtained, and the probability of obtaining the space-time path 1 is 53.3 percent; the probability of spatio-temporal path 2 is 6.7%. Similarly, the space-time path probabilities corresponding to the other two physical paths can be obtained by the above algorithm.
The embodiment 2 discloses a time-share passenger flow space-time distribution system, which comprises a path search module, a space-time path search module, an operation time division module and a time calibration module, wherein the space-time path probability calculation module is used for calculating the probability of a space-time path;
the path searching module is used for realizing physical path searching;
the space-time path searching module is used for realizing space-time path searching;
the running time division module is used for dividing the running time of the train into different time periods;
the time calibration module is used for carrying out time calibration on the segmented space-time path;
the space-time path probability calculation module is used for calculating the space-time path probability and completing the space-time distribution of passenger flow.
Abbreviations and key term definitions of the invention:
the AFC System is an Automatic Fare Collection System and refers to an Automatic Fare Collection System for urban rail transit. The system is a closed automatic network system with automatic ticket selling (including semi-automatic ticket selling), automatic ticket checking and automatic charging and counting, which are controlled by a computer in a centralized way. AFC data means subway card swiping data;
OD is called ORIGIN DESTINATION, and refers to the traffic starting and stopping points, and the OD traffic volume refers to the traffic volume between the starting and stopping points. "O" is derived from english ORIGIN, and refers to the starting place of a trip, "D" is derived from english DESTINATION, and refers to the DESTINATION of a trip;
physical path: the method comprises the following steps that a spatial path scheme for rail passenger flow between OD is selected, and information of stations, lines, transfer stations and lines passing from a starting station to a terminal station is obtained;
space-time path: in the spatio-temporal travel network, a connected spatio-temporal arc sequence between the station-entering spatio-temporal node and the station-exiting spatio-temporal node of a passenger is called a spatio-temporal travel path of the passenger, and the spatio-temporal travel path comprises a physical path of the passenger and an effective riding scheme in each physical path.
In embodiment 3, the computer device of the present invention may be a device including a processor, a memory, and the like, for example, a single chip microcomputer including a central processing unit, and the like. And the processor is used for implementing the steps of the recommendation method capable of modifying the relationship-driven recommendation data based on the CREO software when executing the computer program stored in the memory.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Embodiment 4, computer-readable storage Medium embodiment
The computer readable storage medium of the present invention may be any form of storage medium that can be read by a processor of a computer device, including but not limited to non-volatile memory, ferroelectric memory, etc., and the computer readable storage medium has stored thereon a computer program that, when the computer program stored in the memory is read and executed by the processor of the computer device, can implement the above-mentioned steps of the CREO-based software that can modify the modeling method of the relationship-driven modeling data.
The computer program comprises computer program code which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as described herein. Moreover, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The present invention has been disclosed in an illustrative rather than a restrictive sense, and the scope of the present invention is defined by the appended claims.
Claims (7)
1. The time-sharing passenger flow space-time distribution method is characterized by comprising the following steps:
s1, searching a physical path through a shortest path algorithm;
s2, adding a space-time path searching method;
s3, searching a space-time path in a time-sharing mode;
s4, in the effective space-time path set, big data time calibration is carried out in a time-sharing mode, and the method comprises the following steps: the method for calibrating the big data based on the space-time path in the peak-smoothing period comprises the following concrete implementation processes: screening the unique travel data of the spatio-temporal path to obtain the unique inbound time of each travel, and then calculating the probability distribution of the inbound, transfer and outbound time:
P t =N t /N
P entrance =N t|entrance /N entrance
P transfer =N t|trance /N trance
P exit =N t|exit /N exit
wherein, P t Representing the probability, N t The number of people who get out, get in and transfer time is t is shown, N shows the total number of people, P entrance Representing the probability of arrival time, P transfer Representing the probability of transfer time, P exit Representing the probability of the outbound time;
the big data calibration method based on no transfer and one transfer in the early peak, late peak and holiday periods comprises the following specific implementation processes: screening out unique travel data of a space-time path, and calculating the probability distribution of the outbound time:
P exit =N t|exit /N exit
