AU2019261732A1 - Computer-implemented system for influencing commuter behaviour - Google Patents

Abstract

Abstract: Described herein are systems, frameworks, methodologies, devices and components configured for influencing crowd behaviour at a facility. For example, one embodiment includes a hardware/software framework that is configured to monitor data from input devices thereby to gain awareness of human congestion in areas of a facility, and enable the performance of corrective actions. For instance, a rules engine is operated based on data from those input devices thereby to enable control of one or more crowd influencing devices. In some embodiments the rules engine uses model data thereby to define and implement an optimised crown movement plan.

Description

COMPUTER-IMPLEMENTED SYSTEM FOR INFLUENCING COMMUTER BEHAVIOUR

FIELD OF THE INVENTION [0001] The invention relates to computer-implemented frameworks, methodologies and systems for influencing commuter behaviour, and in particular for influencing the position, movement or distribution of passengers to improve the utilisation of public transport conveyances and related infrastructure prone to congestion or undesirable patterns of ingress, egress or loitering.

[0002] Embodiments of the invention have been developed primarily for use in connection with passenger trains and will be described predominantly in this context. It should be appreciated, however, that the invention is not limited to this particular field of use, being also adaptable to a variety of other public transport conveyances, as well as other applications and venues involving large congregations of people such as entertainment centres, shopping complexes, concert halls, sports stadiums, and the like.

BACKGROUND OF THE INVENTION [0003] The following discussion of the prior art is intended to place the invention in an appropriate technical context and to allow the potential benefits of it to be more fully understood. However, any references to prior art should not be construed as an express or implied admission that such art is widely known or is common general knowledge in the relevant field.

[0004] Mass public transportation systems, such as train networks, are inherently constructed with an objective of efficiently moving a relatively large number of commuters between different locations. However, in cases where a relatively large number of passengers wish to board or de-board a conveyance, there are inherent bottlenecks which lead to congestion and inefficiency.

[0005] For example, trains will typically have some carriages that are relatively and even excessively crowded while others are relatively under-crowded, as a cumulative result of particular platform layouts and boarding patterns at previous stations. If the passengers waiting at the next station are concentrated in areas adjacent the relatively crowded carriages when the train arrives, for example toward the middle of the platform, there is often substantial congestion and delay while the arriving passengers attempt to exit the train through the crowd of waiting passengers on the adjacent area of the platform, and those waiting passengers then subsequently board the train. The resultant backlogs, delays, crowd concentrations or platform chokepoints can have cascading effects on train timetables, as trains are required to remain on platforms for extended and often unpredictable periods of time. This ultimately compromises the

Substitute Sheet (Rule 26) RO/AU

This data, for application number 2014214533, is current as of 2019-11-05 21:00 AEST

WO 2014/121328

PCT/AU2014/000086

-22019261732 06 Nov 2019 efficiency and effectiveness, as well as the user experience, of the entire network. There are also considerable safety hazards. Analogous effects are also encountered at congested bus terminals, airports, shipping terminals and other transport hubs.

[0006] A partial solution, used primarily in Japan, is to employ human staff tasked with physically pushing passengers onto overcrowded trains, thereby to facilitate the closing of carriage doors and the timely departure of the train. However, it will be immediately recognised that such an approach is limited in its effectiveness and is by no means an ideal solution.

[0007] It is an object of the present invention to overcome or ameliorate one or more disadvantages of the prior art, or at least to provide a useful alternative.

SUMMARY OF THE INVENTION [0008] Accordingly, in a first aspect, the invention provides a computer implemented method for influencing commuter behaviour, the method including the steps of:

receiving input data from one or more monitoring devices configured to monitor a plurality of locations within a passenger conveyance;

processing the received input data thereby to determine passenger management data; and based on the determined passenger management data, providing an output signal thereby to control one or more passenger influencing devices at a destination of the passenger conveyance.

[0009] In one embodiment, the passenger conveyance is a train and the monitoring devices include cameras positioned to monitor carriages of a train.

[0010] In some embodiments, the output signal controls the one or more passenger influencing devices thereby to provide a visual indicator of anticipated capacity at the plurality of locations in the passenger conveyance.

[0011] In some embodiments the conveyance data is indicative of a capacity value for each of the plurality of locations, such as carriages on the train, and the output signal controls the one or more passenger influencing devices thereby to direct waiting passengers at subsequent stations to boarding points for one or more of the plurality of locations having relatively lower capacity values. In this way, passengers waiting on a station platform can congregate in specific areas immediately adjacent the least crowded carriages in the train shortly to arrive at that

WO 2014/121328

PCT/AU2014/000086

-32019261732 06 Nov 2019 platform, thereby facilitating both the exiting of passengers from the train at that station, and the boarding of waiting passengers onto the train.

[0012] In some embodiments the passenger influencing devices include visual output devices located at predefined boarding positions at the destination of the passenger conveyance, each boarding position being associated with one of the plurality of locations within the passenger conveyance.

[0013] In some embodiments the method includes receiving additional input data from one or more additional sources, wherein the determination of passenger management data is also influenced by the additional input data.

[0014] In some embodiments the additional input data includes one or more of: ticket sales data; ticket turnstile data; historical passenger movement data; congestion data at a destination of the passenger conveyance; congestion data at one or more further destinations of the passenger conveyance; and layout data for one or more destinations of the passenger conveyance.

[0015] In some embodiments the method includes the step of, based on the passenger management data, providing a further output signal thereby to control one or more further passenger influencing devices located on the passenger conveyance. This enables passengers within a train, for example, to move to less crowded carriages within the train (which may not otherwise be readily identifiable), or to carriages that will be positioned adjacent less congested areas of the platform on arrival at the particular destinations.

[0016] In some embodiments, a given one of the locations has a first boarding passageway and a second boarding passageway, the output signal is configured to influence passengers at the destination to move toward the first boarding passageway for boarding, and the further output signal is configured to influence passengers on the conveyance to move toward a position that will generally correspond, on arrival, to the second boarding passageway for de-boarding.

