EP3841537A1 - Procédé et système de prédiction quasi temps réel d'au moins un indicateur de fonctionnement d'un réseau de transport de passagers - Google Patents
Procédé et système de prédiction quasi temps réel d'au moins un indicateur de fonctionnement d'un réseau de transport de passagersInfo
- Publication number
- EP3841537A1 EP3841537A1 EP19755932.1A EP19755932A EP3841537A1 EP 3841537 A1 EP3841537 A1 EP 3841537A1 EP 19755932 A EP19755932 A EP 19755932A EP 3841537 A1 EP3841537 A1 EP 3841537A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- network
- time interval
- indicator
- transport network
- transport
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 61
- 239000000203 mixture Substances 0.000 claims abstract description 21
- 230000006870 function Effects 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000001105 regulatory effect Effects 0.000 claims description 7
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000002123 temporal effect Effects 0.000 description 3
- 241001328813 Methles Species 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000029305 taxis Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G06Q50/40—
Definitions
- the present invention relates to a method and a system for near real-time prediction of at least one operating indicator of a passenger transport network, as well as an associated transport network.
- the invention relates to the field of passenger transport, in particular urban transport, in the context of a rail network of the urban metro type, for regulating the flow of passengers in the network.
- Such a passenger transport network is characterized by a set of stations and a set of lines, a line being defined by the set of stations served by a transport vehicle.
- such a transport network includes a set of platforms for loading and / or unloading passengers, for example metro platforms.
- Such a network has its own topology, certain stations comprising several such platforms and being served by several lines of the network.
- each station is equipped with gantries, and each user is provided with a card allowing access to the network and having a unique associated identifier, at least between their entry on the network and its exit.
- the gantries are equipped with sensors adapted to read data from the card, which is for example provided with a chip and with data communication means.
- the transport network is equipped with a system making it possible to record, in connection with an identifier, an entry time on the network and an associated entry station, as well as an exit time and a station. associated output.
- the transport network having a given topology has operating parameters, including in particular the frequency of circulation of vehicles on each line, which generally varies as a function of parameters such as time slots, the type of vehicle used, the the taxes.
- the invention proposes a method for predicting at least one operating indicator of a passenger transport network, the network comprising a set of stations, each station comprising at least one loading and / or unloading platform. of passengers in a network transport vehicle, the network being equipped with a system making it possible to record, in association with an identifier, network input / output data, the method comprising a step a), prior to a current time instant, for collecting and storing input / output data of actual paths carried out during a past observation window, preceding the current time instant.
- This method comprises, for at least a first time interval included in said observation window, steps of: b) application of an estimation algorithm, on the basis of said data collected during said first time interval, of at least one operating indicator of the transport network estimated during said first time interval,
- the invention makes it possible to predict one or more operating indicators in the near future relative to the current time instant, with improved precision. Taking these indicators into account, by the transport network operator and / or by passengers, helps to regulate passenger flows and, in particular, to reduce overloads.
- the method of predicting at least one operating indicator of a passenger transport network according to the invention may also have one or more of the characteristics below, taken independently or according to any technically conceivable combination.
- the transport network operation indicator is chosen from an average waiting time for each network platform, an average load in number of passengers waiting on a network platform, an average load, in number of passengers, per vehicle transport.
- Steps b) to e) are repeated with a predetermined time frequency.
- the plurality of machine learning algorithms includes decision methods based on decision tree forests and gradient regression methods.
- Step c) of implementing a plurality of machine learning algorithms comprises implementing the same machine learning algorithm with several different subsets of input / output data, collected during time observation sub-windows of different durations.
- the method further comprises a prior step of learning parameters for each automatic learning algorithm, using data over at least one long learning period, of duration greater than one month.
- the invention relates to a method for regulating the flow of a passenger transport network, the network comprising a set of stations, each station comprising at least one platform for loading and / or unloading passengers in a vehicle.
- network transport the network being equipped with a system making it possible to record, in association with an identifier, network input / output data, the network further comprising one of the electronic equipment and a center for supervision and calculation adapted to communicate with said equipment.
