JP7428232B2 - Processing system, processing method and program - Google Patents

Description

The present invention relates to a processing system, a processing method, and a program.

Unauthorized boarding of vehicles (trains, etc.) without paying the fare for certain sections of the travel route has become a problem. Technologies related to the present invention are disclosed in Patent Documents 1 and 2.

Patent Document 1 identifies the station where each customer boarded the vehicle based on an image generated by a camera installed at the station or vehicle so as to capture the face of the customer boarding the vehicle, and the identified boarding station is located in the commuter pass section. If the venue is outside, the gate will be closed when leaving the venue. In addition, Patent Document 1 discloses that even if the specified boarding station is outside the commuter pass section, if the customer exits outside the commuter pass section, the insufficient fare will be settled and the boarding will no longer be illegal. It has been disclosed that gates will not be closed.

Patent Document 2 discloses a system for illegally boarding a train without paying the fare for an intermediate section sandwiched between two valid sections by using a ticket or a commuter pass that has two valid sections that do not overlap each other, including the boarding and disembarking stations. Discloses a device for discovery. The device writes a ticket gate code on the ticket or commuter pass when boarding the train, and determines that boarding is unauthorized if the ticket code is not written on the ticket or commuter pass at the time of exiting the ticket gate.

JP2019-67210A Japanese Unexamined Patent Publication No. 6-176226

There are high expectations for technology that can detect "unauthorized return rides." As shown in Figure 1, an unauthorized return trip involves a customer who holds a ticket between stations A and B, for example, enters at station A, then rides a vehicle headed for station D and travels to station D. Thereafter, at Station D, the passenger transfers to a vehicle in the opposite direction, travels to Station B, and exits at Station B. In the case of such a ride, the customer needs to pay not only the fare required to travel between stations A and B, but also the fare required to travel back and forth between stations A and D. However, in the case of a system that calculates fares based on the entry station and exit station detected at the entrance/exit gate, it is possible to detect boarding between station A, which is the entry station, and station B, which is the exit station, but it is possible to detect boarding between station A, which is the entry station, and station B, which is the exit station. Boarding to and from D station cannot be detected. If a passenger takes advantage of this fact and performs a turnaround trip as described above using only a ticket between Station A and Station B, this is an illegal turnaround trip.

For example, if D station is the starting station, it is more likely that you will receive benefits such as being able to sit in a seat if you board a train heading towards B station at D station than if you board a train heading towards B station at A station. Become. For these reasons, unauthorized turnarounds may occur.

Patent Document 1 is a technology for detecting illegal return rides. However, as in the technology disclosed in Patent Document 1, when it is determined that an illegal return ride is determined based on the detection of simply boarding a vehicle from outside the commuter pass section, it is also determined that it is an illegal return ride even when it is not an illegal return ride. There is a risk that it will happen. Patent Document 2 is not a technology for detecting illegal return rides.

An object of the present invention is to provide a new technique for detecting unauthorized return rides.

According to the invention,
customer information storage means for storing customer information including commuter pass section information and face information of the customer's commuter pass;
Entry/exit information acquisition means for acquiring information indicating the customer's entrance station and exit station;
customer detection means for identifying the station where the presence of the customer is detected by detecting the customer from an image generated by a camera installed at least one of the station and the vehicle based on the customer information;
Warning means for performing warning processing when the positional relationship of the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected satisfies a predetermined warning condition. and,
A processing system is provided.

Further, according to the present invention,
The computer is
Store customer information including commuter pass section information and facial information of the customer's commuter pass;
Obtaining information indicating the customer's entry station and exit station,
Based on the customer information, the station where the presence of the customer is detected is identified by detecting the customer from an image generated by a camera installed in at least one of the station and the vehicle;
A processing method for performing a warning process when the positional relationship between the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected satisfies a predetermined warning condition. is provided.

Further, according to the present invention,
computer,
customer information storage means for storing customer information including commuter pass section information and face information of the customer's commuter pass;
entrance/exit information acquisition means for acquiring information indicating the customer's entrance station and exit station;
Customer detection means for identifying the station where the presence of the customer is detected by detecting the customer from an image generated by a camera installed at least one of the station and the vehicle based on the customer information;
Warning means for performing warning processing when the positional relationship of the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected satisfies a predetermined warning condition. ,
A program is provided to enable this function.

According to the present invention, a new technique for detecting unauthorized return rides is realized.

FIG. 3 is a diagram for explaining an illegal turnaround. 1 is a diagram illustrating an example of the hardware configuration of a processing system according to the present embodiment. It is an example of the structure of the processing system of this embodiment. It is an example of the functional block diagram of the station system of this embodiment. It is an example of the functional block diagram of the processing system of this embodiment. FIG. 2 is a diagram schematically showing an example of information processed by the processing system of the present embodiment. It is a figure for explaining the effect of the processing system of this embodiment. It is a flowchart which shows an example of the flow of processing of the processing system of this embodiment. It is a flowchart which shows an example of the flow of processing of the processing system of this embodiment. It is a flowchart which shows an example of the flow of processing of the processing system of this embodiment.