[0017] In one embodiment, the method includes the step of operating a rules engine in order to define the output signal(s) configured to control one or more of the passenger influencing devices at a destination of the passenger conveyance.

[0018] In one embodiment, the method further includes the steps of: maintaining access to a repository of facility infrastructure data, including data indicative of areas in a facility (such as a

WO 2014/121328

PCT/AU2014/000086

-42019261732 06 Nov 2019 train platform or station corresponding to a specified destination), and relationships between those areas; and operating the rules engine so as to be influenced by the facility infrastructure data.

[0019] In some embodiments, one or more of the passenger influencing devices include visual outputs, and the output signals control the visual outputs thereby to encourage passenger movement from one area to another. In some embodiments, the visual outputs include lights, signs or display screens.

[0020] In some embodiments, the method includes the step of maintaining a repository of historical and/or predictive conveyance congestion data, thereby to enable predictions of passenger distribution for passenger conveyances which do not carry monitoring devices. For example, in one embodiment visual outputs at a given passenger conveyance destination (for example a train platform) are controlled based on instructions derived from analysis of historical data, as opposed to direct observational data from monitoring devices aboard an incoming passenger conveyance. It will be appreciated that this enables effective implementation of technologies discussed herein across, for example, a train network, without necessarily requiring the installation of monitoring devices aboard all trains. In some embodiments, this predictive modelling includes applying an adaptive learning algorithm, adapted to progressively or periodically update the historical passenger concentration data and/or operator constraints or objectives in a memory module, based on the subsequent acquisition of more current passenger information. In some embodiments, the algorithm includes combinations of elements that are progressively adaptive over time, situationally responsive in real time, and/or that incorporate algorithmic implementations of expert knowledge or experience that may be manually updated from time to time. The rules engine in some embodiments may also incorporate probabilistic or stochastic algorithms, rules or subroutines.

[0021] In some embodiments, the monitoring devices configured to provide current crowd information include cameras and associated software adapted for people recognition. In one embodiment, RGB-D cameras adapted to transmit image and associated field depth data are used. Bayesian recognition techniques, including adaptive techniques may be utilised in conjunction with such systems.

[0022] One embodiment provides a computer implemented method for influencing commuter behaviour in relation to boarding and/or de-boarding a passenger conveyance, the method including:

WO 2014/121328

PCT/AU2014/000086

-52019261732 06 Nov 2019 [0023] receiving input data from one or more monitoring devices configured to monitor a plurality of locations within the passenger conveyance thereby to determine passenger density within those locations;

[0024] processing the input data thereby to determine one or more optimal boarding locations for the passenger conveyance based on passenger density at the locations within the passenger conveyance;

[0025] providing output signals that are configured to control one or more passenger influencing devices at a destination of the passenger conveyance thereby to influence commuters at the destination of the passenger conveyance towards the optimal boarding locations.

[0026] One embodiment provides a computer implemented method including:

[0027] processing the input data thereby to determine one or more optimal de-boarding locations for the passenger conveyance;

[0028] providing output signals that are configured to control one or more passenger influencing devices positioned aboard the passenger conveyance thereby to influence passengers to use the optimal de-boarding locations;

[0029] such that passengers are encouraged to use optimised boarding locations for boarding, and optimised de-boarding locations for de-boarding, thereby to reduce combined boarding and de-boarding at one or more locations.

[0030] One embodiment provides a computer implemented method receiving input data from one or more monitoring devices configured to monitor a plurality of locations at the destination of the passenger conveyance thereby to determine passenger density at those locations, and based on that data determining the optimal de-boarding locations.

[0031] One embodiment provides a computer implemented method for influencing commuter behaviour, the method including the steps of:

[0032] receiving input data from one or more monitoring devices configured to monitor a plurality of locations within a passenger conveyance;

WO 2014/121328

PCT/AU2014/000086

-62019261732 06 Nov 2019 [0033] processing the received input data thereby to determine passenger management data; and [0034] based on the determined passenger management data, providing an output signal thereby to control one or more passenger influencing devices at a destination of the passenger conveyance.

[0035] One embodiment provides a computer implemented method wherein the output signal controls the one or more passenger influencing devices thereby to provide a visual indicator of anticipated capacity at the plurality of locations in the passenger conveyance.

[0036] One embodiment provides a computer implemented method wherein the conveyance data is indicative of a capacity value for each of the plurality of locations, and wherein the output signal controls the one or more passenger influencing devices thereby to direct passengers to boarding points for one or more of the plurality of locations having relatively lower capacity values.

[0037] One embodiment provides a computer implemented method wherein the passenger influencing devices include visual output devices located at predefined boarding positions at the destination of the passenger conveyance, each boarding position being associated with one of the plurality of locations within the passenger conveyance.

[0038] One embodiment provides a computer implemented method including additional receiving input data from one or more additional sources, wherein the determination of passenger management data is influenced by the additional input data.

[0039] One embodiment provides a method wherein the additional input data includes one or more of: ticket sales data; historical passenger movement data; congestion data at the destination of the passenger conveyance; congestion data at a further destination of the passenger conveyance; and layout data for the destination of the passenger conveyance.

[0040] One embodiment provides a computer implemented method including a step of, based on the passenger management data, providing a further output signal thereby to control one or more further passenger influencing devices located on the passenger conveyance.

[0041] One embodiment provides a computer implemented method wherein a given one of the locations has a first boarding passageway and a second boarding passageway, and wherein

WO 2014/121328

PCT/AU2014/000086

-72019261732 06 Nov 2019 the output signal is configured to influence passengers at the destination to the first boarding passageway for boarding, and wherein the further output signal is configured to influence passengers at the location to the second boarding passageway for de-boarding.

[0042] One embodiment provides a computer implemented method for influencing commuter behaviour in relation to a passenger conveyance, the method including:

[0043] monitoring passenger density at a plurality of locations within the passenger conveyance; and [0044] controlling one or more passenger influencing devices located at a destination of the passenger conveyance, thereby to encourage boarding of the passenger conveyance proximal locations of relatively lower passenger density.

[0045] A further aspect of the invention provides a non-transitive carrier medium for carrying computer executable code that, when executed on a processor, causes the processor to perform a method as described herein.

