Method and device for outputting a predicted occupancy distribution in a public means of transportation
The system addresses uneven passenger distribution in public transport by using sensor data and AI/ML to predict and display optimal seating areas, enhancing passenger comfort and reducing congestion through real-time occupancy feedback.
Patent Information
- Application Number
- PCT/EP2024/061901
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-02
- Filing Date
- 2024-04-30
- Publication Date
- 2024-11-07
AI Technical Summary
Public transportation vehicles often experience uneven passenger distribution during peak times, leading to congestion, delayed vehicles, and inconvenience for passengers, as existing systems lack efficient methods to redistribute passengers homogeneously and automatically.
A method and system that utilize sensors and a database to record and forecast occupancy distribution by collecting empirical data on passenger behavior and structural information, using depth image cameras and AI/ML to predict and display optimal seating areas, encouraging passengers to move to less crowded sections through visual and auditory cues.
This system effectively manages passenger distribution, reducing congestion and delays by providing real-time data on occupancy levels and guiding passengers to less crowded areas, thereby improving the efficiency and comfort of public transport.
Smart Images

Figure EP2024061901_07112024_PF_FP_ABST
Abstract
Description
[0001] Method and device for outputting a predicted occupancy distribution in a public transport vehicle
[0002] The invention describes a method for outputting a forecast occupancy distribution in a public transport means between two stops, comprising the method steps of determining empirical data, storing the empirical data in a database of the occupancy distribution forecasting system, detecting an actual state of the occupancy distribution in the public transport means between two stops using a sensor unit of a occupancy distribution forecasting system, reading empirical data from a database of the occupancy distribution forecasting system, creating a forecast of the occupancy distribution from the detected actual state and the empirical data read from the database by a control unit of the occupancy distribution forecasting system, and outputting first data derived from the forecast occupancy distribution on an output device of the occupancy distribution forecasting system, as well as a occupancy distribution forecasting system.
[0003] State of the art
[0004] In buses, trams and other public transport vehicles, the situation regularly arises at peak times that large groups of passengers (e.g. schoolchildren) get stuck in the aisles or passageways shortly after boarding the vehicle, thus not only preventing other areas of the vehicle from being properly filled but also making it difficult or impossible for other passengers to board.
[0005] This results in delays and vehicle delays for the public transport company (transport operator), and inconvenience and even delays for passengers because they have to wait for the next scheduled vehicle. In some cases, the transport operator is forced to deploy additional vehicles during such phases, even though the sheer number of passengers could be transported with the scheduled vehicle deployment. If the transport operator wants to influence passenger distribution on the vehicle, the driver must make appropriate announcements after having gained an overview of whether passenger redistribution is even an option, i.e. whether there are any less busy areas of the vehicle. This is very tedious for the driver, and one-off announcements or instructions are usually missed or ignored by the passengers concerned.A transport company therefore has an interest in achieving a homogeneous passenger distribution in its vehicles while using as little material and personnel as possible.
[0006] A simple, inexpensive, and largely automated device that can be installed in vehicles and detects uneven passenger distribution and helps resolve it represents a desirable investment for transport companies. However, only those vehicles that are also used on the affected routes during critical phases need to be equipped accordingly.
[0007] A system for recording passenger distribution is known, for example, from document DE 10 2004 040 057 A1. This system involves equipping tickets with transmitters, preferably RFID chips, to identify passengers. Using suitable receivers, the distribution of tickets and thus the distribution of passengers in the area can be recorded. This data can then be made available to a traffic control system.
[0008] It is therefore an object of the present invention to provide an improved method for outputting a predicted occupancy distribution.
[0009] It is also an object of the invention to provide a staffing distribution forecasting system.
[0010] Description of the invention
[0011] The object is achieved by means of the inventive method for outputting a predicted occupancy distribution in a public transport vehicle. Advantageous embodiments of the invention are set out in the subclaims. The inventive method for outputting a predicted occupancy distribution in a public transport vehicle between two stops comprises six method steps: In the first method step, empirical data is collected. For the purposes of this document, empirical data has been obtained on a plurality of determined occupancy distributions under different reproducible conditions. The empirical data includes, in particular, data on occupancy distributions and passenger behavior from previous journeys of the public transport vehicle and, optionally, from the stops served by the public transport vehicle.Experience data is collected for a period prior to the output of the predicted occupancy distribution and is optionally continuously updated. The experience data is optionally collected by a suitable sensor unit of an occupancy distribution forecasting system located in the public transport vehicle and / or at the stop.
[0012] In the second step, the experience data is saved in a database of the staffing forecasting system. Optionally, all experience data collected over a configurable period of time can be saved in the database, as well as any additional collected experience data. The database can therefore be continuously updated with newly collected experience data.
[0013] In the third step, the current state of the occupancy distribution in public transport between two stops is recorded using a sensor unit of an occupancy distribution forecasting system.
[0014] In the fourth step, empirical data is read from a database of the staffing forecasting system. The database is optionally connected to a control unit of the staffing forecasting system, which has a memory containing a software program.
[0015] In the fifth step, a control unit of the occupancy distribution forecasting system creates a forecast of the occupancy distribution based on the recorded actual status and the empirical data read from the database. The database is optionally connected to a control unit of the occupancy distribution forecasting system, which has a memory with a software program that can be used to determine a forecast occupancy distribution. The control unit can be located locally or decentrally, i.e., in the vehicle or at the stop. Optionally, it is also possible to provide a central control system that communicates, for example, via cloud computing and / or fog computing. Mixed forms of centralized and decentralized control are also possible.
[0016] In the sixth method step, first data derived from the forecasted occupancy distribution are output on an output device of the occupancy distribution forecasting system.
[0017] An occupancy distribution in the sense of the invention is the number of passengers per unit area as a function of the length of the public transport vehicle. The occupancy distribution therefore indicates how many passengers are located where over the length of the public transport vehicle. Furthermore, the occupancy distribution is the number of passengers per unit area as a function of the length of the platform at a stop. The actual state of the occupancy distribution additionally indicates how many passengers are located where over the length of the public transport vehicle and / or the platform at a stop at a given time. The actual state of the occupancy distribution is recorded and determined, for example, by suitable sensors. The predicted occupancy distribution, on the other hand, indicates how many passengers will be located where over the length of the public transport vehicle and / or the platform at a stop at a given time.
[0018] In particular, passengers are signaled a direction of decreasing occupancy distribution and the direction to an area with a low occupancy distribution. The output device can provide such information visually and / or acoustically, for example. Optionally, the output device can be a smartphone, tablet, or notebook with a suitable app on which the data from the predicted occupancy distribution is displayed.
[0019] For the purposes of this document, public transport is defined as any means of transport for the transport of persons and / or goods that is generally accessible to everyone. This includes means of transport operated by specifically licensed transport companies (e.g., railways, air transport, cable cars, shipping, elevators), means of transport on licensed lines or routes, or means of transport operated by licensed service providers, as well as any commercially operated means of transport for persons and / or goods in the private sector.
