Method and device for predicting passenger traffic pattern when service

Abstract

A computer-implemented method for predicting passenger flow patterns during service disruption in a metro network of a multimodal traffic network. The method comprises the following steps: providing first information associated with the subway network; providing second information associated with an alternative traffic mode of the metro network in a multimodal traffic network; providing third information associated with a topological structure of a part related to service interruption in the subway network; providing fourth information associated with an estimated offload start station-destination station (ODS) demand pattern for the service interruption; providing fifth information associated with predicted irregular routing of passengers in the multimodal traffic network during a service interruption; and predicting a passenger flow pattern associated with the service interruption by computationally simulating based on the first information, the second information, the third information, the fourth information, and the fifth information collectively.

Description

[0001] Cross-references to related applications

[0002] This application claims priority to Provisional Application No. 63 / 672,259, filed July 17, 2024, with the United States Patent and Trademark Office, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The following content generally relates to the near real-time prediction of passenger flow patterns during railway service disruptions, and more specifically, to a computer-implemented method and related equipment for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transport network. Background Technology

[0004] During a subway service disruption, passengers (at stations) may typically exhibit several different behaviors: some may wait until the disruption ends; some may detour within the subway network; while others may seek alternative modes of transport outside the network to continue their journey. As a result, affected passengers deviate from their usual usage patterns, and station and train ridership differs significantly from normal days when subway service is running smoothly.

[0005] By better understanding passenger behavior and the resulting performance of the metro system during service disruptions, metro operators can develop mitigation strategies for emergency response management, such as adjusting train service operations or deploying alternative public transport to reduce delays and improve the passenger experience.

[0006] For traffic system planning and modeling, the Multi-Agent Traffic Simulation Model (MATSim) is a commonly used open-source dynamic simulation model. This model simulates the travel choice decisions of individual agents and the congestion interactions of these decisions on system performance. MATSim is based on activity-based modeling: it incorporates the richness of behaviors linking people's activity patterns, is designed for large-scale scenarios, and performs a holistic micro-simulation of the resulting traffic flow and the congestion caused by that flow. Because MATSim includes behavioral parameters for each agent in addition to various parameters, it can capture the diversion decisions of agents across multiple traffic modes.

[0007] However, MATSim is computationally expensive as it considers detailed network information, including road network attributes, dynamic signal timings, and public transport timetables and routes for all major modes. MATSim also has not been calibrated to model passenger route choice behaviour during service disruptions. MATSim requires long simulation times to perform a simulation and must perform multiple iterations of the simulation to obtain an equilibrium solution, which further increases the computation time. For example, in the case of the Hong Kong region, a full round of simulation in MATSim often requires more than 20 days of computation time. Therefore, predictions that are of practical use cannot be produced in a timely manner.

[0008] Therefore, metro system operators cannot use MATSim to predict the outcome of service disruptions in order to allocate management resources in a timely manner. Furthermore, the assumption of equilibrium passenger route choice can not be applicable as passengers typically do not have perfect information about alternative routes during service disruptions and cannot reach an equilibrium solution through repeated choices.

[0009] That is, in the field of transportation engineering, there is generally a lack of models that can quickly predict passenger flow patterns in near real-time, especially under disruptive operating conditions. Therefore, there is a need for a solution that can address at least one of the problems in the prior art and / or provide an alternative that is useful in the art. SUMMARY

[0010] The technology described herein can relate to a computer-implemented method and related devices for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transport network. A non-limiting objective of the method presented herein is to significantly improve the ability of metro operators to manage metro service disruptions.

[0011] According to a first aspect, there is disclosed a computer-implemented method for predicting a passenger flow pattern during a service disruption in a metro network of a multimodal transport network, the method comprising: providing first information associated with the metro network, the first information comprising a topology of the metro network, a train service timetable in the metro network, and information on train fares; providing second information associated with alternative modes of transport of the multimodal transport network to the metro network, the second information comprising information on fares of the alternative modes of transport, and expected travel times based on routes of the alternative modes of transport; providing third information associated with a topology of a part of the metro network related to a service disruption; providing fourth information associated with an estimated diversion origin-destination station (ODS) demand pattern for the service disruption; providing fifth information associated with a predicted irregular route choice of passengers in the multimodal transport network during the service disruption; and predicting a passenger flow pattern associated with the service disruption collectively based on the first information, the second information, the third information, the fourth information, and the fifth information by computationally simulating.

[0012] Preferably, predicting the passenger flow pattern comprises outputting information on link flows along each metro line, and a number of waiting passengers on platforms arranged at the part of the metro network related to the service disruption.

[0013] Preferably, the topology of the part of the metro network can indicate at least one station affected by the service disruption.

[0014] Preferably, providing the fourth information associated with the estimated diversion ODS demand pattern can comprise configuring a graph neural network (GNN) to capture spatial and temporal information embedded in the metro network, wherein the GNN is further configured with information on the topology of the metro network; providing the third information to the GNN; providing sixth information on a number of passenger demands for origin-destination station (ODS) pairs associated with the service disruption to the GNN; and estimating, by the GNN, passenger diversion behaviour for each ODS pair based on the third information and the sixth information, which collectively enables generation of the estimated diversion ODS demand pattern as the fourth information.

[0015] Preferably, the method can further comprise calibrating a number of ODS pairs associated with the service disruption to match the estimated diversion ODS demand pattern.

[0016] Preferably, the information on the topology of the metro network can comprise information associated with costs of travelling between stations and on links in the metro network.

[0017] Preferably, the GNN can be pre-trained with historical ODS demand patterns based on smart card data associated with travel in the metro network, and in the historical ODS demand patterns, regular passengers with habitual travel patterns can be identified as representative followers to enable determination of passenger irregular route choices during service disruptions based on the habitual travel patterns of the representative followers.

[0018] Preferably, the smart card data associated with travel in the metro network can include data associated with travel in the metro network during service disruptions, and data associated with travel in the metro network during its uninterrupted operation.

[0019] Preferably, the first information can further include information on train types operating in the metro network and respective capacities of the trains.

[0020] Preferably, the computationally simulating to predict the passenger flow patterns can be performed by an event-based metro system simulation model.

[0021] Preferably, the event-based metro system simulation model can be configured with at least the following information: historical ODS demand patterns based on smart card data associated with travel in the metro network, wherein the smart card data includes data associated with travel in the metro network during service disruptions, and data associated with travel in the metro network during its uninterrupted operation; and passenger load information of the trains during service disruptions and during uninterrupted operation of the metro network.

[0022] According to a second aspect, there is disclosed a computing device for predicting passenger flow patterns during a service disruption in a metro network of a multimodal transport network, comprising: one or more memories having executable code; and one or more processors coupled to the one or more memories and configured to execute the code to cause the computing device to: provide first information associated with the metro network, the first information comprising a topology of the metro network, train service schedules in the metro network, and information on train fares; provide second information associated with alternative modes of transport of the metro network in the multimodal transport network, the second information comprising information on fares of the alternative modes of transport, and expected travel times based on routes of the alternative modes of transport; provide third information associated with a topology of a part of the metro network related to a service disruption; provide fourth information associated with an estimated diversion origin-destination station (ODS) demand pattern for the service disruption; provide fifth information associated with predicted irregular route choices of passengers in the multimodal transport network during the service disruption; and predict, based collectively on the first information, the second information, the third information, the fourth information, and the fifth information, a passenger flow pattern associated with the service disruption by computationally simulating.

