Method, server, and system

Abstract

Provided are a computer-implemented method, a server, and a system.　This method comprises: receiving, from a passenger device detector configured to detect a passenger device, passenger device information including the number of estimated passenger devices in a first vehicle of a mass transport system; receiving the number of passengers in the first vehicle from a passenger counting device; and comparing the number of estimated passenger devices from the passenger device detector and the number of passengers from the passenger counting device to generate passenger estimation correction information. The method then comprises: receiving, from a second passenger device detector configured to detect a passenger device, further passenger device information including the number of estimated passenger devices in a second vehicle of the mass transport system; and utilizing the passenger estimation correction information to estimate the number of passengers in the second vehicle from the further passenger device information.

Description

Method, server, and system

[0001] The present invention relates to a computer-implemented method for estimating passenger numbers in a mass transit system and a passenger flow analysis server for estimating passenger numbers in a mass transit system.

[0002]

[0003] Operators of mass transit systems, including multiple vehicles such as buses, streetcars, and trains, require data indicating the number of passengers using the mass transit system in order to predict and meet vehicle requirements and ensure efficient operation of the mass transit system. For example, bus routes and timetables for each route can be adjusted to match predicted demand. Therefore, accurate estimates of the number of passengers using the mass transit system and the origin / destination of passengers during their trip are required.

[0003] Some existing solutions for estimating passenger numbers include automated passenger counting systems, such as camera counting systems or ticket counting systems. Such systems can estimate the number of passengers using each section of a transportation network, such as a section between adjacent bus stops on a bus route. However, these solutions provide little information about the origin / destination of each passenger. Furthermore, mass transit systems often include vehicles and / or routes that are not equipped with such automated passenger counting systems, such as older buses or rail routes with small stations. Therefore, passenger numbers cannot be accurately estimated in such cases. Furthermore, such automated passenger counting systems can be expensive and complex to install, making it undesirable to provide them on every vehicle in a transportation system.

[0004] Additionally, device detection technologies exist for detecting wireless signals from user devices. It is expected that most passengers using mass transit systems will travel with personal devices such as smartphones, tablets, or laptops. Such devices typically perform wireless advertising (e.g., Bluetooth (RTM) or Wi-Fi (RTM)) to request a wireless connection (this is sometimes called a probe request).

[0005] The present invention has been devised with the above considerations in mind.

[0006] Generally, the present invention relates to a method for monitoring passengers using a mass transit system, utilizing a combination of passenger counting devices and passenger device detectors, which utilizes data from the passenger counting devices and passenger device detectors to determine a correction ratio between the number of passenger devices detected in a vehicle and the actual number of passengers in that vehicle, which can be used to estimate the number of passengers in other vehicles not equipped with passenger counting devices.

[0007] Accordingly, in a first aspect, an embodiment of the present invention provides a computer-implemented method for estimating a number of passengers in a mass transit system, the method including: receiving passenger device information including an estimated number of passenger devices in a first vehicle of the mass transit system from a passenger device detector configured to detect passenger devices; receiving a number of passengers in the first vehicle from a passenger counting device; comparing the estimated number of passenger devices from the passenger device detector with the number of passengers from the passenger counting device to generate passenger estimation correction information; receiving further passenger device information including an estimated number of passenger devices in a second vehicle of the mass transit system from a second passenger device detector configured to detect passenger devices; and utilizing the passenger estimation correction information to estimate the number of passengers in the second vehicle from the further passenger device information.

[0008] Advantageously, by utilizing data from the first vehicle having a passenger counting device to determine the correction information, a more accurate estimate of passenger numbers can be determined for vehicles not equipped with passenger counting devices. Thus, accurate measurements of vehicle load, demand, and available capacity can be obtained, allowing mass transit system operators to more accurately forecast further demand and capacity. For example, if passenger counts on a particular vehicle route are low, mass transit system vehicles assigned to that route can be reallocated to save fuel and increase available capacity on other routes. In this manner, mass transit operations can adapt to better meet vehicle demand, reduce passenger travel times, and increase the efficiency of the mass transit system as a whole.

[0009] A mass transit system, also called a transit network or public transit network, can be a plurality of vehicles for transporting passengers, the vehicles following predetermined routes. Each route can include passenger boarding and alighting points where passengers can board and alight the vehicle. For example, the vehicles can include buses running on bus routes with bus stops, trams running on rail tracks with tram stops, and trains running on rail tracks with train stations. The route portions between boarding points can be called segments or route segments. A mass transit system can be operated by a central operator that generates timetables for operating the mass transit system and determines which route and departure time is assigned to each vehicle at any given time.

[0010] The passenger device detector can be a probe request module configured to detect wireless signals from passenger devices called probe requests. For example, the passenger device detector can be configured to detect PAN (personal area network) signals, such as Bluetooth, BLE (Bluetooth Low Energy), or Wi-Fi signals, transmitted from passenger devices. The PAN signals can be advertising signals that include a device ID, such as a MAC address or a Bluetooth device address. The passenger device detector can be configured to count the number of detected advertising signals from different devices (e.g., devices with different device IDs). In some examples, the passenger device detector can be configured to receive one or more advertising signals from one or more passenger devices and form a connection (e.g., pair) with one or more passenger devices.

[0011] The passenger counting device can be an automated passenger counting system that determines the number of people on or boarding the vehicle. For example, the passenger counting device can include a surveillance system with one or more cameras mounted on the vehicle and a module that automatically counts people within the field of view of the one or more cameras. In other examples, the passenger counting device can include a ticket counter or turnstile, or a manual counting device operated, for example, by the vehicle driver. The passenger counting device can be configured to count the number of passengers on the first vehicle. Thus, the passenger counting device can be located on the first vehicle. In other examples, the passenger counting device can be located separately from the first vehicle, such as on a train platform or a bus stop.