[0020] For the purposes of this document, stops are all locations where public transport stops, where passengers board and / or alight, and / or where goods are loaded and / or unloaded. Stops can be fixed, defined stopping points according to a timetable. However, individually agreed stopping points are also considered stops for the purposes of this document.
[0021] Sensors suitable for implementing this method include optical sensors for image recognition (cameras) and sensors that operate with emitted and received light. Furthermore, sensors based on the frequency-modulated or FMCW (Frequency Modulated Continuous Wave) method can also be used, in which the distance is determined from the frequency shift of the reflected light beam based on a frequency-modulated light beam. Also known as the Doppler effect, FMCW is considered a next-generation LiDAR technology. TOF, structured light, and 905nm LiDAR are the classic technologies.
[0022] In a further development of the invention, the empirical data is determined by the occupancy distribution forecasting system. The occupancy distribution forecasting system has a plurality of sensors with which the current state of the occupancy distribution of passengers in public transport can be recorded. Furthermore, the occupancy distribution forecasting system has a database in which the recorded empirical data can be stored.
[0023] In a further embodiment of the invention, the empirical data is determined from experimentally acquired data. The sensors of the population distribution forecasting system determine an actual state of the population distribution; optionally, the sensors determine a plurality of actual states of different population distributions over a definable period of time before outputting the predicted population distribution. This plurality of actual states of different population distributions is stored in the database as empirical data. In a further aspect of the invention, the empirical data is determined by a sensor unit of the population distribution forecasting system.The sensor unit of the occupancy distribution forecasting system determines an actual state of the occupancy distribution. Optionally, the sensor unit determines a plurality of actual states of different occupancy distributions over a specified period of time before outputting the forecast occupancy distribution. This plurality of actual states of different occupancy distributions is stored in the database as empirical data.
[0024] In a further embodiment of the invention, the sensor unit is arranged in the public transport vehicle and / or at a stop. The sensor unit can be used to detect the actual occupancy distribution in the public transport vehicle and / or at a stop. A plurality of actual states of different occupancy distributions are stored in the database as empirical data.
[0025] In an advantageous embodiment of the invention, the empirical data is collected at least one year, preferably one month, particularly preferably 14 days, and especially preferably one week before the forecasted staffing distribution is issued. This ensures that sufficient empirical data is collected over a period of time. This period can optionally also be such that it falls shortly before the forecasted staffing distribution is issued. The empirical data is therefore up-to-date.
[0026] In a further embodiment of the invention, the experience data includes the occupancy and passenger behavior in the public transport vehicle and / or at the stop. The experience data includes, in particular, data on occupancy distributions and passenger behavior from previous journeys of the public transport vehicle and, optionally, from the stops served by the public transport vehicle. Experience data is recorded for a period prior to the output of the predicted occupancy distribution and is optionally continuously updated.
[0027] In a further embodiment of the invention, the forecast of the occupancy distribution is created from event data, whereby the event data is used to select the empirical data used to create the forecast of the occupancy distribution. Event data within the meaning of the invention includes data from temporary events that can influence the occupancy distribution.
[0028] In a further development of the invention, the event data includes time and location information. The location information includes, in particular, the route of the public transport and the location of the stops served by the public transport. The time information optionally includes the date and time of day at which the public transport serves the stops.
[0029] In a further aspect of the invention, time information includes the time of day, season, holidays, vacation periods, weather forecasts, and reservations. All of these time parameters influence the occupancy distribution, or the occupancy distribution varies depending on different time parameters. This information is used to select the empirical data that has the same time parameters.
[0030] In a further embodiment of the invention, the forecast of the occupancy distribution is created from structural data. Structural data includes data from permanent parameters of the stop and / or public transport, in particular, for example, spatial and room conditions. The parameters can also be recorded for a limited time, e.g., from a construction site. These parameters influence the occupancy distribution both in the public transport system and at the stop.
[0031] In a further embodiment of the invention, the structural data includes structural information about the stop and / or the public transport system. Structural information, such as construction sites at a stop and the type and number of carriages of a public transport system, are also essential for the occupancy distribution at the stop or on the public transport system.
[0032] In a further embodiment of the invention, the structural information includes the architectural design and / or the spatial and / or room conditions of the stop and / or public transport. This includes, for example, the number and location of entrances and exits, elevators, construction sites, sales outlets at the stop, as well as the number and location of entrances and exits, the type and number of carriages, and the standing and seating areas of the public transport.
[0033] In a further development of the invention, the structural information comprises the functionality of the respective structure. This includes, for example, the number and location of entrances and exits, elevators, construction sites, sales outlets at the stop, as well as the number and location of entrances and exits, the type and number of carriages, and the number of standing and seating spaces of the public transport vehicle.
[0034] In a further embodiment of the invention, the experience data, structural data, and / or event data are different for different stops. Experience data, structural data, and / or event data are determined for each stop served by the public transport system and stored in the database.
[0035] In a further embodiment of the invention, the current passenger behavior on the public transport vehicle or at the next stop is recorded, with the occupancy distribution forecast being created from the recorded actual state and the recorded current passenger behavior. The actual state of the occupancy distribution indicates how many passengers are located where along the length of the public transport vehicle and / or the platform of a stop at a given time. The actual state of the occupancy distribution is recorded and determined, for example, by suitable sensors. Using knowledge of the actual state of the occupancy distribution and the current passenger behavior at a given time, a forecast of the occupancy distribution is created for a later time.
[0036] In a further development of the invention, the actual state of the occupancy distribution is recorded in a first time interval, wherein the first time interval lies on the route between two consecutive stops. In the first time interval, the public transport is usually in motion, all passengers have boarded the public transport at a first stop and are usually moving within the public transport in order to find and take their standing and / or seating places or have already taken their standing and / or seating places. In a further embodiment of the invention, the actual state of the occupancy distribution is recorded when passenger movement in the public transport is low. Passenger movement in the public transport is not low immediately after departure from a stop, but at a later point in time, when the passengers have taken their standing and / or seating places and, if applicable,have stowed their luggage. Passenger movement at this later time typically only occurs to use the restrooms and / or to purchase drinks and / or food. However, the proportion of these passengers is usually small. When passenger movement is low, occupied and / or complementary unoccupied standing and / or seated spaces on public transport can be recorded and identified more reliably than when passenger movement is high.
[0037] In a further embodiment of the invention, the actual state of the occupancy distribution is detected by a first sensor, wherein the first sensor is a sensor for counting passengers at doors and / or passageways and / or a sensor for capturing image material, and wherein the data detected by the first sensor are analyzed with regard to the actual state of the occupancy distribution. A first sensor is optionally advantageously arranged at entrance doors to the public means of transport and / or doors in the interior, e.g. passenger compartments with standing and / or seating space, and detects the number of passengers located there. Optionally, the first sensor is a depth image camera. The first sensor can capture a depth image of the transport space, which is used to determine an occupancy distribution in the transport space based on the depth image.In a further embodiment of the invention, the first sensor is a sensor for counting passengers at doors and / or passageways and / or a sensor for capturing image material.
