WO2020098079A1 - 预测通行时长的方法和系统 - Google Patents

预测通行时长的方法和系统 Download PDF

Info

Publication number
WO2020098079A1
WO2020098079A1 PCT/CN2018/123291 CN2018123291W WO2020098079A1 WO 2020098079 A1 WO2020098079 A1 WO 2020098079A1 CN 2018123291 W CN2018123291 W CN 2018123291W WO 2020098079 A1 WO2020098079 A1 WO 2020098079A1
Authority
WO
WIPO (PCT)
Prior art keywords
traffic signal
stage
intersection
traffic
segment
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.)
Ceased
Application number
PCT/CN2018/123291
Other languages
English (en)
French (fr)
Inventor
伊峰
孙伟力
朱金清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Didi Infinity Technology and Development Co Ltd
Original Assignee
Beijing Didi Infinity Technology and Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Didi Infinity Technology and Development Co Ltd filed Critical Beijing Didi Infinity Technology and Development Co Ltd
Publication of WO2020098079A1 publication Critical patent/WO2020098079A1/zh
Priority to US17/226,110 priority Critical patent/US20210241613A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/056—Detecting movement of traffic to be counted or controlled with provision for distinguishing direction of travel
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096733—Systems involving transmission of highway information, e.g. weather, speed limits where a selection of the information might take place
    • G08G1/096741—Systems involving transmission of highway information, e.g. weather, speed limits where a selection of the information might take place where the source of the transmitted information selects which information to transmit to each vehicle
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
    • G08G1/096783—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a roadside individual element
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/097—Supervising of traffic control systems, e.g. by giving an alarm if two crossing streets have green light simultaneously

Definitions

  • the present application relates to data processing, and in particular to a method and system for predicting the duration of travel.
  • An aspect of the present application provides a method for predicting the duration of travel, and the method may include at least one of the following operations.
  • the stage at which the first traffic signal light is at when the object enters the intersection of the first traffic signal light can be determined.
  • the duration of the object passing through the sub-segment may be predicted based at least on the stage where the first traffic signal is.
  • a traffic signal cycle includes at least two stages, and the sub-segment includes the first traffic signal intersection.
  • the stage where the first traffic signal light is located when the object enters the intersection of the first traffic signal light includes at least one of the following operations.
  • the initial time when the object moves on the sub-segment and the period of the first traffic signal can be obtained.
  • the stage at which the first traffic signal light is located when the object enters the intersection of the first traffic signal light may be determined based at least on the initial time and the period of the first traffic signal light.
  • the starting point of the sub-segment is the first traffic signal intersection
  • the initial time is the time when the object enters the first traffic signal intersection
  • the sub-segment further includes a second traffic signal intersection
  • the predicting the length of time the object passes through the sub-segment based on at least the stage at which the first traffic signal is located may include at least one of the following operations.
  • the stage of the second traffic signal when the object passes the intersection of the second traffic signal may be predicted based on the stage of the first traffic signal; may be based at least on the stage of the first traffic signal And the stage where the second traffic signal is at, predicting the length of time the object passes through the sub-segment.
  • one traffic signal cycle includes at least a red light stage and a green light stage; the method may further include at least one of the following operations.
  • the second traffic signal is in a red light stage, and a prompt message may be sent, where the prompt information includes that the second traffic signal is in a red light stage.
  • the predicting the stage of the second traffic signal when the object passes the intersection of the second traffic signal based on the stage of the first traffic signal may include at least one of the following operations.
  • the second traffic can be predicted when the object passes through the intersection of the second traffic signal based on the stage where the first traffic signal is located and the traffic signal rules for setting the first traffic signal and the second traffic signal The stage of the semaphore.
  • one traffic signal cycle includes at least a red light stage and a green light stage, and the green light stage includes at least an early green light stage and a late green light stage.
  • the method may further include at least one of the following operations.
  • the first traffic signal is in the initial stage of the green light, and it can be predicted that the second traffic signal is in the green stage when the object passes the second traffic signal intersection.
  • the first traffic signal is in the later stage of green light, and it can be predicted that the second traffic signal is in the red stage when the object passes the second traffic signal intersection.
  • the method may further include at least one of the following operations.
  • the traffic state information of the sub-segment may be obtained; the traffic state information includes at least one of the following: traffic congestion information, historical object trajectory data of the sub-segment, or the moving speed of the object.
  • the length of time that the object passes through the sub-segment may be predicted based at least on the stage where the first traffic signal is located and the traffic state information.
  • the method may further include at least one of the following operations.