[0046] In yet another aspect, the invention provides a system configured for performing a method as described herein.

[0047] Reference throughout this specification to “one embodiment”, “some embodiments” or “an embodiment” means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases “in one embodiment”, “in some embodiments” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment, but may do so. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner, as would be apparent to one of ordinary skill in the art from this disclosure, in one or more embodiments.

[0048] As used herein, unless otherwise specified the use of the ordinal adjectives first, second, third, etc., to describe a common object, merely indicate that different instances of like objects are being referred to, and are not intended to imply that the objects so described must be in a given sequence, either temporally, spatially, in ranking, or in any other manner.

[0049] In the claims below and the description herein, any one of the terms comprising, comprised of or which comprises is an open term that means including at least the

WO 2014/121328

PCT/AU2014/000086

-8 2019261732 06 Nov 2019 elements/features that follow, but not excluding others. Thus, the term comprising, when used in the claims, should not be interpreted as being limitative to the means or elements or steps listed thereafter. For example, the scope of the expression a device comprising A and B should not be limited to devices consisting only of elements A and B. Any one of the terms including or which includes or that includes as used herein is also an open term that also means including at least the elements/features that follow the term, but not excluding others. Thus, including is synonymous with and means comprising.

[0050] As used herein, the term “exemplary” is used in the sense of providing examples, as opposed to indicating quality. That is, an “exemplary embodiment” is an embodiment provided as an example, as opposed to necessarily being an embodiment of exemplary quality.

[0051] The terms preferred, preferably and the like in relation to various embodiments of the invention do not necessarily imply any particular hierarchy of preference in relation to other embodiments, and in particular do not imply that other embodiments are in any way less preferred, or less viable.

BRIEF DESCRIPTION OF THE DRAWINGS [0052] Preferred embodiments of the invention will now be described, by way of example only, with reference to the accompanying drawings in which:

[0053] FIG. 1 schematically illustrates a framework according to one embodiment of the invention;

[0054]

FIG. 2 illustrates a method according to one embodiment of the invention;

[0055] FIG. 3 illustrates a facility in the form of a train station incorporating a framework, method and system according to one embodiment of the invention;

[0056] FIGS. 4A to 4C schematically illustrate a train approaching a station platform, incorporating a framework, method and system according to one embodiment of the invention; and [0057] FIG. 4 illustrates an exemplary user interface according to one embodiment..

WO 2014/121328

PCT/AU2014/000086

-92019261732 06 Nov 2019

DETAILED DESCRIPTION [0058] Described herein are computer implemented frameworks, systems and methodologies for influencing commuter behaviour. In broad overview, an exemplary computer implemented method for influencing commuter behaviour includes the step of receiving input data from one or more monitoring devices configured to monitor a plurality of locations within a passenger conveyance, such as cameras positioned to monitor carriages of a train. The received input data is processed thereby to determine passenger management data. Based on the determined passenger management data, the method includes the further step of providing an output signal to control one or more passenger influencing devices at a destination of the passenger conveyance.

[0059] More specifically, and with reference to the drawings, FIG. 1 illustrates an exemplary framework including hardware/software components configured to provide functionality for various embodiments of the invention. It should be noted that, although FIG. 1 illustrates a number of exemplary components, modules and functionalities, it is by no means necessary that all functionalities be present in a given embodiment. Rather, for the sake of efficient explanation, a number of optional features and functionalities are grouped together into the embodiment shown.

[0060] FIG. 1 illustrates a passenger management system 100, which may be controlled by a single computer system, or a collection of networked computing components. In its simplest form, system 100 is defined by a device having hardware components 151 including a processor 152, a memory module 153, and network modules 154. Memory module 153 contains computer executable code (also referred to as software instructions) that are executable on processor 152 thereby to provide various functionalities and implement various methods, including functionalities and methods described herein.

[0061] In the context of FIG. 1, memory module 152 provides software instructions for a plurality of software “modules” 155 which in essence define logically identifiable functionalities provided by system 100. It is by no means necessary that the software instructions are coded in such a manner as to provide physically distinct modules; rather the modules are functionally defined thereby to enable efficient description of the various functionalities of system 100.

[0062] One or more input processing modules 156 are configured to receive and process input data from a number of sources. For example, this data may be communicated over a wired or wireless network and received by network modules 154, and then processed by modules 156. In broad terms, the input processing modules are configured to receive data from

WO 2014/121328

PCT/AU2014/000086

-102019261732 06 Nov 2019 a range of sources that provide information including data relevant to understanding of current and expected crowd locations and/or crowd dynamics. In the example of FIG. 1, the sources include:

• Devices configured to monitor train carriages 104. These may include the likes of video devices (for example still or video cameras such as RGBD cameras, surveillance systems, and associated hardware), sensors 122 (for example congestion sensors, pressure sensors, heat sensors, and so on).

• Other input devices, which may include devices configured to monitor congestion at a train platform, systems that collect ticketing data, predictive model data sources (for example models which predict likely passenger movements based on historical data), data from ticketing turnstiles, input data based on observations, knowledge and experience of skilled operators, and so on.

[0063] In essence, system 100 is configurable to receive and utilise data from substantially any source; a rules-based approach is preferably implemented such that substantially any form of knowledge, historical data and/or situational awareness data may be incorporated into downstream processing. Additional input data includes one or more of: ticket sales data; historical passenger movement data; congestion data at the destination of the passenger conveyance; congestion data at a further destination of the passenger conveyance; and layout data for one or more destinations of the passenger conveyance, such as train stations or related facilities or infrastructure. In this regard, System 100 maintains communication with a plurality of input devices. The expression “maintaining communication” means that server 100 is configured to receive data from these devices. It is by no means necessary that communication is maintained on a continuous basis; communication may be maintained in such a manner as to either receive periodic data from given monitoring devices (i.e. periodic push data), and/or periodically request or obtain data from such devices (i.e. periodically pull data). Furthermore, the may be via one or more intermediary devices. In this regard, the term “maintaining communication” requires only that system 100 is able to receive, by whatever technical means, data that is defined subject to the operation of one or more of devices 120.