[0023] According to a third aspect, there is disclosed a computing device for predicting passenger flow patterns during a service disruption in a metro network of a multimodal transport network, comprising: means for providing first information associated with the metro network, the first information comprising a topology of the metro network, train service schedules in the metro network, and information on train fares; means for providing second information associated with alternative modes of transport of the metro network in the multimodal transport network, the second information comprising information on fares of the alternative modes of transport, and expected travel times based on routes of the alternative modes of transport; means for providing third information associated with a topology of a part of the metro network related to a service disruption; means for providing fourth information associated with an estimated diversion origin-destination station (ODS) demand pattern for the service disruption; means for providing fifth information associated with predicted irregular route choices of passengers in the multimodal transport network during the service disruption; and means for predicting, based collectively on the first information, the second information, the third information, the fourth information, and the fifth information, a passenger flow pattern associated with the service disruption by computationally simulating.

[0024] According to a fourth aspect, a non-transitory computer-readable medium comprising executable code, which when executed by a processor of a computing device, causes the computing device to perform the method of the first aspect is disclosed.

[0025] Additional benefits and advantages of the aspects disclosed herein can become apparent to those of ordinary skill in the art, upon reading the description and figures. The benefits and / or advantages can be obtained by one or more aspects and features of the disclosure, without requiring all of the aspects and features to be provided in order to obtain such benefits and / or advantages. BRIEF DESCRIPTION OF DRAWINGS

[0026] The accompanying drawings are used to demonstrate various aspects in accordance with the present disclosure and to explain various principles and advantages, in which like reference numerals in the separate views denote or refer to the same or functionally similar elements, and are incorporated in and form part of the specification, and together with the detailed description, serve to explain the principles and advantages of the present disclosure.

[0027] Figure 1 is a flowchart depicting a computer-implemented method for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network, in accordance with aspects of the present disclosure.

[0028] Figure 2 is a flowchart depicting a computer-implemented method for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network, in accordance with aspects of the present disclosure. Figure 1 is a schematic representation of a method of

[0029] Figure 3 is a schematic representation of a statistical model for generating estimated split origin-destination station (ODS) demand patterns, in accordance with aspects of the present disclosure.

[0030] Figure 4 is a flowchart depicting a method for identifying regular passengers with habitual travel patterns from smart card data associated with travel in a metro network, in accordance with aspects of the present disclosure.

[0031] Figure 5 is a flowchart depicting a method for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network, in accordance with aspects of the present disclosure. Figure 1 is a schematic representation of an implementation of an event-based metro system simulation model used in the method of

[0032] Figure 6 and Figure 7 is a block diagram of an apparatus for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network, in accordance with aspects of the present disclosure.

[0033] Figure 8 is a block diagram of a computational manager for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network, in accordance with aspects of the present disclosure. is a flowchart depicting a computer-implemented method for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network, in accordance with aspects of the present disclosure.

[0034] Figure 9 is a schematic diagram of an example computing device for performing the method of Figure 1 according to aspects of the present disclosure.

[0035] Figure 10 is a schematic diagram of an example computing device for performing the method of Figure 1 according to aspects of the present disclosure. DETAILED DESCRIPTION

[0036] Aspects of the present disclosure set forth a method and corresponding device for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network.

[0037] It should be understood that, although the following description provides examples of method(s) and corresponding device(s) for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network, they are not intended to limit the scope, applicability, or examples set forth in the claims. Changes in or additions to the function and arrangement of elements can be made without departing from the scope of the present disclosure. Various examples can omit, substitute, or add various procedures or components as appropriate, or in appropriate combination. For example, the methods described can be performed in an order different from that described, and other steps can be added, omitted, or combined. Also, features described with respect to some examples can be combined in some other examples. For example, any number of the various aspects set forth herein can be employed without departing on scope of the present disclosure. Additionally, the scope of the present disclosure is intended to cover all such changes, substitutions, variations, and additions and is intended to cover the present disclosure and its applications as they can occur to those skilled in the art. It is intended that the scope of the present disclosure should encompass all such changes, substitutions, variations, and additions and be limited only by the claims. It should be understood that any factual statements set forth in the description are believed to be true on the date of the patent application. However, the applicant reserves the right to amend the description to concede that a fact may not be true on any date other than the date of the patent application.

[0038] Aspects of the present disclosure will be described with reference to the attached drawings, which are merely for illustration. Like reference numerals and symbols in the drawings indicate like elements or equivalents.

[0039] Figure 1 is a flowchart illustrating a computer-implemented method 100 for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network according to aspects of the present disclosure. The method 100 is also described with reference to Figure 2 is a schematic diagram of an example computing device for performing the method of Figure 2 depicts a schematic representation 200 of the method 100.

[0040] The operations of the method 100 can be performed by asFigure 9 to Figure 10 The computing devices 900, 1000 (or components thereof) depicted in FIGS. 9 and 10 implement. For example, the operations of the method 100 can be performed by the computing manager 615, 715 as described with reference to FIGS. 6 and 7, which can be installed on and executed by the computing devices 900, 1000 (or components thereof). In some examples, the computing devices 900, 1000 (or components thereof) can execute a set of instructions to control the functional elements of the computing devices 900, 1000 to perform the functions described below. Additionally or alternatively, the computing devices 900, 1000 can perform various ones of the functions described below using special-purpose hardware. Figure 6 to Figure 7

[0041] At 105, the method 100 can include providing first information associated with the metro network, the first information comprising a topology of the metro network, a train service schedule in the metro network, and information about train fares. This corresponds to component 205 in the schematic representation 200. Figure 2 In some cases, the first information can further include information about types of trains operating in the metro network and respective capacities of the trains.

[0042] At 110, the method 100 can include providing second information associated with alternative modes of transport of the metro network in the intermodal transport network, the second information comprising information about fares of the alternative modes of transport, and expected travel times based on routes of the alternative modes of transport. This corresponds to component 210 in the schematic representation 200.

[0043] At 115, the method 100 can include providing third information associated with a topology of a portion of the metro network related to a service disruption. This corresponds to component 215 in the schematic representation 200. In some cases, the topology of the portion of the metro network can indicate at least one station affected by the service disruption.

[0044] At 120, the method 100 can include providing fourth information associated with an estimated diversion origin-destination station (ODS) demand pattern for the service disruption. This corresponds to component 220 in the schematic representation 200.

[0045] At 125, the method 100 can include providing fifth information associated with a predicted irregular route choice of passengers in the intermodal transport network during the service disruption. The fifth information is generated by the “passenger route choice” model 225 (see Figure 2 ) and provided (as input) to the method 100.

[0046] ​At 130, the method 100 can comprise predicting, collectively based on the first information, the second information, the third information, the fourth information, and the fifth information, a passenger flow pattern associated with the service disruption by computationally simulating. Additionally or alternatively, predicting the passenger flow pattern 235 can comprise outputting information about link flows along each metro line (in the metro network), and the number of waiting passengers on platforms arranged at portions of the metro network that are relevant to the service disruption.

