Method and system for predicting passenger flow in a transportation system

Abstract

To predict a passenger flow in a transportation system.SOLUTION: Movement history data related to a plurality of passengers in traffic means is received in order to determine an acceptable delay time and an acceptable congestion in the traffic means. A total number of passengers waiting to board at a station is estimated based on the movement history data. The delay time and congestion in the traffic means are estimated based on the movement history data. For each one or a plurality of waiting passengers, a possibility of changing the traffic means is determined. Moreover, a risk that one or a plurality of passengers will abandon boarding the traffic means at that station is determined. Thereafter, a passenger flow at the station is predicted based on the estimated total number of one or the plurality of waiting passengers and the risk associated with the one or the plurality of waiting passengers.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates generally to the field of passenger flow management. More specifically, the present disclosure relates to a method and system for predicting passenger flow in a transportation system. [Background technology]

[0002] Rapid urbanization and population growth have led to traffic congestion problems in major cities around the world. Many cities are exploring solutions to improve the quality of public transportation services so that residents will choose public transportation as their preferred commuter mode. However, providing a comfortable and satisfactory service quality in a transportation system can be extremely challenging. For example, transportation systems can encounter situations where they are unable to operate as planned due to unforeseen circumstances. Therefore, to manage transportation systems, operators must constantly monitor delays and adjust service intervals accordingly to minimize the impact on passengers. To accurately adjust service intervals, it is important to accurately forecast service schedules to identify potential problems. Summary of the Invention [Problem to be solved by the invention]

[0003] The factors that conventional technologies rely on to improve the public transportation user experience are passenger flow and delays associated with the transportation. Such technologies calculate passenger flow and delays based on sensor data acquired by various sensors. Sensors include, but are not limited to, cameras and weight sensors installed on transportation vehicles to measure congestion levels, and global positioning system (GPS) trackers to calculate transportation delays based on detailed location information. However, conventional technologies only consider the current state of the transportation vehicle when calculating passenger flow and delays. This approach may lead operators to mistakenly believe that the transportation vehicle can or cannot accommodate more passengers at the next station. This may result in excessive or insufficient passengers boarding the transportation vehicle. For example, Figure 1 shows an example operation plan generated by an operator in an existing system based on sensor data related to the current state of the transportation vehicle. The sensor data is received from various sensors. Note that in this operation plan, passengers affected by delays are also counted as passengers waiting to board at subsequent stations. Thus, the prior art cannot achieve ideal results because the estimated passenger flow and delays of transportation modes only take into account the current state of transportation modes.

[0004] Existing approaches to passenger flow estimation are performed through the various sensors mentioned above. However, they do not estimate the future status of transportation modes when they arrive at the next station or when passengers wish to change modes. Existing approaches also include passengers affected by delays in passenger flow estimation. This results in the assumption that, even if a mode is delayed with no prospect of resuming service, the inconvenienced passengers will wait and board the delayed mode. Furthermore, existing approaches are cost-inefficient due to their reliance on expensive sensors.

[0005] The information disclosed in the Background section of this disclosure is solely for the purpose of enhancing understanding of the general background of the present invention and should not be construed as an admission or in any way suggesting that such information constitutes prior art known to those skilled in the art.

[0006] The object of the present invention is to provide a method and system for predicting passenger flow in a transportation system that can accurately predict operation schedules so as to grasp potential future problems in order to accurately adjust operation headways. [Means for solving the problem]

[0007] In an embodiment, the present disclosure discloses a method for predicting passenger flow in a transportation system. The method includes receiving, from one or more sources, travel history data associated with a plurality of passengers to determine an acceptable delay time and acceptable transportation system congestion associated with each of a plurality of passengers of a transportation mode. The method also includes estimating a total number of passengers waiting to board a transportation mode at a station based on the travel history data associated with one or more passengers among the plurality of passengers waiting at a station to board the transportation mode. The method also includes estimating a delay time until the transportation mode arrives at the station and congestion within the transportation mode based on the travel history data. The method further includes determining, for each of the one or more waiting passengers at the station, a probability of changing from one transportation mode to another transportation mode based on the delay time, congestion within the transportation mode, acceptable delay time, and acceptable transportation mode congestion. The method also includes determining a risk that one or more passengers among the plurality of waiting passengers will abandon the transportation mode at the station by aggregating the probability of changing associated with each of the one or more waiting passengers. The method then includes forecasting passenger flow at the station based on the estimated total number of one or more waiting passengers and a risk associated with the one or more waiting passengers.

[0008] In an embodiment, the present disclosure discloses a passenger flow prediction system for predicting passenger flow in a transportation system. The system includes one or more processors and a memory. The one or more processors are configured to receive movement history data associated with a plurality of passengers from one or more sources to determine an acceptable delay time and acceptable congestion of the transportation mode associated with each of a plurality of passengers of the transportation mode. The one or more processors are configured to estimate a total number of passengers waiting to board the transportation mode at a station based on the movement history data associated with one or more passengers among the plurality of passengers waiting at a station to board the transportation mode. The one or more processors estimate a delay time until the transportation mode arrives at the station and congestion within the transportation mode based on the movement history data. The one or more processors are further configured to determine a change possibility for each of the one or more waiting passengers at the station to change from one transportation mode to another transportation mode. The change possibility is determined based on the delay time, congestion within the transportation mode, acceptable delay time, and acceptable congestion of the transportation mode. The one or more processors are further configured to determine a risk that one or more passengers among the plurality of passengers will abandon the transportation mode at the station, where the abandonment risk is determined by aggregating a change probability associated with each of the one or more waiting passengers. The one or more processors are then configured to forecast passenger flow at the station based on the estimated total number of the one or more waiting passengers and the risk associated with the one or more waiting passengers. [Effects of the Invention]

[0009] For accurate headway adjustment, accurate schedules can be predicted to identify potential future problems.

