JPWO2017169068A1 - Train getting-off number prediction system, congestion visualization / evaluation system, and passenger capacity calculation system - Google Patents

Abstract

In the management of the congestion situation in a railway station, a technology is provided that can predict the number of people getting off the train only by information obtained from the single station when the train arrives.
The train getting-off number prediction device is a detection unit composed of a person counting unit that measures the number of people passing through a station premises, and a train arrival and departure detection unit that detects the arrival and departure times of trains, and a past train getting off from a past passing number of people. Number of getting-off persons calculating section for calculating the number of persons, train interval calculating section for calculating the arrival interval of two trains, a prediction model generating section for generating a prediction model of the number of persons getting off the train using the train interval, and the train upon arrival of the train The number of people getting off the train is predicted using the train interval of the train, a calculation unit composed of, a recording unit for recording data used in the measurement unit and the calculation unit, and a prediction result of the number of people getting off the train is output And an output unit.

Description

  The present invention relates to a system for providing congestion status visualization and prediction information.

  In railway stations, in addition to daily congestion such as commuting hours, congestion often increases due to transportation troubles of transportation facilities. There is a concern about the increase in train getting on and off time due to congestion and crowding accidents such as expansion of train delay and falling from the platform. Therefore, it is important to grasp the congestion situation in the station premises in a timely manner and promote appropriate guidance and countermeasures. In order to grasp the congestion situation in the station building in a timely manner, it is necessary to grasp the number of people flowing into the station building in a timely manner. The inflow into the station can be divided into visitors from outside the station and passengers getting off the train, but it is difficult to directly measure the number of passengers getting off the train.

  In Patent Document 1, data including the getting-off station read by the automatic ticket checker is received from a ticket passing through the automatic ticket checker on the entrance side of each station, and the number of people getting off at each getting-off station is totaled for each getting-off station. Pass through the automatic ticket gate with reference to the storage device that stores statistical data that correlates the device, the boarding station of the boarding ticket, and the boarding ratio of users who have boarding tickets that specify the boarding station. A vehicle congestion rate prediction system that requires a means for predicting a vehicle on which a user rides and calculating the number of people who get on each vehicle and the number of people who get off based on the prediction is disclosed.

JP2004-178358

  However, the method disclosed in Patent Document 1 has the following problems in predicting the number of people getting off the train.

  In Patent Document 1, in order to calculate the number of people getting off the train, it is necessary to record the passage of automatic ticket gates at each station. Therefore, even when it is desired to acquire the congestion status of a single station, it is necessary to acquire information on all stations. It is difficult to obtain information on all stations in a complicated railway network due to direct operation between railway operators.

  In addition, in order to obtain the number of people getting off the train in a timely manner, it is necessary to be able to obtain the traffic records of the automatic ticket gates at all stations in a timely manner, and a large investment is required for the automatic ticket gates and associated systems. .

  An object of the present invention is to make it possible to predict the number of people getting off a train using information that can be acquired at a single station.

  A train getting-off number prediction system according to an embodiment of the present invention includes a getting-off number calculating unit for measuring or estimating the number of getting off from an arriving train, a train arrival / deletion detecting unit for detecting arrival of a train, and arrival of two trains. A train interval calculation unit that calculates a train interval that is a time interval, and predicting the number of trains that will arrive in the future based on the number of people getting off and the train intervals.

  The number of people getting off the train can be predicted using information that can be acquired at a single station.

It is the figure which showed an example of the structure of the alighting person prediction apparatus of this invention. It is the figure which showed an example of the installation position of the sensor of a measurement part. It is the figure which showed an example of the data structure of people counting information. It is the figure which showed an example of the data structure of the arrival / departure time information. It is the figure which showed an example of the data structure of alighting person number information. It is the figure which showed an example of the data structure of train space | interval information. It is the figure which showed an example of the data structure of prediction model information. It is the flowchart which showed an example of database creation processing. It is the flowchart which showed an example of the passenger number prediction process. It is the schematic which showed an example of the method of calculating the number of people getting off. It is the flowchart which showed an example of the process of a disembarkation number calculation part. It is the schematic which showed an example of the train space | interval calculation method. It is the schematic diagram which showed an example of the train getting-off person prediction model. It is the flowchart which showed an example of the process of a prediction model preparation part. It is the schematic which showed an example of the train getting-off person prediction model using a delay rate. It is the flowchart which showed an example of the process of an alighting person prediction part.