  • the historical traffic state information passing through a total road segment can be obtained; the historical traffic state information includes at least one of the following: historical traffic congestion information, historical object trajectory data, traffic signal period, historical movement speed of objects, and objects passing The historical travel time of the road segment; the total road segment includes at least one sub-segment, and each sub-segment includes at least one traffic signal intersection.
  • the traffic duration prediction model can be determined based on the historical traffic state information.
  • the transit time of the object through the total road segment may be predicted based at least on the stage at which the traffic signal light is located when the object passes through each sub-segment and the traffic duration prediction model.
  • the method may further include at least one of the following operations. Based at least on the transit time of the object passing through the total road segment, the transit time prediction model is dynamically updated.
  • the method may further include at least one of the following operations.
  • the candidate movement trajectory of the object can be obtained.
  • the sub-segment may be selected from the candidate movement trajectories based on the current movement trajectory of the object.
  • the method may further include at least one of the following operations.
  • the total road segment may be divided into a plurality of sub-segments, and at least one sub-segment of the plurality of sub-segments includes at least one traffic signal intersection.
  • the travel time of the total road segment may be predicted based on the travel time of each sub-road segment.
  • the method may further include at least one of the following operations.
  • the total duration of the total road segment can be dynamically updated.
  • the system includes a determination module and a prediction module.
  • the determination module is used to determine the stage of the first traffic signal when the object enters the intersection of the first traffic signal.
  • the prediction module is used to predict the length of time the object passes through the sub-segment based at least on the stage where the first traffic signal is.
  • a traffic signal cycle includes at least two stages, and the sub-segment includes the first traffic signal intersection.
  • the system further includes an acquisition module for acquiring an initial time at which the object moves on the sub-segment and the period of the first traffic signal.
  • the determination module is further configured to determine the stage of the first traffic signal when the object enters the intersection of the first traffic signal based at least on the initial time and the period of the first traffic signal.
  • the starting point of the sub-segment is the first traffic signal intersection
  • the initial time is the time when the object enters the first traffic signal intersection
  • the sub-segment further includes a second traffic signal intersection; the prediction module is further configured to predict when the object passes the second traffic signal intersection based on the stage where the first traffic signal is located The stage of the second traffic signal. The prediction module is further configured to predict the length of time that the object passes through the sub-segment based on at least the stage where the first traffic signal is located and the stage where the second traffic signal is located.
  • the prediction module is further used to predict the passage of the object based on the stage of the first traffic signal and the traffic signal rules for setting the first traffic signal and the second traffic signal The stage at which the second traffic signal is at the intersection of the second traffic signal.
  • one traffic signal cycle includes at least a red light phase and a green light phase.
  • the system further includes a sending module configured to send prompt information when the object is predicted to pass through the second traffic signal intersection and the second traffic signal is in a red light stage, the prompt information includes the The second traffic signal is at the red light stage.
  • one traffic signal cycle includes at least a red light stage and a green light stage, and the green light stage includes at least an early green light stage and a late green light stage.
  • the prediction module is further configured to predict that the second traffic signal is at a green light when the object enters the first traffic signal intersection when the first traffic signal is at an early stage of green light Stage; when the object enters the first traffic signal intersection when the first traffic signal is in the late green stage, it is predicted that the second traffic signal is in the red light stage when the object passes the second traffic signal intersection.
  • the obtaining module is further configured to obtain traffic state information of the sub-segment; the traffic state information includes at least one of the following: traffic congestion information, historical object trajectory data of the sub-segment, or all Describe the moving speed of the object.
  • the prediction module is further configured to predict the length of time that the object passes through the sub-segment based on at least the stage where the first traffic signal is located and the traffic state information.
  • the system further includes a training module.
  • the training module is used to determine a traffic duration prediction model.
  • the determination method may include at least one of the following operations.
  • the historical traffic state information through a total road segment can be obtained; the historical traffic state information includes at least one of the following: traffic congestion information, historical object trajectory data of the total road segment, traffic signal period, and moving speed of objects;
  • the total road segment includes at least one sub-segment, and each sub-segment includes at least one traffic signal intersection.
  • the traffic duration prediction model can be determined based on the historical traffic state information.
  • the prediction module is also used to predict the transit time of the object passing through each sub-segment based at least on the stage of the traffic signal when the object passes each sub-segment and the traffic duration prediction model.
  • the training module is further configured to dynamically update the transit time prediction model based on the transit time of the object through the total road segment.
  • the obtaining module is further configured to obtain a candidate movement trajectory of the object, and select the sub-segment from the candidate movement trajectory based on the current movement trajectory of the object.
