WO2017149703A1

WO2017149703A1 - Traffic situation estimation system and traffic situation estimation method

Info

Publication number: WO2017149703A1
Application number: PCT/JP2016/056461
Authority: WO
Inventors: 理恵子大塚; 匠井口; 鈴木　敬
Original assignee: 株式会社日立製作所
Priority date: 2016-03-02
Filing date: 2016-03-02
Publication date: 2017-09-08
Also published as: JP6326177B2; EP3425606A4; EP3425606A1; EP3425606B1; JPWO2017149703A1

Abstract

This traffic situation estimation system is provided with a processor that executes a program, and a storage device that stores the program, wherein: a plurality of base stations of a wireless communication system are installed in a boarding facility for using a means of transportation; the storage device stores connection information including places where connection has been initiated and terminated between one of the base stations and terminals owned by users of the means of transportation; and the processor extracts, on the basis of the connection information, terminals of which the places where connection has been initiated and terminated are different, and estimates the number of users staying at the boarding facility in order to use the means of transportation, by multiplying the number of extracted terminals by a prescribed first coefficient.

Description

Traffic situation estimation system and traffic situation estimation method

The present invention relates to a system for estimating traffic conditions.

Railway operators are working on the realization of a service that delivers real-time service status such as train delays, congestion, and station congestion in order to provide passengers with high-quality transportation services. A Japanese railway company collects train location information acquired by train operation management systems and passenger information measured by sensors attached to trains in the suburbs of Tokyo, and provides information such as train delays and congestion. Has started a service to deliver to passengers.

Also, particularly, railway companies and telecommunications companies are the main actors, and wireless base stations (for example, public wireless LAN access points) are being installed in public transportation facilities such as airports, stations, trains, and commercial facilities. Under such an environment, a high-precision positioning verification experiment for measuring the movement of people indoors and outdoors using a public wireless LAN or the like has been performed.

There is Patent Document 1 (Japanese Patent Laid-Open No. 2007-120953) as a prior art in this technical field. Patent Document 1 uses an acceleration sensor mounted on a portable terminal to determine arrival at a station or departure from a station based on a detection result of an acceleration detection unit and a determination result of a communication area determination unit. The technology is disclosed.

Japanese Patent Laid-Open No. 2007-120953

As described above, the method of distributing information acquired by the train operation management system to the passengers requires a system that attaches sensors to the train and collects the measured data via wireless, which requires installation and development costs. A large sum. Also, it is difficult for many railway companies to introduce and operate in a short time.

On the other hand, if high-precision positioning is used, the position of the passenger who owns the mobile terminal in the station premises can be tracked, so it is possible to determine whether the passenger has got on the train and to measure the arrival and departure times of the train in real time. However, in order to measure the train arrival and departure times, it is necessary to detect at least one passenger on each train. Moreover, if the method of patent document 1 is used, although the time when a train arrived at a station can be detected using the acceleration data measured with the portable terminal which an individual owns, the arrival and departure times of all the stations and all the trains are detected. In order to detect, it is necessary to collect and analyze the acceleration data measured by the mobile terminals of many passengers. Therefore, in order to detect the arrival and departure times of all trains by the method described in Patent Document 1, it is necessary to arrange the owners of portable terminals equipped with dedicated applications and sensors in all trains and collect data. There is.

The object of the present invention has been made in view of the above point, and without collecting data from a passenger's portable terminal, to a wireless base station (for example, a public wireless LAN access point) installed in a station premises. It is to estimate the arrival and departure times of trains using connection information.

A typical example of the invention disclosed in the present application is as follows. That is, a traffic situation estimation system including a processor that executes a program and a storage device that stores the program, wherein a plurality of base stations of a wireless communication system are installed in a boarding facility for using a transportation means The storage device stores connection information including a connection start location and a connection end location between a terminal possessed by a user of the transportation means and one of the plurality of base stations, and the processor The number of terminals staying at the boarding / exiting facility for using the means of transportation is extracted by extracting terminals having different connection end locations from the connection information and multiplying the number of extracted terminals by a predetermined first coefficient. presume.

According to one aspect of the present invention, the number of transportation means (for example, trains) users can be estimated. Problems, configurations, and effects other than those described above will become apparent from the description of the following embodiments.

It is a figure which shows the outline | summary of the public wireless LAN in the system of the Example of this invention. It is a figure which shows the relationship between public wireless LAN and the movement action in a station premises in the system of the Example of this invention. It is a figure which shows the structure of the record which stores the public wireless LAN connection information of the Example of this invention. It is a figure which shows the structure of the whole system of the Example of this invention. It is a figure which shows the structure of the data server of the Example of this invention. It is a figure which shows the structure of the calculation server of the Example of this invention. It is a figure which shows the data structure of the master data of the Example of this invention. It is a figure which shows the data structure of the station premises movement data of the Example of this invention. It is a flowchart of the station premises movement data generation process of the Example of this invention. It is a figure explaining the method of estimating the departure / arrival time of the train of the Example of this invention, and the number of passengers of a train. It is a figure which shows the data structure of the train time data of the Example of this invention. It is a flowchart of the train departure / arrival time estimation process of the Example of this invention. It is a flowchart of the train delay calculation process of the Example of this invention. It is a figure which shows the data structure of the ticket gate passer-by number data of the Example of this invention. It is a figure which shows the data structure of the rebate coefficient table | surface of the Example of this invention. It is a flowchart of the rebate coefficient table production | generation process of the Example of this invention. It is a figure which shows the data structure of the train number data of the Example of this invention. It is a flowchart of a production | generation process of the train number data of the Example of this invention. It is a figure which shows the data structure of the station staying number data of the Example of this invention. It is a flowchart of a station staying number data generation process of the Example of this invention. It is a figure which shows an example of the screen which the information delivery server of the Example of this invention delivers. It is a figure which shows an example of the screen which the information delivery server of the Example of this invention delivers. It is a figure which shows an example of the condition setting screen of the Example of this invention. It is a flowchart of the information delivery process of the Example of this invention.

Embodiments of the present invention will be described with reference to FIGS. In addition, although the Example of this invention estimates the time when a train arrives and departs at a station, and the number of users, this invention is applicable to the transportation means (for example, bus, ferry, etc.) which many people use. . Furthermore, the present invention can be applied to a taxi stand to estimate the degree of congestion at the stand (that is, the number of passengers waiting for the ride).