<First embodiment>
First, an overview of the processing system of this embodiment will be explained. The processing system of this embodiment stores, for each customer, customer information including commuter pass section information of a commuter pass and facial information indicating facial appearance characteristics. Then, the processing system identifies the station where the customer was present based on the facial information and an image generated by a camera installed in at least one of the station and the vehicle. Then, the processing system performs a warning process when the positional relationship between the commuter pass section, the entry station, the exit station, and the station where the customer was present satisfies a predetermined warning condition. Warning processing involves closing the entrance/exit gate when a customer exits the station, lighting up a warning lamp, outputting a warning sound, notifying station staff, and calculating the fare for unauthorized boarding. An example of this is a process of notifying the station staff.

The processing system of this embodiment determines that an illegal return ride occurs when the four positional relationships of the commuter pass section, the entry station, the exit station, and the station where the customer was present satisfy a predetermined warning condition. In this way, the processing system of this embodiment makes appropriate judgments using appropriate and necessary information, and determines that it is an illegal return ride when it is not an illegal return ride, or determines that it is an illegal return ride when it is an illegal return ride. It is possible to reduce the occurrence of inconveniences such as determining that the vehicle is not on board.

The configuration of the processing system will be described in detail below. First, an example of the hardware configuration of the processing system will be described.

Each functional part of the processing system consists of the CPU (Central Processing Unit) of any computer, the memory, the program loaded into the memory, and the storage unit such as a hard disk that stores the program (the program is stored in advance at the stage of shipping the device). (In addition to programs, it can also store programs downloaded from storage media such as CDs (Compact Discs) or servers on the Internet, etc.), and is realized by any combination of hardware and software, centering on network connection interfaces. . It will be understood by those skilled in the art that there are various modifications to the implementation method and device.

FIG. 2 is a block diagram illustrating the hardware configuration of the processing system. As shown in FIG. 2, the processing system includes a processor 1A, a memory 2A, an input/output interface 3A, a peripheral circuit 4A, and a bus 5A. The peripheral circuit 4A includes various modules. The processing system may not include the peripheral circuit 4A. Note that the processing system may be composed of a plurality of physically and/or logically separated devices, or may be composed of one physically and/or logically integrated device. When the processing system is composed of a plurality of physically and/or logically separated devices, each of the plurality of devices can be equipped with the above hardware configuration.

The bus 5A is a data transmission path through which the processor 1A, memory 2A, peripheral circuit 4A, and input/output interface 3A exchange data with each other. The processor 1A is, for example, an arithmetic processing device such as a CPU or a GPU (Graphics Processing Unit). The memory 2A is, for example, a RAM (Random Access Memory) or a ROM (Read Only Memory). The input/output interface 3A includes an interface for acquiring information from an input device, an external device, an external server, an external sensor, a camera, etc., an interface for outputting information to an output device, an external device, an external server, etc. . Input devices include, for example, a keyboard, mouse, microphone, physical button, touch panel, and the like. Examples of the output device include a display, a speaker, a printer, and a mailer. The processor 1A can issue commands to each module and perform calculations based on the results of those calculations.

Next, the functional configuration of the processing system will be explained in detail. As shown in FIG. 3, the processing system 10 includes a center system 1 and a plurality of station systems 2. The station system 2 is a system that executes processes related to each station, and is installed at each station. The center system 1 is a system that communicates with a plurality of station systems 2 and manages the entire system in an integrated manner, and is installed at an arbitrary location.

As shown in FIG. 4, the station system 20 includes a station server 21, a camera 22, an entrance/exit gate 23, and the like. The camera 22 is installed at an arbitrary position within the station premises and generates moving images and still images. The station server 21 and camera 22 are configured to be communicable. The station server 21 receives the image generated by the camera 22 and transmits it to the center system 1.

The entry/exit gate 23 is a gate for controlling entry/exit to the station platform. When a customer passes through the entrance/exit gate 23, he/she collects predetermined information (card identification information, customer information, etc.) stored on an IC card, magnetic card, mobile terminal (smartphone, mobile phone, smart watch, tablet terminal, etc.), etc. is input into the entrance/exit gate 23. The entry/exit gate 23 controls opening and closing of the gate based on the input information. Since the processing by the entrance/exit gate 23 is widely known, the explanation here will be omitted. The station server 21 and the entrance/exit gate 23 are configured to be able to communicate with each other. The station server 21 receives the above-mentioned predetermined information from the entrance/exit gate 23 and transmits it to the center system 1.

FIG. 5 shows an example of a functional block diagram of the processing system 10. As illustrated, the processing system 10 includes a customer information storage section 11, an entrance/exit information acquisition section 12, a customer detection section 13, and a warning section 14.