[0012] The passenger estimation correction information may include a ratio between the estimated number of passenger devices and the number of passengers. In some examples, the passenger estimation correction information may further include additional data associated with the state of the first vehicle when the estimated number of passenger devices and the number of passengers were determined, including one or more of vehicle type, vehicle location, route data, route segment data, time data, and / or date data. Thus, as described in more detail below, correction information corresponding to a particular vehicle type, route, time of day, day of week, etc. may be generated. By considering the travel date and travel time, correction information may be determined that takes into account routes, times, and / or dates when particular demographics are expected to use the mass transit network (e.g., children on their way to school). People with different demographics may be expected to own different numbers of passenger devices. Thus, the estimated number of passengers using the correction information may be more accurate than if only overall correction information were determined.

[0013] In some examples, the method may further include determining, from the passenger device information, when and / or where each passenger device boards and / or disembarks the first vehicle and the second vehicle. For example, the passenger device information may include time and / or location data indicating when and / or where each passenger device was detected. Accordingly, the origin and / or destination of each passenger device's journey on a vehicle may be determined by monitoring when and / or where the passenger device was first detected and when / where the passenger device is no longer detectable. In this manner, an estimate of the passenger's journey, including the origin and destination information, may be estimated. Monitoring passenger movements may enable optimization of predetermined vehicle routes utilized by vehicles in a mass transit system. For example, if there are many passengers with the same origin and destination, implementing a more direct vehicle route between the origin and destination may save fuel and reduce passenger travel time.

[0014] In some examples, as described above, the passenger device information includes one or more device identifiers. For example, the device identifiers can be transmitted by each passenger device using a PAN signal. In these examples, the method can include determining when one or more of the device identifiers changed. For example, if a passenger device transmits a first identifier and then transmits a second identifier that is different from the first identifier, the method can include detecting the change and determining that the same passenger device is being detected. Determining when the one or more device identifiers changed can include determining that the first passenger device identifier is no longer detected, detecting a new device identifier, and determining whether the detection of the identified new device corresponds to a time when the vehicle is stopped (a time when the vehicle doors open to allow passengers to board and disembark). If it is determined that the vehicle is not stopped or that the vehicle is not stopped at a predetermined boarding location, it can be determined that the passenger device changed its device identifier from a first identifier to a second identifier. This method allows passenger devices to be tracked through the mass transit system even if their device identifiers change.

[0015] The method may further include receiving location information associated with the first vehicle and / or the second vehicle. In some examples, the method may further include receiving location information associated with the first and / or second passenger device detectors. For example, the passenger device information may include location information. The location information may include a current location of the first vehicle and / or the second vehicle. Thus, the location information may be utilized to determine passenger movement using the mass transit system. Furthermore, in examples described below, the location information may be utilized to generate correction information corresponding to a particular route or location. Thus, the location information associated with the second vehicle may be utilized to select correction information for estimating the number of passengers in the second vehicle for that location or vehicle route.

[0016] For example, the method may further include utilizing the location information to determine when each passenger device enters and / or exits the first and / or second vehicle. Additionally, the location information may be utilized to determine when one or more device identifiers change, for example, by determining whether the vehicle stops at a boarding or disembarking location.

[0017] In a further example, the method can further include using the location information to determine a plurality of estimated passenger counts (e.g., a plurality of passenger counts) corresponding to each of a plurality of route segments traveled by the first vehicle. Each route segment can be a portion of a route traveled by the first vehicle between two boarding and alighting points where passengers can board and alight from the vehicle. For example, a route segment can be a portion of a bus route between two bus stops or a section of railroad track between two stations. In this manner, more detailed corrected information can be generated that takes into account passenger trends for different routes and route segments.

[0018] In this example, generating the passenger estimation correction information may include generating segment correction information corresponding to each route segment traveled by the first vehicle. For example, first segment correction information may be determined for the first route segment, and second segment correction information may be determined for the second route segment.

[0019] Estimating the number of passengers in the second vehicle may include, for one (or each) route segment, utilizing the segment correction information and the additional passenger device information to estimate the number of passengers in the second vehicle for that route segment along which the second vehicle travels.

[0020] In some examples, the method may include receiving, from a passenger counting device, passenger device information and date, day of the week, and / or time of day information associated with the passenger count, such that the day of the week or week, time of year, and / or time of day may also be considered when estimating the passenger count.

[0021] In some examples, the method may include receiving passenger device information and location information, date and / or time information associated with the passenger count from the passenger counting device. Accordingly, the generated correction information may take into account the route, route segment, and time / day / date, respectively. Accordingly, correction information may be determined for different portions of the vehicle timetable and different vehicle routes, thereby taking into account more passenger trends and enabling more accurate estimation of passenger counts and forecasting of future vehicle demand.

[0022] The passenger estimation correction information may include a correction ratio between the number of passengers detected by the passenger counting device and the estimated number of passenger devices detected by the passenger device detector. In some examples, the correction ratio may be determined from an average of multiple individual estimates of the number of passenger devices from one or more different passenger device detectors. Similarly, the correction ratio may be determined from an average of multiple individual numbers of the number of passengers from one or more passenger counting devices. For example, the correction information may be determined using multiple passenger devices and the number of passengers observed, for example, in a particular section and / or at a particular time of day and / or on a particular day of the week. For example, the passenger estimation correction information may be generated for each section and / or travel time of the mass transit system. Generating the correction information using more data may allow for outlier events to be ignored and general trends in passenger behavior to be observed. Thus, a more accurate estimation of the number of passengers may be performed.

[0023] The passenger estimation correction information can be generated by comparing passenger device information received from multiple passenger device detectors associated with multiple vehicles of the mass transit system with passenger counts received from multiple passenger counting devices associated with multiple vehicles. In this manner, multiple different instances of correction information can be generated for each vehicle, or data from each vehicle can be combined as described above, to generate overall passenger correction information (e.g., for a particular route, segment, and / or date / time).

[0024] The passenger estimation correction information can be utilized to estimate passenger numbers for a plurality of second vehicles of a mass transit system, for example, for a plurality of routes and travel times, where the plurality of second vehicles can be vehicles of the mass transit system that are not equipped with passenger counting devices (but are equipped with passenger device detectors).