FIG. 1 is a diagram showing an outline of a public wireless LAN in a system according to an embodiment of the present invention.

The public wireless LAN is a service that provides connection to the Internet through a wireless LAN, and a user 101 connects to the Internet from an access point 102 from a mobile terminal 103 such as a notebook PC, smartphone, or tablet PC. The range in which radio waves can reach from one access point is generally about several tens of e-mails. Therefore, a plurality of access points are often installed in large spaces such as large commercial facilities and stations.

In order to prevent interference when a mobile terminal can communicate with a plurality of access points 102, the wireless LAN access point 102 and each mobile terminal communicate with a common SSID, thereby preventing interference and useless communication. On the access point 102 side, the connection start time and connection end time of each mobile terminal can be acquired. There is also a public wireless LAN service that a user can use in advance by registering a MAC address, which is an identifier of a mobile terminal. For this reason, the movement history of each mobile terminal can be analyzed from the connection data of the wireless LAN. These settings and registrations must basically be made by the mobile terminal owner who wants to use the public wireless LAN.

FIG. 2 is a diagram showing the relationship between the public wireless LAN and the movement behavior in the station premises in the system of the embodiment of the present invention.

Generally, a public wireless LAN access point 102 in a station is installed near a ticket gate or on a platform, and the position of the mobile terminal can be roughly estimated from the radio wave intensity between each access point 102 and the mobile terminal. For example, when a user 101 having a mobile terminal using a public wireless LAN gets off the train, the mobile terminal first connects to the access point 102A installed on the platform floor. When the user 101 heads for the ticket gate 104 to leave the station, the user 101 shifts to connection with the access point 102B installed near the ticket gate. In this way, by tracking the access point 102 to which each mobile terminal is connected in time series, it is possible to estimate the movement of passengers in the station premises.

In addition, a plurality of access points may be installed at the same installation location (for example, 3 units in the platform 1 platform).

FIG. 3 is a diagram showing a structure of a record for storing the public wireless LAN connection information 122 according to the embodiment of the present invention.

The public wireless LAN connection information 122 includes information such as an access point ID 211, a connection time 212, and a connection device ID 213 representing a connected mobile device ID, and is data of a device connected at the time. The connection time 212 may hold records in units of seconds, or may be in units of several seconds. By maintaining the connection time in fine units, the estimation accuracy of the train arrival and departure times is increased. Since the connected device ID 213 only needs to be uniquely identifiable throughout the day, it may be anonymized by changing the ID provision rule every day. The public wireless LAN connection information 122 holds data included in a predetermined time window as in stream data processing, and new data is added and data at the old time is deleted as time advances. Is done.

FIG. 4A is a diagram showing a configuration of the entire system according to the embodiment of the present invention, FIG. 4B is a diagram showing a configuration of the data server 111, and FIG. 4C is a diagram showing a configuration of the calculation server 112.

In recent years, automatic ticket gates 104 are installed in many railway stations, and the automatic ticket gates 104 read non-contact type IC cards (or portable terminals having equivalent functions) or magnetic tickets, thereby User 101 enters the station and leaves the station. Information read by the automatic ticket checker 104 is transmitted to the data management server group 108 managed by the railway operator via the network 107 and stored as ticket pass data. The public wireless LAN access point 102 installed near the ticket gate or on the platform transmits the connected device information to the data management server group 108 in real time as described above. Furthermore, in recent years, surveillance cameras 105 have been installed near the ticket gates and on platforms. The video data acquired by the monitoring camera 105 can be checked in real time via the network 107 at a command station that manages the operation of the railway.

The traffic situation estimation system 110 includes a data server 111, a calculation server 112, and an information distribution server 113, and collects, stores, and analyzes connected device information and ticket gate passage data of the public wireless LAN access point 102. Note that descriptions of functions, configurations, and data processing techniques of the wireless system and the ticket gate, which are not directly related to the description of the present embodiment, are omitted.

The video data and ticket gate passing data acquired by the monitoring camera 105 are transmitted to the data server 111 via the network 107 at the timing when new data is acquired or at predetermined time intervals (every hour, every other day, etc.). Is done. A traffic situation estimation system 110 including a server group such as a data server 111, a calculation server 112, and an information distribution server 113 is used by a computer 117 and a passenger 115 used by a railway operator 116 via

networks

107 and 114. Communication with the terminal 118 is possible. In the present embodiment, the data server 111, the calculation server 112, and the information distribution server 113 are described as server groups. However, one or a plurality of servers may be configured to execute the functions of these server groups. .

As shown in FIG. 4B, the data server 111 is a computer mainly including a network interface, a processor, a memory, and a storage unit.

Processor executes a program stored in memory. The memory includes a ROM that is a nonvolatile storage element and a RAM that is a volatile storage element. The ROM stores an immutable program (for example, BIOS). The RAM is a high-speed and volatile storage element such as a DRAM (Dynamic Random Access Memory), and temporarily stores a program executed by the processor and data used when the program is executed.

The storage unit is configured by a large-capacity and non-volatile storage device such as a magnetic storage device (HDD), a CD-ROM drive, or a flash memory (SSD), and is used when executing a program executed by the processor and a program. Store the data. That is, the program is read from the storage unit, loaded into the memory, and executed by the processor.

The data server 111 receives the public wireless LAN connection information 122 and the ticket passer data 126 via the network 107 at a predetermined timing (predetermined update time interval) and records them in the data storage unit (DB) 121. Specifically, the storage unit includes a data storage unit (DB) 121. The data storage unit 121 includes public wireless LAN connection information 122, master data 123 indicating a station structure, station premises movement data 124, train time data 125, ticket gate passing number data 126, train number data 127, station stay number data 128, and the like. Is stored. The master data 123 is input and updated from the outside (for example, the computer 117 used by the railway operator 116) every time it is changed. The station premises movement data 124, the train time data 125, the train number data 127, and the station stay number data 128 are result data generated by the calculation server 112.

As shown in FIG. 4C, the calculation server 112 uses the data group stored in the data server 111 to execute processing for estimating the train arrival and departure times. The calculation server 112 is a computer mainly including a network interface (I / F (A)) 130, a processor (CPU) 131, a memory 132, and a storage unit 133.