[0064] System 100 includes user interface modules (Ul modules) 157, which enable a user of an exemplary client terminal (not shown) to access functionalities of system 100, for example by way of a web browser arrangement or via a proprietary software arrangement (in which case the substantive software instructions are maintained at terminal 130). Functionalities available to

WO 2014/121328

PCT/AU2014/000086

-11 2019261732 06 Nov 2019 a user of terminal may include modification of configurational aspects, review of analytical data, and manual intervention. An exemplary user interface display is provided in FIG. 5.

[0065] System 100 maintains access to a repository of rule data that defines a plurality of executable rules. For example, this may include rules stored in memory local to system 100, or rules stored in memory of computing components remote of system 100 by in respect of which system 100 maintains access (being either continuous or periodic access. A rules engine 162 operates thereby to perform actions responsive to data received from monitoring devices 120 (and in some embodiments from additional sources of data). Each rule in the repository of rule data is associated with rule conditions, and additionally associated with an action that is to be performed when the rule conditions are satisfied.

[0066] For at least a subset of the rules, the rule conditions include conditions that are able to be satisfied by data in database 115 (for example based on a central data set representing location and movement of persons within multiple regions of the facility). That is, rule conditions may include a threshold number or density of people in a certain region, a certain number or density of people moving towards a certain region, and so on. Various other inputs for rule conditions may also be used, including data relating to facility conditions, such as closure of passageways, approaching trains, and so on. It will be appreciated that the use of a rules engine enabled a flexible and adaptable framework allowing rules to be defined based on a range of conditions, including (but not solely limited to ) location and movement of persons within multiple regions of a given facility.

[0067] For at least a subset of the rules, the action includes, providing output signals that are configured to control one or more crowd influencing devices positioned at locations within the facility. This is discussed in more detail below, however in general terms the rules in this manner enable crowd influencing devices to be automatically controlled based on data including (but not limited to) sensed location and movement of persons within multiple regions of a given facility. Other actions may include providing alerts within system 100, providing input data to another software/hardware component, and so on.

[0068] Rules engine 112 operates thereby to determine whether one or more predetermined conditions are met for a given rule (or in a functionally similar manner defined for an alternate form of rules engine). That is, in the case that one or more of the predefined rule conditions are satisfied for a given rule, the rules engine operates thereby to define output signals in accordance with the action (for example output signals configured to control one or more crowd influencing devices 140). In overview, the passenger influencing devices may take a range of

WO 2014/121328

PCT/AU2014/000086

-12 2019261732 06 Nov 2019 forms, but generally include devices capable of influencing persons in a facility, either by explicit instruction or implicit coercion. For example, passenger influencing devices may include:

• Lighting systems. For example, these may be used to control the operation of one or more lights 107 in a facility (for example on a train station platform). These lights may be used to indicate suggested boarding areas, based on locations of relative congestion within an oncoming train. In one embodiment, a system of colour-coded lights is used, for example green lights to indicate boarding points for carriages of relative undercrowding, orange lights to indicate boarding points for carriages of relatively moderate crowding, and red lights to indicate boarding points for carriages of relative overcrowding. In some embodiments lighting systems are incorporated into bollard devices, each bollard device including multiple lights (for example LEDs) and a communications module configured to receive control signals directly or indirectly from system 100.

• Information display devices, including controllable signs, screens, and so on. By way of example, these may be used to provide messages and/or explicit instructions in relation to particular boarding areas for particular carriages, entrances, exits, pathways or areas that are relatively congested or relatively uncrowded, as the case may be.

• Other influencing devices 144, which may ultimately be less obvious or more surreptitious such as:• Audible signals designed to be either relatively more attractive or repulsive, such as a relatively pleasant bell chime or a relatively unpleasant buzzer.

• Air-conditioning outlets controlled, for example, to create areas of relative comfort and discomfort based on localised differential temperatures.

• Door control mechanisms adapted to make particular access options appear more or less desirable. For example, opening one set of train doors noticeably later than another set of doors encourages people to head towards what is perceived to be the quicker or more certain alternative.

• Display screen or monitor control mechanisms adapted to regulate content displayed to passengers in different areas. For example, display screens in areas likely to become congested may be deactivated, or switched to less desirable entertainment program

WO 2014/121328

PCT/AU2014/000086

-13 2019261732 06 Nov 2019 content, while at the same time display screens in areas less likely to become congested may be activated or switched to relatively more desirable program content.

[0069] In overview, referring again to rules engine 162, in some embodiments rules are configured using logical operators, for example based on IF, THEN and ELSE criteria. For example, a simple rule might be IF a congestion data value from “Video Device A” is greater than “Value B” THEN provide instruction to “Lighting System C” to perform “Action D”. It will be appreciated that a wide range of rules, ranging from simple to complex (for example incorporating operators such as AND and OR), may be defined in the context of configuring system 100. In some embodiments client terminal 130 is enabled to view, modify and/or create rules for rules engine 162.

[0070] FIG. 2 illustrates a method 215 performed by system 100 according to one embodiment. Functional block 211 represents a process including commencing a monitoring process based on a rule. For example, in some embodiments upon creation (or implementation) of a rule, a process is generated thereby to monitor predefined conditions associated with that rule (in some cases including an individual process for each condition or sub-condition). For example, a process may monitor input data from a given camera such as an RGBD video camera (or analytics stream associated with that camera) thereby to determine congestion characteristics of a carriage in an oncoming train. In some cases the video camera (or an associated component) is configured to transmit such data to system 100 based on a defined schedule. In other cases system 100 is configured to perform a query process.

[0071] Functional block 212 represents a process including the monitoring of a predetermined event, which satisfies predefined conditions for a given rule (noting that in some cases a rule may rely on multiple predefined conditions being met, based on the underlying rule logic). In the case that predefined conditions for a rule are satisfied, an action is performed based on that rule at 213 (noting that “performing an action” might include an active decision to take no action). Functional block 214 represents a process including instructing one or more passenger influencing devices based on performance of the rule.