[0010] The foregoing summary is illustrative and not intended to be limiting. In addition to the exemplary aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description. [Brief explanation of the drawings]

[0011] The novel features and characteristics of the present disclosure are set forth in the appended claims. However, the disclosure itself, its preferred modes of use, further objects and advantages thereof will best be understood by reference to the following detailed description of illustrative embodiments taken in conjunction with the accompanying drawings. One or more embodiments will now be described, by way of example only, with reference to the accompanying drawings in which like reference numerals refer to like elements. [Figure 1] 1 shows an exemplary trip plan created by an operator in accordance with the prior art; [Figure 2] 1 illustrates an exemplary environment for predicting passenger flow in a transportation system, according to some embodiments of the present disclosure. [Figure 3] FIG. 1 is a detailed diagram of a passenger flow prediction system for predicting passenger flow in a transportation system, according to some embodiments of the present disclosure. [Figure 4A] 1 is an exemplary graph for forecasting passenger flow in a transportation system according to some embodiments of the present disclosure. [Figure 4B] 1 is an exemplary graph for forecasting passenger flow in a transportation system according to some embodiments of the present disclosure. [Figure 4C] 1 is an exemplary graph for forecasting passenger flow in a transportation system according to some embodiments of the present disclosure. [Figure 5] 1 is an exemplary flowchart illustrating method steps for forecasting passenger flow in a transportation system according to some embodiments of the present disclosure. [Figure 6] FIG. 1 is a block diagram of a generalized passenger flow forecasting system for forecasting passenger flow in a transportation system according to an embodiment of the present disclosure.

[0012] Those skilled in the art will appreciate that any block diagrams herein are conceptual views of illustrative systems embodying the principles of the present invention. Similarly, any flowcharts, flow diagrams, state transition diagrams, pseudocode, etc., are intended to illustrate various processes that may be performed by a computer or processor, whether or not the computer or processor is explicitly indicated. DETAILED DESCRIPTION OF THE INVENTION

[0013] As used herein, the word "exemplary" means "serving as an example, instance, or illustration." Any embodiment or implementation of the invention described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0014] While the present disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and are described in detail below, however, it is to be understood that it is not intended to limit the disclosure to the particular forms disclosed, but rather the disclosure is intended to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure.

[0015] The use of "comprises," "having," or any other variation thereof is intended to cover a non-exclusive inclusion, such that a configuration, device, or method that includes a recited component or step does not include only that component or step, but also includes other components or steps not expressly recited or that are inherent to the configuration, device, or method. In other words, a reference to one or more elements in a system or apparatus preceding "comprises" does not, without further constraints, exclude the presence of other or additional elements in the system or apparatus.

[0016] Urban traffic congestion is a major problem that affects the daily lives of millions of people. Inefficient public transport systems exacerbate this problem by leading to excessive congestion and delays. Therefore, accurate prediction of passenger flow at transport stations is essential to solve this problem and improve commuter experience.

[0017] The present disclosure provides a method and computing system for predicting passenger flow in a transportation system. In the present disclosure, the passenger flow prediction system receives historical travel data related to passengers of a transportation mode. The passenger flow prediction system estimates the delay time until the transportation mode arrives at a station, the congestion within the transportation mode, and the total number of passengers waiting to board at a station. Furthermore, a risk of passengers abandoning the transportation mode at a station is determined. The abandonment risk is determined by calculating the probability of changing from one transportation mode to another. The probability of changing is calculated based on the estimated delay time and the congestion within the transportation mode. That is, the present disclosure considers the risk of passengers abandoning the transportation mode due to delays or overcrowding when predicting passenger flow. Therefore, the present disclosure realizes improved passenger flow prediction accuracy and an efficient decision-making approach by considering the risk of passenger abandonment while setting short-term and long-term operation timetables for transportation modes in a transportation system.

[0018] 2 illustrates an example environment (example system) 200 for predicting passenger flow in a transportation system, according to some embodiments of the present disclosure. The environment 200 includes one or more sources 203 (source 2031, source 2032, ... source 203). N The system includes a passenger flow prediction system 201 connected to a plurality of sources 203 (collectively referred to as one or more sources 203). The one or more sources 203 communicate with the passenger flow prediction system 201 via a communications network 205. The one or more sources 203 may include, but are not limited to, databases including historical data, survey data, and data received from third-party application program interfaces (APIs) related to the transportation system.

[0019] The passenger flow prediction system 201 may have an input / output (I / O) interface 207, a memory 209, and a processor 211. In some embodiments, the memory 209 may be communicatively coupled to the processor 211. The memory 209 stores instructions executable by the processor 211. The processor 211 may execute program components for carrying out user- or system-generated requests. The I / O interface 207 is coupled to the processor 211 for communicating input and / or output signals. For example, movement history data may be received from one or more sources 203 through the I / O interface 207. In one embodiment, the passenger flow prediction system 201 may be implemented in a transportation system compatible with various computing systems, such as a laptop computer, a desktop computer, a personal computer (PC), a notebook computer, a smartphone, a tablet, a server, a network server, a cloud server, etc.

[0020] The passenger flow prediction system 201 receives historical travel data for a plurality of passengers of a transportation mode from one or more sources 203. The historical travel data may include transportation mode status information and passenger location information. In one embodiment, the passenger location information may be obtained based on payment information associated with a previous trip by the passenger, a predetermined identifier associated with a user device, or a tagging device, such as an RFID tag, carried by the passenger.