- This flow regulation method comprises, at a current time instant:
- the use step comprises steps of:
- the step of use comprises a publication of said at least one operating indicator intended for user equipment adapted to communicate wirelessly.
- the invention relates to a system for predicting at least one operating indicator of a passenger transport network, the network comprising a set of stations, each station comprising at least one loading platform and / or unloading of passengers in a network transport vehicle, the network being equipped with a system making it possible to record, in association with an identifier, network input / output data, the system comprising a module for collecting and storing input / output data of actual paths carried out during a past observation window, preceding a current time instant.
- This system comprises at least one calculation processor adapted to be implemented, for at least one first time interval included in said observation window:
- an application module of an estimation algorithm from said data collected during said first time interval, of at least one indicator of operation of the transport network estimated during said first time interval,
- a module for implementing a plurality of automatic learning algorithms for calculating, for each automatic learning algorithm, from at least a subset of the data collected during said observation window and before said first time interval, at least one indicator of operation of the transport network predicted for said first time interval,
- a module for implementing said weighted mixture of relevant machine learning algorithms determined to calculate at least one operating indicator predicted associated with each second time interval.
- the invention relates to an information recording medium, on which software instructions are stored for the execution of a method for predicting at least one parameter characterizing the operation of a transport network. passengers as briefly described above, when these instructions are executed by a programmable device.
- the invention relates to a computer program comprising software instructions which, when implemented by a programmable device, implement a method for predicting at least one parameter characterizing the operation of a passenger transport network as briefly described above.
- FIG. 1 is a schematic representation of a transport network according to one embodiment
- FIG. 2 is a diagram illustrating the topology of a part of a transport network in which the invention is applicable;
- FIG. 3 is a flow diagram of the main steps of a method for predicting at least one operating indicator of a transport network according to one embodiment
- FIG. 4 is a flowchart of an embodiment of a flow control method in a passenger transport network according to one embodiment.
- the invention will be described below in its application in an urban transport network R, for example a metro network.
- a transport network comprises a set of stations and a set of lines, a line being defined by the set of stations served by vehicles, for example trains in the case of a metro network.
- a transport network includes a set of platforms for loading and / or unloading passengers, for example metro platforms.
- Such a network has its own topology, certain stations comprising several such platforms and being served by several lines of the network.
- Each station has an associated geographic location, for example indicated by coordinates in a geolocation reference system such as GPS coordinates.
- each platform has associated geolocation coordinates.
- FIG. 1 schematically represents connected elements of a transport network R in which the invention applies.
- the transport network R comprises a supervision and calculation center 2, comprising programmable electronic devices 4 adapted to perform various calculations and control various pieces of equipment of the network remotely, insofar as these equipment is equipped with command receivers, for example by a radio communication system.
- a programmable electronic device 4 is mentioned, it being understood that the reference 4 may also designate, as a variant, a plurality of interconnected programmable electronic devices.
- the computing and processing center 2 also includes electronic information storage units 6, adapted to store a large volume of data.
- the transport network R comprises electronic equipment, for example each station is equipped with a set 8 of electronic gantries 8A to 8D, and each user is provided with a card allowing access to the network and having an identifier single associate, at least between its entry into the network and its exit.
- the electronic gantries 8A to 8D are equipped with sensors suitable for reading data from the card, which is for example provided with a chip and with data communication means.
- the transport network R is equipped with a system making it possible to record, in connection with a card identifier, an entry time on the network and an associated entry station, as well as an exit time and an associated exit station.
- the electronic gates are suitable for transmitting the input / output data recorded to the supervision and calculation center 2.
- This input / output data is stored for example in the information storage units 6.
- the set 10 of transport vehicles comprises trains adapted to communicate with the supervision and calculation center 2, and to receive control orders, for example by means of radio transmitters / receivers.
- the network R includes equipment 12 facilitating mobility, for example escalators 12A, treadmills 12B or elevators 12C.
- equipment 12 facilitating mobility, for example escalators 12A, treadmills 12B or elevators 12C.
- at least part of the equipment 12 is adapted to receive commands from the supervision and calculation center 2, for example for adjusting the operating speed or stopping the escalators and treadmills.
