CN113276915B - Subway departure scheduling method and system - Google Patents
Subway departure scheduling method and system Download PDFInfo
- Publication number
- CN113276915B CN113276915B CN202110761579.3A CN202110761579A CN113276915B CN 113276915 B CN113276915 B CN 113276915B CN 202110761579 A CN202110761579 A CN 202110761579A CN 113276915 B CN113276915 B CN 113276915B
- Authority
- CN
- China
- Prior art keywords
- subway
- departure
- environment state
- station
- reward
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a subway departure scheduling method and a subway departure scheduling system, wherein the method comprises the following steps: acquiring passenger riding information, line information and train information, and establishing a subway environment state matrix; acquiring subway reward and punishment data, and establishing a departure decision of subway reward and punishment output, wherein the departure decision is used for judging a departure effect and generating a new departure decision; predicting a new environment state matrix at the next time point according to the subway environment state matrix and riding information, and updating the departure decision output by the subway reward and punishment; and inputting the subway environment state matrix and the reward and punishment data of each time point into a convolutional neural network for training, outputting a departure decision after training, and executing subway departure according to the departure decision. According to the method and the system, a Policy gradient algorithm is adopted to carry out reward and punishment output according to the environment state of the subway, so that the intelligent optimization of subway scheduling can be realized, and the output result of the output subway scheduling can be more accordant with humanized design by combining a convolutional neural network.
Description
Technical Field
The invention relates to the field of subway control, in particular to a dispatching method and a dispatching system for dispatching a subway.
Background
The dispatching density of the subway in stages is regulated and controlled in real time based on service personnel in the subway station, when the passenger flow is dense, the passenger flow is controlled by means of queuing, intercepting and the like, dispatching is regulated and controlled, and the dispatching density of the subway has subjectivity and hysteresis. And for the personnel use pressure, the matching pressure is higher, and the experience of passengers in peak period is poor. The premise for realizing train departure is people flow prediction, and the traditional passenger flow prediction means usually only predict the inbound passenger flow information and the outbound passenger flow and do not predict a complete passenger travel, so that the subway scheduling in the prior art also has the problem of unmatched global passenger flow, and the subway passengers need to be subjected to flow prediction again in a special mode.
Disclosure of Invention
One of the purposes of the invention is to provide a subway departure scheduling method and system, the method and system adopt a Policy gradient algorithm to carry out reward and punishment output according to the subway environment state, intelligent optimization of subway scheduling can be realized, and the output result of subway scheduling can be more in line with humanized design by combining a convolutional neural network.
One of the objectives of the present invention is to provide a method and a system for dispatching subway departure, which simultaneously consider the total passenger flow and the local passenger flow to dispatch the subway departure, so as to avoid the rapid increase of the local passenger flow while the dispatching of the subway departure is still determined based on the total passenger flow, thereby improving the satisfaction of passengers.
One of the purposes of the invention is to provide a subway departure scheduling method and system, which can increase the benefits of subway operation according to the total passenger flow and the local passenger flow, and can reduce the overall operation cost while meeting the better experience of passengers.
One of the purposes of the invention is to provide a subway departure scheduling method and system, wherein the method and system obtain a passenger starting station and a passenger target station, judge direct passengers and transfer passengers, and set different matrix state parameters for passengers with different riding modes, so that the change of local flow inside a subway can be considered, and the subway scheduling can be executed by integrating the total flow and the local flow.
In order to achieve at least one of the above objects, the present invention further provides a subway departure scheduling method, including the steps of:
acquiring passenger riding information, line information and train information, and establishing a subway environment state matrix;
acquiring subway reward and punishment data, and establishing a departure decision of subway reward and punishment output, wherein the departure decision is used for judging a departure effect and generating a new departure decision;
predicting a new subway environment state matrix at the next time point according to the subway environment state matrix and riding information, and updating the departure decision output by the subway reward and punishment;
and inputting the subway environment state matrix and the reward and punishment data of each time point into a convolutional neural network for training, outputting a departure decision after training, and executing subway departure according to the departure decision.
According to one preferred embodiment of the present invention, the subway environment state matrix comprises: inbound and outbound columns, the number of passengers per inbound to each destination outbound.
According to another preferred embodiment of the present invention, the method for predicting the subway environment state matrix comprises: judging the station entering, station entering and station exiting of passengers according to the riding information of the current passengers, judging the number of passengers from each current station to each target station in the subway at the next time point, and clearing the number of all the passengers taking the station as the target station in the riding information of the passengers to generate a new subway environment state matrix if the subway is in the station.