[0047] It will be appreciated that, in the example, computationally simulating to predict the passenger flow pattern can be performed by the event-based metro system simulation model 230 (i.e. see Figure 2 It will be appreciated that the “passenger route choice” model 225 and the event-based metro system simulation model 230 can collectively constitute a “public facility-based passenger behaviour” model 240. The formation of the “public facility-based passenger behaviour” model 240 is set out in detail below.

[0048] The event-based metro system simulation model 230 can be configured with at least the following information: a historical ODS demand pattern based on smart card data associated with travel in the metro network (e.g. entry and exit data recorded at station gates in the metro network to the precision of daily time by smart card payment transactions); and train load information during service disruptions and during non-disrupted operation (i.e. normal operating conditions) of the metro network. The smart card data can include data associated with travel in the metro network during service disruptions, and data associated with travel in the metro network during non-disrupted operation thereof.

[0049] It will be appreciated that, within the event-based metro system simulation model 230, individual passengers of each ODS pair are loaded onto trains according to their route choices on a first-come-first-served basis, given the metro network layout, train types and capacities, and service operating schedules. For each ODS pair, a set of time-sequential expected travel times outside the metro network is compiled from various sources. Specifically, a set of complete historical ODS diversion data during previous service disruptions in the metro network is compiled. However, as the historical ODS diversion data for the metro network lacks information about passengers’ route choices to alternative modes of transport outside the metro network, such information is obtained from third-party navigation and route planning platforms (e.g. Google Maps, HKeMobility, etc.).

[0050] With respect to the "passenger route choice" model 225, relative route public facilities can be extracted from the event-based subway system simulation model 230 by comparing route characteristics such as route length and expected travel time experienced within the subway network against expected travel time outside the subway network via other alternative modes of transport. These characteristics are used to calibrate the "public facility-based passenger behavior" model 240 in the context of service disruption scenarios.

[0051] The disclosed method 100 is able to capture passenger diversion patterns within and outside the subway network (such that the event-based subway system simulation model 230 can take into account a comprehensive set of relative route public facilities) without resorting to using agent-based simulation models to generate predicted passenger flow patterns 235 in near real-time. The disclosed method 100 provides the ability to predict changes in ODS passenger demand related to service disruptions in the subway network, and encapsulates calibrated passenger route choice behavior in the context of service disruptions as well as service adjustments by the subway operator. It should be appreciated that the method 100 can also be used for counterfactual studies on past cases, as well as estimation studies on hypothetical cases, to predict changes in ODS passenger demand in the context of service disruptions in the subway network. Furthermore, the event-based subway system simulation model 230 is configured to generate train and platform loads in an efficient manner, such that results can be generated that can be beneficial in forming mitigation strategies for emergency response management in the context of service disruptions in the subway network in a timely manner. Specifically, passenger flow patterns are predicted in the form of train loads and platform loads (i.e., the number of passengers at respective locations at any point in time of the simulation). That is, passenger flow patterns are predicted at the granularity of origin-destination station pairs, and then all passengers are aggregated by time into train loads.

[0052] Figure 3 is a schematic representation 300 of a statistical model for generating fourth information about estimated ODS demand patterns in accordance with aspects of the present disclosure. Specifically, fourth information associated with estimated diversion ODS demand patterns is provided (see Figure 1 ) can include:

[0053] • configuring a graph neural network (GNN) 305 (as the statistical model) to capture spatial and temporal information embedded in the subway network, where the GNN 305 is further configured with information about the topology of the subway network;

[0054] • providing the GNN 305 with the third information (i.e., topology of the portion of the subway network related to the service disruption);

[0055] • providing, to the GNN 305, sixth information about the number of passenger demands for origin-destination station (ODS) pairs associated with the service disruption as ODS input counts at the time of the service disruption (i.e., depicted as component 310 in Figure 3

[0056] • estimating, by the GNN 305, passenger diversion behavior for each ODS pair based on the third information and the sixth information (i.e., depicted as component 315 in Figure 3 Figure 3

[0057] For completeness, this citation provides a survey on state-of-the-art GNNs: Wu Z, Pan S, Chen F, et al.: “A Comprehensive Survey on Graph Neural Networks.” IEEE Transactions on Neural Networks and Learning Systems. 2021 Jan;32(1):4-24. DOI: 10.1109 / tnnls.2020.2978386. PMID: 32217482.

[0058] Additionally or alternatively, the information about the topology of the metro network can include information associated with the cost of traveling between stations and on links in the metro network. It can be appreciated that in transportation engineering, a passenger trip can incur various different costs: e.g., monetary cost, time cost, discomfort cost, and the like. Thus, trip cost can be understood as the total cost incurred by a passenger trip, which is a complex combination of the above-mentioned costs.

[0059] Additionally or alternatively, the GNN 305 can be pre-trained with historical ODS demand patterns (i.e., depicted as component 325 in Figure 3 Figure 3 Figure 3

[0060] ​​​​​​It will be appreciated that the smart card data associated with travel in the metro network can include data associated with travel in the metro network during service disruptions, as well as data associated with travel in the metro network during periods of non-disrupted operation thereof.

[0061] Additionally or alternatively, the method 100 can further comprise calibrating the number of ODS pairs associated with the service disruption to match the estimated diverted ODS demand pattern. It will be appreciated that the term “calibrate” herein means to make appropriate adjustments to the GNN 305 to predict the estimated diverted ODS demand pattern (i.e., the actual passenger ODS demand (i.e., the actual passenger ODS demand (i.e., Figure 3 the component 320 shown in FIG. 3B), so that it is as close as possible (i.e., matches) the actual passenger ODS demand during the service disruption (i.e., Figure 3 the component 310 shown in FIG. 3A), which can mean that the GNN 305 is working well.

[0062] In some embodiments, the operations of the method 100 can be programmed into corresponding computer readable code executable by the computing device 900, 1000 (or components thereof), and stored as the corresponding computer readable code.

[0063] According to aspects of the present disclosure, a computing device (e.g., the computing device 900, 1000 depicted in FIGS. 1A-1B) for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network is disclosed, comprising: Figure 9 to Figure 10 one or more memories having executable code; and one or more processors coupled to the one or more memories and configured to execute the code to cause the computing device to:

[0064] 1) provide first information associated with the metro network, the first information comprising a topology of the metro network, a train service schedule in the metro network, and information about train fares;

[0065] 2) provide second information associated with alternative modes of transportation of the metro network in the multimodal transportation network, the second information comprising information about fares of the alternative modes of transportation and expected travel times based on routes of the alternative modes of transportation;

[0066] 3) provide third information associated with a topology of a portion of the metro network related to service disruptions;

[0067] 4) provide fourth information associated with an estimated diverted origin-destination station (ODS) demand pattern for the service disruptions;

[0068] 5) providing fifth information associated with predicted irregular route choices of passengers in the intermodal transportation network during the service disruption; and

[0069] 6) predicting passenger flow patterns associated with the service disruption collectively based on the first information, the second information, the third information, the fourth information, and the fifth information by computationally simulating.

[0070] Further details regarding some aspects of the disclosed method 100 are set forth in the following description.