[0025] The method may further include allocating vehicles equipped with passenger counting devices to selected routes of the mass transit system and allocating vehicles not equipped with passenger counting devices to other selected routes of the mass transit system based on the estimated number of passengers. Allocating vehicles to selected routes may also include allocating vehicles to selected timetables associated with those routes.

[0026] In some examples, the method can further include determining updated timetable information based on the estimated number of passengers. For example, determining updated timetable information can include assigning a particular vehicle to a selected route, assigning more or fewer vehicles to a selected route, adapting a route, adjusting vehicle travel times, etc. For example, if a large number of passengers are expected to board a particular vehicle (e.g., a bus) at a particular time based on the estimated number of passengers, the method can include adjusting the departure time of a second vehicle (e.g., a train) to make the second vehicle available for those passengers.

[0027] In some examples, the method can further include utilizing passenger device information from the one or more passenger device detectors to determine estimated movements of one or more passengers across the mass transit network, each passenger movement including one or more vehicles and one or more vehicle routes of the mass transit network. Thus, in this example, the computer-implemented method can include determining updated timetable information based on the estimated passenger movements.

[0028] The method may further include transmitting an update signal to the passenger device detector and / or the second passenger device detector based on the passenger device information from the passenger device detector. For example, the update signal may be configured to increase or decrease a monitoring frequency of each passenger device detector. The monitoring frequency may determine how often each passenger device detector evaluates the number of passenger devices within its detection range. For example, if the estimated number of passenger devices exceeds a predetermined threshold number, the transmitted signal may be configured to increase the monitoring frequency. For example, if a large number of passenger devices are detected in the vehicle, increasing the monitoring frequency may improve detection accuracy and reduce the likelihood of devices being falsely counted. Alternatively, if a small number of passenger devices are detected on the vehicle, the signal may be configured to decrease the monitoring frequency to reduce power and resource consumption of the passenger device detector.

[0029] In another example or the same example, the update signal can be configured to change the scan mode of the passenger device detector and / or the second passenger device detector between an active scan mode and a passive scan mode, or vice versa. If the passenger device detector is configured to detect Bluetooth signals, the transmitted update signal can be configured to switch the passenger device detector between passively scanning for Bluetooth signals and actively scanning for Bluetooth signals to change the level of data collected. For example, when the vehicle is stopped at a passenger drop-off point, the signal can be configured to switch the passenger device detector to an active scan mode, which can collect additional information about the passenger devices (e.g., device name in addition to device ID), improving detection accuracy and reducing the likelihood of devices being falsely counted. Alternatively, when the vehicle is not stopped, the signal can be configured to switch the passenger device detector to a passive scan mode, minimizing data collection.

[0030] In a second aspect, embodiments of the present invention provide a method for estimating passenger numbers utilizing pre-calculated correction information. That is, the second aspect of the present invention provides a computer-implemented method for estimating passenger numbers in a mass transit system, the computer-implemented method including receiving passenger device information from a passenger device detector configured to detect passenger devices, the passenger device information including an estimated number of passenger devices in a vehicle of the mass transit system, receiving correction information indicative of a ratio between the number of passengers and the number of passenger devices, and utilizing the correction information and the estimated number of passenger devices to estimate the number of passengers in the vehicle.

[0031] The correction information may be determined using a historical ratio between the number of passengers and the number of passenger devices in the mass transit system. For example, the correction information may be determined using any of the methods described above for the first aspect.

[0032] In this way, even in a vehicle that is not equipped with a passenger counting device, the estimated number of passengers can be determined by counting the number of passenger devices installed in the vehicle and adjusting that number using correction information.

[0033] In a third aspect, embodiments of the present invention provide a passenger flow analysis server configured to perform the computer-implemented method of the preceding aspect. For example, the passenger flow analysis server may be configured to receive passenger device information from a passenger device detector configured to detect passenger devices, the passenger device information including an estimated number of passenger devices in a first vehicle of a mass transit system; receive a number of passengers in the first vehicle from a passenger counting device; compare the estimated number of passenger devices from the passenger device detector with the number of passengers from the passenger counting device to generate passenger estimation correction information; receive further passenger device information from a second passenger device detector configured to detect passenger devices, the passenger device information including an estimated number of passenger devices in a second vehicle of the mass transit system; and utilize the passenger estimation correction information to estimate the number of passengers in the second vehicle from the further passenger device information.

[0034] In a fourth aspect, an embodiment of the present invention provides a system for monitoring passengers of a mass transit system, the system including: a plurality of passenger device detectors configured to detect passenger devices on each vehicle of the mass transit system to generate passenger device information including an estimated number of passenger devices in each respective vehicle; one or more passenger counting devices configured to count the number of passengers in one or more of each vehicle of the mass transit system; and a passenger flow analysis server according to the third aspect.

[0035] An additional aspect of the present invention may relate to a system configured to perform the computer-implemented method of any one of the first and second aspects of the present invention. In particular, the system may include a processor configured to perform the computer-implemented method of each of the first and second aspects of the present invention.

[0036] A further aspect of the present invention may provide a computer program comprising instructions which, when executed by a computer, cause the computer to perform the steps of the computer-implemented methods of the first and second aspects of the present invention. A further aspect of the present invention may provide a computer-readable storage medium having stored thereon a computer program of the aforementioned aspects of the present invention.

[0037] The present invention includes combinations of the described embodiments and preferred features except where such combinations are expressly not permitted or explicitly avoided.

[0038] BRIEF DESCRIPTION OF THE DRAWINGS Embodiments and experiments illustrating the principles of the present invention will now be described with reference to the accompanying drawings.