[0021] Travel history data, including transportation status information, and payment information are associated with the travel history of each of a plurality of passengers. The transportation status information includes, but is not limited to, the location of the transportation, weather information, traffic information, and congestion history information associated with the transportation when the passenger previously rode the transportation. In one embodiment, the payment information includes information related to a ticket obtained by the passenger through payment. The passenger may pay and be issued a ticket at the time of use. In one embodiment, the passenger may make payment through various means, including, but not limited to, cash, integrated circuit (IC) cards, RFID cards for contactless payment, online means using personal devices, smart ticket systems associated with Bluetooth beacons and GPS, etc.

[0022] In an embodiment, the total number of chip cards, Media Access Control (MAC) identifiers, and RFID identifiers detected as they travel from a corresponding station may be calculated to estimate acceptable transportation congestion. In one embodiment, GPS information may be used to track passenger locations, which may be used to estimate acceptable transportation congestion.

[0023] In embodiments, passenger location may be obtained based on payment information generated when a passenger swipes or taps an IC or RFID card to pay for a ticket associated with each trip. In particular, ticket-related information may include, but is not limited to, boarding station, destination station, ticket fare, time, etc.

[0024] In embodiments, passenger location information may be obtained from a predetermined identifier associated with a user device connected to a wireless network. For example, if the user device is connected to Wi-Fi, a MAC identifier may be detected by a networking system associated with a corresponding station where the passenger is located.

[0025] In embodiments, passenger location information may be obtained from location information collected from tagging devices that may be associated with one or more items carried by the passenger. For example, a passenger may carry a tagging device, such as an RFID tag, for tracking their luggage as they travel. Thus, location information may be obtained based on detecting an RFID identifier by a networking system associated with a corresponding station where the passenger is located.

[0026] Furthermore, the transportation status information and passenger location information are used to determine an acceptable delay time and an acceptable transportation congestion associated with the plurality of passengers. Thus, the acceptable delay time and the acceptable transportation congestion become part of the travel history data. The acceptable delay time relates to the amount of time a passenger is willing to wait at a station for the corresponding transportation to arrive. For example, a passenger may not board a bus if the time it takes for the bus to arrive at the station exceeds the acceptable delay time. Furthermore, the acceptable transportation congestion relates to a predetermined congestion rate for the transportation. For example, assume that a bus arrives at the station within the acceptable delay time. Even in such a case, if the congestion on the bus exceeds a predetermined tolerable congestion rate, the passenger may decide not to board the bus. Thus, the acceptable delay time and the acceptable transportation congestion correspond to predetermined thresholds associated with each of the plurality of passengers. In one embodiment, the predetermined thresholds related to the acceptable delay time and the acceptable transportation congestion are determined based on the transportation status information and the passenger location information.

[0027] The passenger flow prediction system 201 estimates the total number of waiting passengers at a station based on movement history data associated with one or more passengers among a plurality of passengers waiting at a station to board a transportation means. Specifically, the passenger flow prediction system 201 estimates the total number of waiting passengers using passenger location information, including payment information associated with the movement history of each of the plurality of passengers. In one embodiment, the process of estimating the total number of waiting passengers is performed by identifying one or more waiting passengers from one or more categories of passengers based on a predetermined clustering technique, such as, but not limited to, a k-means clustering method. Those skilled in the art will appreciate that any other clustering technique not explicitly mentioned herein may be used to identify one or more waiting passengers from one or more categories. Here, the one or more categories of passengers may correspond to frequent flyers and non-frequent flyers. In one embodiment, passenger classification may be performed based on passengers' preferred travel times.

[0028] Furthermore, the passenger flow prediction system 201 estimates the delay time until the transportation means arrives at the station and the congestion within the transportation means based on the movement history data. Here, the delay time and the congestion correspond to the future state of the transportation means. Therefore, the passenger flow prediction system 201 estimates the delay time and the congestion based on the delay history and the congestion history. The estimation is performed based on at least one of a predetermined statistical technique and a predetermined machine learning technique. In one embodiment, the predetermined machine learning technique may include, but is not limited to, logistic regression, k-nearest neighbors, Gaussian naive Bayes, decision tree, support vector machine, random forest, gradient boosting decision tree, etc.

[0029] Additionally, the passenger flow prediction system 201 may determine a change probability, which corresponds to the likelihood of changing from one transportation mode to another. The change probability is determined for each of one or more waiting passengers at a station. The passenger flow prediction system 201 determines the change probability based on the delay time, congestion within the transportation mode, acceptable delay time, and acceptable congestion of the transportation mode associated with each passenger. In one embodiment, the change probability may be determined by calculating the total number of at least one MAC identifier, beacon identifier, and RFID identifier that arrive at the station and depart from the station without boarding the transportation mode.

[0030] The change probability is determined based on the initial probability of changing from one mode to another. Specifically, the initial probability is determined as a function of the total number of mode change histories and the total number of trip histories associated with each of one or more waiting passengers, as shown in the following equation (1):

[0031]

number

[0032] The total number of transportation mode change histories corresponds to the number of times a passenger did not take a transportation mode for various reasons. For example, the arrival of the transportation mode the passenger intended to take is delayed, and the passenger decides to change to another transportation mode, such as a taxi. This situation may correspond to one change in the total number of transportation mode change histories. In another example, if a passenger decides to abandon the planned use, this may also correspond to one change in the total number of transportation mode change histories. In an embodiment of the present disclosure, the total number of transportation mode change histories is specified only for passengers who use regular services. The total number of travel histories is the total number of travel histories for all passengers.

[0033] Furthermore, a change probability is determined for each of one or more waiting passengers at a station based on a function of delay time, congestion within the transportation means, and initial probability, as shown in the following equation (2):

[0034]

number

[0035] Additionally, the passenger flow forecasting system 201 determines the risk that one or more passengers out of the total number of waiting passengers will abandon the transportation mode by aggregating the change probabilities associated with each of the one or more waiting passengers, as shown in the following equation (Equation 3):

[0036]

number

[0037] As shown in Equation (3), the change probability of waiting passengers is calculated for a predetermined time period, i.e., from time t1 to time t2. Further, the change probability is calculated for the next station, i.e., station A in Equation (3).