[0038] In a further embodiment of the invention, passenger behavior is analyzed with regard to preparatory actions for disembarking. In a further configuration of the invention, preparatory actions for disembarking passengers in public transport include passengers getting up from their seats, moving toward the exit of the public transport vehicle, and / or stowing personal belongings. By recording preparatory actions for disembarking, a predicted occupancy distribution after passengers disembark when the public transport vehicle stops at a stop is possible. In a further embodiment of the invention, passenger behavior is analyzed using AI / ML. The control unit's memory contains machine learning data that is applied to the data recorded by the sensor.This means that passengers’ preparatory actions for disembarking are significantly distinguished from other actions.
[0039] In a further embodiment of the invention, the analysis of passenger behavior includes the analysis of movement flows of people and / or a passenger distribution at the next stop. By recording the passenger distribution at the next stop, it is possible to predict in which area of the platform at the stop passengers will board the public transport system, and to calculate a corresponding passenger distribution within the public transport system.
[0040] In a further embodiment of the invention, the analysis of passenger behavior takes place in a second time interval. Typically, the second time interval occurs shortly before reaching the second stop. In the second time interval, the passengers have stowed their personal belongings (e.g., luggage), left their seats, and are moving toward the exits of the public transport vehicle or are in the immediate vicinity of them.
[0041] In a further development of the invention, the second time interval differs from the first time interval. While passenger movement on public transport is low in the first time interval, passenger movement is high in the second time interval because passengers are stowing their personal belongings and / or moving toward the exits of the public transport.
[0042] In a further embodiment of the invention, the second time interval occurs before the next stop is reached. In the second time interval, shortly before the second stop is reached, the passengers have stowed their personal belongings (e.g. luggage), left their seats and are moving towards the exits of the public transport or are in the immediate vicinity of it. In a development of the invention, the second time interval occurs 2 minutes, preferably 1 minute, particularly preferably 30 seconds and especially preferably 15 seconds before the next stop is reached. In a further configuration of the invention, the passenger behavior is analyzed by a second sensor. The second sensor is optionally an image recognition sensor, which can optionally be used to distinguish between people and objects.
[0043] In a further embodiment of the invention, the second sensor is different from the first sensor. While the first sensor enables passenger counting and localization, the second sensor records the passenger behavior of individual passengers.
[0044] In a further aspect of the invention, the second sensor is a camera for image capture. The second sensor is an image recognition sensor, which can optionally distinguish people from objects.
[0045] In an advantageous embodiment of the invention, the occupancy distribution forecast is created for a time immediately after passengers disembark from public transport at the next stop. By recording the distribution of people at the next stop, it is possible to forecast the area of the platform at the stop in which passengers will board the public transport, and to calculate a corresponding passenger distribution in the public transport. In addition, occupied and / or complementary unoccupied standing and / or seating spaces in the public transport are recorded and determined. By displaying unoccupied standing and / or seating spaces in the public transport, passenger flows can be directed, passengers can board and disembark more quickly, and the utilization of the public transport system is improved.
[0046] In a further development of the invention, the point in time is not in the first time interval and / or second time interval. The first time interval is on the route between two consecutive stops. In the first time interval, the public transport vehicle is usually in motion, all passengers have boarded the public transport vehicle at a first stop and are usually moving within the public transport vehicle to find and take their standing and / or sitting places or have already taken their standing and / or sitting places. The second time interval is usually in a period of time shortly before reaching the second stop. In the second time interval, the passengers have stowed their personal belongings (e.g. luggage), have left their seats and are moving towards the exits of the public transport vehicle or are in the immediate vicinity of them.The time of the occupancy distribution forecast is immediately after passengers disembark from public transport at the next stop.
[0047] The problem is further solved by the occupancy distribution forecasting system according to the invention. Advantageous embodiments of the invention are also set forth in the subclaims.
[0048] The occupancy distribution forecasting system according to the invention for a public transport vehicle has a first sensor unit with a first sensor, wherein the first sensor unit is provided and suitable for counting passengers in the public transport vehicle and / or recording passenger behavior in the public transport vehicle. A first sensor is optionally advantageously arranged at entrance doors of the public transport vehicle and / or doors in the interior, e.g. passenger compartments with standing and / or seating areas, and records the number of passengers present there. Optionally, the first sensor is a depth image camera. The first sensor can record a depth image of the transport space, with which an occupancy distribution of the transport space in the public transport vehicle is determined based on the depth image.In a further embodiment of the invention, the first sensor is a sensor for counting passengers at doors and / or passageways and / or a sensor for capturing image material.
[0049] The occupancy distribution forecasting system according to the invention further comprises a second sensor unit with a second sensor, wherein the second sensor unit is provided and suitable for counting passengers at a stop and / or recording passenger behavior at a stop. The second sensor, like the first sensor, is a depth camera. The second sensor can also record a depth image of the transport space, which is used to determine an occupancy distribution of the transport space in the public transport vehicle based on the depth image. In a further embodiment of the invention, the second sensor is a sensor for counting passengers at doors and / or passageways and / or a sensor for recording image material.Furthermore, the occupancy distribution forecasting system according to the invention comprises a control unit designed and adapted to receive the data from the first and second sensor units and to create a forecast occupancy distribution from the received data. It also comprises a database coupled to the control unit, wherein empirical data, structural data, and / or event data are stored in the database. The control unit has a memory with a suitable software program.
[0050] The occupancy distribution forecasting system according to the invention also has an output device for outputting data derived from the forecast occupancy distribution. The output device has a plurality of optical displays and acoustic display devices (loudspeakers). Displays and loudspeakers are arranged, for example, in the ceiling area of the passenger compartment. In areas with a high forecast passenger distribution, the displays are provided to light up red, for example, while in areas with a low forecast passenger distribution, the displays light up green. The color signaling motivates a passenger to move from an area with a high forecast passenger distribution to an area with a low forecast passenger distribution.A preferred direction can also be indicated, for example, by an LED running light installed in the floor of a carriage and / or a platform at a stop. It is also conceivable to indicate a direction in which carriages with a low passenger density are expected. In addition, appropriate announcements are played over the loudspeakers, directing passengers to an area within the carriages with a low passenger density.
[0051] In a further development of the invention, the first sensor unit has a further sensor which differs in its functionality from the first sensor. While passenger counting and localization is possible using the first sensor, the second sensor records the passenger behavior of individual passengers. The second sensor is optionally an image recognition sensor, with which people can optionally be distinguished from objects. In a further aspect of the invention, the first sensor unit is arranged in the public transport vehicle and / or the second sensor unit is arranged at the stop. Both sensor units each have two different sensors with which passengers can be counted and passenger behavior can be recorded both in the public transport vehicle and at the stop.
[0052] In another embodiment, the first sensor functions differently than the second sensor. While the first sensor enables passenger counting and localization, the second sensor records the behavior of individual passengers.
[0053] In a further embodiment of the invention, the first sensor is provided and suitable for counting passengers and / or the further first sensor is provided and suitable for determining passenger behavior. A first sensor is optionally advantageously arranged at entrance doors of the public transport vehicle and / or doors in the interior, e.g. passenger compartments with standing and / or seating areas, and detects the number of passengers present there. Optionally, the first sensor is a depth image camera. The first sensor can detect a depth image of the transport space, which is used to determine the occupancy distribution of the transport space in the public transport vehicle based on the depth image. The further first sensor is an image recognition sensor, which can optionally be used to distinguish between people and objects.