[0071] Figure 4 is a flowchart depicting a (algorithmic) method 400 for identifying representative passengers (i.e., regular commuters) having habitual travel patterns from smart card data associated with travel in a metro network in accordance with aspects of the present disclosure. For clarity, this is associated with various historical ODS demand patterns (i.e., depicted as Figure 3 component 325 in FIG. 4) based on smart card data associated with travel in a metro network. A regular commuter can be defined as a passenger who travels between the same origin-destination station (OD) pair during the disruption time period of a day on each weekday (excluding the day of the service disruption) of a week. The following pseudo-code section outlines how the method 400 can flow accordingly with respect to the determinations made.

[0072] At step 405, it is initially presumed that the passenger indicated in the smart card data is a regular passenger. At the next step 410, it is determined whether the OD pair for the passenger is affected (affected by the metro service disruption in question), and the pseudo-code to be executed is:

[0073] • if the OD pair for the passenger is affected (i.e., the "Yes" leg), then the flow proceeds to step 420; otherwise

[0074] • if the OD pair for the passenger is not affected (i.e., the "No" leg), then the flow proceeds to step 415.

[0075] At step 420, it is determined whether there is metro gate entry-exit information on the service disruption day, and the pseudo-code to be executed is:

[0076] • if there is metro gate entry-exit information on the service disruption day (i.e., the "Yes" leg), then the flow proceeds to step 430; otherwise

[0077] • if there is no metro gate entry-exit information on the service disruption day (i.e., the "No" leg), then the flow proceeds to state 425-a.

[0078] State 425-a is related to "complete diversion outside the metro network" and means that the passenger (identified in step 405) completely diverted his / her journey outside the metro network (using other means of transport) instead of partially diverting his / her journey outside the metro network (using both the metro network and other means of transport to complete his / her initial one-way journey). Alternatively, state 424-a can also be understood as the passenger has abandoned / abandoned his / her journey. In this way, the diversion behavior of the passenger can be identified and classified.

[0079] At step 430, it is determined whether the affected OD pair (based on the existence of metro gate entry-exit information for the service disruption day) is the same as the OD pair on the no-disruption day, and the pseudo code to be executed is:

[0080] • If the affected OD pair (based on metro gate entry-exit information) is the same as the OD pair on the no-disruption day (i.e. the "Yes" route), the flow proceeds to step 440; otherwise

[0081] • If the affected OD pair (based on metro gate entry-exit information) is different from the OD pair on the no-disruption day (i.e. the "No" route), the flow proceeds to step 435.

[0082] At step 435, it is determined whether the origin or destination station is the same (by comparing the affected OD pair with the OD pair on the no-disruption day), and the pseudo code to be executed is:

[0083] • If the origin or destination station is the same (i.e. the "Yes" route), the flow proceeds to state 425-b; otherwise

[0084] • If the origin or destination station is different (i.e. the "No" route), the flow proceeds to step 460.

[0085] State 425-b is related to "partial diversion outside the metro network" and means that the passenger (identified in step 405) partially changed his / her journey route outside the metro network / system (by using both the metro network and other means of transport to complete his / her initial one-way journey). More specifically, this means that the passenger only traveled through some of the route segments in the metro network / system, and his / her journey in the metro network / system is considered incomplete. For example, the passenger can have initially intended to travel from metro station A to metro station C via metro station B, but can have alighted at metro station B in advance. It can then be inferred that the passenger can have completed his / her journey by other means of transport in order to complete the corresponding journey from metro station B to metro station C. In this way, the diversion behavior of the passenger can be identified and classified.

[0086] At step 460, it is determined whether the affected OD pair is around the area where the service disruption is occurring, and the pseudo code to be executed is:

[0087] • If the affected OD pair is around the area where the service disruption is occurring (i.e. the "Yes" leg), the flow proceeds to state 425-b; otherwise

[0088] • If the affected OD pair is not around the area where the service disruption is occurring (i.e. the "No" leg), the flow proceeds to state 425-a.

[0089] Now proceeding to step 440 (based on finding that the affected OD pair is the same as on the no-disruption day), it is determined whether there is an alternative route available, and the pseudo code to be executed is:

[0090] • If an alternative route is available (i.e. the "Yes" leg), the flow proceeds to step 445; otherwise

[0091] • If an alternative route is not available (i.e. the "No" leg), the flow proceeds to step 450.

[0092] At step 445, it is determined whether the available alternative route has a significantly different travel time compared to the corresponding route on the metro network taken on the no-disruption day, and the pseudo code to be executed is:

[0093] • If the travel time is significantly different (i.e. the "Yes" leg), the flow proceeds to state 425-c; otherwise

[0094] • If the travel time is not affected (i.e. the "No" leg), the flow proceeds to step 415.

[0095] State 425-c relates to "rerouting within the metro network", and means that the passenger (identified in step 405) chooses a different (new) route for his / her journey due to the service disruption, but the new route chosen is still entirely within the metro network / system.

[0096] At step 450, it is determined whether a significantly longer travel time is required compared to travelling on the metro network on the no-disruption day, and the code to be executed is:

[0097] • If the travel time is significantly longer (i.e. the "Yes" leg), the flow proceeds to state 425-d; otherwise

[0098] • If the travel time is not significantly longer (i.e. the "No" leg), the flow proceeds to step 455.

[0099] State 425-d is related to "Wait until service disruption ends" and means that the passenger (identified in step 405) chooses to pause his / her journey until the service disruption ends, after which the passenger completes his / her journey as planned, following the original route.

[0100] At step 455, it is determined whether the passenger starts the journey after the service disruption ends, and the pseudo-code to be executed is:

[0101] • If the passenger starts the journey after the service disruption ends (i.e. the "Yes" branch), the flow proceeds to state 425-d; otherwise

[0102] • If the passenger does not start the journey after the service disruption ends (i.e. the "No" branch), the flow proceeds to step 415.

[0103] Figure 5 is a schematic representation 500 of an embodiment of the event-based metro system simulation model 230 used in the method 100 of Figure 1 in accordance with aspects of the present disclosure. In order to form the event-based metro system simulation model 230, the following information (represented as components in Figure 5 is provided to the model 230:

[0104] • Information associated with the metro network, including the topology of the metro network, train service schedules in the metro network, and information about train fares. This is represented as component 205 in Figure 5 .

[0105] • Information associated with alternative modes of transport in the metro network in the intermodal transport network, including information about fares of the alternative modes of transport, and expected travel times based on routes of the alternative modes of transport. This is represented as component 210 in Figure 5 .

[0106] • Information about normal ODS counts, which lists the number of passengers travelling from one origin station to a destination station (one ODS pair) in the absence of disruptions (i.e. the definition of "normal"). For example, there can be 10 passengers travelling between metro station A and metro station B, or 20 passengers travelling between metro station C and metro station D. Thus, in the above two examples, the ODS counts are 10 and 20 respectively. This is represented as component 505 in Figure 5 .

[0107] • Information associated with predicted irregular route choices of passengers in the intermodal transport network during service disruptions. This information is generated by the "passenger route choice" model 225.