  • the obtaining module is further configured to divide the total road segment into a plurality of sub-segments, and at least one sub-segment of the plurality of sub-segments includes at least one traffic signal intersection.
  • the prediction module is further used for predicting the duration of the total road segment based on the duration of each sub-road segment.
  • the prediction module is also used to dynamically update the duration of the total road segment.
  • Another aspect of the present application provides a computer-readable storage medium that stores instructions that perform at least one of the following operations when the instructions are executed. It is possible to determine the stage of the first traffic signal when the object enters the intersection of the first traffic signal. The duration of the object passing through the sub-segment may be predicted based at least on the stage where the first traffic signal is. Wherein, a traffic signal cycle includes at least two stages, and the sub-segment includes the first traffic signal intersection.
  • the apparatus includes a processor, and the processing performs at least one of the following operations when the processing runs.
  • the stage at which the first traffic signal light is at when the object enters the intersection of the first traffic signal light can be determined.
  • the duration of the object passing through the sub-segment may be predicted based at least on the stage where the first traffic signal is.
  • a traffic signal cycle includes at least two stages, and the sub-segment includes the first traffic signal intersection.
  • FIG. 1 is a schematic diagram of an exemplary application scenario for predicting a transit duration according to some embodiments of the present application
  • FIG. 2 is a schematic diagram of exemplary hardware components and / or software components of an exemplary computing device according to some embodiments of the present application;
  • FIG. 3 is a functional block diagram of an exemplary system for predicting the passage duration according to some embodiments of the present application
  • FIG. 4 is an exemplary flowchart of a method for predicting a passing time according to some embodiments of the present application
  • FIG. 5 is an exemplary flowchart of a method for predicting a passing time according to some embodiments of the present application
  • FIG. 6 is an exemplary object movement trajectory diagram according to some embodiments of the present application.
  • a flow chart is used in this application to illustrate operations performed by the system according to an embodiment of the application. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the various steps can be processed in reverse order or simultaneously. At the same time, you can also add other operations to these processes, or remove a certain step or several steps from these processes.
  • FIG. 1 is a schematic diagram of an exemplary application scenario for predicting a passage duration according to some embodiments of the present application.
  • the exemplary application scenario 100 may include a server 110, a network 120, a traffic signal 130, an object 140, and a storage 150.
  • the server 110 may be used as a system for analyzing and processing the collected information to generate analysis results.
  • the server 110 may analyze the stage (for example, the red light stage and the green light stage) of the traffic light 130 (for example, the traffic light 130-1) when the object 140 enters the previous traffic light intersection, and predict that the object 140 enters The stage at which the traffic signal 130 (eg, traffic signal 130-2) is at the next traffic signal intersection.
  • the server 110 may analyze traffic congestion information of the road, historical object trajectory data (eg, historical vehicle trajectory data), the moving speed of the object 140, the stage of the traffic signal 130 when the object 140 enters the intersection of the traffic signal, etc.
  • the server 110 may be a server or a server group.
  • the server group may be centralized, such as a data center.
  • the server group may also be distributed, for example, a distributed system.
  • the server 110 may be local or remote.
  • the server 110 may include an engine 112.
  • the engine 112 can be used to execute the instructions (program code) of the server 110.
  • the engine 112 can execute the instruction of the program for predicting the duration of travel, and then predict the length of time that the object 140 passes a specific road segment at a specific time.
  • the predicted transit duration program may be stored in a computer-readable storage medium (for example, the memory 150) in the form of computer instructions.
  • the network 120 may provide a channel for information exchange.
  • the server 110, the traffic signal 130, the object 140, and / or the storage 150 may exchange information through the network 120.
  • the server 110 may obtain the geographic location of the traffic signal 130, the stage at a specific time, etc. through the network 120.
  • the server 110 may obtain the geographic location, moving speed, and the like of the object 140 through the network 120.
  • the server 110 may acquire information from the storage 150 through the network 120 (for example, the geographic location of the traffic signal 130 and the trajectory data of historical objects).
  • the network 120 may be a single network or a combination of multiple networks.
  • the network 120 may include, but is not limited to, one or a combination of a local area network, a wide area network, a public network, a private network, a wireless local area network, a virtual network, a metropolitan area network, and a public switched telephone network.
  • the network 120 may include various network access points, such as a wired or wireless access point, a base station (such as 120-1, 120-2), or a network switching point, through which the data source is connected to the network 120 and sent through the network information.
  • the traffic signal light 130 refers to a traffic signal light (or traffic light) installed at a road or an intersection.