The network interface 130 is an interface for connecting to the

networks

107 and 114. The processor 131 executes a program stored in the memory 132. The memory 132 includes a ROM that is a nonvolatile storage element and a RAM that is a volatile storage element. The ROM stores an immutable program (for example, BIOS). The RAM is a high-speed and volatile storage element such as a DRAM (Dynamic Random Access Memory), and temporarily stores a program executed by the processor 131 and data used when the program is executed.

The storage unit 133 is configured by a large-capacity and non-volatile storage device such as a magnetic storage device (HDD), a CD-ROM drive, or a flash memory (SSD), for example, and is used when executing the program executed by the processor 131 and the program. Data to be stored. That is, the program is read from the storage unit 133, loaded into the memory 132, and executed by the processor 131. Specifically, the storage unit 133 includes a station premises movement data generation program 134, a train time estimation program 135, a train delay degree calculation program 136, a rebate coefficient calculation program 137, a train passenger count calculation program 138, and a station stay count calculation. A data storage unit (DB) 152 that stores programs such as the program 139 and data such as the rebate coefficient table 153 and stores intermediate data generated in the course of calculation processing is included. Note that the data server 111 may store the rebate coefficient table 153 instead of the calculation server 112.

Note that a plurality of recording devices may be provided, and a program or data may be divided and recorded on a plurality of recording devices.

When the program is executed, data to be analyzed is acquired from the data server 111 and temporarily stored in the memory 132, and the processor 131 reads the

programs

134, 135, 136, 137, 138, and 139 from the memory 132 and executes them. By doing so, various functions are realized. These programs may be automatically executed according to a predetermined time interval (for example, every few seconds, every few minutes, etc.).

As shown in FIG. 4A, the information distribution server 113 is a computer having a network interface (I / F (B)) 145, a processor (CPU) 146, a memory 147, and a storage unit 148.

The network interface 145 is an interface for connecting to the

networks

107 and 114. The processor 146 executes a program stored in the memory 147. The memory 147 includes a ROM that is a nonvolatile storage element and a RAM that is a volatile storage element. The ROM stores an immutable program (for example, BIOS). The RAM is a high-speed and volatile storage element such as DRAM (Dynamic Random Access Memory), and temporarily stores a program executed by the processor 146 and data used when the program is executed.

The storage unit 148 is configured by a large-capacity non-volatile storage device such as a magnetic storage device (HDD), a CD-ROM drive, or a flash memory (SSD), for example, and is used when executing the program executed by the processor 131 and the program. Data to be stored. That is, the program is read from the storage unit 148, loaded into the memory 147, and executed by the processor 146. Specifically, the storage unit 148 stores programs such as the condition acquisition program 141 and the information distribution program 142 and intermediate data generated in the course of calculation processing.

The information distribution server 113 is accessed via the

networks

114 and 151 from the terminal 120 used by the system operator 119, the computer 117 used by the railway operator 116, and the terminal 118 used by the passenger 115, and provides information. For example, information provided by the information distribution server 113 includes information for setting conditions related to user verification and screen display, estimation results of the number of people staying at a station, and the computer or terminal basically accesses the information distribution server 113. Provided at the timing.

The system operator 119 who operates the traffic situation estimation system 110 uses the terminal 120 to transmit the configuration and situation of data stored in the traffic situation estimation system 110 via the network 151, the situation and calculation result of the calculation server 112, You can check the status of search requests from users.

Each

server

111, 112, 113 may have an input interface and an output interface. The input interface is an interface that is connected to a keyboard, a mouse, and the like and receives input from an operator. The output interface is an interface that is connected to a display device, a printer, or the like and outputs the execution result of the program in a form that can be visually recognized by the operator.

A program executed by the

processors

131 and 146 of each server is provided to each

server

112 and 113 via a removable medium (CD-ROM, flash memory, etc.) or a network, and is a non-volatile storage device that is a

non-temporary storage medium

133 and 148. For this reason, each of the

servers

112 and 113 may have an interface for reading data from a removable medium.

Each of the

servers

111, 112, and 113 is a computer system that is configured on a single physical computer or a plurality of logically or physically configured computers, and is a separate thread on the same computer. It may operate on a virtual machine constructed on a plurality of physical computer resources.

FIG. 5 is a diagram illustrating a data structure of the master data 123 stored in the data server 111 according to the embodiment of this invention.

The master data 123 includes information such as installation location information 170 indicating the installation location of the access point 102, movement pattern definition information 180 within the station premises, and a train plan timetable 190.

The installation location information 170 of the access point 102 is data representing the location where the access point 102 of the public wireless LAN is installed, including information such as an access point ID 171, installation station name 172, and installation location details 173. When the location of the access point 102 is changed, the system operator or the railway operator inputs from the outside of the system and updates the data.

The station premises movement definition information 180 includes information such as a station name 181, a connection start location 182, a connection end location 183, and a type 184. For each combination of the public wireless LAN connection start location and connection end location in the station premises, the behavior is defined. Data classified into types. The type 184 can be classified into three types: boarding, getting off, and boarding. Further, when a plurality of access points 102 are installed on the platform, it can be estimated that each mobile terminal is located on the platform, so that the mobile terminal stays in addition to the information of the type 184 of getting on and getting off. Information on the location on the platform may be added. By doing so, it becomes possible to perform detailed analysis such as the number of doors on the train where each mobile terminal got on and off.

The train schedule time table 190 includes information such as a station name 191, a train ID 192, a stop location 193, a date 194, an arrival time 195, and a departure time 196, and is data representing the order of trains that arrive and depart each platform at each station. The railway operator decides an operation schedule in advance for vehicle operation, driver arrangement, and the like, and manages schedule diagram information indicating the timing at which the train is operated. The train schedule timetable 190 may record the schedule information as it is, or may extract and record necessary information. Moreover, the train plan timetable 190 may be updated sequentially at the timing when the plan schedule is formulated and updated, or may be updated by a batch process executed at a predetermined time. Since the operation schedule may be changed depending on the day of the week or the season, the day 194 is used to identify which day the operation schedule is.

FIG. 6 is a diagram illustrating a data structure of the station premises movement data 124 stored in the data server 111 according to the embodiment of this invention.