The customer information storage unit 11 stores customer information of each of a plurality of customers. FIG. 6 schematically shows an example of customer information. Customer information includes information that identifies the customer. Information that identifies customers includes name, gender, age, telephone number, address, facial information, etc. Facial information is information indicating the appearance characteristics of the customer's face. The face information may be a face image or a predetermined feature extracted from the face image. This information is information registered in advance.

Further, the customer information includes information indicating the details of the commuter pass purchased by the customer (commuter ticket information). The commuter pass information includes commuter pass section information indicating the travelable range with the commuter pass and the validity period of the commuter pass. This information is information registered at the time of purchasing a commuter pass.

Further, the customer information includes information indicating an entry station, information indicating an exit station, and information indicating a detection station. The detection station is a station where the presence of the customer was confirmed after entering from the entry station and before exiting from the exit station. These pieces of information are information updated by the entrance/exit information acquisition section 12 and the customer detection section 13, which will be described below.

Note that the customer information may include the amount charged at that time. Further, the customer information may include usage history. The usage history includes entry station, date and time of entry, station of exit, date and time of exit, etc. Further, the usage history may include the usage history of the charged money (date of usage, location of usage, amount of money spent, date of charging, location of charging, amount of charging, etc.). This information is updated according to the amount of money charged or the use of the commuter pass.

The customer information storage unit 11 is provided in the center system 1. That is, the center system 1 holds customer information for each of a plurality of customers. In addition, as a modification, the station system 2 may hold at least a part of the customer information. Then, the customer information held by the center system 1 and the customer information held by the station system 2 may be synchronized using any synchronization means to ensure the sameness of content.

Returning to FIG. 5, the entrance/exit information acquisition unit 12 acquires information indicating the customer's entrance station and exit station. As mentioned above, when the customer passes through the entrance/exit gate 23, the customer must collect predetermined information (card identification information, card identification information, (customer information, etc.) is input into the entrance/exit gate 23. The entrance/exit information acquisition unit 12 receives information for identifying the customer input into the entrance/exit gate 23 (card identification information, customer information, etc.) and information for identifying the station where the entrance/exit gate 23 is installed. get. This information makes it possible to identify which customers entered at which stations and at which stations they exited. Upon acquiring the information indicating the customer's entrance station and exit station, the entrance/exit information acquisition unit 12 registers the entrance station and exit station in the customer's customer information (see FIG. 6) (update of customer information).

The entrance/exit information acquisition unit 12 may be provided in the center system 1 or the station system 2.

In this specification, "acquisition" refers to "a process in which the own device retrieves data stored in another device or storage medium (actively)" based on user input or program instructions. (e.g., requesting or interrogating and receiving from other devices, accessing and reading other devices or storage media, etc.), and based on user input or program instructions. "Inputting data output from another device into one's own device (passive acquisition)," for example, receiving data that is distributed (or sent, push notification, etc.), and receiving received data or information. "Create new data by editing the data (converting it into text, sorting the data, extracting some data, changing the file format, etc.), and ``Obtaining data.''

The customer detection unit 13 detects a customer by searching for a person who has the appearance characteristics indicated by the facial information included in the customer information from images generated by cameras installed in at least one of the station and the vehicle. do. Since the image analysis method is widely known, its explanation here will be omitted.

Through the detection process, the customer detection unit 13 identifies the station where the presence of the customer is detected (detection station). For example, the customer detection unit 13 can identify the station where the camera that generated the image in which the customer was detected is installed as the station where the presence of the customer was detected. Further, if the camera that generated the image in which the customer was detected is installed in the vehicle, the customer detection unit 13 can identify the station where the vehicle was present when the image was generated as the station where the presence of the customer was detected. . There are no particular restrictions on the method of identifying the station where a vehicle was present when a certain image was generated. For example, the camera may be equipped with current position information acquisition means (GPS (global positioning system), etc.), and information indicating the position at the time each image was generated may be added to each image. Note that this illustrated process is just an example, and the process is not limited thereto.

Then, the customer detection unit 13 registers the detection station where the presence of the customer is detected in the customer information (see FIG. 6) of the customer detected from the image (update of customer information). Note that the customer detection unit 13 may register the identified detection station in the customer information when the detection station is not included in the commuter pass section of the customer. If the detected station is included in the customer's commuter pass section, the customer detection unit 13 does not need to register the identified detected station in the customer information.

The customer detection unit 13 is provided in the center system 1. That is, images generated by cameras installed in at least one of the station and the vehicle are transmitted to the center system 1. Then, the center system 1 analyzes the received image, detects the customer from the image, and updates the customer information.

As a modified example, if the station system 2 holds part of the customer information (information necessary for customer detection through image analysis such as facial information and name), the customer detection unit 13 may It may be provided in the server 21. That is, images generated by cameras installed in at least one of the station and the vehicle are transmitted to the station server 21. For example, an image generated by a camera installed at a station is transmitted to the station server 21 of that station. Moreover, the image generated by the camera installed in the vehicle is transmitted to an arbitrary station server 21 (station server 21 of the nearest station). Then, the station server 21 analyzes the received image, detects the customer from the image, and updates the customer information stored in the center system 1.