- the network R also includes electronic equipment 14 such as display panels, distributed in stations or on platforms, making it possible to display various information relating to the operation of the network.
- electronic equipment 14 such as display panels, distributed in stations or on platforms, making it possible to display various information relating to the operation of the network.
- the supervision and computing center 2 is adapted to receive complementary information 16 from remote communication systems, for example planning or maintenance information useful for the operation of the various elements of the network R.
- the programmable electronic device 4 of the supervision and calculation center 2 is adapted to implement a method for predicting at least one indicator of network operation according to the invention, and, if necessary, a modification of the parameters of network operation according to predicted indicators to perform flow regulation in the network.
- the network performance indicators are predicted, for a future time interval, subsequent to a current time instant.
- a network performance indicator associated with a given time interval is for example the average waiting time for at least one network platform for said time interval, or an average load in number of passengers waiting on a network platform during the 'time interval or the average load of passenger vehicles on a given line during the time interval or the average number of trains missed due to overload by a passenger, on a given platform, during the time interval considered.
- a network operating parameter is for example a display on the display panels 14, the frequency of the trains on a given line, the load capacity of the trains (for example the number of trains), the operating speed of the equipment 12 , an operating mode of the electronic access gates 8 (for example blocked or slow operation or fast operation).
- the programmable electronic device 4 comprises a processor 20 capable of implementing:
- a module 22 for collecting and storing input / output data of actual paths during a past observation window, preceding the current time instant, said past observation window having a start instant distant from the current time instant of a duration less than or equal to a first predetermined threshold,
- a module 26 for implementing a plurality of automatic learning algorithms for calculating, for each automatic learning algorithm, from at least a subset of the data collected during said observation window and before said first time interval, at least one indicator of operation of the transport network predicted for the first time interval,
- the programmable electronic device 4 also includes a module 32 for calculating operating parameters to be modified as a function of the predicted operating indicator or indicators and for transmitting parameters, or commands allowing these parameters to be modified, to the equipment concerned.
- these modules 22 to 32 are produced in the form of computer program instructions, executable by the programmable device. Alternatively, they are produced by programmable logic components, or in the form of dedicated integrated circuits (or ASICs).
- the supervision and calculation center 2 allows the transmission of predicted operating indicators to user equipment 18A ... 18C, for example smartphones or any other equipment suitable for receiving wireless communications, so as to warn network users / passengers of possible network congestion.
- This allows an indirect flow regulation, the passengers receiving for example a congestion alert being then able to modify their route (route or timetable for example).
- FIG. 2 is a simplified schematic example of the topology of a part of the transport network R comprising lines L 1; L 2 and L 3 , and stations A, B, C and D, as well as other stations, represented by nodes and not referenced in FIG. 2.
- a route between a departure station A and an arrival station B is defined by a set of lines and connections making it possible to connect A and B.
- An input datum includes an input station on the network, for example a station A, as well as a date and time of entry into the station, denoted T A , in relation to an identifier Id.
- An output datum includes an exit station from the network, for example a station B, as well as a date and time of exit from station B, denoted T B , in relation to an identifier Id.
- the line connects stations A and B in six stops along a first route.
- FIG. 3 is a block diagram of the main steps of a method for predicting the indicator (s) of operation of a transport network according to an embodiment of the invention.
- the method comprises a first step 40 of obtaining data 38, either from memories 6, or from a communication interface with a remote server or with an input / output interface of the programmable electronic device implementing the process.
- the data includes input / output data of actual journeys made during a past observation window.
- the past observation window is determined with respect to a current time instant T c of application of the method.
- the observation window is a window of several tens of minutes to several hours preceding the current instant T c .
- the observation window includes a full day. In a variant, the observation window starts at the start of the current day.
- the past observation window considered is located in the near past relative to the current time instant.
- the time instant at the start of the observation window precedes the current time instant by a duration less than or equal to a threshold, for example 15 minutes.
- the data received 38 also include information on the transport network R, the lines, the stations for example: -GPS coordinates of stations and / or platforms;
- the data 38 is collected and stored in step 40, which is followed by a step 42 of applying an algorithm for estimating at least one operating indicator of the transport network estimated during a first time interval.