based on the travel data without transfer, screening the space-time path with the maximum outbound time probability from the travel data without transfer:
P exit|max =max(N i|exit /N exit ,N i+1|exit /N exit ,、、、,N n|exit /N exit )
obtaining the inbound time based on the space-time path data with the maximum outbound time probability, and further obtaining the inbound time probability distribution:
P entrannce =N t|entrance /N entrance
screening the travel data of one transfer, and screening out the space-time path with the maximum inbound and outbound probability from the travel data of one transfer:
P exitentrance | max
=max(N i|exit /N exit *N i|entrance /N entrance ,N i+1|exit /N exit *N i+1|entrance /N entrance ,、、、,N n|exit /N exit *N n|entrance /N entrance )
obtaining transfer time based on the space-time path data with the maximum outbound and inbound time probability, and further obtaining the probability distribution of the transfer time:
P transfer =N t|trance /N trance
s5, calculating the space-time path probability to complete the passenger flow space-time distribution, wherein the space-time path probability is calculated based on a Bayes algorithm, and the realization process is as follows:
calculating the probability of a time path without transfer:
wherein, P i|entrance Representing the probability of arrival time, P, for trip i i|exit Representing the probability of the outbound time of journey i;
calculating the probability of the time path containing the transfer:
wherein, P i|transfer Representing the travel i transfer time probability;
calculating the probability of the physical path:
based on generalized cost model, total cost of jth physical pathIncluding travel time cost α T, route distance β S, number of transfers γ N, and other costs +>The total travel cost is as follows:
based on the logic model, the physical pathPath probability P physical The following:
calculating the probability of the space-time path:
the spatio-temporal path probability may be decomposed into an effective physical path probability P physical And an active time physical path P time The probability of the space-time path is obtained under the condition of the prior probability of the physical path as follows:
P spacetime =P physical *P time
calculating the probability of the space-time path without transfer:
calculating the probability of the space-time path containing the transfer:
2. the method of time-share passenger flow space-time distribution according to claim 1, wherein the method of physical path search by shortest path algorithm is comprising the steps of:
s11, searching a travel path from a place A to a place B according to an urban rail transit network;
s12, considering riding time, transfer times, transfer time and crowding degree factors, and constructing a path selection probability function according to the travel path based on the generalized cost function and the logit model;
and S13, calculating the selection probability of each physical path based on a logit model.
3. The time-share passenger-flow space-time distribution method according to claim 2, wherein the method of adding the space-time path search method is a method comprising the steps of:
s21, setting a time constraint threshold value to be 0s through the time of the shift of the train operation diagram and the time constraints of the arrival, transfer and departure of AFC data;
s22, the space-time path comprises physical path information and specific getting-on and getting-off time and shift information, a first earliest space-time path is deduced from the arrival time, and a last latest space-time path is deduced from the departure time;
s23, obtaining all space-time paths between the earliest space-time path and the latest space-time path by a depth map traversal method;
s24, deleting the space-time paths which do not accord with the time sequence based on the time sequence, and screening out all effective space-time paths;
s25, screening the minimum station entering time and the minimum station exiting time, and taking the time as a new time constraint threshold value to obtain all space-time path sets.
4. The time-share passenger flow space-time distribution method according to claim 3, wherein the time-share searching for space-time paths is performed by dividing the time of train operation in one day into four time periods of early peak, average peak, late peak and holiday, and acquiring the effective space-time path sets of the four time periods according to the method of S2.
5. The time-share passenger flow space-time distribution system is used for realizing the time-share passenger flow space-time distribution method of any one of claims 1 to 4, and is characterized by comprising a path search module, a space-time path search module, an operation time division module and a time calibration module space-time path probability calculation module;
the path searching module is used for realizing physical path searching;
the space-time path searching module is used for realizing space-time path searching;
the running time division module is used for dividing the running time of the train into different time periods;
the time calibration module is used for carrying out time calibration on the segmented space-time path;
the space-time path probability calculation module is used for calculating the space-time path probability and completing the space-time distribution of passenger flow.
6. An electronic device comprising a memory storing a computer program and a processor implementing the steps of the method of time-share passenger flow space-time distribution according to any one of claims 1-4 when executed by the processor.