  • the traffic signal 130 may include multiple phases.
  • the traffic signal light 130 may include three phases, namely a green light, a yellow light, and a red light.
  • an area or road may include a plurality of traffic lights 130, for example, traffic lights 130-1, traffic lights 130-2, traffic lights 130-3, ..., traffic lights 130-n.
  • the object 140 refers to an object that can move on the road.
  • the objects 140 may include vehicles (cars, trucks, buses, trams, motorcycles, bicycles), people, robots, and the like.
  • a positioning device may be installed on the object 140, for example, a GPS positioning system.
  • the objects 140 moving on the road may include objects 140-1, 140-2, 140-3, ..., 140-n.
  • the memory 150 may refer to a device having a storage function.
  • the memory 150 is mainly used to store data related to the traffic lights 130 and / or objects 140 and various data generated during the operation of the server 110.
  • the memory 150 may store the geographic location of the traffic signal 130, the phase of the traffic signal 130, and historical object trajectory data.
  • the memory 150 may be local or remote.
  • the connection or communication between the system database and other modules of the system may be wired or wireless.
  • the server 110 can directly access and access the data information stored in the memory 150, and can also directly access and access the information of the traffic signal 130 and / or the object 140 through the network 120.
  • the description about the application scenario 100 is for illustrative purposes and is not used to limit the protection scope of the present application.
  • multiple variations and modifications can be made under the instructions of this application. However, these variations and modifications do not deviate from the scope of protection of this application.
  • the storage 150 and the server 110 may be connected locally instead of being connected through the network 120.
  • the computing device 200 may include a processor 210, a memory 220, an input / output interface 230 and a communication port 240.
  • the processor 210 can execute calculation instructions (program code) and perform the functions of the server 110 described in the present invention.
  • the calculation instructions may include programs, objects, components, data structures, processes, modules, and functions (the functions refer to specific functions described in the present invention).
  • the processor 210 can process traffic congestion information of the road in the application scenario 100, historical object trajectory data, the moving speed of the object 140, the stage of the traffic signal 130 when the object 140 enters the intersection of the traffic signal, and predict that the object 140 is passing a specific road time.
  • the processor 210 may analyze the stage of the traffic signal 130 when the object 140 passes the previous traffic signal intersection, and predict the stage described by the traffic signal 130 when the object 140 passes the next traffic signal intersection.
  • the processor 210 may include a microcontroller, a microprocessor, a reduced instruction set computer (RISC), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), and a central processing unit (CPU) , Graphics processing unit (GPU), physical processing unit (PPU), microcontroller unit, digital signal processor (DSP), field programmable gate array (FPGA), advanced RISC machine (ARM), programmable logic device and capable Any circuit, processor, etc. that performs one or more functions, or any combination thereof.
  • the computing device 200 in FIG. 2 only describes one processor, but it should be noted that the computing device 200 in the present invention may further include multiple processors.
  • the memory 220 may store data / information obtained from any subject in the application scenario 100, for example, related information (eg, phase, period) of the traffic signal 130, and the geographic location of the object 140.
  • the memory 220 may include mass storage, removable memory, volatile read and write memory, read-only memory (ROM), etc., or any combination thereof.
  • Exemplary mass storage may include magnetic disks, optical disks, solid-state drives, and the like.
  • Removable memory can include flash drives, floppy disks, optical disks, memory cards, compact disks, and magnetic tapes.
  • Volatile read and write memory can include random access memory (RAM).
  • RAM may include dynamic RAM (DRAM), double-rate synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM), and zero capacitance (Z-RAM).
  • ROM may include mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (PEROM), electrically erasable programmable ROM (EEPROM), compact disk ROM (CD-ROM) and digital universal disk ROM Wait.
  • the input / output interface 230 may be used to input or output signals, data, or information. In some embodiments, the input / output interface 230 may allow an operator to contact the server 110. In some embodiments, the input / output interface 230 may include an input device and an output device. Exemplary input devices may include a keyboard, mouse, touch screen, microphone, etc., or any combination thereof. Exemplary output devices may include display devices, speakers, printers, projectors, etc., or any combination thereof. Exemplary display devices may include a liquid crystal display (LCD), a light-emitting diode (LED) -based display, a flat panel display, a curved display, a television device, a cathode ray tube (CRT), etc., or any combination thereof.
  • LCD liquid crystal display
  • LED light-emitting diode
  • CRT cathode ray tube
  • the communication port 240 may be connected to a network for data communication.