  An embodiment of a train getting-off person prediction apparatus of the present invention will be described below with reference to the drawings.

<Structure of the invention>
FIG. 1 is a diagram showing an example of the configuration of a train getting-off person prediction apparatus according to the present invention. The train getting-off number prediction device is a device that predicts the number of getting-offs from trains at a railway station in a timely manner, and includes a measurement unit 100, a calculation unit 200, a recording unit 300, and an output unit 400. The measurement unit 100, the calculation unit 200, the recording unit 300, and the output unit 400 can communicate with each other, and operate on one or a plurality of interconnected computers.

  The measurement unit 100 includes a number measurement unit 101 that measures the number of people passing through the station, and a train arrival / departure detection unit 102 that detects arrival and departure of a train within the station.

  The calculation unit 200 includes a number of people getting off the train 201 for estimating the number of people getting off the train, a train interval calculating unit 202 for calculating the arrival time interval of the train that has just arrived on the same line as the target train, and a past train interval. A prediction model creation unit 203 that creates a prediction model of the number of passengers getting off the train on the basis of the statistical information of the number of people getting off, a passenger prediction unit 204 that predicts the number of people getting off by inputting the train interval of the train when the train arrives, Have

  The recording unit 300 includes the number-of-passengers measurement information 301 that is a detection result of the number of passing people, the arrival / departure time information 302 that is the arrival and departure times of trains, the getting-off number information 303 that is an estimated value of the number of getting-offs for each train, and the arrival for each train This is a database that holds train interval information 304 that is an interval and prediction model information 305 that is a prediction model for predicting the number of people getting off the train based on the train interval.

  The output unit 400 outputs a prediction result of the number of people getting off the train.

<Description of functions>
Next, functions of each component and data to be used will be described.

  First, the function of the elements constituting the measuring unit 100 will be described.

  The number-of-people measuring unit 101 is a sensor device that can measure the local number of people passing through the station according to the direction of movement, and outputs the number of people passing as time-counting information and number-of-directions information 301 by direction. The number-of-people counting unit 101 is realized by, for example, using a monitoring camera installed in a station premises as a sensor and measuring the number of people by image processing. In the present embodiment, it is assumed that sensors are installed on stairs or escalators connecting the platform and the ticket gate floor in order to estimate the number of trains getting off in the past. For example, sensors are installed at the positions of the camera 701 and the camera 702 in FIG. 2, and the number of passing people at the points 711 and 712 is measured.

  The train arrival / departure detection unit 102 is a sensor device capable of detecting arrival / departure of a train, detects arrival or departure of a train, records a time at that time, and outputs a detection result as arrival / departure time information 302. The train arrival / departure detection unit 102 is realized, for example, by using a monitoring camera installed on the platform as a camera 703 in FIG. 2 as a sensor and detecting arrival / departure of a train by image processing.

  Subsequently, functions of elements constituting the calculation unit 200 will be described.

  The getting-off number calculating unit 201 receives the past number-of-persons measurement information 301 and the past departure / arrival time information 302 as input, estimates the number of getting-off persons of each train by assigning the measured number of passing persons to the train, and outputs it as the getting-off number information 303 To do.

  The train interval calculation unit 202 calculates the arrival interval time of trains arriving on the same line and outputs it as train interval information 304.

  The prediction model creation unit 203 creates a model for predicting the number of train getting off passengers from the train interval based on the data that associates the past getting off passenger information 303 and the past train interval information 304, and outputs the model as prediction model information 305. To do.

  When the arrival of a train is detected, the getting-off number predicting unit 204 receives the train interval output by the train interval calculating unit 202 as an input, and predicts and outputs the number of getting off the train using the prediction model information 305.

  Next, a data structure used in the recording unit 300 will be described.

  The number-of-persons measurement information 301 is data in which the measurement result of the number-of-people counting unit 101 is recorded. As shown in FIG. 3, the position ID for specifying the sensor installation position, the measured date, the measurement start time and the end time are measured. This is data composed of a direction ID for specifying the direction in which the pedestrian moves and the number of people measured, and is stored in the recording unit 300 as a database.