- the first time interval is included in the past observation window, and it is defined by a starting time instant Tu and an ending time instant T 12 .
- the first time interval is of the order of 15 minutes.
- the estimated operating indicator is the average waiting time for each platform of each station on the network during the first time interval.
- the calculation algorithm used is the algorithm described in patent application FR1700181, which has good calculational efficiency.
- This transport network operation indicator estimation algorithm comprises a preliminary step of calculation and recording, for each pair of stations of the network, of at least one path chosen between the two stations of the pair of stations, in static data function characterizing the transport network. It then includes, for each input / output data obtained for the first time interval considered:
- a calculation of at least one indicator characterizing the operation of the network comprising the calculation of an average waiting time for each platform of the network during the first time interval by implementing an iterative algorithm implementing, each iteration:
- the waiting time during the first time interval for each platform on the network is updated at each iteration.
- a first indicator of the operation of the estimated network is obtained, associated with the first time interval, which is the average waiting time per platform, and optionally, other estimated operating indicators, eg load. average per platform or per vehicle are also calculated.
- Step 42 is followed by a step 44 of implementing a plurality of machine learning algorithms to calculate at least one predictor of operation of the transport network predicted for said first time interval.
- a predicted indicator is calculated from at least a subset of the data collected during said observation window and before said first time interval, and from estimated operating indicator values, by example according to the estimation algorithm previously described with reference to step 42, for time intervals included in the observation window and prior to the first time interval.
- the automatic learning algorithms are parameterized by learning parameters, which are obtained during a prior learning step 43, and which are stored.
- the learning step 43 conventionally uses very large volumes of data and requires a lot of calculations. It is performed with a low temporal frequency, for example several months apart, on large volumes of data collected during a long learning period. For example, the learning period is between 1 and 36 months, and preferably equal to 14 months so as to take seasonality into account.
- the training data includes, over the learning period, values of the indicator of the operation of the transport network by platform estimated by an estimation algorithm, by time intervals, for example 15 minutes, the number input / output by station and by time slot, calendar information (for example weekends and holidays).
- the learning parameters calculated for each of the automatic learning algorithms are stored.
- the machine learning algorithms used include on the one hand the prediction method based on forests of decision trees (in English “random forest classifiers"), and on the other hand the method called “gradient boosting” .
- a first Methl machine learning algorithm using forests of decision trees is applied on N different data sets, N being a positive integer greater than or equal to 2 and therefore N results of prediction of operating indicators are obtained.
- the datasets differ by the time observation pane chosen, for example: 15 minutes, 30 minutes, 1 hour, 1 hour and 30 minutes, 2 hours, before the first time interval considered.
- Each dataset is a subset of the data collected in step 40.
- a second machine learning algorithm Meth2 using the “gradient boosting” is applied to M different data sets, M being a positive integer greater than or equal to 2 and therefore M results of prediction of operating indicators are obtained.
- the data sets differ by the temporal observation pane chosen, for example: 15 minutes, 30 minutes, 1 hour, 1 hour and 30 minutes, 2 hours , before the first time interval considered.
- step 44 several sets of predicted operating indicators are obtained for the first time interval considered, each set of predicted indicators being associated with a machine learning algorithm and with a sub-window d 'time observation.
- each set of predicted operating indicators comprises a single predicted operating indicator, for example the predicted average waiting time for the first time interval by platform of the transport network.
- step 46 a step of determining a weighted mixture of machine learning algorithms (in English "Mixture Model"), the most relevant at the current time instant, is implemented among the methods tested.
- relevance refers to predictive efficiency, so it is a weighted mixture of machine learning algorithms that allows you to predict a performance indicator closest to the estimated performance indicator.
- the weighted mixture of learning algorithms provides an aggregated machine learning algorithm that is performing at the current time, for the selected operating indicator.
- step 46 implements a weighting optimization loop defining the weighted mixture of machine learning algorithms.
- the weighted mixture of machine learning algorithms relevant to the current instant determined in step 46 is then used in step 48 to predict a set of network performance indicators ⁇ IFi IF K ⁇ for a second time interval , which is a future time interval, having a start time posterior or equal to the current time instant.