  • the connection may be a wired connection, a wireless connection, or a combination of both.
  • Wired connections may include cables, fiber optic cables, telephone lines, etc., or any combination thereof.
  • the wireless connection may include Bluetooth, Wi-Fi, WiMax, WLAN, ZigBee, mobile network (eg, 3G, 4G, or 5G, etc.), etc., or any combination thereof.
  • the communication port 240 may be a standardized port, such as RS232, RS485, and so on.
  • the communication port 240 may be a specially designed port.
  • FIG. 3 is a functional block diagram of an exemplary system for predicting the passage duration according to some embodiments of the present application.
  • the system 300 for predicting the passage duration may include an acquisition module 310, a determination module 320, a prediction module 330, and a transmission module 340.
  • the obtaining module 310 can obtain the road section and related information, the related information of the traffic signal lamp 130 and the related information of the object 140.
  • the obtaining module 310 can obtain the road segment.
  • the road segment may be used as a road segment to be predicted.
  • the road segment to be predicted may have a specific length, for example, 3 kilometers, or the road segment to be measured may be a road segment with a specific transit time, for example, ten minutes.
  • the speed of the vehicle is a preset speed
  • the time required for the vehicle to pass through the road section to be predicted is a specific passing time.
  • the obtaining module 310 may obtain a candidate movement trajectory of the object 140, and then select a road segment to be predicted from the candidate movement trajectory based on the current movement trajectory of the object 140.
  • the acquiring module 310 may acquire the candidate movement trajectory of the object 140, take the current position of the object 140 as a starting point, and select a candidate movement trajectory of a preset length as the road segment to be predicted.
  • the candidate movement trajectory may be a movement trajectory planned by the system 300 for the predicted transit time for the object 140 or a movement trajectory automatically planned by the object 140.
  • the obtaining module 310 may obtain the candidate movement trajectory of the object 140, or referred to as a total road segment.
  • the obtaining module 310 may divide the total road section into a plurality of sub-road sections, and the sub-road sections may be used as road sections to be predicted.
  • the sub-segment may include at least one traffic signal intersection.
  • the starting point of the sub-segment is a traffic signal intersection.
  • the obtaining module 310 may obtain information about road sections, for example, traffic jam information, object trajectory data, and road section speed limit information.
  • the obtaining module 310 may obtain the traffic congestion information of the road segment at the current time or the predicted traffic congestion information in the future period.
  • the obtaining module 310 can obtain historical object trajectory data of the road segment and object trajectory data of the current time.
  • the traffic congestion information may reflect the congestion situation of the road section.
  • the object trajectory data (for example, vehicle trajectory data) may reflect the object flow (for example, vehicle flow) of the road segment.
  • the object trajectory data can reflect the congestion of road sections.
  • the speed limit information of the road segment may include a maximum speed and / or a minimum speed that allows the object 140 to pass through the road segment.
  • the obtaining module 310 can obtain relevant information of the traffic signal lamp 130, for example, position information, phase, timing of each phase, and period.
  • the timing of each phase refers to the duration of each phase.
  • the timing of the traffic signal 130 refers to the sum of the timing of all phases.
  • the obtaining module 310 can obtain the geographic location (for example, latitude and longitude information) of the traffic signal 130; the three phases of the traffic signal 130 are green light, yellow light, and red light; , 3 seconds and 50 seconds; the period of the traffic light 130 is 83 seconds, which is (30 + 3 + 50) seconds.
  • the acquisition module 310 may determine the period of the traffic signal 130 based on historical trajectory data of objects passing through the road segment (e.g., speed, dwell time, movement time, etc.). For example, the acquisition module 310 may perform statistical analysis on the trajectory data of objects passing through the road segment within a week to determine the period of the traffic signal 130. In some embodiments, the acquisition module 130 may directly acquire the period of the traffic signal 130 through the traffic safety integrated service platform.
  • the transportation platform can be used as a platform for monitoring and controlling road traffic safety and providing services for vehicles.
  • the obtaining module 310 can obtain related information of the object 140, for example, time information, position information, and speed information. For example, the obtaining module 310 may obtain the initial time when the object 140 moves on the road section to be predicted, and the current time when the object 140 moves. For another example, the acquiring module 310 may acquire the geographic location (for example, latitude and longitude information) and movement trajectory of the object 140. The geographic movement trajectory of the object 140 may be composed of multiple geographic locations of the object 140. For another example, the acquiring module 310 can acquire the moving speed of the object 140.
  • time information for example, time information, position information, and speed information.