As another modification, if the station system 2 holds all customer information, the customer detection unit 13 may be provided in the station server 21 of the station system 2. That is, images generated by cameras installed in at least one of the station and the vehicle are transmitted to the station server 21. For example, an image generated by a camera installed at a station is transmitted to the station server 21 of that station. Moreover, the image generated by the camera installed in the vehicle is transmitted to an arbitrary station server 21 (station server 21 of the nearest station). Then, the station server 21 analyzes the received image, detects the customer from the image, and updates the customer information stored in the station system 2. Thereafter, using an arbitrary synchronization means, the customer information held by the center system 1 and the customer information held by the station system 2 are synchronized to ensure the sameness of content.

When the customer exits from the entry/exit gate 23, the warning unit 14 detects that the positional relationship of the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected is in a predetermined manner. Determine whether the warning conditions are met, and perform warning processing if the conditions are met. The warning process includes closing the entrance/exit gate 23, lighting up a warning lamp, outputting a warning sound, notifying the station staff, and calculating the fare for the unauthorized boarding and notifying the station staff. Examples include, but are not limited to. The warning condition includes at least one of the following warning conditions 1 to 5.

"Warning condition 1: Entry station and exit station are within the commuter pass section, and the detection station is outside the commuter pass section"
According to the warning condition, for example, as shown in Figure 7, a customer who holds a commuter pass whose commuter pass section is between stations A and B enters at station A and then enters the train in the direction of station D. It is possible to detect an illegal return ride (pattern 1) in which a person rides a vehicle and travels to station D, then changes to a vehicle in the opposite direction at station D, travels to station B, and exits at station B. In this case, A station is the entry station, D station is the detection station, B station is the exit station, and boarding between A station and D station is illegal boarding.

Also, according to the warning condition, for example, as shown in FIG. 7, a customer who holds a commuter pass whose commuter pass section is between stations A and B, enters at station A and then stops at station B. It is possible to detect an illegal turnaround (pattern 2) in which the user rides a vehicle in the opposite direction and travels to station E, then changes to a vehicle in the opposite direction at station E, travels to station B, and exits at station B. In this case, A station is the entry station, E station is the detection station, B station is the exit station, and the boarding between B station and E station is illegal boarding.

Also, according to the warning condition, for example, as shown in FIG. 7, a customer who holds a commuter pass whose commuter pass section is between stations A and B enters at station A, then stops at station D. Take a vehicle going in the direction and travel to station D, then at station D change to a vehicle in the opposite direction and travel to station E, then change to a vehicle in the opposite direction at station E and travel to station B, then transfer to station B. It is possible to detect an illegal turnaround (pattern 3) in which a passenger exits the vehicle at a stop. In this case, A station will be the entry station, D and E stations will be the detection station, B station will be the exit station, and passengers will be able to board between A and D stations, and between B and E stations. is considered an illegal ride.

Note that, according to the warning condition, it is ensured that no detection station exists between the entry station and the exit station. This avoids the inconvenience of incorrectly determining that a legitimate ride (a ride for which the fare has been correctly paid) is an unauthorized return ride.

Further, according to the warning condition, it is possible to detect an illegal return ride due to the use of a commuter pass, and therefore it is possible to detect an illegal return ride due to the use of a commuter pass, which is presumed to be habitual.

"Warning condition 2: A commuter pass section exists between the entry station and the exit station, the detection station is outside the commuter pass section, and there is no detection station between the entry station and the exit station."
According to the warning conditions, the above patterns 1 to 3 can be detected. Also, according to the warning condition, for example, as shown in FIG. 7, a customer who holds a commuter pass whose commuter pass section is between stations A and B enters at station C, then stops at station D. It is possible to detect an illegal turnaround (pattern 4) in which the user rides a vehicle in the direction of travel to station D, then transfers to a vehicle in the opposite direction at station D, travels to station B, and exits at station B. In this case, C station is the entry station, D station is the detection station, B station is the exit station, and boarding between C station and D station is illegal boarding.

Also, according to the warning condition, for example, as shown in FIG. 7, a customer who holds a commuter pass whose commuter pass section is between stations A and B enters at station C, then stops at station D. It is possible to detect an illegal turnaround (pattern 5) in which the user rides a vehicle in the opposite direction to station D, then transfers to a vehicle in the opposite direction at station D, travels to station F, and exits at station F. In this case, C station is the entry station, D station is the detection station, F station is the exit station, and boarding between C station and D station is illegal boarding.

Also, according to the warning condition, for example, as shown in FIG. 7, a customer who holds a commuter pass whose commuter pass section is between stations A and B, enters at station A and then stops at station B. It is possible to detect an illegal turnaround (pattern 6) in which the user rides a vehicle in the opposite direction to Station E, then transfers to a vehicle in the opposite direction at Station E, travels to Station F, and exits at Station F. In this case, A station is the entry station, E station is the detection station, F station is the exit station, and boarding between E station and F station is illegal boarding.