- the second time interval is defined by a start time T 21 and an end time T 22 , with T 21 equal to the current time instant T c and T 22 equal to the current time instant T c plus 15 minutes.
- the set of operating indicators predicts ⁇ IF ! , .., IF K ⁇ can be limited, for example, to a predicted average waiting time ⁇ F ⁇ for the second future time interval, for each platform on the network.
- a series of predicted operating indicators is determined for successive second time intervals. For example, a series of predicted operating indicators is determined in quarter-hour increments for the 3 hours following the current time instant.
- the method uses a weighted mixture of several machine learning algorithms, trained on different a subset of the data collected in the past, the weighting associated with this weighted mixture being learned in real time.
- step 52 in connection with a clock not shown, new first and second time intervals are selected, with respect to a future time instant.
- steps 40 to 48 are iterated.
- steps 40 to 48 are iterated with a fast time frequency, for example every quarter of an hour.
- a fast time frequency for example every quarter of an hour.
- the weighted mixing of the machine learning algorithms relevant to the current time instant is adaptive and is carried out dynamically, almost in real time.
- the predicted operating indicators ⁇ IFi IF K ⁇ are updated with this rapid repetition time frequency, therefore almost in real time.
- Figure 4 is a block diagram of the main steps of a flow control method in a passenger transport network according to one embodiment, using a method for predicting network operation indicator (s) as described above.
- the method comprises a first step 60 of predicting operating indicators over a future time interval relative to the current time instant.
- step 60 The method described above is implemented in step 60.
- the predicted operating indicators are published, for example via a dedicated application, to user equipment, for example smartphones, thus allowing users / passengers to be informed almost in real time of the operation of the network at forecast during the second time interval, that is to say in the near future, in particular the average waiting time, the load on platforms and vehicles.
- These predicted operating indicators can then be used directly by the users, or can be used by intermediate applications, for example to calculate an optimized journey in time or in comfort between a station A and a station B of the network.
- step 64 implemented substantially in parallel with step 62, the predicted operating indicators are used in calculations to calculate the desired network operating parameters during the associated time interval.
- the operating speed of escalators 12A, treadmills 12B or electronic gantries 8A to 8D is calculated, to avoid opening access to a given platform for which an overload has been predicted for too large a number of passengers .
- the capacity of trains for certain lines or the frequency of circulation is increased.
- the capacity of the trains for certain lines or the frequency of circulation is reduced, and for example certain treadmills or escalators are stopped. Consequently, advantageously, the consumption of electrical energy is reduced.
- the flow of passengers in the network will be regulated.
- the operating parameters calculated in step 64 are transmitted, possibly in the form of commands to be applied, to various electronic devices of the network in step 66, for example to devices 12 facilitating mobility in the network.
- the calculated operating parameters are then applied by the electronic equipment concerned in step 68.
- the invention makes it possible to improve the regulation of the flow of passengers, and therefore to optimize the use of resources (eg electricity), prevent wear and tear on equipment and, in the event of an anticipated overload, improve passenger safety and comfort.