[0108] The above information is loaded into the event-based metro system simulation model 230 to form / implement the model 230. The event-based metro system simulation model 230 outputs information related to passenger link flows along each metro line (denoted as component 510 in Figure 5 Next, the train’s passenger load information (denoted as component 515 in Figure 5 is used to match the uninterrupted case with the information related to passenger link flows along each metro line to obtain a set of results which are then used to calibrate the “passenger route choice” model 225. In this way, the train’s passenger load information can be used to calibrate the “passenger route choice” model 225 through the event-based metro system simulation model 230 in the case of disruption. It can be appreciated that the “passenger route choice” model 225 refers to a model that is specifically used to predict passenger route choice behavior in the normal case of no disruption, and thus the train’s passenger load information is used to “match” the uninterrupted case with the passenger link flows information along each metro line output by the event-based metro system simulation model 230 (i.e. component 510 in Figure 5

[0109] Figure 6 is a block diagram of a device 605 for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transportation network in accordance with aspects of the present disclosure. The device 605 can be an example of aspects of the computing device 900, 1000 of Figure 9 to Figure 10 and can be configured to perform the method 100 of Figure 1 The device 605 can include a receiver 610, a computing manager 615, and a transmitter 620. The computing manager 615 can be implemented at least in part by one or both of a modem and a processor. Each of these components can communicate with one another (e.g., via one or more buses).

[0110] The receiver 610 can receive information such as packets, user data, or control information associated with various information channels (e.g., control channels, data channels, or similar channels). The information can be passed on to other components of the device 605. The receiver 610 can be an example of aspects of a radio receiver or an Ethernet adapter. In some examples, the receiver 610 can utilize a single antenna or a set of antennas (e.g., for MIMO communication).

[0111] The computing manager 615 can be configured to perform the following operations:

[0112] 1) provide first information associated with the metro network, the first information including a topology of the metro network, a train service schedule in the metro network, and information about train fares; ​

[0113] 2) providing second information associated with alternative modes of transport in the metro network of the intermodal transport network, the second information comprising information on fares of the alternative modes of transport, and expected travel times based on routes of the alternative modes of transport;

[0114] 3) providing third information associated with a topology of a part of the metro network related to the service disruption;

[0115] 4) providing fourth information associated with an estimated diversion origin-destination (ODS) demand pattern for the service disruption;

[0116] 5) providing fifth information associated with a predicted irregular route choice of passengers in the intermodal transport network during the service disruption; and

[0117] 6) predicting a passenger flow pattern associated with the service disruption collectively based on the first information, the second information, the third information, the fourth information, and the fifth information by computationally simulating.

[0118] Transmitter 620 can transmit signals generated by other components of the device 605. For example, the transmitter 620 can be an example of aspects of a radio transmitter or an Ethernet adapter. In some examples, the transmitter 620 can utilize a single antenna or a set of antennas (e.g., for MIMO communication). In some examples, the transmitter 620 can be placed in a transceiver component with the receiver 1210.

[0119] Figure 7 is a block diagram of a device 705 for predicting a passenger flow pattern during a service disruption in a metro network of an intermodal transport network in accordance with aspects of the present disclosure. The device 705 can be an example of the device 605 or Figure 9 to Figure 10 aspects of the computing devices 900, 1000, and can be configured to perform Figure 1 the method 100. The device 705 can include a receiver 710, a computation manager 715, and a transmitter 720. The computation manager 715 can be implemented at least in part by one or both of a modem and a processor. Each of these components can be in communication with one another (e.g., via one or more buses).

[0120] The receiver 710 can receive information such as packets, user data, or control information associated with various information channels (e.g., control channels, data channels, or similar channels). The information can be passed on to other components of the device 705. The receiver 710 can be an example of aspects of a radio receiver or an Ethernet adapter. The receiver 710 can utilize a single antenna or a set of antennas (e.g., for MIMO communication).

[0121] The computation manager 715 can include a first providing component 715-1, a second providing component 715-2, a third providing component 715-3, a fourth providing component 715-4, a fifth providing component 715-5, and a simulation component 725.

[0122] In some examples, it can be possible that the first providing component 715-1, the second providing component 715-2, the third providing component 715-3, the fourth providing component 715-4, and the fifth providing component 715-5 can alternatively be implemented as a single providing component (not shown) configured to provide the collective functionality of all of the providing components 715-1, 715-2, 715-3, 715-4, 715-5.

[0123] The first providing component 715-1 can provide first information associated with a metro network, the first information including a topology of the metro network, a train service schedule in the metro network, and information about train fares.

[0124] The second providing component 715-2 can provide second information associated with alternative modes of transport of the metro network in a multimodal transport network, the second information including information about fares of the alternative modes of transport, and expected travel times based on routes of the alternative modes of transport.

[0125] The third providing component 715-3 can provide third information associated with a topology of a portion of the metro network related to a service disruption.

[0126] The fourth providing component 715-4 can provide fourth information associated with an estimated diversion origin-destination station (ODS) demand pattern for the service disruption.

[0127] The fifth providing component 715-5 can provide fifth information associated with a predicted irregular route choice of passengers in the multimodal transport network during the service disruption.

[0128] The simulation component 725 can collectively predict a passenger flow pattern associated with the service disruption by computationally simulating based on the first information, the second information, the third information, the fourth information, and the fifth information.

[0129] The transmitter 720 can transmit signals generated by other components of the device 705. For example, the transmitter 720 can be an example of aspects of a radio transmitter or an Ethernet adapter. The transmitter 720 can utilize a single antenna or a set of antennas (e.g., for MIMO communication). In some examples, the transmitter 720 can be collocated with a receiver 710 in a transceiver component.

[0130] Figure 8 is a block diagram of a traffic manager 805 for predicting passenger flow patterns during a service disruption in a metro network of a multimodal transportation network in accordance with aspects of the present disclosure. The traffic manager 805 can be an example of aspects of the computing manager 615 (in Figure 6 ) or the computing manager 715 (in Figure 7 ) described herein. The traffic manager 805 can include a first providing component 810-1, a second providing component 810-2, a third providing component 810-3, a fourth providing component 810-4, a fifth providing component 810-5, and a simulation component 820. Each of these components can be in direct or indirect communication with one another (e.g., via one or more buses) 825.

[0131] The first providing component 810-1 can provide first information associated with the metro network, including a topology of the metro network, a train service schedule in the metro network, and information about train fares.

[0132] The second providing component 810-2 can provide second information associated with alternative modes of transportation of the metro network in the multimodal transportation network, including information about fares of the alternative modes of transportation and expected travel times based on routes of the alternative modes of transportation.

[0133] The third providing component 810-3 can provide third information associated with a topology of a portion of the metro network related to the service disruption.

[0134] The fourth providing component 810-4 can provide fourth information associated with an estimated diversion origin-destination station (ODS) demand pattern for the service disruption.

[0135] The fifth providing component 810-5 can provide fifth information associated with predicted irregular route choices of passengers in the multimodal transportation network during the service disruption.

[0136] The simulation component 820 can predict, collectively based on the first information, the second information, the third information, the fourth information, and the fifth information, a passenger flow pattern associated with the service disruption by computationally simulating.