[0054] In a further embodiment of the invention, the control unit is coupled to the first sensor unit, the second sensor unit, the database, and / or the output unit. A method for outputting a predicted occupancy distribution in a public transport vehicle can be implemented by means of the control unit.
[0055] In a further aspect of the invention, the second sensor unit comprises a plurality of second sensors. The number and arrangement of the second sensors are selected such that all passengers on a public transport vehicle and / or on the platform of a stop can be detected. In a further embodiment of the invention, the plurality of second sensors of the second sensor unit monitor passenger behavior on the public transport vehicle and / or at the next stop. The second sensors are image recognition sensors, which can optionally be used to distinguish between people and objects.
[0056] In a further embodiment of the invention, the data acquired by the second sensor is evaluated using AI / ML. The control unit's memory contains machine learning data that is applied to the data acquired by the sensor. This allows passengers' preparatory actions for disembarking to be significantly differentiated from other actions.
[0057] The embodiments are shown schematically in simplified form in the following drawings and explained in the following description.
[0058] Fig. 1 a: Occupancy distribution forecasting system in a public transport system
[0059] Fig. 1 b: Current state of the occupancy distribution in a public transport system
[0060] Fig. 2 a: Occupancy distribution forecasting system in a platform
[0061] Fig. 2 b: Current state of the occupancy distribution in a platform
[0062] Fig. 3 a: Occupancy distribution forecasting system in a public transport system, first and second sensors
[0063] Fig. 3 b: Occupancy distribution forecasting system in a platform, first and second sensors
[0064] Fig. 4 a: Actual state of the occupancy distribution and predicted occupancy distribution in a public transport system
[0065] Fig. 4 b: Actual state of the occupancy distribution and predicted occupancy distribution in a platform
[0066] Fig. 5 a: Occupancy distribution forecasting system in a public transport vehicle, first and second sensors, output device
[0067] Fig. 5 b: Occupancy distribution forecasting system on a platform, first and second sensors, output device
[0068] Fig. 6: Flowchart of the process for outputting a predicted occupancy distribution in a public transport system Fig. 7 a: Flowchart of the process for outputting a predicted occupancy distribution in a public transport system
[0069] Fig. 7 b: Flowchart of the process for outputting a predicted occupancy distribution in a public transport system, permanent output of the actual state and the predicted occupancy distribution
[0070] Fig. 8 a: Connections of first sensors, second sensors, AI / ML unit, database with the control unit and output devices as well as data flow, sensors in public transport
[0071] Fig. 8 b: Connections of first sensors, second sensors, AI / ML unit, database with the control unit and output devices as well as data flow, sensors in public transport and at the second stop
[0072] Fig. 8 c: Connections of first sensors, second sensors, AI / ML unit, database with the control unit and output devices as well as data flow, sensors in public transport and at the second stop, output devices in public transport and at the second stop
[0073] Fig. 8 d: Connections of first sensors, second sensors, AI / ML unit, database with the control unit and output devices as well as data flow, sensors in public transport and at stops, output devices in public transport and at stops
[0074] Fig. 1 shows an embodiment of the occupancy distribution forecasting system BVPS according to the invention arranged in a public transport vehicle OV. The public transport vehicle OV in this and all further embodiments is a light rail vehicle which travels on tracks G at regular intervals to a plurality of stops H1, H2 and stops at the stops H1, H2. The public transport vehicle OV has a plurality of carriages W coupled to one another which are continuously connected. The carriages W have passenger seats P. By means of the doors T, a passenger F can enter and leave the carriages W and the passenger compartments A. Passengers F get on and off at the stops H1, H2, H3, with platform H3 being reached after platform H2 and platform H2 after platform H1. The stops H1, H2 each have a platform B.In this exemplary embodiment, the actual state of the occupancy distribution with passengers F in the carriages W of the public transport OV is recorded at a given time during the journey of the public transport OV. For this purpose, the interior of the carriages W of the public transport OV has the occupancy distribution forecasting system BVPS (Fig. 1a). The occupancy distribution forecasting system BVPS has the first sensor unit SE1 with a plurality of first sensors S1. The first sensors S1 are arranged in the passenger compartments A of the carriages W and in the areas of the doors T. Each first sensor S1 is a depth image camera. The first sensors S1 are connected to the control unit C, which is arranged in the public transport OV. Passengers F and their positions in the carriages W are detected by means of the first sensors S1.
[0075] The analysis of three-dimensional depth images captured by the first sensors S1 has the advantage that, unlike a simple person count, the space actually occupied by people and / or luggage can be detected. For example, particularly in rail transport, it is easily possible to detect excessive occupancy of an area of the carriage with luggage or, in particular, bicycles.
[0076] At this point in time, the passenger seats P of the carriages W are not fully occupied; the carriages W have free passenger seats FP. The total number of first sensors S1 detects the position of each passenger F in the carriages W at this given point in time. The control unit C determines the actual state of the occupancy distribution based on the data provided by the first sensors S1, whereby the occupancy distribution is the function of the number of passengers F over the length L(OV) of the public transport vehicle OV. The actual state of the occupancy distribution therefore indicates how many passengers F are located where in the public transport vehicle OV at a given point in time. Complementary to the occupancy distribution is the distribution of free passenger seats FP over the length L(OV) of the public transport vehicle OV (Fig. 1 b).This distribution of free passenger seats FP over the length L(OV) of the public transport OV is of particular interest to passengers F and the transport company itself in order to ensure uniform and as complete a occupancy as possible of the public transport OV. Fig. 2 shows an embodiment of the occupancy distribution forecasting system BVPS according to the invention arranged on a platform B. The platform B has a plurality of doors T and elevators E for passengers F to enter and exit from the platform B. The platform B itself is separated from the track G on which the public transport OV runs by a platform edge BK.
[0077] In this exemplary embodiment, the actual state of the occupancy distribution with passengers F on platform B of the public transport system OV is recorded at a given point in time. For this purpose, platform B has the occupancy distribution forecasting system BVPS (Fig. 2 a). The occupancy distribution forecasting system BVPS has the first sensor unit SE1 with a plurality of first sensors S1 that are connected to the control unit C. The control unit C determines the actual state of the occupancy distribution based on the data provided by the first sensors S1, wherein the occupancy distribution is the function of the number of passengers F over the length L(V) of platform B (Fig. 2 b). The actual state of the occupancy distribution thus indicates how many passengers F are located where on platform B at a given point in time.