- resources eg electricity
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR1800906A FR3085218B1 (fr) | 2018-08-24 | 2018-08-24 | Procede et systeme de prediction quasi temps reel d'au moins un indicateur de fonctionnement d'un reseau de transport de passagers |
PCT/EP2019/072567 WO2020039061A1 (fr) | 2018-08-24 | 2019-08-23 | Procédé et système de prédiction quasi temps réel d'au moins un indicateur de fonctionnement d'un réseau de transport de passagers |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3841537A1 true EP3841537A1 (fr) | 2021-06-30 |
Family
ID=65200863
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP19755932.1A Withdrawn EP3841537A1 (fr) | 2018-08-24 | 2019-08-23 | Procédé et système de prédiction quasi temps réel d'au moins un indicateur de fonctionnement d'un réseau de transport de passagers |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP3841537A1 (fr) |
FR (1) | FR3085218B1 (fr) |
SG (1) | SG11202101931YA (fr) |
WO (1) | WO2020039061A1 (fr) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112949939B (zh) * | 2021-03-30 | 2022-12-06 | 福州市电子信息集团有限公司 | 基于随机森林模型的出租车载客热点预测方法 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2014214533A1 (en) * | 2013-02-06 | 2015-09-24 | University Of Technology, Sydney | Computer-implemented system for influencing commuter behaviour |
WO2014121329A1 (fr) * | 2013-02-06 | 2014-08-14 | University Of Technology, Sydney | Système mis en œuvre par ordinateur pour influencer une foule |
CN104952240A (zh) * | 2014-03-24 | 2015-09-30 | 中国移动通信集团公司 | 获取公交位置信息及公交到站时间的方法、装置及系统 |
-
2018
- 2018-08-24 FR FR1800906A patent/FR3085218B1/fr active Active
-
2019
- 2019-08-23 EP EP19755932.1A patent/EP3841537A1/fr not_active Withdrawn
- 2019-08-23 SG SG11202101931YA patent/SG11202101931YA/en unknown
- 2019-08-23 WO PCT/EP2019/072567 patent/WO2020039061A1/fr unknown
Also Published As
Publication number | Publication date |
---|---|
WO2020039061A1 (fr) | 2020-02-27 |
FR3085218A1 (fr) | 2020-02-28 |
SG11202101931YA (en) | 2021-03-30 |
FR3085218B1 (fr) | 2022-04-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111966729B (zh) | 一种车辆轨迹数据处理方法、装置、设备及存储介质 | |
US10551842B2 (en) | Real-time vehicle state trajectory prediction for vehicle energy management and autonomous drive | |
US20220326025A1 (en) | Technologies for route navigation sharing in a community cloud | |
US20190339087A1 (en) | Deep reinforcement learning for optimizing carpooling policies | |
US11248920B1 (en) | Systems and methods for assessment of rideshare trip | |
US11301948B2 (en) | Parking continuity with unused duration between automated vehicles | |
CA2937414A1 (fr) | Procede et systeme de reequilibrage d'une installation d'utilisation partagee de vehicules, installation mettant en oeuvre un tel procede et/ou systeme | |
US9959339B2 (en) | Journey time estimation | |
JP6939911B2 (ja) | 適応的に車両を制御する方法及び装置 | |
US20200201357A1 (en) | Systems and methods for vehicle scheduling and routing | |
US11285961B2 (en) | Predictive car wash services for a vehicle based on anticipated routes of travel | |
CN112435469B (zh) | 车辆预警控制方法、装置、计算机可读介质及电子设备 | |
FR3010238A1 (fr) | Procede de regeneration electrique d'un accumulateur d'energie | |
JP2020524342A (ja) | 輸送事業者の効率を最適化するための方法及び装置 | |
EP3841537A1 (fr) | Procédé et système de prédiction quasi temps réel d'au moins un indicateur de fonctionnement d'un réseau de transport de passagers | |
EP4020368A1 (fr) | Collaboration avec les opérateurs de transport pour améliorer l'expérience de l'utilisateur et l'efficacité opérationnelle | |
US20190340315A1 (en) | Method and device for providing vehicle navigation simulation environment | |
CN111667083B (zh) | 网约车预估价确定方法和装置 | |
WO2023094602A1 (fr) | Procédé et système de supervision automatisée de l'affluence de passagers à court terme dans un réseau de transport | |
US20220110021A1 (en) | Flow forecasting for mobile users in cellular networks | |
CN112101677B (zh) | 一种公共交通出行路径规划方法、装置、设备及存储介质 | |
EP3586302A1 (fr) | Procédé d'estimation d'au moins un indicateur caractérisant le fonctionnement d'un réseau de transport de passagers et procédé de modification d'au moins un paramètre de fonctionnement de réseau de transport associé | |
CN113269339A (zh) | 一种网约车任务自动创建和分发的方法及系统 | |
EP2803550A1 (fr) | Dispositif et procédé de régulation de la vitesse d'un équipement de transport | |
US20240140239A1 (en) | Management of vehicle-related services based on demand and profitability |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20210222 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40045246 Country of ref document: HK |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20220408 |
|
P01 | Opt-out of the competence of the unified patent court (upc) registered |
Effective date: 20230524 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
18D | Application deemed to be withdrawn |
Effective date: 20230721 |