[0039] 1 shows a diagram of a system for estimating passenger numbers according to an aspect of the invention; 2 shows a flow diagram of a method for estimating passenger numbers according to an aspect of the invention; 3 shows another diagram of a system for estimating passenger numbers; 4 shows a flow diagram of a method for optimizing the operation of a mass transit system; 5 shows a flow diagram of a method for monitoring passenger movement using a mass transit system; 6 shows a table of exemplary passenger numbers received from passenger counting devices; 7 shows a table of exemplary passenger device information received from a passenger device detector; 8 shows an exemplary correction ratio determined from the number of passengers and the estimated number of passenger devices; 9 shows a table of example total count data; 10 shows an exemplary output of a trip estimation unit of a passenger flow analysis; 11 shows an exemplary output of a movement estimation unit; 12 shows an exemplary vehicle assignment output of an optimization unit; 13 shows an exemplary timetable change output of an operations module.

[0040] Aspects and embodiments of the present invention will now be described with reference to the accompanying drawings, and further aspects and embodiments will be apparent to those skilled in the art.

[0041] 1 shows a diagram of a system for estimating passenger numbers in a mass transit system. The mass transit system includes a plurality of vehicles 200 for transporting passengers. The vehicles may be any mode of transportation in the mass transit network, such as buses, streetcars, or trains. While FIG. 1 shows a first vehicle 200A and a second vehicle 200B, the system may include many more vehicles 200.

[0042] The system for estimating passenger numbers includes a passenger flow analysis server. The passenger flow analysis server includes a data collection module 102 that receives data from sensors disposed in the mass transit system, an estimation comparison module 104 that compares the data from the sensors to generate correction information, and an estimation correction module 106 that estimates the number of passengers using the generated correction information. The sensors include a passenger device detector 204 configured to detect passenger devices moving on a vehicle of the mass transit system and a passenger counting device 202 configured to count passengers moving in the vehicle.

[0043] In this example, the data collection module 102 is configured to receive passenger device information from a passenger device detector 204A in a first vehicle. The passenger device information includes an estimated number of passenger devices in the first vehicle. The data collection module 102 is also configured to receive a number of passengers in the first vehicle from a passenger counting device 202A. The passenger counting device may be located within the first vehicle (e.g., a ticket counting device or a camera system) or outside the first vehicle (e.g., a turnstile). Additionally, the data collection module receives additional passenger device information from a second passenger device detector in the second vehicle, including an estimated number of passenger devices in the second vehicle.

[0044] The term "module" is used herein to refer to a functional module configured or adapted to perform a particular function. A module may be implemented in hardware (i.e., may be a separate physical component within a computer), software (i.e., may represent separate sections of code that, when executed by a processor, cause the processor to perform a particular function), or a combination of both.

[0045] The vehicle 200 is connected to the passenger flow analysis server 100 via a network, for example, a wide area network (e.g., the Internet). In some examples, the vehicle includes a cellular Internet modem, allowing it to establish a remote (wireless) connection with the passenger flow analysis server 100.

[0046] 2 shows a flow diagram of a method for estimating passenger numbers according to an aspect of the present invention. For example, the method can be performed by the passenger flow analysis server of FIG.

[0047] First, in step S100, the data collection module 102 receives passenger device information from a passenger device detector in a first vehicle, the passenger device information including an estimated number of passenger devices in the first vehicle.

[0048] Next, in step S102, the data collection module 102 receives a passenger count representing the number of passengers in the first vehicle from a passenger counting device in the first vehicle.

[0049] Next, in step S104, the estimation comparison module compares the estimated number of passenger devices from the passenger device detector with the number of passengers from the passenger counting device to generate passenger estimation correction information, where the passenger estimation correction information includes a ratio of the number of passengers to the number of passenger devices detected in the first vehicle.

[0050] Next, in step S106, the data collection module receives additional passenger device information from a second passenger device detector in the second vehicle, the additional passenger device information including an estimated number of passenger devices detected in the second vehicle.

[0051] Finally, in step S108, an estimation correction module utilizes the passenger estimation correction information and the additional passenger device information to estimate the number of passengers in the second vehicle, for example, by multiplying the correction ratio by the estimated number of devices in the second vehicle to generate the estimated number of passengers.

[0052] Although steps S100, S102, and S106 are shown in sequence, they may be performed in any order (including simultaneously). For example, the passenger count received in step S102 may be received before or simultaneously with receiving the passenger device information in S101. However, both the passenger device information and the passenger count must be received before step S104 can be performed. Similarly, step S106 may occur at any time before step S108.

[0053] FIG. 3 shows another view of the system for estimating passenger numbers in more detail.

[0054] The system includes a passenger flow analysis server 100 in communication with passenger device detectors 204 and passenger counting devices 202 associated with various vehicles 200A, 200B of a mass transit system, such as a bus or subway. Typically, some vehicles are equipped with both passenger counting devices and passenger device detectors, as shown in the first vehicle 200A of FIG. 3. However, some vehicles may only have passenger device detectors and no passenger counting devices, such as the second vehicle 200B of FIG. 3. The flow analysis server communicates with multiple passenger device detectors and multiple passenger counting devices (with or without passenger counting devices) associated with multiple vehicles (only two shown) of the mass transit system. Finally, the system includes an operations module 300.

[0055] As described above, the passenger flow analysis server 100 is configured to receive passenger counts from passenger counting devices and estimated passenger device counts from passenger device detectors to generate corrected passenger estimation information. The passenger flow analysis server is further configured to combine the passenger counts counted by the multiple passenger counting devices and the estimated passenger device count monitored by the passenger device detectors to generate combined corrected passenger estimation information. The passenger flow analysis server can estimate passenger counts for all services in the mass transit network.

[0056] The passenger flow analysis server includes a correction module 106, a journey estimation module 108, a movement estimation module 110, and an optimization module 112. The passenger flow analysis server may be implemented on a cloud server, and the data connection between the passenger counting devices or probe monitoring devices and the passenger flow analysis server is via an internet connection.