  The arrival / departure time information 302 is data in which the detection result of the train arrival / departure detection unit is recorded. As shown in FIG. 4, the line ID that identifies the arrival number of the target train, the date and time when the train was detected, Is data that is classified according to whether it is arrival or departure, and is stored in the recording unit 300 as a database.

  The number of passengers getting off information 303 is data in which the number of people getting off is recorded for each train. As shown in FIG. 5, the information about the number of people getting off is data including the date when the train was detected, the line ID, the arrival time, and the number of people getting off. As a database. The date, line ID, and arrival time are information for uniquely identifying a train, and data that associates the train ID with the number of people getting off may be used by attaching a train ID for each train.

  The train interval information 304 is data that records the train interval with the train just before each train, and as shown in FIG. 6, the train interval information 304 is data composed of the date the train was detected, the line ID, the arrival time, and the train interval. Yes, and stored in the recording unit 300 as a database. The date, line ID, and arrival time are information for uniquely identifying a train, and data that associates the train ID with the number of people getting off may be used by attaching a train ID for each train.

  The prediction model information 305 is data in which a model for predicting the number of people getting off the train from the train interval is recorded, and includes a time zone, an attribute, a line ID, and a model formula as shown in FIG. In this embodiment, the prediction model is recorded as a model formula, but the model is not limited to the formula. For example, you may hold | maintain in the form of the table which matched delay time and the number of people who got off according to conditions.

<Description of processing>
Subsequently, an example of the overall processing flow of the train getting-off number prediction device will be described, and then an example of the processing flow of each part constituting the train getting-off number prediction device will be described. The processing of the train getting-off person prediction device can be divided into a database creation process and a getting-off person prediction process.

  First, the processing flow of database creation processing will be described using the flowchart of FIG. In the following description, step is abbreviated as S. For example, step 4001 is expressed as S4001.

  S4001: The number of people counting unit 301 is used to measure the number of people passing through a predetermined location in the station, and the measurement result is stored in the recording unit 300 as the number of people counting information 301, thereby creating a database of the number of people counting information 301.

  S4002: The train arrival / departure detection unit 102 is used to detect the arrival / departure time of a train that arrives and departs from the station, and the detection result is stored in the recording unit 300 as arrival / departure time information 302, thereby creating a database for the arrival / departure time information 302. .

  S4003: The number-of-passengers calculation unit 201 divides the number of passing people recorded in the number-of-passengers measurement information 301 by the train arrival time recorded in the departure / arrival time information 302, and the arrival time of the next train that arrives from the arrival time of each train. By assigning the number of passengers to the train to the train, the number of people getting off the train is calculated, and stored in the recording unit 300 as the number of people getting off the information 303, thereby creating a database of the number of people getting off the train 303.

  S4004: When the train detection unit 102 detects arrival of a train and the arrival / departure time information 302 is output by the train interval calculation unit 202, the same train as the train is obtained from the arrival / departure time information 302 recorded in the recording unit 300. A train interval information database is created by calculating an interval from the arrival time of the train that arrived immediately before the number line as a train interval and storing it in the recording unit 300 as train interval information 304.

  S4005: The prediction model creation unit 203 associates the information about the number of people getting off 303 recorded in the recording unit 300 with the train interval information 304, classifies the conditions according to conditions such as the number of lines, the time zone, and the like. A relational expression of the number of people getting off is calculated and stored in the recording unit 300 as prediction model information 305, thereby creating a prediction model information database.

  Thus, all the databases recorded in the recording unit 300 can be created. The database is updated by repeating the above processing in a timely or periodic manner according to the measurement result of the measurement unit 100. The term “periodic” refers to updating on a daily basis, for example.

  Next, a processing flow of the process for predicting the number of people getting off when the train arrives will be described with reference to the flowchart of FIG.

  S4101: When the train arrival / departure detection unit 102 detects an arriving train, the arrival / departure time information 302 is output, and the getting-off number prediction process is started.

  S 4102: The train interval calculation unit 202 calculates the arrival interval of the arrival train immediately before the same line as the train from the arrival / departure time information 302.

  S4103: The number of passengers getting off the vehicle in the conditions is obtained by acquiring the prediction model information 305 that matches the conditions at the time of arrival of the train from the recording unit 300 and inputting the previous train interval in the prediction model. Calculate the predicted value.