[0078] Fig. 3 and Fig. 4 show embodiments of the occupancy distribution forecasting system BVPS according to the invention arranged in a public transport vehicle OV (Fig. 3 a) and on a platform B (Fig. 3 b). In addition to the embodiments shown so far (see Figs. 1 a, 2 a), the occupancy distribution forecasting system BVPS has a second sensor unit SE2 with a plurality of second sensors S2. The first sensors S1 are arranged in the passenger compartments A of the carriages W in the areas of the doors T. The second sensors S2 are also arranged in the passenger compartments A of the carriages W in such a way that they have an unobstructed line of sight (LoS) of the passengers in the passenger compartments A and in the areas between the carriages W (Fig. 3 a). On platform B (Fig.3 b) the second sensors S2 of the second sensor unit SE2 are also arranged in a structural unit with the first sensors S1 in such a way that they have an unobstructed line of sight to passengers F.
[0079] A first sensor S1 is, as explained, a depth-image camera. The first sensors S1 are connected to the control unit C, which is arranged in the public transport vehicle OV. The first sensors S1 detect passengers F and their positions in the carriages W. Based on the data provided by the first sensors S1, the control unit C determines the actual state of the occupancy distribution, where the occupancy distribution is the function of the number of passengers F over the length L(OV) of the public transport vehicle OV. The actual state of the occupancy distribution thus indicates how many passengers F are located where in the public transport vehicle OV at a given time.
[0080] Based on the data provided by the first sensors S1, the control unit C determines the actual state of the occupancy distribution of platform B, where the occupancy distribution is a function of the number of passengers F over the length L(V) of platform B (Fig. 3 b). The actual state of the occupancy distribution thus indicates how many passengers F are located where on platform B at a given time. The control unit C for determining the occupancy distribution of platform B is located on platform B.
[0081] A second sensor S2 is also a camera suitable for capturing images. Unlike the first sensor S1, the second sensor S2 is not a depth-of-field camera, but rather creates images of passengers F. The second sensor S2 continuously updates the images, digitizes them, and forwards them to the control unit C. The control unit C uses the images created by the second sensors S2 to analyze passenger behavior. The control unit C has a memory and suitable software for analyzing the images. The first sensors S1 and second sensors S2 are arranged in such a way that the entire passenger area A and the entire platform B can be captured three-dimensionally across the sum of all detection areas.
[0082] The analysis of passenger behavior includes the analysis of movement flows of passengers F in public transport OV (Fig. 3 a). In public transport OV, the analysis of movement flows of passengers F includes the predicted passenger distribution FP(PRO) over the length L(OV) of the public transport OV at the time the public transport OV reaches the stop H2 (see Fig. 4 a). The predicted passenger distribution FP(PRO) therefore indicates how many passengers F will be where in the public transport OV at the time the public transport OV reaches the stop H2. On platform B, the analysis of movement flows of passengers F includes the predicted passenger distribution FP(PRO) over the length L(B) of platform B at the time the public transport OV reaches the
[0083] Stop H2 reached (see Fig. 4 b).
[0084] To analyze the predicted passenger distribution FP(PRO), the control unit C accesses the determined actual state of the occupancy distribution at a given point in time, which was determined using the first sensors S1 (see Fig. 1, Fig. 2). In addition, the preparatory actions of the passengers F for disembarking are analyzed using the second sensors S2. The preparatory actions include, for example, the passengers F getting up from their seats, stowing personal belongings, putting on clothing and, in particular, the movement of passengers towards the exit T of the public transport vehicle. The memory of the control unit C also contains machine learning data that is applied to the image recordings. This allows the preparatory actions of the passengers F for disembarking to be significantly differentiated from other actions.
[0085] Fig. 5 shows further embodiments of the occupancy distribution forecasting system BVPS according to the invention, arranged in a public transport vehicle OV (Fig. 5 a) and at a platform B of a stop H2 (Fig. 5 b). The arrangement and operation of the occupancy distribution forecasting system BVPS have already been described in the previous embodiment (see Fig. 3). The analysis of the predicted passenger distribution FP(PRO) is also described in the previous embodiment (see Fig. 3, Fig. 4).
[0086] In addition, the occupancy distribution forecast system BVPS has an output device A. The output device A has a plurality of optical displays D and acoustic display devices (loudspeakers) L. Displays D and loudspeakers L are arranged in the ceiling area of the passenger compartment A (Fig. 5 a). In the area of a high predicted passenger distribution FP(PRO), the displays D are intended to light up red, while in areas with a low predicted passenger distribution FP(PRO), the displays D light up green. Due to the color signaling, a passenger F is motivated to move from an area with a high predicted passenger distribution FP(PRO) to an area with a low predicted passenger distribution FP(PRO). A preferred direction can also be indicated, for example, by a running direction of an LED running light arranged in the floor of a carriage.Particularly in multi-unit trains, it is conceivable to signal a direction in which carriages W with a low predicted passenger distribution FP(PRO) are expected. In addition, corresponding announcements are played over the loudspeakers L, informing passengers F of an area in the carriages W with a low predicted passenger distribution FP(PRO).
[0087] Similarly, on platform B, passengers F are visually indicated an area with a low predicted passenger distribution FP(PRO) in the approaching public transport vehicle OV by displays D and acoustically by loudspeakers L (Fig. 5 b). This also motivates passengers F to seek out an area with a low predicted passenger distribution FP(PRO) on platform B before boarding the public transport vehicle OV. This accelerates the boarding and disembarking of passengers F from and to the public transport vehicle OV.
[0088] Using the BVPS occupancy distribution forecasting system, additional empirical data is collected (see Fig. 6). For empirical data, data on the actual state of the occupancy distribution is used, which was collected one week (7 days) before the forecasted occupancy distribution is issued. Optionally, empirical data is collected at least one year, preferably one month, and particularly preferably 14 days before the forecasted occupancy distribution is issued. The empirical data is collected using sensors S1, S2 of the BVPS occupancy distribution forecasting system. The actual state of the occupancy distribution is collected as already described. In particular, the empirical data is collected over a period of time, i.e.a plurality of actual states are recorded within a definable period of time before the output of the predicted occupancy distribution by the sensors S1, S2, the respective actual states of the occupancy distribution are stored in the database DB and can be retrieved by the control unit C.
[0089] The experience data also includes data on the current state of passenger behavior, which is also determined using the passenger distribution forecasting system (BVPS) as described above. The data on the current state of passenger behavior is also collected multiple times over a period of time and stored in the DB database.
[0090] Fig. 6 shows embodiments of the method for outputting a-PROG of a predicted
[0091] Occupancy distribution and the collection of empirical data. It shows which process step is executed on which component of the occupancy distribution forecasting system (BVPS) at which time t. The public transport vehicle (OV) leaves the first stop (H1) at time v-H1, reaches the second stop (H2) at time a-H2, and requires a travel time (FZ) to do so.
[0092] In time interval Z1, the first sensors S1 record the actual state of the occupancy distribution in the public transport vehicle OV (d-IST) when passenger movement in the public transport vehicle OV is low. In this time interval Z1, passenger movement within the carriages W is usually low; passengers F have taken their seats. The recorded sensor data from the first sensors S1 are sent to the control unit C, which determines the actual state of the occupancy distribution in the public transport vehicle OV (c-IST). This determined actual state of the occupancy distribution (c-IST) is stored in the database DB (see Fig. 8) (s-IST).