[0038] Thereafter, the passenger flow prediction system 201 predicts passenger flow at the station based on the risk calculated and determined by Equation (3) and the estimated total number of one or more waiting passengers. The prediction is made by calculating the number of waiting passengers as shown in the following Equation (4).

[0039]

number

[0040] As with Equation 3, Equation 4 also calculates the predicted number of waiting passengers for a given period and for the next station to predict passenger flow at a station. In this way, passenger flow prediction system 201 predicts the number of passengers waiting at the next station, taking into account the risk that passengers will abandon their boarding due to delays or overcrowding.

[0041] FIG. 3 is a detailed diagram of a passenger flow prediction system 201 for predicting passenger flow in a transportation system, according to some embodiments of the present disclosure.

[0042] In some implementations, passenger flow prediction system 201 may include data 302 and module 316. In one example, data 302 is stored in memory 209 associated with passenger flow prediction system 201. In some embodiments, data 302 may include input data 304, passenger estimation data 306, change probability data 308, abandonment risk data 310, prediction data 312, and other data 314. In some embodiments, data 302 may be stored in memory 209 in the form of various data structures.

[0043] The input data 304 may include travel history data associated with multiple passengers of a transportation mode. The travel history data may be used to determine acceptable delay times and acceptable transportation mode congestion associated with each of the multiple passengers. The travel history data may further include details regarding transportation mode status information and passenger location information associated with the travel history of each of the multiple passengers. The transportation mode status information may include, but is not limited to, the location of the transportation mode, weather information, traffic information, and congestion history information associated with the transportation mode when the passenger previously rode the transportation mode. Furthermore, the passenger location information may be obtained based on payment information, which further includes information related to the passenger's ticket. A passenger may be given a ticket upon payment at the time of their trip. In one embodiment, the passenger may pay with their own cash or IC card. When a passenger pays for a ticket by paying cash or swiping their IC card before boarding the transportation mode, payment data is generated for the corresponding trip. In one embodiment, the ticket-related information may include, but is not limited to, the transportation mode number, the boarding station, the destination station, the ticket fare, the time, etc.

[0044] The passenger estimate data 306 may include the total number of passengers estimated to be waiting at the station. The passenger estimate data 306 may also include information about the delay time for the transportation means to arrive at the station and congestion information within the transportation means.

[0045] The change possibility data 308 may include one or more change possibilities determined for each of one or more waiting passengers at a station.

[0046] The abandonment risk data 310 may include an aggregate of the total number of waiting passengers calculated based on the change probability data 308. The aggregate is calculated by adding together one or more change probabilities associated with each of one or more waiting passengers.

[0047] The forecast data 312 may include a number of waiting passengers calculated based on the passenger estimate data 306 and the abandonment risk data 310 .

[0048] Other data 314 may include temporary data and temporary files and may be stored data generated by the module 316 to perform various functions of the passenger flow prediction system 201 .

[0049] In an embodiment, the data 302 in the memory 209 is processed by one or more modules 316 residing in the memory 209 of the passenger flow prediction system 201 .

[0050] The one or more modules 316 function in conjunction with the data 302 to predict passenger flow in the transportation system. In one implementation, the one or more modules 316 may include, without limitation, a receiving module 318, an estimation module 320, a change feasibility determination module 322, an abandonment risk determination module 324, a prediction module 326, and one or more other modules 328.

[0051] In embodiments, one or more of the modules 316 may be implemented as dedicated units. As used herein, the term module refers to an application-specific integrated circuit (ASIC), an electronic circuit, a field-programmable gate array (FPGA), a programmable system-on-a-chip (PSoC), a combinational logic circuit, and / or other suitable components that provide the described functionality. In some implementations, one or more of the modules 316 may be communicatively coupled to the processor 211 to enable the passenger flow prediction system 201 to perform one or more functions. When the modules 316 are configured with the functionality of the present disclosure, they constitute new hardware.

[0052] The receiving module 318 may receive input data 304 including historical data for a plurality of passengers of a transportation mode. The receiving module 318 may determine an acceptable delay time and an acceptable transportation mode congestion associated with each of the plurality of passengers based on the travel history data. The acceptable delay time and the acceptable transportation mode congestion are determined based on transportation mode status information and passenger location information. The acceptable delay time relates to an acceptable time for a passenger if the transportation mode is delayed in arriving at a station. The acceptable transportation mode congestion relates to a predetermined congestion rate for the transportation mode. In one embodiment, the acceptable delay time and the acceptable transportation mode congestion may correspond to predetermined thresholds associated with each of the plurality of passengers. Thus, one or more passengers may decide not to board a transportation mode at a station if the delay time and the congestion within the transportation mode do not meet the respective thresholds.

[0053] In an embodiment, the receiving module 318 receives historical data associated with a predetermined classification corresponding to a category of frequent flyers. In one embodiment, a predetermined clustering technique, such as k-means clustering, is used to classify the historical data into frequent flyer and non-frequent flyer categories. FIG. 4A is a graph illustrating passenger classification categories. The two categories shown in FIG. 4A correspond to frequent flyers and non-frequent flyers, which are classified based on the number of trips by multiple passengers and the duration of the trips. That is, the frequent flyer category is a passenger group that travels more frequently during peak hours than non-peak hours and travels more frequently than non-frequent flyers.

[0054] Table 1 below holds exemplary historical data for queued passenger "1" waiting at Station A. The historical data shows the decisions queued passenger "1" made regarding various trips in relation to different combinations of delay times and congestion within the transportation mode.