  S4104: The output unit 400 outputs a predicted value of the number of people getting off. For example, by using the number of pedestrians as an input, by estimating the congestion of a predetermined space by simulating the movement of pedestrians, and outputting the predicted value of the number of people getting off to a known pedestrian simulator device that can be visualized and evaluated Realize visualization and prediction of congestion in the station premises. In addition, when having a means for measuring or estimating the number of passengers in the train by a known method, the number of passengers after getting off can be calculated by subtracting the predicted value of the number of people getting off from the number of passengers, By subtracting the number of passengers after getting off the train capacity, the number of people who can get on the train can be calculated. As a result, the number of people staying on the platform can be visualized and predicted more precisely.

  This is the end of the description of the processing flow of the getting-off person prediction process.

  Subsequently, an example of the processing flow of each unit in the present embodiment will be described.

  Since the measurement unit 100 is realized using a known sensing technology, the recording unit 300 is realized using a known database technology, and the output unit 400 is realized using a known data transfer technology, description of the processing flow is omitted.

  An example of the processing flow of the getting-off person calculation unit 201 will be described with reference to FIGS. 10 and 11.

  First, the outline of the processing of the getting-off person calculation unit 201 will be described with reference to FIG. Symbols 1001 to 1006 represent the number of people passing in the target line and direction from the number of people measurement information 301, and represent the number of people passing in each time zone. Symbols 1011 and 1012 are train arrival times of the target number line extracted from the arrival / departure time information 302. As shown in FIG. 10, the number-of-getting-off person calculating unit 201 divides the number of passing persons by the train arrival time, and assigns the number of passing persons to the immediately preceding train, thereby calculating the number of getting off the previous train. For example, the symbols 1001 to 1003 are the number of people who have passed the stairs on the platform in the direction toward the ticket gate floor from the arrival of the train 1011 until the arrival of the train 1012, and can be estimated as the number of people who got off the train 1011.

  Next, an example of the processing flow of the getting-off person calculation unit 201 will be described using the flowchart of FIG.

  S5001: The number measurement information 301, which is the number ID of the target number for calculating the number of people getting off and the direction ID in the direction of moving from the platform to the ticket gate floor, is extracted from the recording unit 300.

  S5002: The arrival / departure time information 302, which is the number ID of the number for which the number of people getting off, is calculated is extracted from the recording unit 300.

  S5003: The extracted number measurement information is divided by the train arrival time in the extracted arrival / departure time information.

  S5004: The total value of the number of people measurement information divided by the train arrival time is set as the number of people getting off the train that arrives immediately before.

  S5005: The number of people getting off is output as the number of people getting off information 303 and recorded in the recording unit 300.

  Next, an example of the processing flow of the train interval calculation unit 202 will be described with reference to the flowchart of FIG.

  S5101: When the train arrival / departure detection unit 102 detects the arrival of a train, the arrival / departure time information 302 at the arrival of the train that arrived immediately before the same line as the train is extracted from the recording unit.

  S5102: The difference between the train arrival time of the extracted arrival / departure time information 302 and the arrival time of the train is calculated as the train interval of the train.

  S5103: The train interval is output as train interval information 304 and recorded in the recording unit 300.

  Subsequently, an example of a processing flow of the prediction model creation unit 203 will be described with reference to FIGS. 13 and 14.

  First, the outline of the process of the prediction model creation unit 203 will be described with reference to FIG. FIG. 13 is a scatter diagram in which the horizontal axis represents the train interval and the vertical axis represents the number of people getting off the train. Ranges 1101 to 1103 represent data distributions distinguished by attributes, line numbers, time zones, and the like. Curves 1111 to 1113 are relational expressions of the train interval and the number of people getting off the train corresponding to the data in the ranges 1101 to 1103, respectively. The relational expression is calculated, for example, by regression analysis using the train interval as an explanatory variable and the number of people getting off the train as an objective variable. The prediction model creation unit 203 creates a relational expression for each condition as a prediction model and outputs it as prediction model information 305.

  Next, an example of the processing flow of the prediction model creation unit 203 will be described using the flowchart of FIG.

  S5201: The train interval information 304 and the information about the number of people getting off are associated with each other by date, line ID, and arrival time.

  S5202: The associated data is classified and distinguished based on conditions such as date, line ID, time zone of arrival time, and the like.

  S5203: A relational expression between the train interval and the number of people getting off the train is calculated for the data for each condition, and is used as a model expression. The relational expression is calculated, for example, by regression analysis using the train interval as an explanatory variable and the number of people getting off the train as an objective variable.