According to another preferred embodiment of the present invention, if it is further inquired that there is a transit station in the passenger riding information, after the subway class arrives at the transit station, the passenger number is cleared to zero in the subway environment state matrix of the destination station, and the cleared passenger number is added to the corresponding subway environment state matrix point by taking the current transit station as the starting station and the next transit station or destination station as the destination station, so as to form a new subway environment state matrix.
According to another preferred embodiment of the present invention, the departure decision includes a departure probability of the subway train in each direction at each time point, a departure probability matrix is established, the departure probability matrix is input to the convolutional neural network, a reward and penalty value of all reward and penalty outputs of each bus is calculated, and an average reward and penalty value is calculated, so as to determine an effect of the overall subway operation.
According to another preferred embodiment of the present invention, the method for dispatching subway departure further comprises: acquiring the subway environment state matrixes of all stations at the current moment, establishing a subway pedestrian flow prediction model through an LSTM + CNN neural network, inputting the subway environment state matrixes of all stations at the current moment into the subway pedestrian flow prediction model, and predicting the subway pedestrian flow prediction model at a later time point.
According to another preferred embodiment of the present invention, the method of awarding the punishment output includes:
obtaining a passenger carrying rate m _ p of a train compartment, obtaining a departure cost index m _ m and obtaining a passenger satisfaction index m _ s;
wherein m _ p = the number of people in the train/the total number of people in the subway system, m _ m = the number of trains/the initial acceptance amount in the environment, and m _ s = the average waiting time length/the initial waiting time length;
the reward and punishment value reward is calculated in the following mode: reward =1+ (m _ p-m _ s)/m _ m.
According to another preferred embodiment of the present invention, the distance between two adjacent trains of subway buses is obtained, a minimum distance threshold is set, if the distance between two adjacent trains of subway buses is smaller than the minimum distance threshold, it is determined that the current subway environment state is dead, departure of a subway bus is prohibited, the subway environment state is initialized until the distance between two adjacent trains of subway buses is greater than the minimum distance threshold, and the current subway environment state matrix is obtained again.
In order to achieve at least one of the above-mentioned objects, the present invention further provides a dispatching system for subway departure, which executes the dispatching method for subway departure.
The present invention further provides a computer-readable storage medium storing a computer program, which can be executed by a processor to perform the dispatching method for train departure of subway.
Drawings
Fig. 1 is a schematic flow chart showing a subway departure scheduling method according to the present invention.
FIG. 2 shows a schematic diagram of the convolutional neural network training of the present invention.
Fig. 3 is a schematic diagram showing the processing of the transit passenger in the subway environment state matrix according to the present invention.
Fig. 4 is a schematic diagram showing the processing of express passengers in the subway environment state matrix according to the present invention.
Detailed Description
The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as defined in the following description, may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
It is understood that the terms "a" and "an" should be interpreted as meaning "at least one" or "one or more," i.e., that a quantity of one element may be one in one embodiment, while a quantity of another element may be plural in other embodiments, and the terms "a" and "an" should not be interpreted as limiting the quantity.
Referring to fig. 1-4, the invention discloses a subway departure scheduling method and system, which are used for realizing optimized scheduling of a subway based on a Policy gradient algorithm-based manner of creating reward and punishment output, wherein a subway environment state matrix is created by acquiring passenger riding information, and a dynamic subway scheduling optimization scheme is realized according to the subway environment state matrix and considering local and total flow simultaneously. Therefore, passenger experience and departure efficiency can be considered in subway scheduling, and the departure cost of the subway can be saved on the whole.
Specifically, the passenger's inbound data including the inbound time is recorded by swiping a card or other data of the passenger, and all subway lines, all station data and the number of subway trains of each line of the subway system are obtained. The method comprises the steps of obtaining regular bus states of the subway, wherein the regular bus states comprise survival states and death states, the survival states are states of regular buses in operation, and the death states are states of regular buses in a starting point or a terminal station of the subway. And acquiring the maximum passenger capacity of the subway class cars, wherein the passenger capacity of each class car cannot exceed the maximum passenger capacity.