[0072] Several examples of the operation of system 100 in the context of commuter or passenger management are provided below. It will be appreciated that these may be implemented in isolation, or in various combinations and permutations.

[0073] Example 1: The output signal controls one or more passenger influencing devices thereby to provide a visual indicator of anticipated capacity at each of the plurality of locations in

WO 2014/121328

PCT/AU2014/000086

-142019261732 06 Nov 2019 the passenger conveyance. For example, the conveyance data is indicative of a capacity value for each of the plurality of locations (for example carriages), and the output signals control the lighting units thereby to direct passengers waiting at a nearby station to boarding points for one or more of the plurality of carriages having relatively lower capacity values. Preferably the passenger influencing devices include visual output devices (such as lights) located at predefined boarding positions at the destination of the passenger conveyance each boarding position being associated with one of the plurality of carriages within the passenger conveyance (for example at points where carriage doors are known to be located upon arrival of a train).

[0074] Example 2: Output signals are used to control one or more passenger influencing devices located on the passenger conveyance. For example, a reverse approach to Example 1 may be adopted, thereby to inform passengers on a train as to exit locations on the train that will correspond to platform positions with relatively less congestion (thereby to permit more streamlined de-boarding).

[0075] Example 3: This applies where a given one of the carriages has a first boarding passageway and a second boarding passageway. A first output signal is configured to influence passengers at the destination platform to wait for the train at a location for the first boarding passageway, and a second output signal is configured to influence passengers in the carriage to move towards the second boarding passageway for de-boarding. In this manner, a train carriage is conveniently able to be boarded through one door, and simultaneously de-boarded through the other door, thereby avoiding inefficiency as a result of opposing passenger flows effectively colliding, or the need for boarding and de-boarding to occur in an orderly but sequential manner.

[0076] FIG. 3 illustrates diagrammatically one particular implementation of a preferred embodiment, in the context of a railway station 300, incorporating a ticket turnstile 301 and multiple station platforms 302 with respective entrances and exits 303. The platforms incorporate monitoring devices in the form of cameras (not shown) such as RGBD video cameras with associated human recognition software adapted to generate input data indicative of relative crowd density at different parts of the platform, and at different platforms in the station, in real time.

[0077] Platform areas A, B, C, D, E and F incorporate passenger influencing devices in the form of embedded floor lighting modules 304, adapted to change colour in response to output signals from system 100 (for example the lighting modules are controlled by a lighting system 141). In some cases, lighting modules 304 are configured to display directional arrows, runway

WO 2014/121328

PCT/AU2014/000086

-15 2019261732 06 Nov 2019 lights or the like to indicate the direction the crowd should move. For example, these assist in splitting a crowd between the stairs adjacent areas A/D and areas B/F, based on capacity of an oncoming train.

[0078] In other embodiments, the lighting modules may simply illuminate different colours in different locations, for example red to indicate relatively high passenger density for an approaching carriage, orange to indicate relatively moderate passenger density, and green to indicate relatively low passenger density. It should be appreciated that the physical layout of the system is condensed in the diagrammatic representation of figure 3, for illustrative purposes.

[0079] FIG. 4A to FIG. 4C provides a more detailed schematic view of a train 400 and a railway platform 450, illustrating various components and that operate in conjunction with system 100 thereby to enable commuter management.

[0080] Train 400 has four carriages, labelled 401a to 401 d. Corresponding features are denoted by corresponding numerical labels, with the letters “a” to “d” suffixed thereby to identify a carriage to which they relate.

[0081] Referring to carriage 401a, a camera device 402a is mounted so as to monitor congestion in the carriage. This may be a conventional video camera, or a camera specially adapted to assist in congestion monitoring. Pressure sensors or the like may be used to provide supplementary data, or as an alternative. Camera device 402a is configured to communicate with system 100. This may be via a carriage specific data transmitter, a data transmitter that operates across cameras of multiple carriages, and/or various intermediary servers. Regardless of the approach used, system 100 is able to determine carriage-specific passenger congestion data.

[0082] Carriage 401a includes a front door 403a and associated visual output device 404a, and a rear door 405a and associated visual output device 406a. Output devices 404a and 406a may be, for example, lights or signs, and are preferably configured to be remotely controlled by system 100 (for example to influence passengers to de-board through one door in preference to the other).

[0083] Platform 450 includes, in relation to carriage 401a, a first boarding zone 407a and associated visual output device 408a, and a second boarding zone 409a and associated visual output device 410a. As shown in FIG. 4A, boarding zone 407a is for boarding/de-boarding via door 403a, and boarding zone 409a is for boarding/de-boarding via door 405a. Visual output

WO 2014/121328

PCT/AU2014/000086

-16 2019261732 06 Nov 2019 devices 408a and 410a are preferably operated to encourage/discourage boarding via zone

407a (door 403a) and zone 409a (door 405a) respectively. For example, this may include either or both of the following:

• Indications as to congestion, based on processing of data received from either camera 402a, or from a combination of cameras 402a to 402d (it will be appreciated that the combination approach allows assessment of relative carriage congestion, as opposed to absolute carriage congestion.

• Indications as to which of the zones/doors is reserved for boarding, and which is reserved for de-boarding. In the case of the latter, a determination is preferably made based on the locations of stairways 411 and 412. That is, it is preferable to have passengers boarding via door 403a and de-boarding via door 405a, so as to minimise cross-flow of passengers on the platform between carriage 402a and stairs 411.

[0084] In some embodiments, not all trains in a train network are fitted with monitoring devices. In such cases, predictive modelling may be used to control display devices at platforms so as to direct passengers to carriages anticipated to be relatively uncrowded. This is optionally based upon historically collected data. In that regard, in some embodiments, a data processing method includes the step of maintaining a repository of historical conveyance congestion data, thereby to enable predictive modelling of passenger distribution for passenger conveyances which do not carry monitoring devices.

[0085] In some embodiments, this predictive modelling includes applying an adaptive learning algorithm, adapted to progressively or periodically update the historical passenger concentration data and/or operator constraints or objectives in a memory module, based on the subsequent acquisition of more current passenger information. In some embodiments, the algorithm includes combinations of elements that are progressively adaptive over time, situationally responsive in real time, and/or that incorporate algorithmic implementations of expert knowledge or experience that may be manually updated from time to time. The rules engine in some embodiments may also incorporate probabilistic or stochastic algorithms, rules or subroutines.