[0137] In some examples, it can be possible that the first providing component 810-1, the second providing component 810-2, the third providing component 810-3, the fourth providing component 810-4, and the fifth providing component 810-5 can be implemented as a single providing component (not shown) configured to collectively perform all the functions of the providing components 810-1, 810-2, 810-3, 810-4, 810-5.

[0138] Figure 9 is a schematic diagram of an exemplary (first) computing device 900 for performing and conducting the method 100 in accordance with aspects of the present disclosure. Figure 1 is a schematic diagram of an exemplary (first) computing device 900 for performing and conducting the method 100 in accordance with aspects of the present disclosure.

[0139] The computing device 900 can include a keypad 902, a touch screen 904, a microphone 906, a speaker 908, and an antenna 910. The computing device 900 can be operated by a user to perform a variety of different functions / tasks, such as making a telephone call, sending an SMS message, browsing the Internet, sending an email, providing satellite navigation, or similar functions.

[0140] The computing device 900 can include hardware for performing communications functions (e.g., telephony or data communications), as well as an application processor and corresponding support hardware for enabling the computing device 900 to establish other functions (e.g., messaging, Internet browsing, email functionality, or similar functions). The communications hardware can include a radio frequency (RF) processor 912 that provides RF signals to the antenna 910 for transmitting and receiving data signals. A baseband processor 914 can be provided that provides signals to and receives signals from the RF processor 912. The baseband processor 914 can also interact with a subscriber identity module (SIM) 916, as is known in the art. The communications subsystem enables the computing device 900 to communicate via a variety of different communication protocols, including 3G, 4G, 5G, New Radio (NR), GSM, WiFi, Bluetooth TM and / or CDMA. The communications subsystem of the computing device 900 is not within the scope of the present disclosure.

[0141] The keypad 902 and the touch screen 904 are controlled by the application processor 918. A power supply and audio controller 920 is provided to supply power from a battery 922 to the communications subsystem, the application processor 918, and other hardware. The power supply and audio controller 920 can also control input from the microphone 906 and audio output via the speaker 908. A global positioning system (GPS) antenna and associated receiver elements 924 can also be provided that are controlled by the application processor 918 and are capable of receiving GPS signals for use with satellite navigation functionality of the computing device 900.

[0142] Various types of memory can be provided in the computing device 900 to supplement the operation of the application processor 918. The computing device 900 may include random access memory (RAM) 926 coupled to the application processor 918, into which data and program code can be written and read. Executable code stored in RAM 926 can be executed by the application processor 918 from RAM 926. RAM 926 represents the form of volatile memory in the computing device 900.

[0143] The computing device 900 may also include a non-volatile (long-term) storage device 928 coupled to the application processor 918. The storage device 928 may be logically divided into three partitions: an operating system (OS) partition 930, a system partition 932, and a user partition 934. The storage device 928 may represent the non-volatile memory of the computing device 900.

[0144] In the example, OS partition 930 may include the firmware of computing device 900, which includes the operating system. Other computer programs, such as applications (also called apps) and similar programs, may also be stored in storage device 928. Specifically, applications considered essential to the functionality of computing device 900 (e.g., communication applications and similar programs in the case of a smartphone) are typically stored in system partition 932. Applications stored in system partition 932 are typically programmed into computing device 900 according to their default factory settings.

[0145] Applications subsequently added and installed by the user on computing device 900 can typically be stored in user partition 934.

[0146] Figure 9 The various functional components shown can alternatively be configured together as a single component. For example, storage device 928 may include NAND flash, NOR flash, hard disk, or a combination of these devices.

[0147] Figure 10 It is based on the various aspects of this disclosure that can be used for implementation and execution. Figure 1 A schematic diagram of an exemplary (second) computing device 1000 for method 100. The following description of the computing device 1000 is provided by way of example only and is not intended to be limiting.

[0148] like Figure 10As depicted, the example computing device 1000 can include a processor 1004 for executing software routines / programs. While only a single processor is shown for simplicity, the computing device 1000 can also be configured as a multi-processor system (i.e., include multiple processors). The processor 1004 is coupled to a communication infrastructure 1006 for communication with other components of the computing device 1000. The communication infrastructure 1006 can include, for example, a communication bus, cross-over switch network, or network.

[0149] The computing device 1000 further includes a main memory 1008, such as random access memory (RAM), and a secondary memory 1010. The secondary memory 1010 can include, for example, a hard disk drive 1012 and / or a removable storage drive 1014, which can include a floppy disk drive, a magnetic tape drive, an optical disk drive, or the like. The removable storage drive 1014 reads from and / or writes to a removable storage unit 1018, as is known in the art. The removable storage unit 1018 can include a floppy disk, a magnetic tape, an optical disk, a universal serial bus (USB) floppy disk, or the like, which is read by and / or written to by the removable storage drive 1014. As will be appreciated by persons skilled in the relevant art, the removable storage unit 1018 can also include a computer readable storage medium having stored therein computer executable program code instructions and / or data.

[0150] In other aspects, the secondary memory 1010 can additionally or alternatively include other similar means for allowing computer programs or other instructions to be loaded into the computing device 1000 for execution. Such means can include, for example, a removable storage unit 1022 and an associated interface 1020. Examples of the removable storage unit 1022 and the associated interface 1020 can include a USB flash drive and USB interface, a program cartridge and cartridge interface (such as that found in video game controller devices), a removable memory chip (e.g., EPROM or PROM) and associated socket, and other examples of removable storage units 1022 and interfaces 1020, which can allow software programs and / or data to be transferred between the removable storage unit 1022 and the computing device 1000.

[0151] The computing device 1000 also includes at least one communication interface 1024. The communication interface 1024 allows software and data to be transferred between computing device 1000 and external devices via a communication path 1026. In various aspects, the communication interface 1024 permits data to be transferred between the computing device 1000 and a data communication network, such as a public data or private data communication network. The communication interface 1024 can be configured to enable connection to the Internet, Intranet, Extranet, or a local area network. The communication interface 1024 can be used to exchange data with a number of other computing devices, which together can form a local area network, a wide area network, or a global network such as the Internet. Examples of communication interfaces 1024 can include a modem, a network interface (e.g., an Ethernet card), a communication port, an antenna, or the like, together with associated circuitry. The communication interface 1024 can be configured to communicate data via wired or wireless communication. Software and data transferred via the communication interface 1024 are in the form of signals, which can be electronic, electromagnetic, optical, or other signals capable of being received by the communication interface 1024. These signals are provided to the communication interface via a communication path 1026.

[0152] The computing device 1000 can also include a display interface 1002 configured to perform operations for rendering images to an associated display 1030, and an audio interface 1032 for performing operations for playing audio content via an associated speaker 1034.