After obtaining the riding information of each passenger, the subway system initializes a subway environment state matrix, please refer to fig. 3-4, where the subway environment state matrix includes a starting station column of the passenger and a passenger destination station column, where a-e in a horizontal column represents the starting point of the passenger entering, a-e in a vertical column represents the destination station of the passenger leaving, and numbers in the matrix represent the number of passengers from the horizontal column station to the vertical column station, such as: the coordinate value of (c, d) in the matrix is 14, which indicates that 14 passengers from the c station to the d station are present, and it should be noted that the subway environment state matrix indicates riding data of passengers waiting at all stations of the same subway line at the current time.
In one preferred embodiment of the invention, when a passenger gets on the train, the passenger is kept unchanged in the subway environment state list, if the passenger takes a train, the passenger is cleared in the subway environment state list, and from the aspect of the train, when the train arrives at the station, the number of all passengers taking the train to the station is cleared. For example: the number of passengers from the station c to the station d is 14, when the passengers arrive at the station d by taking the nearest shift train, the value of the matrix point (c, d) in the subway environment state matrix is changed to o, it should be noted that, in the present embodiment, the arrival of the train itself is taken as the judgment basis, and the situation that the passengers stay at the station or the passengers sit at the station is not considered, because generally, most passengers directly take the nearest shift train after entering the station, and few passengers stay at the station or sit at the station, so the present embodiment of passengers staying and sitting at the station is not considered any more. It should be noted that the subway environment state matrix in the above embodiments is described in a static state (assuming that there is no new passenger entering and no other passenger getting off), while in an actual implementation process, new passengers continuously enter each station of the subway, and there is a passenger getting off at each station, so the subway environment state matrix is a dynamically changing process. Therefore, the subway system updates the subway environment state matrix according to the real-time pedestrian flow interval fixed time. In general, the fixed time interval may be set to update the subway environment state matrix every 1-3 minutes. Therefore, the lattice point data of the subway environment state matrix also comprises riding data of new passengers after updating and clearing, and the actual number of people is not zero. In the embodiment, the travel of passengers in the subway does not need to be recorded, so that the calculation pressure can be reduced.
In another preferred embodiment of the present invention, further considering the situation that the passenger stays at the station or passes through the station, in this embodiment, the total riding time in the subway is calculated based on the passenger swiping card record, and the time point from the inbound to the inbound is recorded by using the modes including but not limited to face recognition and mark recognition, when the passenger swipes or otherwise enters the station, the time spent by the passenger entering to the riding is recorded by adding one to the matrix point value corresponding to the subway environment state matrix of the route according to the passenger travel information, and the time is the waiting time of the passenger and can be used for calculating the passenger satisfaction. Recording passenger arrival time after the passenger takes a bus, clearing away after the passenger arrives at the station the passenger is in from initial website to destination website the value in the iron environment state matrix on the spot makes the numerical value of the corresponding matrix point of subway environment state matrix subtracts one to the time of getting off to the station is recorded from getting off, in this embodiment, has recorded the stay condition of passenger at the station, and has recorded the condition that the passenger got off or sat the station in advance, therefore can fully master more careful traffic in the subway. The subway system can acquire the total number of people of the subway system at the current moment by acquiring the inbound and outbound records of the passengers.
It should be noted that in other preferred embodiments of the present invention, it is necessary to fully consider whether the passenger gets off in the subway is a direct get-off or a transit get-off, and if the passenger gets off at the get-off target station, the value in the state matrix of the subway environment of the passenger is cleared when the passenger arrives at the subway or gets off the subway. If the destination station after the passenger gets off is a transfer station, when the vehicle arrives or the passenger gets off, clearing the numerical value in the subway environment state matrix taking the transfer station as the destination station under the current bus line of the passenger, transferring the numerical value to the station taking the current transfer station as the starting station, taking one station of another subway line as the destination station or the ending station, adding the cleared transfer station passenger numerical value in the corresponding station in the subway environment state matrix of the other subway line, adding one to the numerical value of the corresponding station in the subway environment state matrix of the other line, and adding the passenger numerical value in the corresponding subway environment state matrix station according to the number of the passenger when a plurality of passengers exist in the transfer station as the starting point and reach the same station in the other subway line. The method and the device can realize the monitoring of the transit passenger flow, and have the defect of monitoring the transit passenger compared with the traditional monitoring that the passenger flow can only go from the inbound to the outbound of the passenger. It should be noted that the subway environment state matrices of different lines may be visually designed and displayed in different matrices, or may be designed in the same matrix according to requirements, for example, for a responsible person of each line, a visualized subway environment state matrix map may be obtained for the line responsible for the responsible person. When a person in charge of the whole subway system needs to look up, the subway environment state matrix spliced and integrated by all lines can be retrieved, and supervision control of different levels is realized.