The station premises movement data 124 is generated from the public wireless LAN connection information 122. The in-station movement data 124 includes information such as the connected device ID 231, station name 232, date 233, connection start time 234, connection start location 235, connection end time 236, and connection end location 237, and each mobile terminal is connected within the station premises. This is data representing the time and place at which the connection is started and the time and place at which the connection is finished. Using the combination of the station name 232, the connection start location 235, and the connection end location 237 included in the station premises movement data 124, referring to the station premises movement definition information 180 of the master data 123, the action type in the station premises of each mobile terminal is determined. Can be sought.

FIG. 7 is a flowchart of processing in which the station premises movement data generation program 134 of the embodiment of the present invention generates the station premises movement data 124.

First, all records included in the public wireless LAN connection information 122 in the data server 111 are rearranged by the connection time 212 and the connection device ID 213 (step 301). Then, the following processing is repeated for all connected device IDs using the rearranged data (step 302).

In the repetition of step 302, first, the value of the connection time 212 is referred to, and the data is divided at a place where an interval of t minutes or more is available (step 303). This is because a certain person divides a communication record using the public wireless LAN several times in the day, such as morning and night, and processes it correctly. The threshold t is generally a time interval for passengers to use the station, and may be defined between several tens of minutes to several hours, or an accurate time interval may be obtained using public wireless LAN information. That is, one set of connection start time and connection end time generated in step 302 is divided into a plurality of sets of connection start time and connection end time in step 302. In this division, the connection start time and another connection end time may be combined, and the connection end time and another connection start time may be combined. Alternatively, it may be determined that the connection is established for a predetermined time from the connection start time and the connection is established for a predetermined time before the connection end time. In the latter case, the connection time can be obtained accurately even if the metal data is missing.

The following processing is repeated using the divided data (step 304). In the repetition of step 304, the value of the connection time 212 is obtained from the first record and is held as the connection start time (step 305). Further, the value of the access point ID 211 is obtained from the first record, and the station name and installation location are searched with reference to the installation location information 220 included in the master data 123 (step 306). Next, the value of the connection time 212 is acquired from the last record and held as the connection end time (step 307). Further, the value of the access point ID 211 is obtained from the last record, and the station name and the installation location are searched with reference to the installation location information 220 included in the master data 123 (step 308). Note that when a plurality of access points are installed at the same installation location (for example, three in the home of the No. 1 line), the installation locations of the plurality of access points are handled as the same in the above processing.

Then, the information on the connected device ID, the acquired station name, the connection start time, the connection start location, the connection end time, and the connection end location is stored in the station premises movement data 124 (step 309). The date information stores the date of the current time.

FIG. 8 is a diagram for explaining a method of estimating the departure / arrival time of a train and the number of passengers on the train from the in-station movement data 124 according to the embodiment of the present invention.

In this embodiment, the following three objects are estimated using the station premises movement data 124.
A. Train arrival time Train departure time Number of people on the train

The mobile terminal owned by the passenger on the train starts connection to the access point 102 installed at the station when the train arrives at the station. For this reason, by creating a histogram with the number of connected devices that have started connection on the platform and analyzing the time series change, the arrival time of the train is detected as shown in “A. Detection of arrival time of train”. be able to. Similarly, by analyzing a time-series change in the number of connected devices that have ended connection on the platform, the departure time of the train can be detected as shown in “B. Detection of departure time of the train”.

Also, a mobile terminal owned by a passenger on the train is connected to a public wireless LAN access point at the station while the train is stopped at the station. Therefore, it can be presumed that the connection device having the same platform as the connection start location and the connection end location of the in-station movement data 124 is a passenger who is on the train. By counting the number of connected devices that satisfy this condition, the number of people on the train can be detected as shown in “C. Detection of the number of people on the train”.

As shown in FIG. 8, the histogram may include noise. Noise can be filtered by removing data with the number of devices less than a predetermined threshold. The threshold value used for filtering may be a fixed value or a dynamically changing value (for example, an average value for a predetermined period before the time). Further, noise may be filtered by removing data whose appearance time width in the histogram is shorter than a predetermined time.

FIG. 9 is a diagram illustrating a data structure of the train time data 125 stored in the data server 111 according to the embodiment of this invention.

The train time data 125 includes information such as a station name 241, a train ID 242, a station premises 243, a date 244, an arrival time 245 and a departure time 246, and is data representing arrival / departure time information of each train. The train time data 125 stores the result of estimating train arrival / departure information using the station premises movement data 124.

FIG. 10 is a flowchart of a process in which the train time estimation program 135 according to the embodiment of the present invention estimates the train arrival and departure times from the station premises movement data 124. The train time estimation program 135 is executed for each station.

First, referring to the station name 181 of the station premises movement definition information 180 included in the master data 123, all records including the corresponding station are extracted (step 401). Then, the following processing is repeated for all the extracted records (definition patterns) (step 402).

In the repetition of step 402, all the records corresponding to the definition pattern are extracted with reference to the connection start location 235 and the connection end location 237 of the station premises movement data 124 (step 403). Using the connection start time 234 and connection end time 236 of the extracted record, a record number histogram is created in accordance with a predetermined time unit (step 404). As shown in FIG. 8, when estimating the arrival time of a train, attention is paid to passengers who get off the train to the platform, and a histogram is created using the connection start time 234. Further, when estimating the departure time of the train, attention is paid to passengers who have left the station on the train, and a histogram is created using the connection end time 236. The time unit for creating the histogram is determined in advance from several seconds to several tens of seconds according to the target station and the target time zone. For example, in a station or time zone with a large number of connected devices, a train created in a short time (for example, every second) can detect the arrival and departure times of trains with high accuracy, but in a station or time zone with a small number of connected devices. The data may be collected for a long time (for example, every several tens of seconds).

Next, data is detected from the histogram, train IDs are assigned in the order of detection (step 405), and stored in the train time data 125 (step 406). The detection of data from the histogram may be performed by detecting peaks, rising edges, and falling edges from the histogram. For example, when the peak is detected, the arrival time of the train can be accurately estimated. Moreover, when the rising edge is detected, the departure time of the train can be accurately estimated.