[0057] Additionally, the passenger flow analysis server 100 receives operational information for the mass transit network from the operations module 300. The operational information includes, but is not limited to, vehicle route timetables (stored in the timetable management module 302), vehicle assignments to selected routes and times, planned vehicle assignments, and historical records of vehicle assignments and trips (stored in the vehicle assignment module 304). The correction module 106, the trip estimation module 108, the trip estimation module 110, and the optimization module 112 are configured to utilize the operational information in their respective calculations. For example, the trip estimation module is configured to utilize vehicle timetables and passenger device estimations to determine trips taken by passengers.

[0058] The correction module 106 compares the number of passengers in each section 1021 with the number of passenger devices brought on board 1022, calculates a corrected ratio between these numbers for each route and time period, and stores the ratio in a correction ratio database 1062. Based on the correction ratios stored in database 1062, the correction module 106 estimates the number of passengers in each section even for vehicles that do not have passenger counting devices, and stores the result as a total number 1024. In some examples, the data stored in 1024 can be referred to as probe paths, i.e., paths (time and space) traveled by devices identified during data collection can be stored. This provides both (i) a count of the number of devices (paths per device), and (ii) origin / destination information for each device.

[0059] The trip estimation module 108 calculates the estimated passenger trip within each single route based on the number of passengers, the number of devices in 1022, and the respective correction ratios in the database 1062, indicating the first and last stops and the service / vehicle used.

[0060] The movement estimation module 110 calculates estimated passenger movement throughout the mass transit network with multiple routes, indicating first and last stops and services / vehicles used, based on the number of devices 1022 and the trip estimation, and stores this estimated movement data, or estimated origin / destination matrix, in the database 1015.

[0061] The optimization module 112 allocates vehicles with and without passenger counting devices to services to reduce the uncertainty in estimating passenger loads on services operated by vehicles without passenger counting devices. The optimization module 112 also plans timetable changes to improve the operation of the mass transit network based on the estimated origin / destination matrix or estimated passenger movements throughout the mass transit network.

[0062] The data stored in the passenger count database 1021, device count database 1022, correction ratio database 1062, total count database 1014, and estimated origin / destination matrix database 1015 are shown in Figures 6, 7, 8, 9, and 10, respectively. The estimated journeys calculated by the journey estimation unit (1002) are shown in Figure 11. Also, the vehicle assignments and timetable changes calculated by the optimization unit (1004) are shown in Figures 12 and 13, respectively.

[0063] The passenger counting device 202 in the vehicle 200 counts the number of passengers boarding at each section between stops of adjacent vehicles and uploads the count data to a passenger flow analysis server. To implement such a passenger counting device, any existing method known per se in the art can be used, such as a method of counting passengers by analyzing CCTV images inside the vehicle, or a method of detecting the number of passengers passing through the boarding doors by analyzing a dedicated video camera or infrared sensor.

[0064] The passenger device detector 204 monitors the routes of passenger devices brought into the vehicle. It uploads probe route data, such as the number of passenger devices in each section, to the passenger flow analysis server. The on-board passenger device detector 204 includes a probe receiver 2042, a locator 2043, and a control unit 2041. The probe receiver 2042 receives probe requests from passenger devices via wireless communication protocols such as Wi-Fi and Bluetooth, and transmits the data to the control unit 2041. The probe receiver 2042 can change configurations, such as the frequency and type of packets to be monitored, to monitor probe requests based on instructions from the control unit 2041. The locator 2043 identifies the location of the vehicle equipped with the probe monitoring device and the current timestamp, and transmits the data to the control unit 2041.

[0065] The control unit 2041 processes the probe request data and the vehicle configuration to estimate the device's path. The probe path data indicates the range from the first stop to the last stop where the device is installed, by distinguishing between the possibility that the device's address will change while the vehicle is traveling between two adjacent stops. The control unit 2041 also uploads the probe path data to the passenger flow analysis server 100. Furthermore, the control unit 2041 can determine the configuration of the probe receiver 2042 based on the vehicle's configuration, timestamp, and correction ratios calculated by the passenger flow analysis server 100.

[0066] The detailed process of the passenger device detector 204 is shown in Figure 5. Also, the probe path data transmitted from the passenger device detector 204 to the passenger flow analysis server is shown in Figure 7. The control unit 2041 of the passenger device detector 204 can be implemented in the passenger flow analysis server 100.

[0067] The operations module 300 manages timetables and vehicle assignments for routes within the mass transit network. The operations module 300 enables timetables and vehicle assignments to be updated by the optimization module 112 of the passenger flow analysis server. The operations module distributes timetable and vehicle assignment data to the driver navigation units 206 of the vehicles 200.

[0068] The driver navigation unit 206 displays the timetable and related information of the corresponding vehicle to the driver based on the data delivered from the operation module 300. For example, the driver navigation unit displays driving instructions to the driver, such as the route the vehicle should take, the names of the next bus stops, and the arrival and departure times. The driver drives the vehicle according to the instructions, such as the departure times at each bus stop.

[0069] Combining data from the passenger counting devices and probe monitoring equipment described herein allows for accurate estimation of passenger flow data within a mass transit network, including the number of passengers in vehicles without passenger counting devices and the origin-destination of passenger trips. Optimizing vehicle allocation with and without passenger counting devices improves accuracy. Improved passenger flow data allows mass transit operations, such as bus schedules, to be better aligned with local travel demand.

[0070] The correction information and passenger device information may also include information regarding the vehicle route, route segment, time of day, or day of week to which the information corresponds, so that estimated passenger numbers can be generated for a particular route, segment, time of day, and / or day of week.

[0071] FIG. 4 shows a flow diagram of a method for optimizing the operation of a mass transit system. This method can be performed periodically, for example, weekly, daily, or every two hours. In a first step S200, a given route (e.g., a bus route, a train route, etc.) is selected from a set of routes to be optimized. Next, in step S202, correction information is updated for the selected route by comparing the stored number of passengers with the stored number of devices. This step can be performed by the correction module 106. For route segments served by vehicles equipped with passenger counting devices, the correction module 106 calculates the number of passenger devices. Next, the correction module calculates the ratio of the number of passenger devices to the number of passengers for each segment. For each segment, the correction module searches for the corresponding group in the correction ratio database 1062. Next, the correction module updates the group's correction ratio (device / passenger ratio) with the average value for a predetermined period (e.g., the past 30 days). The correction module also updates the amount of data collected during the same period.