  • the obtaining module 310 may obtain the initial time when the object 140 moves on the road section to be predicted, and the current time when the object 140 moves.
  • the acquiring module 310 may acquire the geographic location (for example, latitude and longitude information) and movement trajectory of the object 140.
  • the geographic movement trajectory of the object 140 may be composed of multiple geographic locations of the object 140.
  • the acquiring module 310
  • the determination module 320 may determine the stage in which the traffic signal 130 is.
  • a traffic signal cycle may include more than two stages. Each stage can reflect the progress of the traffic signal cycle at a specific moment.
  • the traffic signal light 130 has three phases, namely a green light, a yellow light, and a red light, and the corresponding timings are 30 seconds, 3 seconds, and 50 seconds, respectively.
  • the traffic signal 130 cycle includes four stages, namely the initial stage of green light, the later stage of green light, the initial stage of red light and the later stage of red light.
  • the initial stage of the green light can reflect that the progress of the traffic signal cycle at a specific moment is the initial stage of the green light.
  • the first 15 seconds of the green light can be divided into the initial stage of the green light.
  • the later stage of the green light can reflect that the progress of the traffic signal cycle at a specific moment is the later stage of the green light.
  • the last 15 seconds of the green light can be divided into the late green light stage.
  • the initial stage of the red light may reflect that the progress of the traffic signal cycle at a specific moment is the yellow light period and / or the early red light period. For example, 3 seconds of the yellow light period and the first 24 seconds of the red light can be divided into the initial stage of the red light.
  • the later stage of the red light can reflect that the progress of the traffic signal cycle at a particular moment is the later stage of the red light. For example, the last 26 seconds of the red light can be divided into the later stage of the red light.
  • the phase of the traffic lights 130 and the phase of the traffic lights 130 may correspond to each other.
  • the phase of the traffic light 130 when the traffic signal light 130 is in the initial stage of the green light or the late stage of the green light, the phase of the traffic light 130 is a green light.
  • the phase of the traffic signal light when the traffic signal light 130 is in the later stage of the red light, the phase of the traffic signal light is a red light.
  • the phase of the traffic signal 130 and the phase of the traffic signal 130 may not correspond to each other.
  • the phase of the traffic light 130 is yellow light and red light.
  • one cycle of the traffic signal light 130 may include three stages, such as a red light stage, a green light stage, and a green light stage.
  • the early stage of the green light and the later stage of the green light can be collectively referred to as the green light stage.
  • the determination module 310 may determine the stage at which the traffic light 130 is at the current moment or when a specific behavior occurs.
  • the determination module 320 may determine the stage in which the traffic signal 130 is located when the object 140 enters the intersection of the traffic signal.
  • the entry of the object 140 into the intersection refers to a preset range (for example, three hundred meters) of the road where the object 140 enters the intersection. For example, when entering an intersection from a certain road, the area within 300 meters from the stop line is considered as an intersection. For another example, a range extending 300 meters outward from the center point of the intersection is regarded as an intersection.
  • the range determined by the traffic instruction line on the road surface is an intersection, such as a crossroad, and the area enclosed by the stop lines of the roads in four directions is an intersection.
  • intersection such as a crossroad
  • the area enclosed by the stop lines of the roads in four directions is an intersection.
  • the specific range of the intersection may be set according to actual needs.
  • the range may be 10 meters, 50 meters, 100 meters, 150 meters, 200 meters, and so on.
  • the determination module 320 may determine the stage of the traffic light 130 when the object 140 enters the intersection of the traffic light at least based on the initial time at which the object 140 moves at the road section to be predicted. For example, the determination module 320 may predict the length of time required for the object 140 to enter the traffic light intersection from the initial position of the road segment to be predicted according to the current moving speed of the object 140 and the distance between the current position of the object 140 and the traffic light intersection. With reference to the initial time when the object 140 moves on the road section to be predicted, the determination module 320 may predict the time when the object 140 enters the intersection of the traffic light.
  • the determination module 320 may determine the stage in which the traffic signal 130 is located based on the time when the object 140 enters the traffic signal intersection. For example, when an object 140 enters a traffic signal intersection at 10:00 am, the period of the traffic signal is 1 minute. Assuming that the phase change of the traffic signal in a cycle is green, yellow, and red, then the traffic The signal light is at the beginning of the green light stage (also called the initial stage of the green light).
  • the starting point of the road segment to be predicted may be a traffic signal intersection.
  • the initial time when the object 140 moves on the road segment to be predicted is the time when the object 140 enters the intersection of the traffic light.