[0086] As briefly noted further above cameras are able to be applied to track movement using known technologies, and this may be used to provide a data-driven representation of the location and movement of individuals within a region observed by one or more cameras, and this

WO 2014/121328

PCT/AU2014/000086

-17 2019261732 06 Nov 2019 is optionally used to generate a real time facility crowd map. FIG. 5 illustrates an application of such technology, by way of an exemplary user interface screenshot.

[0087] User interface 500 is rendered at a client terminal, for example within a window of a web browser application. An interface object 505 provides a graphical representation of a region in a facility (for example by way of a floor plan). This is preferably able to be navigated, for example using pan/zoom controls (and/or other navigation controls 530) thereby to change the viewed region. Object 505 is populated using real time data derived from sensing equipment thereby to display positions and movement of sensed persons. In this case, each sensed person is represented by a dot 520. It will be appreciated that the display might lag behind precise “real time” based on network delays and the like. Object 505 also displays crowd influencing devices 510, along with data indicative of their current states (for example, colour may be used to reflect the state of a derive in the context of a light it is currently displaying).

[0088] Objects 530 provide an indicative selection of Ul objects that may be provided by way of such a user interface. These include:

• Navigation controls 531, which enable a user to exercise control over which region of a facility is to be viewed.

• Incoming train information, which provides information concerning train arrivals, passenger densities, predicted de-board rates, and so on.

• Alert modules 533, which provide to the user information regarding observed problematic congestion, failures in equipment, and the like.

• Control modules 534, which assist a user in manually controlling hardware, including crowd influencing devices and other devices (such as doors, escalators, turnstiles, and so on). These controls may also allow operator influence over rules that are being applied to automate control.

[0089] It will be appreciated that a user interface such as interface 500 is useful in the context of providing operator awareness over human congestion in a facility, and in allowing manual override of automated crowd influencing functions.

[0090] Provided below is description of an exemplary algorithm that is used in some embodiments thereby to implement an optimised crown movement plan (via a rules driven

WO 2014/121328

PCT/AU2014/000086

-18 2019261732 06 Nov 2019 approach). This explanation serves to provide a high level overview and explanation in order to provide a conceptual and functional understanding. In this example, a 'cost/value function' optimisation type algorithm is used, with provisions for uncertainty. The example is specifically relevant to a train station.

[0091] For this example, the following input values (which are preferably available in database 115) are initially used:

I. Immediate area ACTUAL occupancy: The actual sensed occupancy of an area, such as a platform.

//. Local ACTUAL occupancy: The actual sensed occupancy of a local area, such as a boarding area on a platform.

III. From-incoming-trains EXPECTED occupancy: a calculated expected occupancy based on expected egress from a train at a given platform area. This may be derived from sensing equipment on trains.

IV. From-arriving-through-gates&thoroughfairs PREDICTED occupancy: a predicted occupancy based on data collected from gates and thoroughfares approaching an area.

V. From-arriving-based-on-historical-data-collected-by-the-system PREDICTED expected:

This makes use of historical data to weigh in on predictions.

VI. Operators-current-OVERRIDE-objective'. this allows an operator manual override to influence the algorithm,.

[0092] These input items are used to define an influencing actuation using weighting values w1 to w6\

Inf = w1 immediate area ACTUAL occupancy + w2*Local ACTUAL occupancy + w3*From-incoming-trains EXPECTED occupancy + w5*From-arriving-throughgates&thoroughfairs PREDICTED occupancy + w5*From-arriving-based-on-historicaldata-collected-by-the-system PREDICTED expected + w6*operators-currentO VERRIDE-objective [0093] This may be conceptualised as a the supervisory control layer.

WO 2014/121328

PCT/AU2014/000086

-19 2019261732 06 Nov 2019 [0094] There are three categories/types of inputs for the various items in the cost function:

• Actual real time sensed data (I to III) from sensing components.

• Predicted data (IV and V); predictions are made based on looking at current behaviours and situations against past observations to predict (estimate) outcomes with reasonable accuracy, e.g. people walking in that particular direction that do a big turn around that particular column tend to go to platform 5 (IV) and based on past data about 70% of people arriving between 2-3pm go to platform 1 (V).

• Operator objectives (IV); the operator may want to override the entire system for special events or emergencies, due to unexpected changes or the like.

[0095] Each of these items/categories has several layers of underlying processing:

• Interpretation for the sensing to determine information such as the number of people, their paths, their direction of movement, their behaviours, etc • Pattern matching, data searching, expert system encoding and retrieval, etc. that form the basis upon which accurate and meaningful predictions are made.

• A cognitive layer that allow operators to express objectives in operators’ terms and translates those objective into system terms and actions.

[0096] Then, for each individual item in the overall function there is a weighting term unique for each item (w1 to w6). A weighting term is both firstly mechanism for setting the importance or impact of that particular item to the overall output. For instance, in an event the weighting of the operator objective term would be set very high to bias the output heavily towards serving that requirement; and secondly a scaling factor to compensate for 'how well' the influencing actuation works at that point. For instance, at the gates 90% of people might be influenced, but at the stairs only 60% of people are influenced, and then again on the platform 85% of people might be influenced. This weight term allows compensation for such differences.

[0097] The weightings are preferably derived from expert knowledge and/or are empirically derived. For influence, in one example the immediate area influence weighting w1 is set to 30% as expert knowledge in the fields of behaviour science, psychology and human-robot interaction suggests that this is a reasonable and conservative estimate. However, some experimental

WO 2014/121328

PCT/AU2014/000086

-202019261732 06 Nov 2019 results suggest that this weight should be set closer to 85% in certain real-world circumstances. Accordingly, weightings may require optimisation over time for any given implementation. In this way, the algorithm supports 'best guess' from the experts and allows for over arching meaningful control in that condition. However, it further supports empirical calibration meaning it is possible change the weighting factor with this new 'more accurate' value and our over arching control will be improved as a result.