Furthermore, according to the warning condition, for example, as shown in FIG. It is possible to detect an illegal turnaround (pattern 7) in which the user rides a vehicle in the opposite direction and travels to Station E, then changes to a vehicle in the opposite direction at Station E, travels to Station F, and exits at Station F. In this case, C station is the entry station, E station is the detection station, F station is the exit station, and boarding between E station and F station is illegal boarding.

Also, according to the warning condition, for example, as shown in FIG. 7, a customer who holds a commuter pass whose commuter pass section is between stations A and B enters at station C, then stops at station D. Get on a car going in the direction and go to station D, then change to a car in the opposite direction at station D and go to station E, then change to a car in the opposite direction at station E and go to station F, then go to station F. It is possible to detect an illegal turnaround (pattern 8) in which the passenger exits the vehicle at a stop. In this case, C station will be the entry station, D station and E station will be the detection station, F station will be the exit station, and passengers will be able to board between C and D stations and between E and F stations. is considered an illegal ride.

Also, according to the warning condition, for example, as shown in FIG. 7, a customer who holds a commuter pass whose commuter pass section is between stations A and B enters at station A, then stops at station D. It is possible to detect an illegal turnaround (pattern 9) in which a passenger rides a vehicle in the direction of the train to station D, then changes to a vehicle in the opposite direction at station D, travels to station F, and exits at station F. In this case, A station is the entry station, D station is the detection station, F station is the exit station, and boarding between A station and D station is illegal boarding.

Furthermore, according to the warning condition, for example, as shown in FIG. It is possible to detect an illegal return ride (pattern 10) in which the user rides a vehicle in the opposite direction and travels to station E, then changes to a vehicle in the opposite direction at station E, travels to station B, and exits at station B. In this case, C station is the entry station, E station is the detection station, B station is the exit station, and the boarding between B station and E station is illegal boarding.

Note that the condition that ``no detection station exists between the entry station and the exit station'' avoids the inconvenience of erroneously determining that a legitimate boarding (boarding for which the fare has been correctly paid) is an unauthorized return boarding.

Further, according to the warning condition, it is possible to detect an illegal return ride due to the use of a commuter pass, and therefore it is possible to detect an illegal return ride due to the use of a commuter pass, which is presumed to be habitual.

"Warning condition 3: The entry station is within the commuter pass section, the detection station is outside the commuter pass section, the exit station is outside the commuter pass section, and the exit station is opposite the detection station across the commuter pass section. It's a nearby station.''
According to the warning condition, for example, pattern 9 described above can be detected. Note that, according to the warning condition, it is ensured that no detection station exists between the entry station and the exit station. This avoids the inconvenience of incorrectly determining that a legitimate ride (a ride for which the fare has been correctly paid) is an unauthorized return ride. Further, according to the warning condition, it is possible to detect an illegal return ride due to the use of a commuter pass, and therefore it is possible to detect an illegal return ride due to the use of a commuter pass, which is presumed to be habitual.

Warning condition 4: The exit station is within the commuter pass section, the detection station is outside the commuter pass section, the entry station is outside the commuter pass section, and the entry station is on the same side of the commuter pass section as the detection station. station, and the entry station is a station between the detection station and the exit station.
According to the warning condition, for example, pattern 4 described above can be detected. Note that the condition that "the entry station is a station between the detection station and the exit station" ensures that there is no detection station between the entry station and the exit station. This avoids the inconvenience of incorrectly determining that a legitimate ride (a ride for which the fare has been correctly paid) is an unauthorized return ride. Further, according to the warning condition, it is possible to detect an illegal return ride due to the use of a commuter pass, and therefore it is possible to detect an illegal return ride due to the use of a commuter pass, which is presumed to be habitual.

Warning condition 5: The detection station is outside the commuter pass section, the exit station is outside the commuter pass section, the exit station is on the opposite side of the commuter pass section from the detection station, and the entry station is outside the commuter pass section. outside, the entry station is on the same side of the commuter pass section as the detection station, and the entry station is between the detection station and the exit station.
According to the warning condition, for example, pattern 5 described above can be detected. Note that the condition that "the entry station is a station between the detection station and the exit station" ensures that there is no detection station between the entry station and the exit station. This avoids the inconvenience of incorrectly determining that a legitimate ride (a ride for which the fare has been correctly paid) is an unauthorized return ride. Further, according to the warning condition, it is possible to detect an illegal return ride due to the use of a commuter pass, and therefore it is possible to detect an illegal return ride due to the use of a commuter pass, which is presumed to be habitual.

The warning unit 14 is provided in the station system 2. That is, the station server 21 or the entrance/exit gate 23 refers to the customer information stored in the center system 1 or the station system 2, and determines the commuter pass section, entry station, exit station, and detection station indicated by the commuter pass section information. It is determined whether the positional relationship between the two satisfies a predetermined warning condition, and if the condition is satisfied, a warning process is performed. In addition, as a modification, the center system 1 may include the warning unit 14 and perform the above-mentioned judgment and warning processing.