  • the determination module 320 may determine the stage where the traffic signal 130 is located based only on the initial time when the object 140 moves on the road section to be predicted. The determination method can refer to the above example.
  • the prediction module 330 may predict the length of time the object 140 passes through the road segment to be predicted based at least on the stage at which the traffic light 130 is at when the object 140 enters the intersection of the traffic light.
  • the road section to be predicted includes the traffic signal intersection.
  • the duration of the object 140 passing through the road section to be predicted may be divided into the duration of the object 140 passing through the traffic signal intersection in the road section to be predicted and the duration of passing the non-traffic signal intersection in the road section to be predicted.
  • the prediction module 330 may predict the length of time the object 140 passes the road section to be predicted by predicting the length of time the object 140 passes the traffic signal intersection in the road section to be predicted and the time of the object 140 passing the non-traffic signal intersection in the road section to be predicted.
  • the road segment to be predicted may include a traffic signal intersection.
  • the prediction module 330 may predict the length of time that the object 140 passes through the traffic signal intersection in the to-be-predicted road segment based on the stage of the traffic signal when the object 140 enters the traffic signal intersection. For example, when the object 140 enters the intersection of traffic lights, the traffic signal is in the green light stage (for example, the initial stage of the green light and the late stage of the green light), and the object 140 can directly pass the intersection of the traffic lights without stopping.
  • the prediction module 330 may be based on the distance between the geographic location of the object 140 entering the traffic light intersection and the geographic location of the object 140 leaving the traffic light intersection (marked S1) and the moving speed of the object 140 (marked V) ), Predict the time when the object 140 passes the intersection of the traffic lights. For another example, when the object 140 enters a traffic signal intersection, the traffic signal is at the initial stage of the red light or the late stage of the red light. The object 140 cannot directly pass through the traffic signal intersection, and needs to wait for a period of time (marked as tw). The prediction module 330 may predict the time when the object 140 passes the traffic signal intersection based on S1, V, and tw.
  • the road segment to be predicted may include two traffic signal intersections, marked as a first traffic signal intersection and a second traffic signal intersection.
  • the prediction module 330 may predict the length of time that the object 140 passes the first traffic signal intersection based on the stage where the first traffic signal lamp is when the object 140 enters the first traffic signal intersection. Further, the prediction module 330 may predict the stage of the second traffic signal when the object enters the intersection of the first traffic signal based on the stage of the object 140 entering the intersection of the first traffic signal. Then, the prediction module 330 may predict the length of time the object 140 passes through the second traffic signal intersection based on the predicted stage at which the object 140 enters the second traffic signal intersection. Based on the length of time that the object 140 passes through the first traffic signal intersection and the second traffic signal intersection, the prediction module 330 may predict the duration of the object 140 passing through the traffic signal intersection in the road segment to be predicted.
  • the road segment to be predicted may include three or more traffic signal intersections, labeled as first traffic signal intersection, second traffic signal intersection, ... Signal intersection, Nth traffic signal intersection.
  • the prediction module 330 may predict the stage of the second traffic signal when the object enters the intersection of the first traffic signal based on the stage of the object 140 entering the intersection of the first traffic signal.
  • the prediction module 330 may predict the stage of the third traffic signal when the object enters the intersection of the third traffic signal based on the stage of the object 140 entering the intersection of the second traffic signal.
  • the prediction module 330 may predict the stage of the Nth traffic signal when the object enters the N-1 traffic signal intersection based on the stage of the N-1 traffic signal when the object 140 enters the N-1 traffic signal intersection.
  • the prediction module 330 may predict the length of time that the object 140 passes through each traffic light intersection based on the stage where each traffic signal is located, and then predict the length of time that the object 140 passes through the traffic signal intersection in the road segment to be predicted.
  • the prediction module 330 may use various methods to predict the length of time that the object 140 passes through each traffic signal intersection.
  • the prediction module 330 may be based on the geographic location of the object 140 entering a traffic signal intersection (ie, the geographic location when entering the traffic signal intersection preset range) and the geographic location leaving the traffic signal intersection (ie, leaving the traffic signal intersection
  • the distance between the geographical position at the preset range) and the current speed of the object 140 predict the time (marked t1) at which the object 140 passes the distance.
  • the prediction module 330 may predict the time the object 140 waits (marked as t2) according to the stage the traffic light is at when the object enters the intersection of the traffic signal. Based on t1 and t2, the prediction module 330 may predict the length of time that the object 140 passes through the traffic signal intersection.
  • a specific moment corresponds to a specific stage of a traffic signal.