[0072] In step S204, the correction module applies the updated correction ratio to estimate the number of passengers based on the number of devices. The correction module obtains the number of passengers and the number of devices from each database for the selected route, and calculates the number of passenger devices for sections of the route served by vehicles that are not equipped with passenger counting devices. The correction module then calculates the estimated number of passengers by dividing the number of devices by the corresponding correction ratio. The correction module then stores the calculated estimated number of passengers in, for example, the total number database 1024.

[0073] In step S206, which is performed by the trip estimation module 108, the trips of passengers on the selected route are estimated and transmitted to the movement estimation module 110. An example of an estimated passenger trip is shown in FIG. 10. The trip estimation unit obtains passenger device information (probe path information in this example) for the selected route. The trip estimation unit then adds the appropriate group's correction ratio from the correction ratio database 1062 to each probe path. The trip estimation unit then adjusts the added ratio to minimize the difference between segments between the number of passengers counted by the passenger counting device and the estimated number of passengers calculated by dividing the number of ongoing probe paths (i.e., the number of devices) by the added ratio. If the adjusted ratio is less than 1, it means that the passenger has multiple devices. Therefore, the passenger trip includes multiple probe IDs with the same (or very similar) path. On the other hand, if the adjusted ratio is greater than 1, it means that multiple passengers in the group have one device (or fewer devices than the number of passengers in the group). In this case, multiple passenger trips will have the same probe ID. The trip estimation module sorts out these combined overlapping trips and sends the data to the movement estimation module, as shown in FIG.

[0074] Steps S200-S206 are repeated until all routes of interest have been completed. If yes, the method moves to step S208, which may be performed by the movement estimation module. The movement estimation module obtains estimated trips from the trip estimation module and connects all multiple trips on different routes that have a common probe ID during transfers on different routes (trips). The movement estimation module then stores these trips in the estimated origin / destination matrix database 1015.

[0075] Finally, the method moves to step S210, which may be executed by an optimization module. The optimization module assigns vehicles equipped with passenger counting devices to services or routes with a high percentage of missing data (e.g., 20%) compared to the data collected in the correction ratio table. The optimization module assumes a basic allocation of vehicles and considers options for swapping vehicles equipped with passenger counting devices with vehicles without them to better cover sections with significant missing data with vehicles equipped with passenger counting devices. An example of vehicle assignment is shown in FIG. 12. The optimization module also modifies portions of the timetable (e.g., arrival and / or departure times at specific stops) based on the latest trip demand or estimated origin / destination matrix, or estimated trips stored in the estimated origin / destination matrix database 1015. For example, if 20 passengers are waiting 10 minutes to board a bus due to connections, but the previous bus is scheduled to depart 30 seconds earlier, delaying the previous bus by one minute will reduce the overall travel time for the passengers. An example of such a timetable modification is shown in FIG. 13.

[0076] FIG. 5 shows a flow diagram of a method for monitoring passenger movements using a mass transit system. The passenger device detector 204 starts the process at step S300. The entire process can be repeated periodically, for example, every 100 milliseconds. In step S300, the passenger device detector's control unit 2041 updates the configuration of the probe receiver 2042, and the probe receiver monitors probe requests from passenger devices. This data is sent to the control unit. To update the probe receiver configuration, the control unit receives a correction ratio corresponding to the location (along which section or route) the vehicle is traveling from the passenger flow analysis server based on the vehicle's location and timestamp. The control unit then modifies the probe receiver configuration (e.g., the frequency and type of monitored packets) based on the correction ratio and the number of monitored devices. For example, if the corresponding correction ratio is greater than 2.0 and / or the number of monitored devices is sufficiently large, the control unit can double the monitoring frequency to prevent packet loss in situations with a large number of devices and packets. Otherwise, the frequency can be reduced to a default value to minimize data processing.

[0077] In step S302, the control unit detects the state of the vehicle. Specifically, the control unit determines whether the vehicle is stopped at a specific stop (e.g., a bus stop) if the position data from the locator 2043 matches a predetermined position of the specific stop (e.g., a bus stop) and the position data is sufficiently stable (e.g., for more than a few seconds, e.g., 10 seconds).

[0078] In step S304, if the detected vehicle state is not stopped ("No"), the control unit detects the address change of the probe request due to device-based randomization and connects the changed address (Device ID2 is the new ID of Device ID1 because Device ID1 has stopped broadcasting and Device ID2 has started broadcasting, but the passenger has not left the vehicle). Then, once the vehicle has stopped, the method moves to step S306, where updated probe path data is sent to the passenger flow analysis server.

[0079] 6 is a table of exemplary passenger counts received from a passenger counting device located in a vehicle of a mass transit system. Each record in the table represents the number of passengers in a vehicle equipped with a passenger counting device, the vehicle traveling a route segment between two adjacent bus stops (in this example, from a departure bus stop to the next arrival bus stop). For other vehicles, the segment can be defined by a predetermined distance or by different nodes, such as stations.

[0080] The first column 401 contains an ID number assigned to each record, represented by each row in the table. The second column 402 contains a timestamp associated with each record. In this example, each timestamp is the time the vehicle arrived at the bus stop where it is arriving or departing. If the vehicle does not stop at the arrival or departure bus stop, for example, because passengers are not boarding or disembarking the bus, the time it passes the bus stop can be used in this column. The next columns 403, 404, 405, 406, and 407 contain the route ID, service ID, vehicle ID, and departure and arrival bus stop IDs of the record from which the data for each column in the table was collected. A service refers to a single transportation service on a route by a vehicle. On different dates, the same service (e.g., a bus service scheduled to depart from a bus stop at a specific time defined in a timetable) can be operated by different vehicles. The vehicle ID indicates the physical vehicle used to operate the identified service on that day. The next column 408 contains the number of passengers detected on the vehicle within the identified route section by the passenger counting device. The final columns 409 and 410 contain the number of passengers who boarded the bus at the departure bus stop and disembarked at the arrival bus stop.