When the train plan timetable 190 is available as the master data 123, the train arrival time 195 or the planned departure time 196 is compared with the estimated time, the train ID 192 having the closest departure / arrival time is searched, and the train You may store in train ID242 of the time data 125. When the difference between the train operation status on the day and the plan is small, it is more useful for analyzing the delay for each train to give the planned train ID.

FIG. 11 is a flowchart of a process in which the train delay degree calculation program 136 according to the embodiment of the present invention calculates a train delay.

The train delay degree calculation program 136 uses the train time data 125 to calculate the delays of all trains operated on a certain day. First, all the records of the specified date are extracted from the train time data 125 (step 501), rearranged using the station name 241, train ID 242, and station premises 243 as keys (step 502), and the following processing is performed for all records. Repeat (step 503).

In the repetition of step 503, when the train ID is given using the train plan timetable 190 in the process of generating the train time data (125), the delay is simply compared with the planned arrival time and departure time. Specifically, a record including the corresponding train ID is extracted from the train plan timetable 190 (step 504), and a train arrival time value ATplan and a train departure time value DTplan are acquired (step 505). Further, the train arrival time value AT and the train departure time value DT are acquired from the train time data 125 (step 506). Finally, the ATplan is subtracted from the AT to calculate the train arrival time delay, and the DTplan is subtracted from the DT to calculate the train departure time delay (step 507).

By averaging the train delay calculated by the above method for a predetermined period (for example, the most recent month), it is possible to know the chronic delay of the train and to improve the transportation by revising the train schedule. .

In addition, when the train ID is given according to the arrival order of the train for each station and each platform in the process of generating the train time data 125, the combination of the station name 241, the train ID 242 and the station premises 243 is the same in the past predetermined period. The record may be extracted from the train time data 125, the average value of the train arrival times may be calculated as ATplan, and the average value of the train departure times may be calculated and compared as DTplan with the train arrival time AT and the train departure time DT. By using the average value, the train arrival time and the train departure time delay can be obtained without the train plan timetable 190.

FIG. 12 is a diagram showing a data structure of the ticket passing number data 126 stored in the data server 111 according to the embodiment of this invention.

The ticket gate passing number data 126 includes information such as a station name 251, a date 252, a time zone 253, a type 254, and a passing number 255, and is data representing the number of passengers who have passed the ticket gate of the station. The ticket passing number data 126 can be created by counting the passing records of the automatic ticket gate 104 and IC ticket data. Alternatively, a person may be detected from video captured by the monitoring camera 105 installed near the ticket gate using image analysis technology or signal analysis technology, and the number of people passing through the ticket gate may be counted. The data server 111 may execute the process of calculating the number of passing ticket gates by video analysis or signal analysis, or may be processed outside the system.

If the daily data cannot be obtained, a statistical value (for example, an average value) obtained from the already stored ticket passer data 126 may be used. The number of passing people may be recorded separately for the visitors and the participants, or the total value may be recorded without dividing the visitors and the participants.

The unit of the time zone 253 is determined in advance from several minutes to several hours. The ticket gate passing number data 126 is necessary for estimating the total number of passengers using the station. Because some passengers do not use the public wireless LAN and have a plurality of mobile terminals alone, the number of connected devices and the total number of passengers obtained from the public wireless LAN connection information 122 Because they are not equal. The ratio of public wireless LAN connected devices and the total number of passengers will vary slightly depending on the station and time zone, as the percentage of people with mobile devices will increase at the nearest stations and commuting hours in the business district. It is done.

FIG. 13 is a diagram illustrating a data structure of the rebate coefficient table 153 stored in the calculation server 112 according to the embodiment of this invention.

The rebate coefficient table 153 includes data on the station name 261, the time zone 262, and the coefficient 263, and is data representing the ratio between the number of public wireless LAN connected devices and the total number of passengers. The granularity of the time zone 262 may be aligned with the time zone 253 of the ticket gate passing number data 126. Also, the rebate coefficient table 153 may record different coefficients depending on day attributes such as weekdays and holidays. Further, the rebate coefficient table 153 may record different coefficients depending on the action type, such as boarding, getting off, getting on the train, and staying at the station. Furthermore, the rebate coefficient table 153 may record different coefficients depending on the location within the station. By subdividing the rebate coefficient table 153, the number of persons can be estimated more accurately.

FIG. 14 is a flowchart of processing for generating the rebate coefficient table 153 by the rebate coefficient calculation program 137 according to the embodiment of this invention.

The rebate coefficient calculation program 137 need not be executed every day, but may be executed at a predetermined timing (once every several days, once every several weeks, etc.). First, a record for the corresponding period is extracted from the ticket passing number data 126 and the station premises movement data 124 (step 601). A certain day may be designated as the relevant period, or a plurality of days may be designated. However, it is preferable to use data on the day when both the ticket gate passing number data 126 and the station premises movement data 124 exist. Although it is preferable to use the ticket gate passing number data 126 and the station premises movement data 124 on the same day, the statistical values (for example, average values) of the ticket gate passing number data 126 and the station premises movement data 124 on the same day are used. Also good. Next, the following processing is repeated for all stations (step 602).

In the repetition of step 602, the station premises movement data 124 is totaled according to the granularity of the time zone 253 of the ticket passing number data 126, and the number N of connected devices in each time zone is obtained (step 603). The time information used for counting may be the connection start time 234 or the connection end time 236.

Then, the following processing is repeated for all time zones (step 604). In the repetition of step 604, the record of the corresponding station and time zone is extracted from the ticket gate passing number data 126, and the passing number T is acquired (step 605). When the ticket gate passing number data 126 is stored separately for entrance and exit, the total value is calculated. Finally, T ÷ N is calculated, and the calculated coefficient is stored in the rebate coefficient table 153 (step 606).

FIG. 15 is a diagram illustrating a data structure of the train number data 127 stored in the data server 111 according to the embodiment of this invention.

The train number data 127 includes information such as a station name 271, a train ID 272, a station premises 273, a date 274, a type 275, and a number 276, and is data representing the number of passengers on each train, the number of people getting off, and the number of people on the train. . As the type 275, one of the three types of getting on, getting off, and getting on is recorded.

FIG. 16 is a flowchart of a process in which the train passenger counting program 138 according to the embodiment of the present invention generates the train passenger number data 127.