[0093] Within the second time interval Z2, 15 s before reaching a-H2 the next stop H2, the passenger behavior FV of the passengers F is recorded d- FV using the second sensors S2. In further embodiments of the method, the second time interval Z2 can be 2 min, preferably 1 min, and particularly preferably 30 s. The recorded d-FV sensor data of the second sensors S2 are also sent to the control unit C, which determines a predicted passenger distribution c-PROG. This created c-PROG is also stored in the database DB s-PROG. The predicted passenger distribution is determined for the time ZP c-PROG, which is immediately after passengers F get off the public transport OV at the next stop H2. The determined c-PROG predicted passenger distribution is also stored in the database DB.The predicted passenger distribution is sent to the output unit A, which outputs data of the predicted passenger distribution via loudspeaker L and displays D.
[0094] Fig. 7 shows exemplary embodiments of the method for outputting a-PROGn of predicted occupancy distributions as well as the implementation of empirical data, structural data and event data. In a first variant (Fig. 7 a), in the time interval Z1 at time Zp1, the actual state of the occupancy distribution d-OV is recorded by means of the sensors S1 arranged in the public transport OV when the passenger movement in the public transport OV is low. In this time interval Z1 at time Zp1.1, the passenger movement within the carriages W is usually low, the passengers F have taken their seats. In addition, at the same time Zp1.1, the current passenger behavior is recorded by means of the first sensors S1. The recorded sensor data d-OV of the first sensors S1 is sent to the control unit C, which determines the actual state of the occupancy distribution as well as the current passenger behavior and stores it as empirical data in the database DB.
[0095] Within the second time interval Z2 15 s before reaching a-H2 the next stop H2, the actual state of the occupancy distribution and the passenger behavior FV of the passengers F are recorded dH by means of the second sensors S2 on platform B of the second stop H2 at time Zp2. In further embodiments of the method, the second time interval Z2 can be 2 min, preferably 1 min, and particularly preferably 30 s. The recorded sensor data dH of the second sensors S2 are also sent to the control unit C, which determines a forecast passenger distribution C-PROG2. The forecast passenger distribution is determined C-PROG2 for the time ZP, which is immediately after passengers F disembark from the public transport OV at the next stop H2.The predicted passenger distribution is sent to the output unit A, which outputs data of the predicted passenger distribution via loudspeaker L and displays D at time Zp2 a-PROG2.
[0096] In a variant (Fig. 6 b) of the method, in the time interval Z1, at time Zp1.1, by means of the sensors S1 arranged in the public transport OV within the third time interval Z3, which lies within the first time interval Z1 and has a shorter duration than the first time interval Z1, multiple detections d-OVn, determinations c-OVn taking into account the empirical data, structural data and event data stored in the database DB and outputs a-OVn of actual states of the occupancy distribution at regular, adjustable time intervals at the times Zp1 .1 to Zp1 .n. The outputs a-OVn are made via loudspeakers L and displays D within the public transport OV. In this way, passengers F receive updated information about free seats within the public transport OV during the travel time FZ.
[0097] Fig. 8 shows variants of the connections of first sensors S1, second sensors S2, the AI / ML unit and the database DB with the control unit C and the output devices L, D as well as the data flow between the mentioned components both in the public transport OV and on the platform B of the second stop H2. In contrast to previously shown embodiments, the control unit C is arranged such that a preferably wireless data exchange can take place between the components arranged in the moving public transport OV and the components arranged in the stop H2.
[0098] The control unit C is connected to an AI / ML unit AI / ML, which contains stored AI / ML data. The AI / ML unit AI / ML contains machine learning data that is applied to the data acquired by the sensors S1, S2. This optionally significantly distinguishes the preparatory actions of passengers F for disembarking from other actions. The database DB, which is also connected to the control unit C, contains empirical data, structural data, and event data.
[0099] Empirical data are occupancy distributions recorded by sensors S1, S2 at different times at stops Hn and of the public transport OV that serves the stops Hn. The database DB also contains structural data, which is also applied to the recorded sensor data to create the predicted occupancy distribution. Structural data contains data on the architectural design, the spatial and / or space conditions of the stop and the public transport. Event data includes time and location information. The location information includes in particular the route of the public transport OV and the location of the stops Hn that the public transport OV serves. The time information includes the date and time of day at which the public transport OV serves the stops Hn.The time information is used to select the experience data that have the same time parameters.
[0100] In a first variant (Fig. 7 a), the first sensors S1 are arranged in the public transport vehicle OV and the second sensors S2 are arranged on the platform of stop H2 and send the recorded d-OVn, d-Hn data to the control unit C, which sends the determined actual states c-OVn, c-Hn and predicted states c-PROGn of the occupancy distribution to the output devices L, D of stop H2, where they are output a-OVn, a-PROGn. In a further variant (Fig. 7 b), first sensors S1 are arranged in the public transport vehicle OV and send the recorded d-OVn data to the control unit C. Second sensors S2 are arranged at stop H2 and also send their recorded d-Hn data to the control unit C.The control unit C determines c-OVn, c-Hn actual states and predicted states c-PROGn of the occupancy distribution of both the public transport OV and the stop H2, sends the determined c-OVn, c-Hn actual states and predicted states c-PROGn of the occupancy distribution to the output devices L, D of the stop H2 and the public transport OV, where they are output a-OVn, a-PROGn, respectively.
[0101] In a further variant (Fig. 8 c), sensors S1, S2 are arranged in the public transport OV and send the recorded data to the control unit C. Sensors S1, S2 are also arranged at the stop H2 and also send their recorded data to the control unit C. The control unit C determines actual states c-ISTn and predicted states c-PROG of the occupancy distribution both of the public transport OV and of the stop H2, sends the determined actual states c-ISTn and predicted states c-PROG of the occupancy distribution to the output devices L, D of the stop H2 and of the public transport OV, where they are output a-IST, a-PROG respectively.
[0102] In a variant of the above embodiment (see Fig. 8 c), sensors S1, S2 are arranged at three different stops H1, H2, H3 and send their recorded data to the control unit C. First and second sensors S1, S2 are also arranged in the public transport OV and send the recorded data to the control unit C. The control unit C determines actual states c-ISTn and predicted states c-PROG of the occupancy distribution both of the public transport OV and of each individual stop H1, H2, H3 and sends the determined actual states c-ISTn and predicted states c-PROG of the occupancy distribution to the output devices L, D of each stop H1, H2, H3 and of the public transport OV, where they are each output a-IST, a-PROG.
[0103] According to the invention, the method presented here and the arrangement of the connections of first sensors S1, second sensors S2 with the control unit C and the output devices L, D as well as the data flow between the said components can be carried out in the public transport OV with any number of stops Hn.
[0104] Fig. 5 shows further embodiments of the occupancy distribution forecasting system BVPS according to the invention, arranged in a public transport vehicle OV (Fig. 5 a) and at a platform B of a stop H2 (Fig. 5 b). The arrangement and operation of the occupancy distribution forecasting system BVPS have already been described in the previous embodiment (see Fig. 3). The analysis of the predicted passenger distribution FP(PRO) is also described in the previous embodiment (see Fig. 3, Fig. 4).