7. A computer-readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the method for timesharing passenger flow spatiotemporal distribution of any of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210441873.0A CN114723163B (en) | 2022-04-26 | 2022-04-26 | Time-sharing time-space passenger flow distribution method and system, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210441873.0A CN114723163B (en) | 2022-04-26 | 2022-04-26 | Time-sharing time-space passenger flow distribution method and system, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114723163A CN114723163A (en) | 2022-07-08 |
CN114723163B true CN114723163B (en) | 2023-04-07 |
Family
ID=82245727
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210441873.0A Active CN114723163B (en) | 2022-04-26 | 2022-04-26 | Time-sharing time-space passenger flow distribution method and system, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114723163B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020215760A1 (en) * | 2019-04-25 | 2020-10-29 | 中国科学院深圳先进技术研究院 | Infectious disease diffusion analysis method and system based on subway space |
CN111861841A (en) * | 2020-06-30 | 2020-10-30 | 南昌轨道交通集团有限公司 | Method, device, equipment and storage medium for determining traffic network passenger flow distribution |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101964085A (en) * | 2010-09-27 | 2011-02-02 | 北京航空航天大学 | Method for distributing passenger flows based on Logit model and Bayesian decision |
KR101582283B1 (en) * | 2014-05-02 | 2016-01-04 | 서울대학교 산학협력단 | Method for estimating route of passenger in a metro network |
CN104217129B (en) * | 2014-09-22 | 2018-02-02 | 北京交通大学 | A kind of urban rail road network passenger flow evaluation method |
CN107067103A (en) * | 2017-03-22 | 2017-08-18 | 北京交通大学 | A kind of passenger's Path selection analysis method based on AFC system |
CN110019569B (en) * | 2017-07-21 | 2021-06-04 | 北京交通大学 | Method for acquiring urban rail transit operation state information |
CN111401614B (en) * | 2020-03-09 | 2022-09-02 | 西南交通大学 | Dynamic passenger flow distribution method and system for urban rail transit |
CN111582750B (en) * | 2020-05-18 | 2021-01-01 | 北京交通大学 | Method and system for identifying reverse passengers and determining riding class of rail transit |
WO2021243516A1 (en) * | 2020-06-01 | 2021-12-09 | 深圳先进技术研究院 | Urban public transport passenger travel trajectory estimation method and system, terminal, and storage medium |
-
2022
- 2022-04-26 CN CN202210441873.0A patent/CN114723163B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020215760A1 (en) * | 2019-04-25 | 2020-10-29 | 中国科学院深圳先进技术研究院 | Infectious disease diffusion analysis method and system based on subway space |
CN111861841A (en) * | 2020-06-30 | 2020-10-30 | 南昌轨道交通集团有限公司 | Method, device, equipment and storage medium for determining traffic network passenger flow distribution |
Also Published As
Publication number | Publication date |
---|---|
CN114723163A (en) | 2022-07-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kim et al. | Route choice stickiness of public transport passengers: Measuring habitual bus ridership behaviour using smart card data | |
Zhou et al. | Bus arrival time calculation model based on smart card data | |
Jackson et al. | An empirical study of travel time variability and travel choice behavior | |
WO2019136341A1 (en) | Systems and methods for managing and scheduling ridesharing vehicles | |
US20160364645A1 (en) | Learning mobility user choice and demand models from public transport fare collection data | |
CN106529711B (en) | User behavior prediction method and device | |
Yazici et al. | Modeling taxi drivers’ decisions for improving airport ground access: John F. Kennedy airport case | |
CN113287124A (en) | System and method for ride order dispatch | |
CN111932925A (en) | Method, device and system for determining travel passenger flow of public transport station | |
Saint-Guillain et al. | Time-dependent stochastic vehicle routing problem with random requests: Application to online police patrol management in Brussels | |
Yamamoto et al. | Structured random walk parameter for heterogeneity in trip distance on modeling pedestrian route choice behavior at downtown area | |
CN110956296A (en) | User loss probability prediction method and device | |
CN111858806A (en) | Passenger travel track detection method, device, equipment and storage medium | |
CN110657817A (en) | Method and device for recommending travel route | |
Lee et al. | Path-oriented synchronized transit scheduling using time-dependent data | |
Schmaranzer et al. | Population-based simulation optimization for urban mass rapid transit networks | |
CN114723163B (en) | Time-sharing time-space passenger flow distribution method and system, electronic equipment and storage medium | |
CN116386330A (en) | Copula-based travel time distribution prediction method and system | |
CN113449902B (en) | Information processing apparatus, information processing method, and information processing system | |
Ukam et al. | Factors affecting paratransit travel times at route and segment levels | |
Wessel | Accessibility beyond the schedule | |
Hermawan | Transportation Network Companies'(TNC) Impacts and Potential on Airport Access | |
Hobi | The impact of real-time information sources on crowd-sourced parking availability prediction | |
Roosmalen | Forecasting bus ridership with trip planner usage data: A machine learning application | |
Rahaman | Context-aware mobility analytics and trip planning |
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 |