[0081] 7 illustrates a table of exemplary passenger device information received from passenger device detectors located on vehicles of a mass transit system, where each record (i.e., row) in the table represents a device detected on board a vehicle in service along a route segment, such as between two adjacent bus stops from a departure bus stop to a next arrival bus stop.

[0082] The first column 501 contains the ID assigned to each record. The second column 502 contains the ID of the probe monitor (i.e., passenger device detector) associated with each record. The third column 503 contains the timestamp of each record, i.e., the time the probe monitor arrived at the departure or arrival bus stop. For example, if the vehicle does not stop at the departure or arrival bus stop, i.e., no passengers board or disembark, the time of passing the stop can be used in this column.

[0083] The next columns 504, 505, 506, 507, and 508 contain the route ID, service ID, vehicle ID, and origin and destination bus stop IDs for each record, indicating where the data for each row was collected.

[0084] The next column 509 contains, in each row, the single device / probe ID or multiple device / probe IDs detected by the probe monitor and identified as coming from the passenger device. If it is determined that the passenger device utilizes the same network address for the entire route segment, then this column contains only a single ID. However, if the passenger device's network address changes while the vehicle is within the route segment (i.e., between stops), such as through randomization techniques, then this column contains multiple device IDs. The device ID can be a non-reversible hash value of the network address utilized by the detected passenger device. The final column 510 contains the connection ID assigned to each passenger device by the probe monitor for the duration of the passenger device's journey within the same vehicle.

[0085] In the general case, multiple records associated with each route segment are expected, such as when columns 502, 503, 504, 505, 506, 507, and 508 in Figure 7 have the same value. The passenger flow analysis server 100 can count the number of passenger devices on that route segment for that vehicle by counting the number of records that appear in the table for that segment.

[0086] For records with the same vehicle ID 506 and connection ID 510, the passenger flow analysis server 100 is configured to identify the travel path of the passenger device by recording the origin / destination of the passenger device. For example, the departure bus stop ID with the earliest timestamp in the passenger device's record is determined as the device's origin, and the arrival bus stop ID with the latest timestamp in the passenger device's record is determined as the destination.

[0087] 8 illustrates a table of exemplary correction ratios determined from the number of passengers detected by the passenger counting device and the number of estimated passenger devices detected by the passenger device detector. Each record (i.e., row) in the table represents a group and correction information associated with that group. Each group includes ranges and time periods of route segments (e.g., defined by bus stops) determined to exhibit similar characteristics, such as a correction ratio between the number of passengers and the number of passenger devices.

[0088] The first column contains the record ID for each record. The next columns 602, 603, and 604 contain the route ID, node (e.g., bus stop) ID range, and time period, which combine to form the definition of each group associated with each record in the table. The next column contains a correction ratio, which is the estimated ratio of the number of passenger devices to the number of passengers in each group.

[0089] The next column 606 contains the number of collected data corresponding to the group for calculating a correction ratio for a fixed period (e.g., 30 days), while the next column 607 stores the number of missing data corresponding to the group for the same period, in other words, the number operated by vehicles without passenger counting devices. If the ratio between column 607 and column 606 in the record exceeds a certain value (e.g., 1 / 10), the optimization unit 1004 is configured to assign vehicles with passenger counting devices to the services included in that group.

[0090] The table in FIG. 9 shows total count data stored in the total count database 1024 of the passenger flow analysis server 100. This table combines passenger count data stored in the passenger count database 1021 with estimated passenger counts calculated by the correction unit correction module 106 based on device count / probe path data stored in the device count database 1022. The records in the table represent the number of passengers in vehicles with and without passenger counting devices during service operations between two adjacent bus stops from a departure bus stop to the next arrival bus stop. The columns in this table include all the columns in the table in FIG. 6. This table has an additional column for data source 709. This table includes all the records in the table in FIG. 6 with the data source "Count." In addition, this table also includes records of passenger counts for vehicles without passenger counting devices. These records were calculated by the correction module 106 based on the probe path data stored in the device count database 1022 and have the data source "Probe Estimate."

[0091] The table in Figure 10 shows the output of the trip estimation module 108 of the passenger flow analysis server 100. Each record in the table represents a trip by a passenger on a single route in a mass transit network. The record is based on the passenger device's trip, but adjusted with a correction factor. Column 801 stores the record's ID. Columns 802, 803, and 804 store the route, service, and vehicle IDs used by the estimated passenger. Columns 805 and 806 store the IDs of the first (origin) and last (destination) bus stops of the trip. Columns 807 and 808 store the timestamps of the first and last bus stops of the trip. Columns 809 and 810 store the probe IDs collected on the first and last legs of the trip.

[0092] The table in Figure 11 shows the output of the journey estimation module 110, which is stored in the estimated origin / destination matrix database 1015 of the passenger flow analysis server 100. The records in the table represent journeys by passengers across the network. A record can be a single trip in the table in Figure 10, or it can connect multiple trips in the table in Figure 10 that have a common probe ID while connecting on different routes (trips). Column 901 stores the ID of the record. Columns 902 and 903 store the IDs of the first (origin) and last (destination) bus stops of the trip. Column 904 stores the IDs of the trips that make up the trip. Columns 905 and 906 store the timestamps of the first and last bus stops during the trip.

[0093] The table in Figure 12 shows the vehicle allocation output of the optimization module 112 of the passenger flow analysis server 100, which is then sent to the vehicle allocation module 304 of the operations module 300. The records in the table represent vehicles with or without passenger counting devices that provide the services defined in the timetable. The example row in the table shows that service ID 426 must be operated by vehicle ID 2100 with a passenger counting device.