[0153] As used herein, the term "computer program product" can refer, in part, to the removable storage unit 1018, the removable storage unit 1022, the hard disk installed in the hard disk drive 1012, or a carrier wave carrying software embodied in a communication signal over a communication path 1026 (e.g., a wireless link or cable) to the communication interface 1024. A computer readable storage medium is any non-transitory tangible storage medium that provides recorded instructions and / or data to a computing device 1000 for execution and / or processing. Examples of such storage media include floppy disks, USB memory, magnetic tape, CD-ROM, DVD, Blu-ray discs, hard disk drives, ROM or flash memory, solid-state drives, or any other storage medium which can be used to store and / or transport computer readable instructions and / or data. The computing device 1000 can be any general purpose TM computer, such as a laptop computer, a desktop computer, a handheld computer, a smartphone, a tablet computer, a personal digital assistant, a gaming console, or the like. The computing device 1000 can also be a special purpose computer, such as a server, a server farm, a server cluster, a server blade, a web server, a network server, an Internet server, a work station, a mini-computer, a mainframe computer, a supercomputer, a network appliance, an embedded processor, a digital signal processor, or the like. The computing device 1000 can also be a mobile device, such as a mobile phone, a smart phone, a tablet computer, a laptop computer, a handheld computer, a personal digital assistant, a gaming console, or the like. The computing device 1000 can also be a virtual machine, a virtual device, a virtual server, a virtual workstation, a virtual computer, a virtual storage device, or the like. The computing device 1000 can also be a virtual machine, a virtual device, a virtual server, a virtual workstation, a virtual computer, a virtual storage device, or the like.

[0154] Computer programs (also referred to as computer program code / instructions) are stored in primary memory 1008 and / or secondary memory 1010. Computer programs can also be received via the communication interface 1024. Such computer programs, when executed, enable the computing device 1000 to perform one or more aspects of the present disclosure as previously discussed. In various aspects of the present disclosure, the computer programs, when executed, enable the processor 1004 to perform the aspect(s) of the present disclosure. Accordingly, such computer programs can represent a (logical) controller of the computing device 1000.

[0155] The software can be stored in a computer program product and loaded into the computing device 1000 using the removable storage drive 1014, the hard drive 1012 or the interface 1020. Alternatively, the computer program product can be downloaded into the computing device 1000 over the communications path 1026. The software, when executed, along with the processor 1004, causes the computing device 1000 to perform various aspects of the present disclosure.

[0156] It should be understood that the computing device 1000 illustrated in Figure 10 is presented by way of example only. In some aspects, one or more features of the computing device 1000 can be omitted from the computing device 1000. Also, in other aspects, one or more features of the computing device 1000 can be combined or arranged in a different manner. Additionally, in some aspects, one or more features of the computing device 1000 can be divided into one or more component parts.

[0157] It should be understood that the elements illustrated in Figure 10 may be further used to provide means for performing various functions of the method 100 disclosed in Figure 1 as described in accordance with aspects of the present disclosure. Also, the term computing device 900, 1000 can include or can refer to a mobile device, a wireless device, a remote device, a handheld device, a smart phone, a tablet computer, a laptop computer, a computer server, a computer terminal, a blade server, and other examples. The computing devices 900, 1000 described herein can be capable of communicating with various types of devices, such as other computing devices 900, 1000 that can sometimes act as relays, or work cooperatively in configurations to act as computer clusters for performing high performance computing.

[0158] All of the methods described herein describe possible implementations, and that the operations and the steps can be rearranged or otherwise modified and that other implementations are possible. Further, aspects from two or more of the methods can be combined in a single method, and further aspects can be left out or combined.

[0159] Information and signals described herein can be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that can be referenced throughout the description can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0160] The various illustrative blocks and components described in connection with the disclosure herein can be implemented or performed with a general-purpose processor, a DSP, an ASIC, a CPU, a FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The general-purpose processor can be a microprocessor, but in the alternative, the processor can be any processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration).

[0161] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope of the disclosure and appended claims. For example, due to the nature of software, functions described herein can be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions can also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.

[0162] Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium can be any available medium that can be accessed by a general purpose or special purpose computer. By way of example, and not limitation, non-transitory computer-readable media can include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compact disk (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of computer-readable medium. Disk and disc, as used herein, include CD, laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above are also included within the scope of computer-readable media.

[0163] As used herein, including in the claims “or” as used in a list of items (for example, a list of items prefaced by a phrase such as “at least one of’ or “one or more of’) indicates an inclusive list such that, for example, a list of “at least one of A, B, or C” means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” can be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on.”

[0164] In the drawings, like reference numerals can be used to denote similar components throughout the several views. Further, various components of the same type can be distinguished by following the convention of placing the primary reference number followed by a dash and a secondary reference number that indicates the specific instance. For example, the secondary reference number can be 1, A or 1-A to indicate a first component of a first type, a second component of a first type, or a first component of a first type, respectively. If only the primary reference number is used, then the description is applicable to any of the components of the same type.

[0165] The description set forth herein, in connection with the appended drawings, describes example configurations and does not represent all the examples that can be implemented or that are within the scope of the claims. The term “example” is used herein to mean “serving as an example, instance, or illustration,” and not “preferred” or “advantageous over other examples.” The detailed description includes specific details for the purpose of providing an understanding of the described techniques. These techniques, however, can be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described examples.

[0166] The description herein is presented to enable a person of ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.

[0167] Examples

[0168] In accordance with aspects of the disclosure, the following examples are disclosed.

[0169] Example 1 : A computer-implemented method for predicting passenger flow patterns during a service disruption in a metro network of a multimodal transportation network, the method comprising: providing first information associated with the metro network, the first information comprising a topology of the metro network, a train service schedule in the metro network, and information about train fares for the metro network; providing second information associated with alternative modes of transportation of the multimodal transportation network that are associated with the metro network, the second information comprising information about fares for the alternative modes of transportation, and expected travel times based on routes of the alternative modes of transportation; providing third information associated with a topology of a portion of the metro network that is relevant to a service disruption; providing fourth information associated with an estimated diversion origin-destination station (ODS) demand pattern for the service disruption; providing fifth information associated with predicted irregular route choices of passengers in the multimodal transportation network during the service disruption; and collectively predicting a passenger flow pattern associated with the service disruption by computationally simulating based on the first information, the second information, the third information, the fourth information, and the fifth information.

[0170] Example 2: The method of example 1, wherein predicting the passenger flow pattern comprises: outputting information about link flows along each metro line, and a number of waiting passengers on platforms arranged at the portion of the metro network that is relevant to the service disruption.

[0171] Example 3: The method of any one of Examples 1-2, wherein the topology of the portion of the metro network indicates at least one station affected by the service disruption.

[0172] Example 4: The method of any one of Examples 1-3, wherein providing the fourth information associated with the estimated diverted ODS demand pattern comprises: configuring a graph neural network (GNN) to capture spatial and temporal information embedded in the metro network, wherein the GNN is further configured with information about the topology of the metro network; providing the third information to the GNN; providing sixth information about a number of passenger demands for origin-destination station (ODS) pairs associated with the service disruption to the GNN; and estimating, by the GNN, passenger diversion behavior for each ODS pair based on the third information and the sixth information, the passenger diversion behavior collectively enabling generation of the estimated diverted ODS demand pattern as the fourth information.

[0173] Example 5: The method of Example 4, further comprising calibrating a number of ODS pairs associated with the service disruption to match the estimated diverted ODS demand pattern.

[0174] Example 6: The method of Example 4, wherein the information about the topology of the metro network comprises information associated with a cost of traveling between stations and on links in the metro network.