Next, an example of the processing flow of the processing system 10 will be explained.

The flowchart in FIG. 8 shows an example of the flow of processing performed by the processing system 10 when a customer enters through the entrance/exit gate 23. The entrance/exit information acquisition unit 12 receives information for identifying the customer input into the entrance/exit gate 23 (card identification information, customer information, etc.) and information for identifying the station where the entrance/exit gate 23 is installed. When acquired (Yes in S10), the station specified by the information is registered as an entry station in the customer information (see FIG. 6) of the customer specified by the information (S11).

The flowchart in FIG. 9 shows an example of the flow of processing that the processing system 10 continuously performs while the vehicle is in operation.

When the customer detection unit 13 acquires an image generated by a camera installed in at least one of a station and a vehicle (S20), the customer detection unit 13 identifies a customer from among the images based on the customer's facial information stored in the customer information storage unit 11. A process of detecting is performed (S21). When the customer detection unit 13 detects a customer from the image, the customer information includes the station indicated by the image (the station where the camera is installed, the station where the camera was located when the image was generated). is registered as a detection station (S22). Note that the customer detection unit 13 may register the identified detection station in the customer information when the detection station is not included in the commuter pass section. If the detected station is included in the commuter pass section, the customer detection unit 13 does not need to register the specified detected station in the customer information.

The flowchart in FIG. 10 shows an example of the flow of processing performed by the processing system 10 when a customer exits from the entrance/exit gate 23. The entrance/exit information acquisition unit 12 receives information for identifying the customer input into the entrance/exit gate 23 (card identification information, customer information, etc.) and information for identifying the station where the entrance/exit gate 23 is installed. When acquired (Yes in S30), the station specified by the information is registered as an exit station in the customer information (see FIG. 6) of the customer specified by the information (S31).

Next, the warning unit 14 determines whether the positional relationship among the commuter pass section, entry station, exit station, and detection station registered in the customer information satisfies a predetermined warning condition (S32). If the warning condition is satisfied (Yes in S32), the warning unit 14 performs warning processing. On the other hand, if the warning condition is not satisfied (No in S32), the warning unit 14 does not perform the warning process. The warning process includes closing the entrance/exit gate 23, lighting up a warning lamp, outputting a warning sound, notifying the station staff, and calculating the fare for the unauthorized boarding and notifying the station staff. Examples include, but are not limited to.

Here, a modification of this embodiment will be described. The customer information (see FIG. 6) may include the number of times fraudulent return rides have been detected. Then, if the positional relationship between the commuter pass section, the entry station, the exit station, and the detection station satisfies a predetermined warning condition, the warning unit 14 increases the number of detected fraudulent return rides in the customer information of that customer by "1". You can. Then, the warning unit 14 may perform the above-mentioned warning process when the number of times exceeds a threshold value. With such a configuration, it is possible to detect a habitual user who repeatedly makes illegal return rides.

According to the processing system 10 of the present embodiment described above, four pieces of appropriate information: the commuter pass section, the entry station, the exit station, and the detection station (the station where the customer was present) are used to prevent fraudulent call-backs based on the positional relationship between these pieces of information. Decide whether to ride or not. In this way, by making appropriate judgments using appropriate and necessary information, the processing system 10 of the present embodiment can determine that it is an unauthorized return ride when it is not an unauthorized return ride, or determine that it is an unauthorized return ride when it is an unauthorized return ride. It is possible to reduce the occurrence of inconveniences such as determining that it is not a return ride.

In addition, by setting the characteristic warning conditions as described above, it is possible to detect illegal turnarounds with high accuracy. For example, it is possible to detect multiple patterns of unauthorized return rides as described above.

In addition, by referring to the commuter pass section in the process of detecting unauthorized return rides, it is possible to detect unauthorized return rides that are presumed to be habitual due to the use of commuter passes.

In addition, as mentioned above, by registering only the detected stations that are not included in the commuter pass section among the identified detected stations in the customer information, processing of unnecessary information is avoided and the computer burden is reduced. . As is clear from the above description, the detection stations included in the commuter pass section are information that is not necessary for detecting unauthorized return rides.

<Second embodiment>
The customer detection unit 13 of the present embodiment detects information in the image based on customer information of a customer for whom information indicating an entrance station has been acquired by the entrance/exit information acquisition unit 12, and for which information indicating an exit station has not been subsequently acquired. Perform processing to detect customers from . Note that the customer detection unit 13 does not need to use customer information of other customers in the process of detecting customers from images.

A "customer for whom information indicating the station of entry has been acquired by the entrance/exit information acquisition unit 12, and information indicating the exit station has not been acquired after that" is a customer who enters from the entrance/exit gate 23 of a certain station and then exits the station. Not a customer. In other words, the customer is a customer who may travel in a vehicle. By narrowing down the facial information referenced in image processing to such customer facial information, the processing load on the computer can be reduced, and customer detection accuracy can be improved. Since customers other than the customer have not entered the station premises at that time, the customers will not be detected from the image. Therefore, there is no particular problem even if such customer face information is not referred to.