  S5204: The model formula is output as prediction model information 305 and stored in the recording unit 300.

  The prediction model creation method in the prediction model creation unit 203 is not limited to the above. For example, the difference between the input train interval and the standard train interval is delayed with the train interval and the average or average value of the train get-off number as the standard train interval and train drop-off number under the condition. As the time, a model formula may be created by a relational formula between the delay time and the number of people getting off the train. Further, as shown in FIG. 15, a model equation is obtained by a relational expression of a delay rate that is a ratio of the delay time to a standard delay time and a change rate of the number of people getting off the train that is a ratio of the number of people getting off the train to a standard number of people getting off the train. May be created. By normalizing as a ratio in this way, it is not always necessary to create a model formula for every condition (time period). Moreover, it becomes possible to use the model formula of a certain station for another station whose statistical information is not sufficient.

  Next, an example of the processing flow of the getting-off person prediction unit 204 will be described using the flowchart of FIG.

  S5301: The number-of-get-offs prediction unit receives as input the train interval calculated by the train interval calculation unit 202 when the train arrives.

  S5302: Predictive model information 305 that matches the conditions of the train is extracted from the recording unit 300.

  S5303: The number of trains getting off is predicted by substituting the input train interval into the extracted model formula.

  S5304: The predicted number of people getting off the train is output.

  The processing of the getting-off person prediction unit 204 is changed according to the method of creating the prediction model. For example, when a prediction model is created using a relational expression of the delay rate and the number of people getting off the train, the delay rate is calculated from the train interval, and the rate of change in the number of people getting off the train is calculated using the relational expression. The number of people getting off the train is obtained by multiplying the number of people changing by the standard number of people getting off the train.

<Effect>
By using only the information obtained from a single station by the train getting-off number prediction device of this embodiment, the train interval is calculated from the arrival time of the train at the stage where the arrival of the train is detected, and based on the train interval Statistically, the number of people getting off the arrival train can be predicted. As a result, by inputting the number of people getting off to the public pedestrian simulator device when the train arrives, it is possible to visualize and predict the congestion situation in the station premises including the train getting off passengers in real time with only a single station information Become. It is also possible to grasp the congestion situation using only information obtained from a single station.

  By making it possible to predict the number of people getting off the train in a timely manner using information that can be acquired at a single station, it is possible to realize a timely grasp of the congestion situation in the station premises at a low cost. The term “timely” refers to the arrival stage of the train before the passenger gets off the train.

  100 measurement unit, 200 calculation unit, 201 getting-off number calculation unit, 202 train interval calculation unit, 203 prediction model creation unit, 204 train number prediction unit, 300 recording unit, 301 people measurement information, 302 departure / arrival time information, 303 getting-off number information 304 train interval information, 305 prediction model information, 400 output unit, 701 cameras, 702, 703 cameras, 711 points, 712 points

Claims (5)

A passenger count calculator that measures or estimates the number of passengers getting off the train,
A train arrival and departure detection unit that detects the arrival of a train,
A train interval calculation unit that calculates a train interval that is an interval between arrival times of two trains,
A train getting-off number prediction system for predicting the number of getting off trains that will arrive in the future based on the number of getting-off people and the train interval. A recording unit in which the number of getting off persons measured or estimated by the getting off number calculating part is recorded in association with the train interval;
The train drop-off number prediction system according to claim 1, further comprising: a calculation unit that creates a prediction model from the statistical information of the number of drop-offs recorded in the recording unit.   The calculation unit creates a prediction model using a delay time that is a difference from a past standard train interval or a delay rate that is a ratio of the delay time to the standard train interval. The system for predicting the number of people getting off the train according to Item 2.   A congestion visualization / visualization comprising: a pedestrian simulator that estimates the congestion situation of a space by simulating the movement of a pedestrian by using the number of persons getting off predicted by the system for predicting the number of persons getting off the train according to claim 1. Evaluation system.   It has a means for measuring or estimating the number of passengers in a train according to claim 1 and means for measuring or estimating the number of passengers in a train, and is calculated by subtracting the number of people getting off the train output from the train getting-off number prediction system. A system for calculating the number of passengers that can be boarded by subtracting the number of passengers after getting off the train capacity.

Images