The invention needs to be further combined with a neural network to predict the subway pedestrian flow, and subway regular bus optimized dispatching is carried out according to the prediction result of the subway pedestrian flow. Specifically, the method comprises the following steps: acquiring a subway environment state matrix of each time point separated by a certain time period in a day, wherein a matrix group combining the time point pedestrian flow can be represented as (T, X)m,n) Wherein T represents a time point, Xm,nThe passenger number matrix from the m station to the n station has an independent matrix at different time points, so the invention uses the passenger flow matrix X at different time pointsm,nInputting the training data into an LSTM + CNN neural network for training, and collecting a training set in the pedestrian volume matrix by setting a sliding window with a certain size, wherein the size of the sliding window can be set to be less than or equal to the pedestrian volume matrix Xm,nThe horizontal column values and the vertical column values of (1) in the image data. And calculating a loss function and adjusting the weight of the neural network to obtain a final people flow prediction model. It should be noted that, the neural network has a plurality of neurons, and the output weight of each neuron can be set to adjust the output of the entire neural network, and the LSTM + CNN neural network is an existing model, and the model is not improved in the present invention, so that the present invention is not described in detail in this prior art.
The subway departure scheduling system further comprises a departure decision module, wherein the departure decision module is used for judging whether a current shift queue should be departed, in the subway system, the departure module needs to acquire an initial departure time table, the initial departure time table comprises the earliest departure time fixed in the current day, at the moment, the departure module directly executes departure action according to the initial earliest departure time, and departure is carried out according to the subway environment state matrix in the rest departure time. Wherein the departure module can identify 2 states 1 and 0, 1 represents that the shift at the time point is a survival state, and the departure step can be executed. 0 represents that the vehicle is in a death state and the departure is not allowed, so the departure decision at different time points can be represented as (T, Vs), T represents the time point, and Vs represents the departure decision matrix.
It is worth mentioning that the reward punishment value reward is calculated based on the subway environment state matrix through Policy gradient algorithm, and the calculation method of the reward punishment value comprises the following steps: reward =1+ (m _ p-m _ s)/m _ m. Wherein m _ p is the passenger carrying rate of a train carriage, m _ p = the number of people in the train/the total number of people in the subway system, m _ m departure cost index, m _ m = the number of trains in the environment/the initial acceptance, m _ s passenger satisfaction index, and m _ s = the average waiting time length/the initial waiting time length. The larger the m _ p value is, the better the utilization rate of the regular bus is, but the maximum passenger capacity cannot be exceeded, the smaller the m _ m value is, the better the utilization rate of the regular bus is, and the shorter the waiting time of passengers is. And the reward and punishment value reward is further used as reference data of the subway departure decision, so that the reward and punishment output of the subway departure can be realized. The initialization waiting time is a preset reasonable time, and the initialization acceptance is the maximum train number in the preset subway environment.
Further, the subway environment state matrix, the reward and punishment value reward and the departure decision matrix Vs are taken as arrays and put into a convolutional neural network for training, a subway departure decision model is established, the subway environment state matrix is taken as input, the departure decision matrix Vs is taken as output, weight attenuation model training is carried out according to the reward and punishment value reward, cross entropy is taken as a loss function of the convolutional neural network model, the average value of each round of reward is calculated after multiple rounds of training until the loss function is converged, the subway departure decision model is described to be trained and optimized, subway scheduling is executed according to the departure decision matrix output by the subway departure decision model as a departure decision, and it needs to be described that the convolutional neural network is the prior art and is not repeated.
In particular, according to embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section, and/or installed from a removable medium. The computer program, when executed by a Central Processing Unit (CPU), performs the above-described functions defined in the method of the present application. It should be noted that the computer readable medium mentioned above in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wire segments, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless segments, wire segments, fiber optic cables, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It will be understood by those skilled in the art that the embodiments of the present invention described above and illustrated in the accompanying drawings are illustrative only and not restrictive of the broad invention, and that the objects of the invention have been fully and effectively achieved and that the functional and structural principles of the present invention have been shown and described in the embodiments and that modifications and variations may be resorted to without departing from the principles described herein.