[0098] In this regard, each item that influences the algorithm has its own specific algorithms to turn the data into meaningful information (i.e. perception layers), and each item has a scaling factor depending on how much influence that item actually has and how much influence it is required to have (expert knowledge, apriori, and learning layers). Additionally there is preferably an over-arching supervisory algorithm that connects and coordinates the multiple algorithms.

[0099] Various modifications may be made to the embodiments disclosed above without departing from the overall scope of the present disclosure. For example, in some embodiments system 100 is maintained on train 500, as opposed to at a central location, so that trains are in effect able to influence lighting/signage systems at upcoming platforms.

[00100] It will be appreciated that the disclosure above provides various systems and methods for influencing crowds and passenger movements, for example in the context of managing commuter behaviour, which in preferred embodiments provide practical and commercially significant improvements over the prior art.

[00101] Unless specifically stated otherwise, as apparent from the following discussions, it is appreciated that throughout the specification discussions utilizing terms such as processing, computing, calculating, “determining”, analyzing” or the like, refer to the action and/or processes of a computer or computing system, or similar electronic computing device, that manipulate and/or transform data represented as physical, such as electronic, quantities into other data similarly represented as physical quantities.

[00102] In a similar manner, the term processor may refer to any device or portion of a device that processes electronic data, e.g., from registers and/or memory to transform that electronic data into other electronic data that, e.g., may be stored in registers and/or memory. A “computer” or a “computing machine” or a computing platform may include one or more processors.

WO 2014/121328

PCT/AU2014/000086

- 21 2019261732 06 Nov 2019 [00103] The methodologies described herein are, in one embodiment, performable by one or more processors that accept computer-readable (also called machine-readable) code containing a set of instructions that when executed by one or more of the processors carry out at least one of the methods described herein. Any processor capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken are included. Thus, one example is a typical processing system that includes one or more processors. Each processor may include one or more of a CPU, a graphics processing unit, and a programmable DSP unit. The processing system further may include a memory subsystem including main RAM and/or a static RAM, and/or ROM. A bus subsystem may be included for communicating between the components. The processing system further may be a distributed processing system with processors coupled by a network. If the processing system requires a display, such a display may be included, e.g., a light emitting diode (LED) display, a liquid crystal display (LCD) or a cathode ray tube (CRT) display. If manual data entry is required, the processing system also includes an input device such as one or more of an alphanumeric input unit such as a keyboard, a pointing control device such as a mouse, and so forth.

[00104] The term memory unit as used herein, if clear from the context and unless explicitly stated otherwise, also encompasses a storage system such as a disk drive unit. The processing system in some configurations may include a sound output device, and a network interface device. The memory subsystem thus includes a computer-readable carrier medium that carries computer-readable code (e.g., software) including a set of instructions to cause performing, when executed by one or more processors, one of more of the methods described herein. Note that when the method includes several elements, e.g., several steps, no ordering of such elements is implied, unless specifically stated. The software may reside in the hard disk, or may also reside, completely or at least partially, within the RAM and/or within the processor during execution thereof by the computer system. Thus, the memory and the processor also constitute computer-readable carrier medium carrying computer-readable code. Furthermore, a computerreadable carrier medium may form, or be included in a computer program product.

[00105] In alternative embodiments, the one or more processors operate as a standalone device or may be connected, e.g., networked to other processor(s), in a networked deployment, the one or more processors may operate in the capacity of a server or a user machine in serveruser network environment, or as a peer machine in a peer-to-peer or distributed network environment. The one or more processors may form a personal computer (PC), a tablet PC, a set-top box (STB), a Personal Digital Assistant (PDA), a cellular telephone, a web appliance, a network router, switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine.

WO 2014/121328

PCT/AU2014/000086

- 22 2019261732 06 Nov 2019 [00106] Note that while diagrams only show a single processor and a single memory that carries the computer-readable code, those in the art will understand that many of the components described above are included, but not explicitly shown or described in order not to obscure the inventive aspect. For example, while only a single machine is illustrated, the term machine shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.

[00107] Thus, one embodiment of each of the methods described herein is in the form of a computer-readable carrier medium carrying a set of instructions, e.g., a computer program that is for execution on one or more processors, e.g., one or more processors that are part of web server arrangement. Thus, as will be appreciated by those skilled in the art, embodiments of the present invention may be embodied as a method, an apparatus such as a special purpose apparatus, an apparatus such as a data processing system, or a computer-readable carrier medium, e.g., a computer program product. The computer-readable carrier medium carries computer readable code including a set of instructions that when executed on one or more processors cause the processor or processors to implement a method. Accordingly, aspects of the present invention may take the form of a method, an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of carrier medium (e.g., a computer program product on a computer-readable storage medium) carrying computer-readable program code embodied in the medium.

[00108] The software may further be transmitted or received over a network via a network interface device. While the carrier medium is shown in an exemplary embodiment to be a single medium, the term carrier medium should be taken to include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) that store the one or more sets of instructions. The term carrier medium shall also be taken to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by one or more of the processors and that cause the one or more processors to perform any one or more of the methodologies of the present invention. A carrier medium may take many forms, including but not limited to, non-volatile media, volatile media, and transmission media. Nonvolatile media includes, for example, optical, magnetic disks, and magneto-optical disks. Volatile media includes dynamic memory, such as main memory. Transmission media includes coaxial cables, copper wire and fiber optics, including the wires that comprise a bus subsystem. Transmission media also may also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications. For example, the term carrier medium shall accordingly be taken to included, but not be limited to, solid-state memories, a

WO 2014/121328

PCT/AU2014/000086

- 23 2019261732 06 Nov 2019 computer product embodied in optical and magnetic media; a medium bearing a propagated signal detectable by at least one processor of one or more processors and representing a set of instructions that, when executed, implement a method; and a transmission medium in a network bearing a propagated signal detectable by at least one processor of the one or more processors and representing the set of instructions.