[0094] The table in Figure 13 shows the timetable changes output of the optimization module 112 of the passenger flow analysis server 100, which are then sent to the timetable management module 302 of the operations module 300. The records in this table represent how the arrival and departure times in the timetable should be changed taking into account the latest trip demand or the estimated origin-destination matrix in the estimated origin / destination matrix database 1015. The example row in the table indicates that the departure time of service ID 425 at bus stop ID 325 needs to be delayed by one minute.

[0095] The features disclosed in the foregoing description, or the following claims, or the accompanying drawings, are, as appropriate, expressed in their specific form, or in terms of means for performing a disclosed function, or methods or processes for obtaining a disclosed result, and such features can be utilized individually or in any combination to realize the invention in its various forms.

[0096] While the present invention has been described in conjunction with the exemplary embodiments set forth above, many equivalent modifications and variations will be apparent to those skilled in the art upon reading this disclosure. Accordingly, the exemplary embodiments of the invention set forth above are to be considered illustrative and not limiting. Various changes can be made to the described embodiments without departing from the spirit and scope of the invention.

[0097] For the avoidance of doubt, any theoretical explanations provided herein are provided for the purpose of improving the understanding of the reader, and the inventors do not wish to be bound by any of these theoretical explanations.

[0098] Any section headings used herein are for organizational purposes only and are not to be construed as limiting the subject matter described.

[0099] Throughout this specification, including in the claims which follow, unless the context otherwise requires, the words "comprise" and "include", and variations such as "comprises", "comprising", and "including", will be understood to mean the inclusion of a specified integer or step or group of integers or steps, but not the exclusion of any other integer or step or group of integers or steps.

[0100] It should be noted that, as used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Ranges can be expressed herein as from "about" one particular value, and / or to "about" another particular value. When such a range is expressed, another embodiment includes from the one particular value and / or to the other particular value. Similarly, when values ​​are expressed as approximations, by use of the antecedent "about," it will be understood that the particular value forms another embodiment. The term "about" with respect to numerical values ​​is optional and can mean, for example, + / - 10%.

Claims

1. A computer-implemented method for estimating a passenger count in a mass transit system, comprising: receiving passenger device information from a passenger device detector configured to detect passenger devices, the passenger device information including an estimated number of passenger devices in a first vehicle of the mass transit system; receiving a number of passengers in the first vehicle from a passenger counting device; comparing the estimated number of passenger devices from the passenger device detector with the number of passengers from the passenger counting device to generate passenger estimation correction information; receiving further passenger device information from a second passenger device detector configured to detect passenger devices, the passenger device information including an estimated number of passenger devices in a second vehicle of the mass transit system; and utilizing the passenger estimation correction information to estimate the number of passengers in the second vehicle from the further passenger device information.

2. The method of claim 1, further comprising determining from the passenger device information when and / or where each passenger device will board and / or exit the first and second vehicles.

3. The method of claim 2, wherein the passenger device information includes one or more device identifiers, and the method includes determining when the one or more device identifiers have changed.

4. The method of claim 3, further comprising receiving location information associated with the first and second vehicles and / or the first and second probe monitors.

5. The method of claim 4, further comprising utilizing the location information to determine when each passenger device enters or exits the first and / or second vehicle and / or when one or more of the device identifiers change.

6. The method of claim 5, further comprising utilizing the location information to determine a plurality of estimated passenger counts corresponding to each of a plurality of route segments traveled by the first vehicle.

7. The method of claim 6, wherein generating the passenger estimation correction information includes generating segment correction information corresponding to each of the route segments traveled by the first vehicle.

8. The method of claim 7, wherein estimating the number of passengers in the second vehicle includes utilizing the segment correction information and the further passenger device information for each route segment to estimate the number of passengers in the second vehicle for each route segment traveled by the second vehicle.

9. The method of claim 8, wherein the passenger estimation correction information comprises a ratio between the number of passengers detected by the passenger counting device and the estimated number of passenger devices detected by the passenger device detector.

10. The method of any one of claims 9, wherein the passenger estimation correction information is generated by comparing passenger device information received from a plurality of passenger device detectors associated with a plurality of vehicles of the mass transit system with passenger counts received from a plurality of passenger counting devices associated with the plurality of vehicles.

11. The method of any one of claims 1 to 10, further comprising allocating vehicles equipped with passenger counting devices to selected routes of the mass transit system, and allocating vehicles not equipped with passenger counting devices to other selected routes of the mass transit system based on the estimated number of passengers.

12. The method of any one of claims 1 to 11, further comprising determining updated timetable information based on the estimated number of passengers.

13. The method of any one of claims 1 to 12, further comprising sending an update signal to the passenger device detector and / or the second passenger device detector based on the passenger device information from the passenger device detector, wherein the update signal is configured to: increase or decrease a monitoring frequency of each of the probe monitoring devices, the monitoring frequency determining how often each passenger device detector assesses the number of passenger devices it can detect; and / or change a scan mode of the passenger device detector and / or the second passenger device detector between an active scan mode and a passive scan mode, or vice versa.

14. A passenger flow analysis server for estimating a number of passengers in a mass transit system, the passenger flow analysis server being configured to: receive passenger device information from a passenger device detector configured to detect passenger devices, the passenger device information including an estimated number of passenger devices in a first vehicle of the mass transit system; receive a number of passengers in the first vehicle from a passenger counting device; compare the estimated number of passenger devices from the passenger device detector with the number of passengers from the passenger counting device to generate passenger estimation correction information; receive further passenger device information from a second passenger device detector configured to detect passenger devices, the passenger device information including an estimated number of passenger devices in a second vehicle of the mass transit system; and utilize the passenger estimation correction information to estimate the number of passengers in the second vehicle from the additional passenger device information.

15. A system for estimating passenger numbers in a mass transit system, the system comprising: a plurality of passenger device detectors configured to detect passenger devices on each vehicle of the mass transit system and generate passenger device information including an estimated number of passenger devices in each respective vehicle; one or more passenger counting devices configured to count the number of passengers in one or more of the vehicles of the mass transit system; and the passenger flow analysis server of claim 14.

Images