Further, the customer detection unit 13 of the present embodiment detects the images generated by each camera based on the information indicating the entrance station acquired by the entrance/exit information acquisition unit 12 and the information indicating the position of the camera that generated the image. Customer information used in the process of detecting customers from among them may be narrowed down. For example, if X station and Y station are far apart, it is unlikely that a customer who entered at X station will be included in the images generated at Y station. By removing customer face information that is unlikely to be detected from the reference information, the processing load on the computer can be reduced and customer detection accuracy can be improved. Here, an example of a narrowing down algorithm will be described, but it is not limited to this.

For example, if it is detected that customer A has entered at station X, the face information of customer A may be referenced when analyzing an image generated at a station whose distance from station X is within a threshold value. Further, the threshold value may be changed so as to gradually increase as time elapses from the timing when entry at the X station is detected.

The other configuration of the processing system 10 is the same as that of the first embodiment.

According to the processing system 10 of this embodiment described above, the same effects as those of the processing system 10 of the first embodiment are realized. In addition, since the customer face information referred to in the image analysis by the customer detection unit 13 can be appropriately narrowed down, it is possible to reduce the number of customer detection failures, reduce the processing load on the computer, and improve customer detection accuracy. Can be done.

<Third embodiment>
The processing system 10 of this embodiment aims at detecting illegal return rides when boarding based on a ticket other than a commuter pass. A ride based on a ticket other than a commuter pass is, for example, a ride based on an IC card charged with a certain amount, a magnetic card, a mobile terminal (smartphone, mobile phone, smart watch, tablet terminal, etc.), etc. For example, when an IC card or magnetic card is issued, customer information as shown in FIG. 6 is registered in the processing system 10 in association with the issued IC card or magnetic card. Further, at the time of initial registration using a predetermined application installed on the mobile terminal, customer information as shown in FIG. 6 is registered in the processing system 10.

When a customer passes through the entrance/exit gate 23, he/she collects predetermined information (card identification information, customer information, etc.) stored on an IC card, magnetic card, mobile terminal (smartphone, mobile phone, smart watch, tablet terminal, etc.), etc. is input into the entrance/exit gate 23. The subsequent processing is the same as in the first and second embodiments.
The warning condition of this embodiment is "there is no detected station between the entry station and the exit station".

The other configurations of the processing system 10 are the same as those in the first and second embodiments.

According to the processing system 10 of this embodiment described above, the same effects as those of the processing system 10 of the first and second embodiments are realized. Further, according to the processing system 10 of the present embodiment, it is possible to detect fraudulent return rides when boarding based on a ticket other than a commuter pass.

<Modified example>
Modifications applicable to all embodiments will be described. Up to this point, it has been assumed that the processing system 10 is configured by the center system 1 and the station system 2, but the processing system 10 may be configured by only one of the center system 1 and the station system 2. That is, either the center system 1 or the station system 2 may include all of the customer information storage section 11, the entrance/exit information acquisition section 12, the customer detection section 13, and the warning section 14.

Although the present invention has been described above with reference to the embodiments (and examples), the present invention is not limited to the above embodiments (and examples). The configuration and details of the present invention can be modified in various ways that can be understood by those skilled in the art within the scope of the present invention.

Part or all of the above embodiments may be described as in the following supplementary notes, but the embodiments are not limited to the following.
1. customer information storage means for storing customer information including commuter pass section information and face information of the commuter pass;
Entry/exit information acquisition means for acquiring information indicating the customer's entrance station and exit station;
customer detection means for identifying the station where the presence of the customer is detected by detecting the customer from an image generated by a camera installed at least one of the station and the vehicle based on the customer information;
Warning means for performing warning processing when the positional relationship of the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected satisfies a predetermined warning condition. and,
A processing system with
2. The customer detection means detects the image based on the customer information of the customer for whom the information indicating the entry station has been acquired by the entry/exit information acquisition means, and for which the information indicating the exit station has not been subsequently acquired. 2. The processing system according to 1, which performs a process of detecting the customer from inside.
3. The customer detection means selects one of the images generated by the camera based on information indicating the entrance station acquired by the entry/exit information acquisition means and information indicating the position of the camera that generated the image. 3. The processing system according to 1 or 2, which narrows down the customer information used in the process of detecting the customer.
4. 4. The processing system according to any one of 1 to 3, wherein the warning condition is that the entry station and the exit station are within the commuter pass section, and the detection station is outside the commuter pass section.
5. The warning condition is that the commuter pass section exists between the entry station and the exit station, the detection station is outside the commuter pass section, and the station is between the entry station and the exit station. 5. The processing system according to any one of 1 to 4, wherein the detection station does not exist.
6. The warning condition is such that the entry station is within the commuter pass section, the detection station is outside the commuter pass section, the exit station is outside the commuter pass section, and the exit station is outside the commuter pass section. 6. The processing system according to any one of 1 to 5, which is a station on the opposite side of the detection station across a section.
7. The warning condition is such that the exit station is within the commuter pass section, the detection station is outside the commuter pass section, the entry station is outside the commuter pass section, and the entry station is outside the commuter pass section. 7. The processing system according to any one of 1 to 6, wherein the station is on the same side as the detection station, and the entry station is a station between the detection station and the exit station.
8. The warning condition is that the detection station is outside the commuter pass section, the exit station is outside the commuter pass section, and the exit station is a station on the opposite side of the commuter pass section from the detection station. , the entry station is outside the commuter pass section, the entry station is on the same side of the commuter pass section as the detection station, and the entry station is between the detection station and the exit station. The processing system according to any one of 1 to 7, which is a station.
9. The computer is
Store customer information including commuter pass section information and face information of the commuter pass;
Obtaining information indicating the customer's entry station and exit station,
Based on the customer information, the station where the presence of the customer is detected is identified by detecting the customer from an image generated by a camera installed at least one of the station and the vehicle;
A processing method for performing a warning process when the positional relationship of the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected satisfies a predetermined warning condition. .
10. computer,
customer information storage means for storing customer information including commuter pass section information and face information of the commuter pass;
entrance/exit information acquisition means for acquiring information indicating the customer's entrance station and exit station;
customer detection means for identifying the station where the presence of the customer is detected by detecting the customer from an image generated by a camera installed in at least one of the station and the vehicle based on the customer information;
Warning means for performing warning processing when the positional relationship of the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected satisfies a predetermined warning condition. ,
A program that functions as