[0055] [Table 1]

[0056] As shown in Table 1, on days when the delay and congestion history associated with the bus did not fall within the predetermined thresholds associated with the acceptable delay and acceptable mode congestion, waiting passenger "1" did not board the bus. As can be seen from Table 1, the acceptable delay corresponds to 4.3 hours, and the acceptable congestion corresponds to 41%. Therefore, if the thresholds are not met, waiting passenger "1" may not board the bus. Figures 4B and 4C are graphs illustrating the likelihood of waiting passenger "1" boarding the bus, taking into account the delay and congestion history, with respect to Table 1. The graphs show that as the delay and congestion history increase, waiting passenger "1"'s likelihood of boarding decreases. For example, the highest likelihood of boarding occurs when the delay and congestion history values ​​are zero. Therefore, the x- and y-axes of the graphs are inversely proportional.

[0057] Additionally, the historical data also includes mode status information, payment information, delay history, and congestion history (not shown in Table 1) associated with the travel history of each of the plurality of passengers.

[0058] 3 , the estimation module 320 estimates the total number of passengers waiting to board a transportation mode at a station based on movement history data associated with one or more passengers among a plurality of passengers waiting at the station to board a transportation mode. The estimation module 320 utilizes passenger location information associated with the movement history of each of the plurality of passengers to estimate the total number of passengers waiting to board a transportation mode at a station. For example, passenger location information, including payment information such as the number of tickets sold to a particular destination, time aboard the transportation mode, and transportation mode number, may be considered to estimate the total number of passengers waiting to board a transportation mode.

[0059] Furthermore, the estimation module 320 estimates the delay time until the transportation means arrives at the station and the congestion within the transportation means based on the movement history data. The estimation module 320 estimates the delay time and congestion corresponding to the future state using the delay time history and the congestion history. In other words, the delay time and congestion are estimated for the next station where the transportation means has not yet arrived. Therefore, the estimation module 320 estimates the delay time and congestion using at least one of a predetermined statistical technique or a predetermined machine learning technique.

[0060] The change possibility determination module 322 determines a change possibility corresponding to the possibility of changing transportation modes. The change possibility determination module 322 determines the possibility of each of one or more waiting passengers at a station changing transportation modes. Furthermore, the change possibility determination module 322 determines the change possibility based on the delay time, congestion within the transportation mode, acceptable delay time, and acceptable congestion of the transportation mode associated with each passenger. The change possibility determination module 322 determines an initial probability of changing transportation modes based on a function of the total number of transportation mode change histories and the total travel history associated with each of one or more waiting passengers. For example, when the values ​​listed in Table 2 are substituted, the initial probability of change in Equation (1) corresponds to 0.5.

[0061]

number

[0062] therefore,

[0063]

number

[0064] The change probability determination module 322 determines the change probability based on a function of delay time, congestion within the transportation means, and initial probability. In one embodiment, the change probability is determined based on predetermined statistical techniques or Bayes' probability theorem. Substituting the values ​​in Equation 2, the resulting change probability for one waiting passenger corresponds to 0.4. Table 2 shows an example change probability calculated for 10 waiting passengers.

[0065] [Table 2]

[0066] The abandonment risk determination module 324 receives the change likelihood data 308 from the change likelihood determination module 322. Upon receiving the change likelihood data 308, the abandonment risk determination module 324 determines the risk that one or more passengers out of the total number of waiting passengers will abandon the transportation mode. The abandonment risk determination module 324 aggregates the change likelihood associated with each of the one or more waiting passengers. From Table 2, substituting the values ​​in Equation 3, the risk is determined to be 3.3.

[0067]

number

[0068] Thereafter, the prediction module 326 receives one or more total numbers of waiting passengers from the estimation module 320, and further receives data related to the risk of passengers abandoning the transportation mode from the abandonment risk determination module 324. Therefore, based on the received data, the prediction module 326 predicts passenger flow at the station based on the determined risk calculated by Equation (3) and the one or more previously estimated total numbers of waiting passengers. That is, by substituting the value of Equation (4), the predicted number of waiting passengers corresponds to 16.7.

[0069]

number

[0070]

number

[0071] Thus, for each station that the means of transport may visit in a day, the number of passengers waiting to board can be predicted.

[0072] 5 is an exemplary flowchart illustrating method steps for predicting passenger flow in a transportation system according to some embodiments of the present disclosure. As shown in FIG. 5, method 500 may include one or more steps. Method 500 may be described in the general context of computer-executable instructions. Generally, computer-executable instructions include routines, programs, objects, components, data structures, procedures, modules, and functions that perform particular functions or implement particular abstract data types.

[0073] The order in which method 500 is described is not intended to be limiting, as any number of method blocks may be combined in any order to perform the method. Furthermore, blocks may be omitted from the method without departing from the scope of the inventions described herein. Furthermore, the method may be implemented in any suitable hardware, software, firmware, or combination thereof.

[0074] The method 500 may include, in step 501, receiving, by the passenger flow prediction system 201, historical travel data associated with a plurality of passengers of a transportation mode from one or more sources to determine an acceptable delay time and an acceptable transportation mode congestion associated with each of the plurality of passengers. The acceptable delay time and the acceptable transportation mode congestion correspond to predetermined thresholds associated with each of the plurality of passengers.

[0075] In step 503, the method 500 may include the passenger flow prediction system 201 estimating a total number of waiting passengers at a station based on historical travel data associated with one or more passengers among a plurality of passengers waiting at the station to board a transportation mode. Estimating the total number of waiting passengers includes identifying one or more waiting passengers from one or more categories of passengers based on a predetermined clustering technique. The one or more categories of passengers include frequent flyers and non-frequent flyers, classified based on travel time.

[0076] The method 500 may include, in step 505, the passenger flow prediction system 201 estimating a delay time for the transportation means to arrive at the station and congestion within the transportation means based on the travel history data associated with the travel history of each of the plurality of passengers.