[00109] It will be understood that the steps of methods discussed are performed in one embodiment by an appropriate processor (or processors) of a processing (i.e., computer) system executing instructions (computer-readable code) stored in storage. It will also be understood that the invention is not limited to any particular implementation or programming technique and that the invention may be implemented using any appropriate techniques for implementing the functionality described herein. The invention is not limited to any particular programming language or operating system.

[00110] It should be appreciated that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

[00111] Furthermore, while some embodiments described herein include some but not other features included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention, and form different embodiments, as would be understood by those skilled in the art. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[00112] Furthermore, some of the embodiments are described herein as a method or combination of elements of a method that can be implemented by a processor of a computer system or by other means of carrying out the function. Thus, a processor with the necessary instructions for carrying out such a method or element of a method forms a means for carrying out the method or element of a method. Furthermore, an element described herein of an

WO 2014/121328

PCT/AU2014/000086

-242019261732 06 Nov 2019 apparatus embodiment is an example of a means for carrying out the function performed by the element for the purpose of carrying out the invention.

[00113] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

[00114] Similarly, it is to be noticed that the term coupled, when used in the claims, should not be interpreted as being limited to direct connections only. The terms coupled and connected, along with their derivatives, may be used. It should be understood that these terms are not intended as synonyms for each other. Thus, the scope of the expression a device A coupled to a device B should not be limited to devices or systems wherein an output of device A is directly connected to an input of device B. It means that there exists a path between an output of A and an input of B which may be a path including other devices or means. Coupled may mean that two or more elements are either in direct physical or electrical contact, or that two or more elements are not in direct contact with each other but yet still co-operate or interact with each other.

[00115] Thus, while there has been described what are believed to be the preferred embodiments of the invention, those skilled in the art will recognise that other and further modifications may be made thereto without departing from the spirit of the invention, and it is intended to claim all such changes and modifications as falling within the scope of the invention. For example, any formulas given above are merely representative of procedures that may be used. Functionality may be added or deleted from the block diagrams and operations may be interchanged among functional blocks. Steps may be added or deleted to methods described within the scope of the present invention.

Claims (15)

1. Claims

   1. A computer implemented method for influencing commuter behaviour in relation to boarding and/or de-boarding a passenger conveyance, the method including:

   receiving input data from one or more monitoring devices configured to monitor a plurality of locations within the passenger conveyance thereby to determine passenger density within those locations;

   processing the input data thereby to determine one or more optimal boarding locations for the passenger conveyance based on passenger density at the locations within the passenger conveyance;

   providing output signals that are configured to control one or more passenger influencing devices at a destination of the passenger conveyance thereby to influence commuters at the destination of the passenger conveyance towards the optimal boarding locations.
2. 2. A computer implemented method according to claim 1 including:

   processing the input data thereby to determine one or more optimal de-boarding locations for the passenger conveyance;

   providing output signals that are configured to control one or more passenger influencing devices positioned aboard the passenger conveyance thereby to influence passengers to use the optimal de-boarding locations;

   such that passengers are encouraged to use optimised boarding locations for boarding, and optimised de-boarding locations for de-boarding, thereby to reduce combined boarding and de-boarding at one or more locations.
3. 3. A computer implemented method according to claim 2 including receiving input data from one or more monitoring devices configured to monitor a plurality of locations at the destination of the passenger conveyance thereby to determine passenger density at those locations, and based on that data determining the optimal de-boarding locations.
4. 4. A computer implemented method for influencing commuter behaviour, the method including the steps of:

   receiving input data from one or more monitoring devices configured to monitor a plurality of locations within a passenger conveyance;

   processing the received input data thereby to determine passenger management data; and

   This data, for application number 2014214533, is current as of 2019-11-05 21:00 AEST

   WO 2014/121328

   PCT/AU2014/000086

   - 26 2019261732 06 Nov 2019 based on the determined passenger management data, providing an output signal thereby to control one or more passenger influencing devices at a destination of the passenger conveyance.
5. 5. A method according to claim 4 wherein the output signal controls the one or more passenger influencing devices thereby to provide a visual indicator of anticipated capacity at the plurality of locations in the passenger conveyance.
6. 6. A method according to claim 5 wherein the conveyance data is indicative of a capacity value for each of the plurality of locations, and wherein the output signal controls the one or more passenger influencing devices thereby to direct passengers to boarding points for one or more of the plurality of locations having relatively lower capacity values.
7. 7. A method according to any one of claims 5 to 6 wherein the passenger influencing devices include visual output devices located at predefined boarding positions at the destination of the passenger conveyance, each boarding position being associated with one of the plurality of locations within the passenger conveyance.
8. 8. A method according to any one of claims 5 to 7 including additional receiving input data from one or more additional sources, wherein the determination of passenger management data is influenced by the additional input data.
9. 9. A method according to claim 8 wherein the additional input data includes one or more of: ticket sales data; historical passenger movement data; congestion data at the destination of the passenger conveyance; congestion data at a further destination of the passenger conveyance; and layout data for the destination of the passenger conveyance.
10. 10. A method according to any one of claims 5 to 9 including a step of, based on the passenger management data, providing a further output signal thereby to control one or more further passenger influencing devices located on the passenger conveyance.
11. 11. A method according to claim 10 wherein a given one of the locations has a first boarding passageway and a second boarding passageway, and wherein the output signal is configured to influence passengers at the destination to the first boarding passageway for boarding, and wherein the further output signal is configured to influence passengers at the location to the second boarding passageway for de-boarding.

    WO 2014/121328

    PCT/AU2014/000086

    - 27 2019261732 06 Nov 2019
12. 12. A computer implemented method for influencing commuter behaviour in relation to a passenger conveyance, the method including:

    monitoring passenger density at a plurality of locations within the passenger conveyance; and controlling one or more passenger influencing devices located at a destination of the passenger conveyance, thereby to encourage boarding of the passenger conveyance proximal locations of relatively lower passenger density.
13. 13. A computer system configured to perform a method according to any one of claims 1 to 12.
14. 14. A computer program configured to perform a method according to any one of claims 1 to 12.
15. 15. A non-transitive carrier medium carrying computer executable code that, when executed on a processor, causes the processor to perform a method according to any one of claims 1 to 12.