The train passenger number counting program 138 is executed on a daily basis and on a station basis based on information input from the outside, and generates train number data 127 using the station premises movement data 124. First, a record of a corresponding day and a corresponding station is extracted from the station premises movement data 124 (step 701). The following process is repeated for all the extracted records (step 702).

In the repetition of step 702, the combination of the station name 232, the connection start location 235, and the connection end location 237 of the station premises movement data 124 is used as a key to refer to the station premises movement definition information 180 and extract the corresponding type 184 (step 702). 703). Next, the train time data 125 is referred to, and the train estimated to be used by the passenger who owns the connected device is specified (step 704). Here, when the type 184 is “boarding”, paying attention to the connection end location 237 and the connection end time 236, referring to the departure time 246 of the train time data 125, the difference between the connection end time 236 and the departure time 246. Train ID of the train with the smallest (or less than a predetermined threshold). Similarly, when the type 184 is “get off”, paying attention to the connection start location 235 and the connection start time 234, referring to the arrival time 245 of the train time data 125, the difference between the connection start time 234 and the arrival time 245 Train ID of the train with the smallest (or less than a predetermined threshold). When the type 184 is “in boarding”, the train ID is acquired by a method such as comparing the connection start time 234 with the arrival time 245 of the train time data 125 and determining whether it is within a predetermined threshold. At this time, the connection end time 236 and the departure time 246 of the train time data 125 may be compared.

Then, by using the arrival time 245 or departure time 246 of the train ID acquired in Step 704, the rebate coefficient table 153 is referred to and a rebate coefficient is acquired (Step 705). When the rebate coefficient table 153 holds rebate coefficients for weekdays and holidays, a rebate count is acquired in consideration of the day of the week on the date of the day.

Then, it is searched whether the record of “station name, train ID, date, type” corresponding to the record of the train number data 127 is included. If the train number data 127 includes a record of “station name, train ID, date, type”, the value of “rebate coefficient × 1” is added to the number data. If the train number data 127 does not include the corresponding “station name, train ID, date, type” record, a new record is created, and “rebate coefficient × 1” is recorded as the number of people.

FIG. 17 is a diagram showing a data structure of station staying number data 128 stored in the data server 111 of the embodiment of the present invention.

The station staying number data 128 includes information such as the station name 281, the station premises location 282, the date 283, the time zone 284, and the staying number 285, and is data representing the number of staying persons in the station and the station premises. The division of the time zone 284 may be defined in advance between several seconds to several hours. If the station staying number data 128 is generated with a fine granularity such as several seconds or several minutes, it is possible to accumulate the short-term changes in the congestion in the station yard accompanying the arrival and departure of the train.

FIG. 18 is a flowchart of a process in which the staying person totaling program 139 according to the embodiment of the present invention generates station staying person data 128.

The station staying person totaling program 139 is executed on a daily basis and on a station-by-station basis based on information input from the outside in the same manner as the train passenger numbering totaling program 138. 128 is generated.

First, a record of a corresponding day and a corresponding station is extracted from the movement data 124 in the station (step 801). The following process is repeated for all the extracted records (step 802).

In the repetition of step 802, the connection start location 235 and the connection end location 237 are acquired from the station premises movement data 124, and it is determined whether the connection start location 235 and the connection end location 237 are the same (step 803). A record in which the connection start place 235 and the connection end place 237 are the same is presumed to belong to a passenger on the train, and the process is skipped so as not to be counted as a staying person at the station (step 808).

If the connection start location 235 and the connection end location 237 are different, the number of staying persons is counted for each connection start location and connection end location. First, the connection start time 234 is acquired, and the corresponding time zone is obtained in accordance with the granularity of the time zone of the station staying person data 128 (step 804). Then, it is searched whether there is a record of “station name, connection start location, date, time zone” in the station residence number data 128. If the corresponding record exists, the rebate coefficient table 153 is referred to and the rebate coefficient value is added. If there is no corresponding record, a new record is added to the station staying number data 128 (step 805).

Next, the connection end time 236 is acquired, and the corresponding time zone is obtained according to the granularity of the time zone of the station staying person data 128 (step 806). Then, it is searched whether there is a record of “station name, connection end location, date, time zone” in the station residence number data 128. If the corresponding record exists, the rebate coefficient table 153 is referred to and the rebate coefficient value is added. If there is no corresponding record, a new record is added to the station residence number data 128 (step 807).

FIG. 19 is a diagram illustrating an example of a screen 1001 distributed by the information distribution server 113 according to the embodiment of this invention.

A screen 1001 is a screen distributed to the terminal 120 of the system operator 119 and the computer 117 of the railway operator 116, and displays, for example, the current train delay status, train congestion status, station congestion status, and the like. . The screen 1001 includes a map display area 1011, a ranking display area 1012, and a graph display area 1013. In the map display area 1011, the number of people staying at the station corresponding to the degree of congestion of the station and the number of passengers on the train corresponding to the degree of congestion of the train are displayed on the map. In the ranking display area 1012, the number of people staying and the number of passengers are displayed in ascending or descending order. In the graph display area 1013, the number of people staying and the number of passengers from the first departure on the day to the current time are displayed in a time series graph.

Also, if the train delay condition or the number of people staying at the station is an abnormality that satisfies a predetermined condition (for example, far from the past average value), a warning 1014 that informs the user of the abnormality may be displayed. In addition, when a certain date in the past is specified and displayed, the date and time when the data is displayed may be displayed on the screen. Information on the number of people staying at the station and the number of trains is communicated to the user in an easy-to-understand manner by changing the display mode of the stations and trains (for example, the size and color of the images) based on a predetermined leveling definition. be able to.

Also, information on the number of people staying at the station and the number of trains may be displayed in text. Further, the stations may be sorted and displayed in a table format in the order of congestion throughout a certain time period or one day. By presenting an overview screen to system operators and railway operators, it is possible to obtain information for business improvement such as reviewing operation plans and planning measures to eliminate congestion at stations. These screens can be operated using an input interface such as a mouse or keyboard. For example, you can use the wheel buttons to zoom in / out the map screen, select a station or train with a mouse click, Detailed information such as operation results may be displayed.

FIG. 20 is a diagram illustrating an example of a screen 1020 that is distributed to the terminal 118 by the information distribution server 113 according to the embodiment of this invention.