[0105] In addition, the occupancy distribution forecast system BVPS has an output device A. The output device A has a plurality of optical displays D and acoustic display devices (loudspeakers) L. Displays D and loudspeakers L are arranged in the ceiling area of the passenger compartment A (Fig. 5 a). In the area of a high predicted passenger distribution FP(PRO), the displays D are intended to light up red, while in areas with a low predicted passenger distribution FP(PRO), the displays D light up green. Due to the color signaling, a passenger F is motivated to move from an area with a high predicted passenger distribution FP(PRO) to an area with a low predicted passenger distribution FP(PRO). A preferred direction can also be indicated, for example, by a running direction of an LED running light arranged in the floor of a carriage.Particularly in multi-unit trains, it is conceivable to signal a direction in which carriages W with a low predicted passenger distribution FP(PRO) are expected. In addition, corresponding announcements are played over the loudspeakers L, informing passengers F of an area in the carriages W with a low predicted passenger distribution FP(PRO).
[0106] Similarly, on platform B, passengers F are visually indicated an area with a low predicted passenger distribution FP(PRO) in the incoming public transport vehicle OV by displays D and acoustically by loudspeakers L (Fig. 5 b). This also motivates passengers F to seek out an area with a low predicted passenger distribution FP(PRO) on platform B before boarding the public transport vehicle OV. This accelerates the boarding and disembarking of passengers F from and to the public transport vehicle OV.
[0107] Figure 6 shows exemplary embodiments of the method for outputting a-PROG of a predicted occupancy distribution. It shows which method step is executed on which component of the occupancy distribution forecasting system BVPS at which time t.
[0108] The public transport OV leaves the first stop H1 at time v-H1, reaches the second stop H2 at time a-H2 and requires a travel time FZ to do so (Fig. 6 a). In the time interval Z1, the actual state of the occupancy distribution is recorded d-IST using the first sensors S1 if the passenger movement in the public transport OV is low. In this time interval Z1, the passenger movement within the carriages W is usually low, and the passengers F have taken their seats. The sensor data recorded by the first sensors S1 are sent to the control unit C, which determines the actual state of the occupancy distribution c-IST. Within the second time interval Z2, 15 s before reaching the next stop H2 a-H2, the passenger behavior FV of the passengers F is recorded d-FV using the second sensors S2. In further embodiments of the method, the second time interval Z2 can be 2 min, preferably 1 min, and particularly preferably 30 s.The recorded sensor data from the second sensor S2 is also sent to the control unit C, which calculates a predicted passenger distribution (c-PROG). The predicted passenger distribution is calculated for the time ZP (c-PROG), which occurs immediately after passengers F disembark from the public transport vehicle (OV) at the next stop (H2). The predicted passenger distribution is sent to the output unit A, which outputs the data of the predicted passenger distribution via loudspeaker L and displays D (a-PROG).
[0109] In one variant (Fig. 6 b) of the method, an output a-IST of the actual state of the occupancy distribution is also carried out within the time interval Z1. Passengers F, in particular within public transport OV, are thus informed about the actual state of the occupancy distribution and can specifically take up free seats, especially in a heavily occupied public transport OV. In another variant (Fig. 6 c) of the method, multiple recordings d-ISTn, determinations c-ISTn and outputs a-ISTn of actual states of the occupancy distribution are additionally carried out within the first time interval Z1 at regularly adjustable time intervals. In this way, passengers F, in particular within public transport OV, receive updated information about free seats.
[0110] Fig. 7 shows variants of the connections of first sensors S1, second sensors S2 with the control unit C and the output devices L, D as well as the data flow between the mentioned components both in the public transport OV and on the platform B of the second stop H2. In contrast to previously shown embodiments, the control unit C is arranged such that a preferably wireless data exchange can take place between the components arranged in the moving public transport OV and the components arranged in the stop H2.
[0111] In a first variant (Fig. 7 a), the sensors S1, S2 are arranged in the public transport OV and send the recorded data to the control unit C, which sends the determined actual states c-ISTn and predicted states c-PROG of the occupancy distribution to the output devices L, D of the stop H2, where they are output a-IST, a-PROG.
[0112] In a further variant (Fig. 7 b), sensors S1, S2 are arranged in the public transport OV and send the recorded data to the control unit C. Sensors S1, S2 are also arranged at the stop H2 and also send their recorded data to the control unit C. The control unit C determines actual states c-ISTn and predicted states c-PROG of the occupancy distribution both from the public transport OV and from the stop H2, sends the determined actual states c-ISTn and predicted states c-PROG of the occupancy distribution to the output devices L, D of the stop H2, where they are output a-IST, a-PROG.
[0113] In a further variant (Fig. 7 c), sensors S1, S2 are arranged in the public transport OV and send the recorded data to the control unit C. Sensors S1, S2 are also arranged at the stop H2 and also send their recorded data to the control unit C. The control unit C determines actual states c-ISTn and predicted states c-PROG of the occupancy distribution both of the public transport OV and of the stop H2, sends the determined actual states c-ISTn and predicted states c-PROG of the occupancy distribution to the output devices L, D of the stop H2 and of the public transport OV, where they are output a-IST, a-PROG respectively.
[0114] In a variant of the above embodiment (see Fig. 7 c), sensors S1, S2 are arranged at three different stops H1, H2, H3 and send their recorded data to the control unit C. First and second sensors S1, S2 are also arranged in the public transport OV and send the recorded data to the control unit C. The control unit C determines actual states c-ISTn and predicted states c-PROG of the occupancy distribution both of the public transport OV and of each individual stop H1, H2, H3 and sends the determined actual states c-ISTn and predicted states c-PROG of the occupancy distribution to the output devices L, D of each stop H1, H2, H3 and of the public transport OV, where they are each output a-IST, a-PROG.
[0115] According to the invention, the method presented here and the arrangement of the connections of first sensors S1, second sensors S2 with the control unit C and the output devices L, D as well as the data flow between the said components can be carried out in the public transport OV with any number of stops Hn.