Claims (7)
1. A subway departure scheduling method is characterized by comprising the following steps:
acquiring passenger riding information, line information and train information, and establishing a subway environment state matrix;
acquiring subway reward and punishment data, and establishing a departure decision of subway reward and punishment output, wherein the departure decision is used for judging a departure effect and generating a new departure decision;
predicting a new subway environment state matrix at the next time point according to the subway environment state matrix and riding information, and updating the departure decision output by the subway reward and punishment;
inputting the subway environment state matrix and the reward and punishment data of each time point into a convolutional neural network for training, outputting a departure decision after training, and executing subway departure according to the departure decision;
the subway reward and punishment output method comprises the following steps:
obtaining a passenger carrying rate m _ p of a train compartment, obtaining a departure cost index m _ m and obtaining a passenger satisfaction index m _ s;
wherein m _ p = number of persons in train/total number of persons in subway system, m _ m = number of trains in environment/initial acceptance, m _ s = average waiting duration/initial waiting duration;
the reward and punishment value reward is calculated in the following mode: reward =1+ (m _ p-m _ s)/m _ m;
the subway environment state matrix comprises: an inbound point column, an outbound point column, the number of passengers from each inbound point to each destination outbound point;
if a transfer station exists in the passenger riding information, after a subway train arrives at the transfer station, the number of passengers in the subway environment state matrix with the transfer station as a destination station taken by the passengers in the train is cleared, the cleared number of passengers is added to a corresponding subway environment state matrix point by taking the current transfer station as an initial station and the number of passengers in the next transfer station or destination station as a destination station, and a new subway environment state matrix is formed.
2. The method for dispatching trains of claim 1, wherein the method for predicting the subway environment state matrix comprises the following steps: judging the station entering, station entering and station exiting of passengers according to the riding information of the current passengers, judging the number of passengers from each current station to each target station in the subway at the next time point, and clearing the number of all the passengers taking the station as the target station in the riding information of the passengers to generate a new subway environment state matrix if the subway is in the station.
3. The subway departure scheduling method according to claim 1, wherein the departure decision includes a subway train departure probability in each direction at each time point, a departure probability matrix is established, the departure probability matrix is input into the convolutional neural network, a reward and punishment value output by all the rewards and punishment of each coach is calculated, and an average reward and punishment value is calculated for judging the effect of the whole subway operation.
4. The subway departure scheduling method according to claim 1, further comprising: acquiring the subway environment state matrixes of all stations at the current moment, establishing a subway pedestrian flow prediction model through an LSTM + CNN neural network, inputting the subway environment state matrixes of all stations at the current moment into the subway pedestrian flow prediction model, and predicting the subway pedestrian flow prediction model at a later time point.
5. The dispatching method for subway departure according to claim 1, wherein the distance between two adjacent trains of subway buses is obtained, a minimum distance threshold is set, if the distance between two adjacent trains of subway buses is smaller than the minimum distance threshold, the current subway environment state is determined to be dead, the subway buses are prohibited from departure, the subway environment state is initialized until the distance between two adjacent trains of subway buses is larger than the minimum distance threshold, and the current subway environment state matrix is obtained again.
6. A subway departure scheduling system, characterized in that it performs a method as claimed in any one of the preceding claims 1-5.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and the computer program can be executed by a processor to execute a dispatching method for subway departure as claimed in any one of the above claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110761579.3A CN113276915B (en) | 2021-07-06 | 2021-07-06 | Subway departure scheduling method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110761579.3A CN113276915B (en) | 2021-07-06 | 2021-07-06 | Subway departure scheduling method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113276915A CN113276915A (en) | 2021-08-20 |
| CN113276915B true CN113276915B (en) | 2022-07-15 |
Family
ID=77286430