The screen 1020 is a screen distributed to the terminal 118 of the passenger 115. The mobile terminal 118 of the passenger 115 needs to configure the screen in consideration of the characteristics that the screen size is small and the resolution is low. For example, the screen 1020 includes an interface 1021 for selecting a route, a direction, and a station, and an information display area 1022 having a scroll function. For this reason, the user can easily select a station or train for which information is desired.

Also, in conjunction with the GPS function of the terminal 118, station information close to the current location of the user may be selected and displayed. The screen 1020 displays the delay situation of the train that will arrive at the station where the user is staying and the congestion situation. Thereby, the user can determine whether to get on the next train or on the next train.

FIG. 21 is a diagram illustrating an example of a screen 1110 for setting conditions for information distributed by the information distribution server 113 according to the embodiment of this invention.

The condition setting screen 1110 is a screen displayed on the computer 117 of the railway operator 116, the terminal 118 of the passenger 115, and the terminal 120 of the system operator 119. On the condition setting screen 1110, a request is transmitted to the information distribution server 113 by directly inputting or selecting a search target station 1111, a search target date 1112, or the like using a pull-down menu and operating an execution button 1113. These display conditions can be set by the user using an input interface such as a mouse, a keyboard, or a touch panel.

In the condition setting screen 1110 shown in FIG. 21, one of each of the target route, the station, and the target date can be selected, but an interface for selecting a plurality of options simultaneously may be adopted. Moreover, when selecting a some station, you may employ | adopt a stepwise interface, such as selecting a station after selecting a route.

FIG. 22 is a flowchart of information distribution processing according to the embodiment of this invention.

When the information distribution server 113 receives a request according to the search condition input on the condition setting screen 1110, the information distribution server 113 executes an information distribution process. First, the condition input on the search condition setting screen 1100 is acquired from the received request (step 1200). Next, records corresponding to the stations and dates to be counted are extracted from the train time data 125, the train number data 127, and the station staying number data 128 according to the input search conditions (step 1201). Thereafter, the extracted record is processed into a format such as a time series graph or mapping to a map screen, and distributed to the device that transmitted the request (step 1202).

The information distribution server 113 may create a distribution screen by combining a plurality of programs in accordance with the characteristics of the distribution destination device and the content of the information to be distributed. For example, the technology of a web server can be used for screen distribution, and information distributed can be viewed by a web browser executed by a distribution destination apparatus. Note that a dedicated application executed on the distribution destination device may create a screen to be displayed using the data transmitted from the information distribution server 113.

As described above, according to the embodiment of the present invention, it is possible to estimate the time when the train (transportation means) arrives at the station (alighting facility) and the time when the train leaves the station. In addition, the number of people on the train, the number of people who get off the train, and the number of people on the train can be estimated. Furthermore, by accumulating estimated values of train arrival / departure times, number of passengers, and number of people staying at the station, and calculating average values, it is possible to know whether train delays and congestion are abnormal than usual.

Specifically, a terminal having a different connection start location and connection end location is extracted from the public wireless LAN connection information 122, and the number of extracted terminals is multiplied by a rebate coefficient to obtain a transportation means (eg, train, bus, etc.). The number of people staying at boarding / exiting facilities (stations, terminals, etc.) is estimated in order to use a ferry, taxi, etc., so it is possible to know the degree of congestion of stations, etc. without making large capital investments. For this reason, when a plurality of stations are available, the passenger can select and use a vacant station. Transportation operators can ensure the safety of stations, etc. by assigning personnel or regulating the number of people according to the congestion level of stations. In addition, many transportation means (buses, taxis, etc.) can be dispatched to crowded platforms to reduce congestion in a short time.

In addition, the number of terminals using the transportation means is extracted by extracting from the public wireless LAN connection information 122 terminals whose connection start location and connection end location are the same, and multiplying the number of extracted terminals by a rebate coefficient. Therefore, it is possible to know the degree of congestion of trains and the like without making a large capital investment. Passengers can select and use available trains. Transportation companies can use it as basic data when planning congestion mitigation measures (for example, schedule revisions).

Further, when the time from the connection start time to the connection end time of the same terminal acquired from the public wireless LAN connection information 122 is equal to or longer than the predetermined time t, the time from the connection start time to the connection end time is divided. It is possible to estimate the exact number of people by appropriately dividing the data of users who used a station multiple times.

Also, since different rebate coefficients are defined depending on the time of day, it is possible to estimate the exact number of people corresponding to the fact that the nature of users varies depending on the time of day.

Further, the connection data between the base station and the terminal installed at the landing is obtained from the public wireless LAN connection information 122, and the statistical processing of the data is used to determine the time when the number of terminals that started the connection is large. Since the estimated time is the arrival time of the transportation means, it is possible to know the operation status (delay) of the train without making a large capital investment. The passenger can know the delay of the train before going to the station. Transportation companies can use the daily arrival time data as basic data for timetable improvement.

In addition, the connection data between the base station and the terminal installed at the landing is obtained from the public wireless LAN connection information 122, and the statistical processing of the data determines the time when the number of terminals that have completed the connection is large. Since the time is estimated to be the departure time of the transportation means, it is possible to know the operation status (delay) of the train without making a large capital investment. The passenger can know the delay of the train before going to the station. Transportation companies can use the daily arrival time data as basic data for timetable improvement.

In addition, when statistically processing connection data, since at least one of data less than a predetermined number and data whose appearance time is shorter than a predetermined time in a unit time is excluded, it is possible to accurately extract data resulting from the arrival and departure of transportation means. It is possible to prevent erroneous detection of time.

In addition, the average value of the estimated arrival time or departure time in a predetermined period is calculated, and the delay of the means of transportation is estimated by the difference between the calculated average value and the estimated arrival time or departure time. You can know the delay without a table.

The following are typical examples of aspects of the present invention other than those described in the claims.

(1) A traffic situation estimation system comprising a processor that executes a program and a storage device that stores the program,
Multiple base stations for wireless communication systems are installed at boarding facilities to use transportation means,
At least one of the base stations is installed at a place of getting on and off of the transportation means,
The storage device stores connection information including a connection start location and a connection end location between a terminal possessed by a user of the transportation means and any of the plurality of base stations,
The processor is
A terminal whose connection start location and connection end location are the same boarding / exiting location is extracted from the connection information,
A traffic situation estimation system for estimating the number of people using a transportation means by multiplying the number of extracted terminals by a predetermined second coefficient.