[0077] The method 500 may include, in step 507, the passenger flow prediction system 201 determining, for each of one or more waiting passengers at the station, a feasibility of changing from one transportation mode to another transportation mode based on the delay time, congestion within the transportation mode, an acceptable delay time, and an acceptable congestion of the transportation mode.

[0078] The method 500 may include, in step 509, the passenger flow forecasting system 201 determining a risk that one or more passengers out of the total number of waiting passengers at the station will abandon transportation by aggregating the change probability associated with each of the one or more waiting passengers.

[0079] The method 500 may include, in step 511, the passenger flow prediction system 201 predicting passenger flow at the station based on the estimated total number of one or more waiting passengers and a risk associated with the one or more waiting passengers.

[0080] Computer Systems FIG. 6 is a block diagram of an example computer system 600 for implementing embodiments consistent with the present disclosure. In one embodiment, the example computer system 600 may be the passenger flow prediction system 201. Accordingly, the example computer system 600 may be used to receive data from one or more sources 203. The example computer system 600 may include a central processing unit 602 (also referred to as a "CPU" or "processor"). The processor 602 may include at least one data processor. The processor 602 may include specialized processing units such as an integrated system (bus) controller, a memory management control unit, a floating-point unit, a graphics processing unit, a digital signal processing unit, etc. The processor 602 may be used to implement the processor 211 shown in FIG. 2.

[0081] The processor 602 may be arranged to communicate with one or more input / output (I / O) devices (not shown) through an I / O interface 601. The I / O interface 601 may utilize communication protocols / methods such as, but not limited to, audio, analog, digital, mono, RCA, stereo, IEEE (Institute of Electrical and Electronics Engineers)-1394, serial bus, universal serial bus (USB), infrared, PS / 2, BNC, coaxial, component, composite, digital visual interface (DVI), high-definition multimedia interface (HDMI), radio frequency (RF) antenna, S-Video, VGA, IEEE 802.n / b / g / n / x, Bluetooth, cellular (e.g., code division multiple access (CDMA), high-speed packet access (HSPA+), global system for mobile communications (GSM), long-term evolution (LTE), WiMax, etc.).

[0082] The computer system 600 may communicate with one or more I / O devices using the I / O interface 601. For example, the input device(s) 610 may be an antenna, keyboard, mouse, joystick, (infrared) remote control, camera, card reader, fax machine, dongle, biometric reader, microphone, touch screen, touch pad, trackball, stylus, scanner, storage device, walkie-talkie, video device / source, etc. The output device(s) 611 may be a printer, fax machine, video display (e.g., cathode ray tube (CRT), liquid crystal display (LCD), light emitting diode (LED), plasma, plasma display panel (PDP), organic light emitting diode display (OLED), etc.), audio speaker, etc.

[0083] The processor 602 may be arranged to communicate with a communications network 609 via a network interface 603. The network interface 603 may communicate with the communications network 609. The network interface 603 may utilize communications protocols including, but not limited to, direct connect, Ethernet (e.g., twisted pair 10 / 100 / 1000BaseT), Transmission Control Protocol / Internet Protocol (TCP / IP), Token Ring, IEEE 802.11a / b / g / n / x, etc. The communications network 609 may include, but is not limited to, a direct interconnect, a local area network (LAN), a wide area network (WAN), a wireless network (e.g., using the Wireless Application Protocol), the Internet, etc. The network interface 603 may utilize communications protocols including, but not limited to, direct connect, Ethernet (e.g., twisted pair 10 / 100 / 1000BaseT), Transmission Control Protocol / Internet Protocol (TCP / IP), Token Ring, IEEE 802.11a / b / g / n / x, etc.

[0084] The communication network 609 may include, but is not limited to, a direct interconnection, an e-commerce network, a peer-to-peer (P2P) network, a local area network (LAN), a wide area network (WAN), a wireless network (e.g., using the Wireless Application Protocol), the Internet, Wi-Fi, etc. The first network and the second network may be either a dedicated network or a shared network, representing an association of different types of networks utilizing various protocols, such as HyperText Transfer Protocol (HTTP), Transmission Control Protocol / Internet Protocol (TCP / IP), Wireless Application Protocol (WAP), etc., to communicate with each other. Furthermore, the first network and the second network may include various network devices, including routers, bridges, servers, computing devices, storage devices, etc. The passenger flow prediction system 201 may receive data (movement history data) from one or more sources 203 via the communication network 609.

[0085] In some embodiments, processor 602 may be arranged to communicate with memory 605 (e.g., RAM, ROM, etc., not shown in FIG. 6 ) through storage interface 604. Storage interface 604 may be connected to memory 605, including, but not limited to, memory drives, removable disk drives, etc., utilizing connection protocols such as Serial Advanced Technology Attachment (SATA), Integrated Drive Electronics (IDE), IEEE-1394, Universal Serial Bus (USB), Fibre Channel, Small Computer System Interface (SCSI), etc. Memory drives may further include drum, magnetic disk drives, magneto-optical drives, optical drives, redundant array of independent disks (RAID), solid state memory devices, solid state drives, etc.

[0086] Memory 605 may store program or database components, including, but not limited to, a user interface 606, an operating system 607, a web browser 608, etc. In some embodiments, computer system 600 may store user / application data, such as data, variables, and records, as described in this disclosure. The database may be implemented as a fault-tolerant, relational, scalable, and secure database, such as Oracle® or Sybase®. Memory 605 may be used to implement memory 209 shown in FIG. 2. Memory 605 may be communicatively coupled to processor(s) 602. Memory 605 stores instructions executable by one or more processors 602. When executed, the instructions may cause processor(s) 602 to predict passenger flows.