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110761579.3A Active CN113276915B (en) | 2021-07-06 | 2021-07-06 | Subway departure scheduling method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113276915B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113450032A (en) * | 2021-08-31 | 2021-09-28 | 浙江非线数联科技股份有限公司 | Subway departure strategy method and system based on genetic algorithm |
| CN114004452A (en) * | 2021-09-28 | 2022-02-01 | 通号城市轨道交通技术有限公司 | Urban rail scheduling method and device, electronic equipment and storage medium |
| CN114420132A (en) * | 2022-03-28 | 2022-04-29 | 天津市北海通信技术有限公司 | Train voice broadcast content verification method, system and storage medium |
| CN115170006B (en) * | 2022-09-08 | 2022-11-29 | 南方科技大学 | Dispatching method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105128894A (en) * | 2015-09-02 | 2015-12-09 | 深圳市地铁集团有限公司 | Train running scheduling method and running scheduling system |
| CN108216311A (en) * | 2017-07-12 | 2018-06-29 | 南京交通职业技术学院 | A kind of rail traffic dispatching method based on big data and Internet of Things |
| CN108622142A (en) * | 2018-03-30 | 2018-10-09 | 卡斯柯信号有限公司 | A kind of train intelligent operation adjustment system and method based on real-time passenger flow |
| CN111079875A (en) * | 2019-12-17 | 2020-04-28 | 广州交通信息化建设投资营运有限公司 | Public transport passenger flow monitoring method and device based on multi-source data and storage medium |
| KR20200059394A (en) * | 2018-11-21 | 2020-05-29 | 한양대학교 산학협력단 | Method and device for railway capacity allocation |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107914740B (en) * | 2017-11-23 | 2020-04-17 | 交控科技股份有限公司 | Train self-organizing dispatching system and method based on real-time passenger flow |
| CN108510741B (en) * | 2018-05-24 | 2020-10-30 | 浙江工业大学 | Conv1D-LSTM neural network structure-based traffic flow prediction method |
-
2021
- 2021-07-06 CN CN202110761579.3A patent/CN113276915B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105128894A (en) * | 2015-09-02 | 2015-12-09 | 深圳市地铁集团有限公司 | Train running scheduling method and running scheduling system |
| CN108216311A (en) * | 2017-07-12 | 2018-06-29 | 南京交通职业技术学院 | A kind of rail traffic dispatching method based on big data and Internet of Things |
| CN108622142A (en) * | 2018-03-30 | 2018-10-09 | 卡斯柯信号有限公司 | A kind of train intelligent operation adjustment system and method based on real-time passenger flow |
| KR20200059394A (en) * | 2018-11-21 | 2020-05-29 | 한양대학교 산학협력단 | Method and device for railway capacity allocation |
| CN111079875A (en) * | 2019-12-17 | 2020-04-28 | 广州交通信息化建设投资营运有限公司 | Public transport passenger flow monitoring method and device based on multi-source data and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113276915A (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113276915B (en) | Subway departure scheduling method and system | |
| CN111354212A (en) | Taxi dispatching method, server and dispatching equipment applied to station airport | |
| Huang et al. | A novel bus-dispatching model based on passenger flow and arrival time prediction | |
| Gu et al. | Exploring alternative service schemes for busy transit corridors | |
| CN105373840A (en) | Designated-driving order predicting method and designated-driving transport capacity scheduling method | |
| CN110084397B (en) | Subway through line planning method | |
| CN114743401B (en) | Data visualization bus dispatching management platform based on bus digital transformation | |
| CN110570656B (en) | Method and device for customizing public transport line | |
| CN110675032A (en) | Vehicle scheduling method and device | |
| CN106875670A (en) | Taxi concocting method based on gps data under Spark platforms | |
| CN114117883A (en) | Self-adaptive rail transit scheduling method, system and terminal based on reinforcement learning | |
| CN113393137A (en) | Scheduling sharing system based on Internet of vehicles | |
| Shviatsova et al. | The Smart Urban Transport System | |
| CN111754095B (en) | Vehicle scheduling method, device and system based on artificial intelligence | |
| CN113763695A (en) | Dispatching method and system for automatic driving vehicle | |
| CN116109081A (en) | Dynamic bus scheduling optimization method and device based on Internet of things | |
| CN112598331A (en) | Dynamic scheduling method, system, computer equipment and storage medium for rail transit | |
| CN113536692B (en) | Intelligent dispatching method and system for high-speed rail train under uncertain environment | |
| CN113935595B (en) | Urban rail transit road network peak large passenger flow dredging system | |
| CN110222892B (en) | Passenger getting-off station prediction method and device | |
| Javadinasr et al. | A deep-learning based optimization approach to address stop-skipping strategy in urban rail transit lines | |
| CN109409563A (en) | A kind of analysis method, system and the storage medium of the real-time number of bus operation vehicle | |
| Dou et al. | Coordination of feeder bus schedule with train service at integrated transport hubs | |
| CN116654058A (en) | Rail transit network operation adjustment method, device, equipment and storage medium | |
| CN115208892B (en) | Vehicle-road collaborative online task scheduling method and system based on dynamic resource demand |
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 |