[0175] Example 7: The method of Example 4, wherein the GNN is pre-trained with a historical ODS demand pattern based on smart card data associated with travel in the metro network, and wherein in the historical ODS demand pattern, regular passengers with habitual travel patterns are identified as representative commuters to enable determination of irregular route choices of passengers during a service disruption based on the habitual travel patterns of the representative commuters.

[0176] Example 8: The method of Example 7, wherein the smart card data associated with travel in the metro network comprises data associated with travel in the metro network during service disruptions, and data associated with travel in the metro network during its non-disrupted operation.

[0177] Example 9: The method of any one of Examples 1-8, wherein the first information further comprises information about types of trains operating in the metro network and respective capacities of the trains.

[0178] Example 10: The method of any one of Examples 1-9, wherein the computationally simulating to predict the passenger flow pattern is performed by an event-based metro system simulation model.

[0179] Example 11: The method of any one of examples 1-10, wherein the event-based subway system simulation model is configured with at least the following information: a historical ODS demand pattern based on smart card data associated with travel in the subway network, wherein the smart card data includes data associated with travel in the subway network during service disruptions and data associated with travel in the subway network during its non-disrupted operation; and passenger load information for the trains during service disruptions and during non-disrupted operation of the subway network.

[0180] Example 12: A computing device for predicting passenger flow patterns during service disruptions in a subway network of a multimodal transportation network, comprising: one or more memories having executable code; and one or more processors coupled to the one or more memories and configured to execute the code to cause the computing device to: provide first information associated with the subway network, the first information including a topology of the subway network, train service schedules in the subway network, and information about train fares; provide second information associated with alternative modes of transportation in the multimodal transportation network to the subway network, the second information including information about fares of the alternative modes of transportation and expected travel times based on routes of the alternative modes of transportation; provide third information associated with a topology of a portion of the subway network related to a service disruption; provide fourth information associated with an estimated diversion origin-destination station (ODS) demand pattern for the service disruption; provide fifth information associated with predicted irregular route choices of passengers in the multimodal transportation network during service disruptions; and collectively predict a passenger flow pattern associated with the service disruption by computationally simulating based on the first information, the second information, the third information, the fourth information, and the fifth information.

[0181] Example 13: A computing device for predicting passenger flow patterns during a service disruption in a metro network of a multimodal transportation network, comprising: means for providing first information associated with the metro network, the first information comprising a topology of the metro network, a train service schedule in the metro network, and information about train fares for the metro network; means for providing second information associated with alternative modes of transportation of the metro network in the multimodal transportation network, the second information comprising information about fares for the alternative modes of transportation and expected travel times based on routes of the alternative modes of transportation; means for providing third information associated with a topology of a portion of the metro network that is related to a service disruption; means for providing fourth information associated with an estimated diversion origin-destination station (ODS) demand pattern for the service disruption; means for providing fifth information associated with a predicted irregular route choice of passengers in the multimodal transportation network during the service disruption; and means for collectively predicting a passenger flow pattern associated with the service disruption by computationally simulating based on the first information, the second information, the third information, the fourth information, and the fifth information.

[0182] Example 14: A non-transitory computer-readable medium comprising executable code that, when executed by a processor of a computing device, causes the computing device to perform the method of any one of Examples 1-11.

Claims

1. A computer-implemented method for predicting passenger flow patterns during service disruptions in a metro network of a multimodal transport network, the method comprising: Provide first information associated with the metro network, the first information including the topology of the metro network, train service timetables in the metro network, and information about train fares; Provide second information associated with alternative modes of transport in the metro network within the multimodal transport network, the second information including fare information for the alternative modes of transport and expected travel time for routes based on the alternative modes of transport; Provide third information associated with the topology of the portion of the metro network related to service disruptions; Provide fourth information associated with the estimated diversion origin-destination ODS demand pattern for the service disruption; Provide fifth information related to the predicted irregular route choices of passengers in the multimodal transport network during service disruptions; as well as Collectively, based on the first, second, third, fourth, and fifth information, passenger flow patterns associated with the service disruption are predicted through computational simulation.

2. The method of claim 1, wherein predicting the passenger flow pattern comprises: Output information about link traffic along each metro line, as well as the number of waiting passengers on platforms located at the sections of the metro network associated with the service disruption.

3. The method of claim 1, wherein the topology of the portion of the metro network indicates at least one station affected by the service disruption.

4. The method of claim 1, wherein providing the fourth information associated with the estimated diversion ODS demand pattern comprises: A graph neural network (GNN) is configured to capture spatial and temporal information embedded in the metro network, wherein the GNN is also configured with information about the topology of the metro network; Provide the third information to the GNN; The GNN is provided with sixth information regarding the number of passengers in demand for origin-destination ODS pairs associated with the service disruption; as well as The GNN estimates passenger diversion behavior for each ODS pair based on the third and sixth information, and the passenger diversion behavior collectively enables the generation of the estimated diversion ODS demand pattern as the fourth information.

5. The method according to claim 4, further comprising: The number of ODS pairs associated with the service interruption is calibrated to match the estimated offload ODS demand pattern.

6. The method of claim 4, wherein the information regarding the topology of the metro network includes information associated with the cost of travel between stations and on links within the metro network.

7. The method of claim 4, wherein the GNN is pre-trained using historical ODS demand patterns based on smart card data associated with travel in the metro network, and In the historical ODS demand pattern, regular passengers with habitual travel patterns are identified as representative trackers, so that irregular route choices of passengers during service interruptions can be determined based on the habitual travel patterns of the representative trackers.

8. The method of claim 7, wherein the smart card data associated with travel in the metro network includes data associated with travel in the metro network during service interruptions and data associated with travel in the metro network during uninterrupted operation.

9. The method of claim 1, wherein the first information further includes information about the type of trains operating in the metro network and the corresponding capacity of the trains.

10. The method of claim 1, wherein the computational simulation to predict the passenger flow pattern is performed using an event-based metro system simulation model.

11. The method of claim 10, wherein the event-based metro system simulation model is configured with at least the following information: Historical ODS demand patterns, based on smart card data associated with travel within the metro network, wherein the smart card data includes data associated with travel within the metro network during service disruptions and data associated with travel within the metro network during uninterrupted operation; and Passenger load information of the trains during service interruptions and during uninterrupted operation of the metro network.

12. A computing device for predicting passenger flow patterns during service interruptions in a metro network of a multimodal transport network, comprising: One or more memories, the one or more memories having executable code; as well as One or more processors, coupled to the one or more memories, and configured to execute the code to enable the computing device to: Provide first information associated with the metro network, the first information including the topology of the metro network, train service timetables in the metro network, and information about train fares; Provide second information associated with alternative modes of transport in the metro network within the multimodal transport network, the second information including fare information for the alternative modes of transport and expected travel time for routes based on the alternative modes of transport; Provide third information associated with the topology of the portion of the metro network related to service disruptions; Provide fourth information associated with the estimated diversion origin-destination ODS demand pattern for the service disruption; Provide fifth information related to the predicted irregular route choices of passengers in the multimodal transport network during service disruptions; and Collectively, based on the first, second, third, fourth, and fifth information, passenger flow patterns associated with the service disruption are predicted through computational simulation.

13. A non-transitory computer-readable medium comprising executable code that, when executed by a processor of a computing device, causes the computing device to perform the method of claim 1.

Images