(2) A traffic situation estimation system comprising a processor that executes a program and a storage device that stores the program,
The base station of the wireless communication system is installed at the landing of the transportation means in a boarding facility for using the transportation means,
The storage device stores connection information including a connection start location and a connection start time between a terminal possessed by a user of the transportation means and any of the plurality of base stations,
The processor is
By statistical processing of connection data between the base station and the terminal installed at the landing included in the connection information, determine the time when the number of terminals that started connection is large,
A traffic situation estimation system for estimating the determined time as an arrival time of a transportation means.

(3) A traffic situation estimation system comprising a processor that executes a program and a storage device that stores the program,
The base station of the radio communication system is installed at the boarding place of the transportation means at the boarding facility for using the transportation means,
The storage device stores connection information including a connection end location and a connection end time between a terminal possessed by a user of the transportation means and any of the plurality of base stations,
The processor is
By the statistical processing of the connection data between the base station and the terminal installed at the landing included in the connection information, determine the time when the number of terminals that have terminated the connection is large,
A traffic situation estimation system for estimating the determined time as a departure time of a transportation means.

The present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the scope of the appended claims. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and the present invention is not necessarily limited to those having all the configurations described. A part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Moreover, you may add the structure of another Example to the structure of a certain Example. In addition, for a part of the configuration of each embodiment, another configuration may be added, deleted, or replaced.

In addition, each of the above-described configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them, for example, with an integrated circuit, and the processor realizes each function. It may be realized by software by interpreting and executing the program to be executed.

Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, and an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, and a DVD.

Also, the control lines and information lines indicate what is considered necessary for the explanation, and do not necessarily indicate all control lines and information lines necessary for mounting. In practice, it can be considered that almost all the components are connected to each other.

Claims

A traffic situation estimation system comprising a processor that executes a program and a storage device that stores the program,
Multiple base stations for wireless communication systems are installed at boarding facilities to use transportation means,
The storage device stores connection information including a connection start location and a connection end location between a terminal possessed by a user of the transportation means and any of the plurality of base stations,
The processor is
A terminal having a different connection start location and connection end location is extracted from the connection information,
A traffic situation estimation system for estimating the number of people staying at the boarding / exiting facility to use a transportation means by multiplying the number of extracted terminals by a predetermined first coefficient.
The traffic situation estimation system according to claim 1,
At least one of the base stations is installed at a place of getting on and off of the transportation means,
The processor is
A terminal whose connection start location and connection end location are the same boarding / exiting location is extracted from the connection information,
A traffic situation estimation system for estimating the number of people using a transportation means by multiplying the number of extracted terminals by a predetermined second coefficient.
The traffic situation estimation system according to claim 1,
The connection information includes a connection start time and a connection end time between the terminal and the base station,
The processor determines that the time between the connection start time and the connection end time is long by comparing the time from the connection start time to the connection end time of the same terminal acquired from the connection information with a predetermined time. A traffic situation estimation system that divides the time from the connection start time to the connection end time.
The traffic situation estimation system according to claim 1,
The traffic condition estimation system in which the storage device stores the first coefficient so that a different coefficient can be defined depending on a time zone.
The traffic situation estimation system according to claim 1,
The connection information includes a connection start time between the terminal and the base station,
At least one of the base stations is installed at the landing of the means of transportation;
The processor is
By statistical processing of connection data between the base station and the terminal installed at the landing included in the connection information, determine the time when the number of terminals that started connection is large,
A traffic situation estimation system for estimating the determined time as an arrival time of a transportation means.
The traffic situation estimation system according to claim 1,
The connection information includes a connection end time between the terminal and the base station,
At least one of the base stations is installed at a transportation platform,
The processor is
By the statistical processing of the connection data between the base station and the terminal installed at the landing included in the connection information, determine the time when the number of terminals that have terminated the connection is large,
A traffic situation estimation system for estimating the determined time as a departure time of a transportation means.
The traffic situation estimation system according to claim 5,
When the processor statistically processes the connection data, the processor extracts data resulting from the departure of the vehicle by excluding at least one of data less than a predetermined number and data having an appearance time shorter than the predetermined time in a unit time. Traffic situation estimation system.
The traffic situation estimation system according to claim 5,
The processor is
Calculating an average value of the estimated arrival time in a predetermined period;
A traffic situation estimation system for estimating a delay of a transportation means based on a difference between the calculated average value and the estimated arrival time.
A traffic situation estimation method executed by a computer,
The computer includes a processor that executes a program, and a storage device that stores the program,
Multiple base stations for wireless communication systems are installed at boarding facilities to use transportation means,
The storage device stores connection information including a connection start location and a connection end location between a terminal possessed by a user of the transportation means and any of the plurality of base stations,
The traffic situation estimation method is:
The processor extracting, from the connection information, a terminal having a connection start location and a connection end location different from each other;
The processor estimates the number of people staying at the boarding / alighting facility for using the transportation means by multiplying the number of extracted terminals by a predetermined first coefficient.
The traffic situation estimation method according to claim 9,
At least one of the base stations is installed at a place of getting on and off of the transportation means,
The traffic situation estimation method is:
The processor extracting from the connection information a terminal where the connection start location and the connection end location are the same boarding location;
A method of estimating the number of people using the transportation means by the processor multiplying the number of extracted terminals by a predetermined second coefficient.
The traffic situation estimation method according to claim 9,
The connection information includes a connection start time between the terminal and the base station,
At least one of the base stations is installed at the landing of the means of transportation;
The traffic situation estimation method is:
The processor determines a time when the number of terminals that have started connection is large by statistical processing of connection data between the base station installed at the landing and the terminal included in the connection information;
A method of estimating the traffic situation, wherein the processor estimates the determined time as an arrival time of a transportation means.
The traffic situation estimation method according to claim 9,
The connection information includes a connection end time between the base station and the terminal,
At least one of the base stations is installed at a transportation platform,
The processor determines a time when the number of terminals that have completed connection is large by statistical processing of connection data between a base station and the terminal installed at the landing included in the connection information;
A step of estimating the determined time as the departure time of the transportation means by the processor.