[0087] Operating system 607 may facilitate resource management and operation of computer system 600. Examples of operating systems include, but are not limited to, APPLE MACINTOSH® OSX®, UNIX®, UNIX-like system distributions (e.g., BERKELEY SOFTWARE DISTRIBUTION™ (BSD), FREEBSD™, NETBSD™, OPENBSD™, etc.), LINUX DISTRIBUTIONS™ (e.g., RED HAT™, UBUNTU™, KUBUNTU™, etc.), IBM™ OS / 2, MICROSOFT™ WINDOWS® (XP™, VISTA™ / 7 / 8, 10, etc.), APPLE® IOS™, GOOGLE® ANDROID®, BLACKBERRY® OS, etc.

[0088] In some embodiments, computer system 600 may execute program components stored on a web browser 608. Web browser 608 may be, for example, a hypertext display application such as MICROSOFT® INTERNET EXPLORER™, GOOGLE® CHROME™, MOZILLA® FIREFOX™, APPLE® SAFARI™, etc. Secure web browsing may be achieved using Secure Hypertext Transport Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TLS), etc. Web browser 608 may utilize facilities such as AJAX™, DHTML™, ADOBE® FLASH™, JAVASCRIPT™, JAVA™, application programming interfaces (APIs), etc. In some embodiments, exemplary computer system 600 may execute program components stored on a mail server (not shown). The mail server may be an Internet mail server such as Microsoft Exchange. The mail server may utilize facilities such as ASP™, ACTIVEX™, ANSI™ C++ / C#, MICROSOFT®, .NET™, CGI SCRIPTS™, JAVA®, JAVASCRIPTS™, PERL™, PHP™, PYTHON®, WEBOBJECTS™, etc. The mail server may utilize communication protocols such as Internet Message Access Protocol (IMAP), Messaging Application Programming Interface (MAPI), MICROSOFT® Exchange, Post Office Protocol (POP), Simple Mail Transfer Protocol (SMTP), etc. In some embodiments, computer system 600 may implement program components that a mail client stores.The email client (not shown) may be an email viewing app such as APPLE® MAIL™, MICROSOFT® ENTOURAGE™, MICROSOFT® OUTLOOK™, MOZILLA® THUNDERBIRD™, or the like.

[0089] Furthermore, one or more computer-readable storage media may be utilized to implement embodiments of the present disclosure. A computer-readable storage medium refers to any type of physical memory in which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions that cause a processor(s) to perform steps or stages according to embodiments described herein. The term "computer-readable medium" should be understood to include tangible objects and exclude carrier waves and transitory signals, i.e., non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, non-volatile memory, hard drives, compact disc read-only memory (CD-ROM), digital video discs (DVDs), flash drives, disks, and other known physical storage media.

[0090] The present disclosure predicts the number of passengers waiting at the next station, taking into account future conditions related to the risk of passenger abandonment due to delays or overcrowding. Thus, the predictions help transportation systems optimize and adjust long-term and short-term operation plans to maintain appropriate schedules for an improved passenger experience.

[0091] The terms "an embodiment," "embodiment," "embodiments," "the embodiment," "the embodiments," "one or more embodiments," "some embodiments," and "one embodiment" mean "one or more (but not all) of the embodiments of the invention(s)," unless expressly stated otherwise.

[0092] The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless expressly stated otherwise.

[0093] The listing of numbered elements does not imply that any or all of the elements are mutually exclusive unless expressly stated otherwise. "A," "an," and "the" mean "one or more" unless expressly stated otherwise.

[0094] A description of an embodiment having several components in communication with each other does not imply that all such components are required, but rather a variety of optional components are described to illustrate various possible embodiments of the present invention.

[0095] Where a single device or article is described herein, it will be readily apparent that multiple devices / articles (whether or not cooperating with each other) may be utilized in place of the single device / article. Similarly, where multiple devices or articles are described herein (whether or not cooperating with each other), it will be readily apparent that a single device / article, or a number of devices / articles different from the number of devices or programs illustrated, may be utilized in place of the multiple devices / articles. Alternatively, the functionality and / or features of a device may be implemented by one or more other devices not expressly described as having that functionality / feature. Thus, other embodiments of the present invention may not include a device per se.

[0096] The operations depicted in FIG. 5 depict certain events occurring in a particular order. In alternative embodiments, certain operations may be performed in a different order, modified, or omitted. Additionally, steps may be added to the logic described above and still be consistent with the described embodiments. Additionally, operations described herein may be performed sequentially, or certain operations may be processed in parallel. Still further, operations may be performed by a single processing unit or by distributed processing units.

[0097] Finally, the language used herein has been chosen primarily for ease of reading and instruction, and may differ from that chosen to define or define the scope of the invention. Accordingly, the scope of the invention is not intended to be limited by this detailed description, but rather by any claims filed based hereon. Accordingly, this disclosure of embodiments of the invention is intended to illustrate, but not limit, the scope of the invention, which is set forth in the following claims.