[0116] LIST OF REFERENCE SYMBOLS
[0117] A passenger compartment
[0118] B Platform
[0119] BK platform edge
[0120] BVPS staffing distribution forecasting system
[0121] C Control unit
[0122] D Display
[0123] E Elevator
[0124] DB database
[0125] F Passenger
[0126] FP Free Passenger PI rates
[0127] FV Current passenger behavior
[0128] FZ travel time
[0129] G track
[0130] H1, H2, H3 stops
[0131] AI / ML storage with AI / ML data
[0132] L Speaker
[0133] L(OV) Length of public transport
[0134] L(B) Length of the platform
[0135] P Unoccupied seat / standing place
[0136] PB Predicted staffing distribution
[0137] PF Occupied seat / standing place
[0138] OV Public Transport
[0139] SE1 First sensor unit
[0140] SE2 Second sensor unit
[0141] S1 First Sensor
[0142] S2, Second Sensor
[0143] T Timeline T Door
[0144] Z1 First time interval
[0145] Z2 Second time interval
[0146] Z3 Third time interval
[0147] ZP Time of the predicted occupancy distribution v-H1 Leaving the first stop a-H2 Arriving at the second stop d-IST, d-IST1, d- Recording the actual state of the occupancy distribution IST2, d-ISTn d-FV Recording the current passenger behavior c-IST, C-IST1, C-IST2, Determination of the actual state of the occupancy distribution c-ISTn s-IST Saving the actual state of the occupancy distribution a-IST, a-IST1, a- Output of the actual state of the occupancy distribution IST2, a-ISTn c-PROG Calculating a predicted occupancy distribution a-PROG Output of a predicted occupancy distribution
Claims
PATENT CLAIMS 1. Procedure for outputting a predicted occupancy distribution (PB) in a public transport (OV) between two stops (H1, H2) with the following procedural steps: • Determination of empirical data, • Saving the experience data in a database (DB) of the staffing distribution forecasting system (BVPS), • Recording an actual state of the occupancy distribution (IB) in public transport (OV) between two stops (H1, H2) using a sensor unit (SE1) of an occupancy distribution forecasting system (BVPS), • Reading out experience data from a database (DB) of the staffing distribution forecasting system (BVPS), • Creating a forecast of the staffing distribution (PB1) from the recorded actual state and the experience data read from the memory by a control unit (C) of the staffing distribution forecasting system (BVPS), • Output of first data derived from the forecasted occupancy distribution (PB) on an output device (L, D) of the occupancy distribution forecasting system (BVPS).
2. Method for outputting a forecast occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to claim 1, characterized in that the empirical data are determined by the occupancy distribution forecasting system (BVPS).
3. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the empirical data are determined from experimentally recorded data.
4. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to claim 3, characterized in that the empirical data are determined by a sensor unit (SE1, SE2) of the occupancy distribution forecasting system (BVPS).
5. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to claim 4, characterized in that the sensor unit (SE1, SE2, SEn) is arranged in the public transport means (OV) and / or at a stop (H1, H2, Hn).
6. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the empirical data are determined at least one year, preferably one month, particularly preferably 14 days and especially preferably one week before the output of the predicted occupancy distribution (PB).
7. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the experience data include the occupancy and passenger behavior in the public transport (OV) and / or the stop (H1, H2, Hn).
8. Method for outputting a forecast occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the forecast of the occupancy distribution (PB1) is created from event data, wherein the event data are used to create the forecast of the occupancy distribution (PB) in order to select the empirical data used for creating the forecast of the occupancy distribution (PB).
9. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to claim 8, characterized in that the event data comprise time and location information.
10. Method for outputting a predicted occupancy distribution (PB) in a public transport vehicle (OV) between two stops (H1, H2) according to claim 9, characterized in that Time information including time of day, season, holidays, vacation times, weather forecasts, reservations.
11. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the forecast of the staffing distribution (PB1) is created from structural data.
12. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to claim 11, characterized in that the structural data comprise structural information of the stop (H1, H2, Hn) and / or the public transport means (OV).
13. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to claim 12, characterized in that the structural information comprises the architectural design and / or the spatial and / or space conditions of the stop (H1, H2, Hn) and / or the public transport means (OV).
14. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to claim 11 or 12, characterized in that the structural information comprises the functionality of the respective structure.
15. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the experience data, structural data and / or the event data are different for different stops (H1, H2, Hn).
16. Method for outputting a forecast occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the current passenger behavior (FV) in the public transport means (OV) or at the next stop (H2) is recorded, wherein the forecast of the occupancy distribution (PB) is created from the recorded actual state and the recorded current passenger behavior (FV).
17. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the analysis of the passenger behavior (FV) is carried out with regard to the preparatory actions for disembarking passengers (F).
18. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that Preparatory actions for passengers (F) to disembark from public transport (OV) include passengers (F) getting up from their seats, moving towards the exit of the public transport (OV) and / or stowing personal belongings.
19. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the analysis of the passenger behavior (FV) is carried out with the aid of AI / ML.
20. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the analysis of passenger behavior (FV) comprises the analysis of movement flows of persons and / or a distribution of persons at the next stop (H2).
21. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the analysis of the passenger behavior (FV) is carried out by a second sensor (S2).
22. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the second sensor (S2) is different from the first sensor (S1).
23. Method for outputting a predicted occupancy distribution (PB) in a public transport means (OV) between two stops (H1, H2) according to one or more of the preceding claims, characterized in that the second sensor (S2) is a camera for image capture.
24. Occupancy distribution forecasting system (BVPS) for a public transport (OV) with: • a first sensor unit (SE1) with a first sensor (S1), wherein the first sensor unit (SE1) is intended and suitable for counting passengers (F) in public transport (OV) and / or recording passenger behaviour (FV) in public transport (OV), • a second sensor unit (SE2) with a second sensor (S2), wherein the second sensor unit (SE2) is provided and suitable for counting passengers (F) at a stop (H1, H2) and / or detecting passenger behavior (FV) at a stop (H1, H2), • a control unit (C) which is provided and suitable for receiving the data from the first and second sensor units (SE1, SE2) and for creating a predicted occupancy distribution (PB) from the received data, • a database (DB) coupled to the control unit (C), wherein experience data, structural data and / or event data are stored in the database (DB), • an output device (A) for outputting data derived from the predicted occupancy distribution (PB).
25. Occupancy distribution forecasting system (BVPS) for a public transport (OV) according to claim 24, characterized in that the first sensor unit (SE1) has a further sensor (S1.2) which differs in its functionality from the first sensor (S1.1).
26. Occupancy distribution forecasting system (BVPS) for a public transport vehicle (OV) according to claim 24 or 25, characterized in that the first sensor unit (SE1) is arranged in the public transport vehicle (OV) and / or the second sensor unit (SE2) is arranged at the stop (H1, H2).
27. Occupancy distribution forecasting system (BVPS) for a public transport (OV) according to one or more of claims 24 to 26, characterized in that the first sensor (S1.1, S1.2) is different in its functionality from the second sensor (S2.1).
28. Occupancy distribution forecasting system (BVPS) for a public transport (OV) according to claim 27, characterized in that the first sensor (S1.1) is provided and suitable for counting passengers (F) and / or the further first sensor (S1.2) is provided and suitable for determining the passenger behavior (FV).
29. Occupancy distribution forecasting system (BVPS) for a public transport (OV) according to one or more of claims 24 to 28, characterized in that the control unit (C) is coupled to the first sensor unit (SE1), to the second sensor unit (SE2), to the database (DB) and to the output unit (A).
30. Occupancy distribution forecasting system (BVPS) for a public transport (OV) according to one or more of claims 24 to 29, characterized in that the evaluation of the data acquired by the second sensor (S2) is carried out with AI / ML support.
Citation Information
Patent Citations
traffic control system
DE102004040057A1
Passenger number forecasting method for use in passenger number polling telecontinuous system, involves receiving stopping point from user and actual position of public transportation over wireless network
DE102011087039A1
procedures for directing passengers on public transport
DE102014215857A1
Device and method for determining the usage behavior of a passenger when using public transport
DE102020110964A1
Passenger guidance system and procedures for guiding passengers
DE102021001388A1