Claims (5)

customer information storage means for storing customer information including commuter pass section information and face information of the customer's commuter pass;
Entry/exit information acquisition means for acquiring information indicating the customer's entrance station and exit station;
customer detection means for identifying the station where the presence of the customer is detected by detecting the customer from an image generated by a camera installed at least one of the station and the vehicle based on the customer information;
Warning means for performing warning processing when the positional relationship of the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected satisfies a predetermined warning condition. and,
has
The customer detection means selects one of the images generated by the camera based on information indicating the entry station acquired by the entry/exit information acquisition means and information indicating the position of the camera that generated the image. A processing system that narrows down the customer information used in the process of detecting the customer . The customer detection means detects the image based on the customer information of the customer for whom the information indicating the entry station has been acquired by the entry/exit information acquisition means, and for which the information indicating the exit station has not been subsequently acquired. The processing system according to claim 1, wherein the processing system performs a process of detecting the customer from inside. The warning condition is
The entry station and the exit station are within the commuter pass section, and the detection station is outside the commuter pass section;
The commuter pass section exists between the entry station and the exit station, the detection station is outside the commuter pass section, and the detection station exists between the entry station and the exit station. What not to do,
The entry station is within the commuter pass section, the detection station is outside the commuter pass section, the exit station is outside the commuter pass section, and the exit station is located on either side of the commuter pass section. The station must be on the opposite side of the detection station.
The exit station is within the commuter pass section, the detection station is outside the commuter pass section, the entry station is outside the commuter pass section, and the entry station is located at the detection station across the commuter pass section. and the entrance station is a station between the detection station and the exit station, and
The detection station is outside the commuter pass section, the exit station is outside the commuter pass section, the exit station is a station on the opposite side of the commuter pass section from the detection station, and the entry station is The station is outside the commuter pass section, the entry station is on the same side of the commuter pass section as the detection station, and the entry station is between the detection station and the exit station. ,
The processing system according to claim 1 or 2, comprising at least one of the following conditions. The computer is
Store customer information including commuter pass section information and facial information of the customer's commuter pass;
Obtaining information indicating the customer's entry station and exit station,
Based on the customer information, the station where the presence of the customer is detected is identified by detecting the customer from an image generated by a camera installed in at least one of the station and the vehicle;
If the positional relationship of the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected satisfies a predetermined warning condition, perform a warning process;
In the process of identifying the station where the presence of the customer is detected, the information in the image generated by the camera is based on the acquired information indicating the entry station and information indicating the position of the camera that generated the image. A processing method for narrowing down the customer information to be used in a process of detecting the customer . computer,
customer information storage means for storing customer information including commuter pass section information and face information of the customer's commuter pass;
entrance/exit information acquisition means for acquiring information indicating the customer's entrance station and exit station;
Customer detection means for identifying the station where the presence of the customer is detected by detecting the customer from an image generated by a camera installed at least one of the station and the vehicle based on the customer information;
Warning means for performing warning processing when the positional relationship of the commuter pass section indicated by the commuter pass section information, the entry station, the exit station, and the detection station where the presence of the customer is detected satisfies a predetermined warning condition. ,
function as
The customer detection means selects one of the images generated by the camera based on information indicating the entry station acquired by the entry/exit information acquisition means and information indicating the position of the camera that generated the image. A program that narrows down the customer information used in the process of detecting the customer .

Images