[0098] While various aspects and embodiments are described herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments described herein are for illustrative purposes and are not intended to be limiting. The actual scope is indicated by the following claims. [Explanation of symbols]

[0099] 200 Example Environment 201 Passenger Flow Forecasting System 203 One or more sources 205 Communication Network 207 I / O Interface 209 Memory 211 processor 302 Data 304 Input Data 306 Passenger Estimate Data 308 Mutable Data 310 Abandonment Risk Data 312 Forecast Data 314 Other Data 316 modules 318 Receiver Module 320 Estimation Module 322 Changeability Decision Module 324 Abandonment Risk Assessment Module 326 Prediction Module 328 Other Modules 600 Computer Systems 601 I / O interface 602 processor 603 Network Interface 604 Storage Interface 605 memory 606 User Interface 607 Operating Systems 608 Web Browser 609 Communication Network 610 Input Devices 611 Output Devices

Claims

1. a passenger flow prediction system receiving, from one or more sources, historical travel data associated with a plurality of passengers to determine an acceptable delay time and an acceptable congestion of the transportation system associated with each of the plurality of passengers of the transportation mode; the passenger flow prediction system estimating a total number of passengers waiting to board at the station based on the movement history data related to one or more passengers among the plurality of passengers waiting at the station to board the transportation means; the passenger flow prediction system estimating a delay time until the transportation means arrives at the station and congestion within the transportation means based on the movement history data related to the movement history of each of the plurality of passengers; the passenger flow prediction system determines, for each of one or more waiting passengers at the station, a possibility of changing the transportation mode to another transportation mode based on the delay time, the congestion in the transportation mode, the acceptable delay time, and the acceptable congestion of the transportation mode; the passenger flow forecasting system determining, for the station, a risk that the one or more passengers out of the total number of waiting passengers will abandon the transportation mode by aggregating the change probabilities associated with each of the one or more waiting passengers; the passenger flow prediction system predicting passenger flow at the station based on the estimated total number of one or more waiting passengers and the risk associated with the one or more waiting passengers; A method for predicting passenger flow in a transportation system, comprising:

2. 10. The method of claim 1, wherein estimating the total number of waiting passengers comprises identifying the one or more waiting passengers from one or more categories of passengers based on a predetermined clustering technique.

3. The method of claim 2 , wherein the one or more categories of passengers include frequent flyers and non-frequent flyers classified based on travel time.

4. Determining the likelihood of each of the one or more waiting passengers changing from the transportation mode to the other transportation mode includes: determining an initial likelihood that each of the one or more waiting passengers will change from the transportation mode to the other transportation mode based on a function of a total number of transportation mode changes and a total travel history determined based on the travel history data associated with each of the one or more waiting passengers; and determining the likelihood that each of the one or more waiting passengers will change from the transportation mode to the other transportation mode based on a function of the delay time, the congestion in the transportation mode, and the initial likelihood.

5. The method of claim 1 , wherein the mutability is determined utilizing at least one of statistical or machine learning techniques.

6. The method of claim 1 , wherein the acceptable delay time and the acceptable transportation congestion correspond to predetermined thresholds associated with each of the plurality of passengers.

7. the travel history data includes transportation status information and passenger location information associated with the travel history of each of the plurality of passengers; The method of claim 1 , wherein the predetermined thresholds related to the acceptable delay time and the acceptable transportation congestion are estimated based on the transportation status information and the passenger location information.

8. The method of claim 7 , wherein the transportation status information is determined based on at least one of the location of the transportation, weather information, and traffic information.

9. The passenger location information is a predetermined identifier associated with a user device of each of the plurality of passengers; Payment information related to the travel history of each of the plurality of passengers; and location information of tagging devices of one or more objects associated with each of the plurality of passengers.

10. A passenger flow prediction system that predicts passenger flow in a transportation system, a processor; a memory communicatively connected to the processor; The memory stores processor instructions that, when executed, cause the processor to: receiving, from one or more sources, travel history data associated with a plurality of passengers for determining an acceptable delay time and an acceptable transportation congestion associated with each of the plurality of passengers of the transportation; estimating a total number of passengers waiting to board the station based on the movement history data associated with one or more passengers among the plurality of passengers waiting at the station to board the transportation means; estimating a delay time until the transportation means arrives at the station and congestion within the transportation means based on the movement history data; determining, for each of one or more waiting passengers at the station, a possibility of changing the transportation mode to another transportation mode based on the delay time, the congestion in the transportation mode, the acceptable delay time, and the acceptable transportation mode congestion; determining, for the station, a risk that the one or more passengers among the plurality of passengers will abandon the transportation mode by aggregating the change probabilities associated with each of the one or more waiting passengers; and predicting the passenger flow at the station based on the estimated total number of one or more waiting passengers and the risk associated with the one or more waiting passengers.

11. 11. The passenger flow prediction system of claim 10, wherein the processor estimates the total number of waiting passengers by identifying the one or more waiting passengers from one or more categories of passengers based on a predetermined clustering technique.

12. The passenger flow forecasting system of claim 11 , wherein the one or more categories of passengers include regular passengers and non-regular passengers classified based on travel time.

13. Determining, by the processor, the likelihood of each of the one or more waiting passengers changing from the transportation mode to the other transportation mode includes: determining an initial likelihood that each of the one or more waiting passengers will change from the transportation mode to the other transportation mode based on a function of a total number of transportation mode changes and a total travel history determined based on the travel history data associated with each of the one or more waiting passengers; and estimating the possibility that each of the one or more waiting passengers will change from the transportation mode to the other transportation mode based on a function of the delay time, the congestion in the transportation mode, and the initial possibility.

14. The passenger flow prediction system according to claim 10 , wherein the processor determines the change probability using at least one of a statistical technique and a machine learning technique.

15. The passenger flow prediction system according to claim 10 , wherein the tolerable delay time and the tolerable congestion of transportation means correspond to predetermined thresholds associated with each of the plurality of passengers.

16. the travel history data includes transportation status information and passenger location information associated with the travel history of each of the plurality of passengers; The passenger flow prediction system according to claim 10 , wherein the processor estimates predetermined thresholds related to the tolerable delay time and the tolerable congestion of transportation means based on the transportation means status information and the passenger location information.

17. The passenger flow prediction system of claim 16 , wherein the processor determines the transportation status information based on at least one of a location of the transportation, weather information, and traffic information.

18. The processor: a predetermined identifier associated with a user device of each of the plurality of passengers; Payment information related to the travel history of each of the plurality of passengers; and location information of tagging devices of one or more objects associated with each of the plurality of passengers.

Images