  • the above is based on predicting where the traffic light (marked as a front traffic light) when the object 140 enters one traffic light intersection is where the traffic signal (marked as a rear traffic light) is entered when the object 140 enters another traffic light intersection
  • the stage of may be equivalent to predicting the time corresponding to the intersection of the traffic lights after the object 140 enters based on the time corresponding to the intersection of the traffic lights before the object 140 enters.
  • the prediction module 330 may predict the length of time required for the object 140 from the front traffic signal intersection to the rear traffic signal intersection based on the current speed (or predicted speed) of the object 140 and the distance between the two traffic signal intersections.
  • the prediction module 330 may predict the time corresponding to the object 140 entering the rear traffic light intersection. Furthermore, the prediction module 330 can predict the stage that the rear traffic lights are in when the object 140 enters the intersection of the rear traffic lights.
  • multiple traffic lights 130 may be set according to specific traffic signal rules. For example, two consecutive traffic lights 130 on the road, labeled as front traffic lights (eg, first traffic lights) and rear traffic lights (eg, second traffic lights), may be set according to specific traffic signal rules.
  • the traffic signal rule may reflect the correspondence between the phase of the traffic signal, the timing of each phase of the traffic signal, and the periodic process of different traffic signals at the same time (for example, the stage in which the traffic signal is located). Then, the prediction module 330 may predict the stage at which the traffic lights are located when the object 140 enters the intersection of the traffic lights according to the traffic light rules.
  • the traffic signal setting rule may be that the first traffic signal and the second traffic signal each include three phases, namely a green light, a yellow light, and a red light; when the first traffic signal is in the initial stage of the green light, the second The traffic signal is in the late stage of the green light; when the first traffic signal is in the late stage of the green light, the second traffic signal is in the initial stage of the red light.
  • the prediction module 330 may make the following prediction.
  • the preset speed of the object 140 may be the average speed of all vehicles on the road at a specific time, or the average speed within the speed limit of the road (eg, the average of the maximum speed limit and the minimum speed limit) value).
  • FIG. 6 is an exemplary object movement trajectory diagram according to some embodiments of the present application.
  • the abscissa of the object movement trajectory 600 is time, and the ordinate is distance.
  • the object movement track diagram 600 includes a plurality of object movement tracks, for example, a movement track 640 and a movement track 650.
  • the movement trajectory 640 describes the movement trajectory formed by the first object moving from the first traffic signal intersection 610, through the second traffic signal intersection 620, to the third traffic signal intersection 630.
  • the movement trajectory 650 describes the movement of the second object from the first traffic signal intersection 610, through the second traffic signal intersection 620, to the third traffic signal intersection 630.
  • the moving speeds of the first object and the second object are the same or equivalent, and are within a preset speed range.
  • the traffic lights set at the traffic signal intersection 610 have three phases, namely a green light 611, a yellow light 612, and a red light 613.
  • the traffic signal lights set at the traffic signal intersection 620 have three phases, namely a green light 621, a yellow light 622, and a red light 623.
  • the traffic lights set at the traffic signal intersection 630 have three phases, namely a green light 631, a yellow light 632 and a red light 633.
  • the traffic lights at the traffic signal intersection 610, the traffic signal intersection 620, and the traffic signal intersection 630 are set according to certain traffic signal setting rules.
  • the first traffic signal is green light 611 (or called green light initial stage)
  • the first object passes the second traffic signal intersection 620
  • the second traffic signal is green light 621 (or called green light) Stage)
  • the first object passes the third traffic signal intersection 630
  • the third traffic signal is green light 631 (or called green light stage).
  • the passage time of the first object through the movement track 640 is T1.
  • the second object passes the first traffic signal intersection 610, the first traffic signal is a green light 611 (or called the green stage), the second object passes the second traffic signal intersection 620, the second traffic signal is a red light 623 (or called At the red light stage), the second object passes through the third traffic signal intersection 630.
  • the third traffic signal light is the red light 633 (or called red light stage).
  • T1 is much smaller than T2. It can be seen that the stage of the traffic signal 130 when the object 140 enters the intersection of the traffic signal has a greater influence on the length of time the object 140 passes through the intersection of the traffic signal.
  • the first traffic signal is at the initial stage of the green light, the duration of the object 140 passing the road section to be predicted is shorter; when the object 140 enters the first traffic signal intersection, the first traffic When the signal light is in the later stage of the green light, the length of time that the object 140 passes through the road section to be predicted is longer.
  • the prediction module 330 may also predict the length of time that the object 140 passes the non-traffic signal intersection in the road segment to be predicted.
  • the non-traffic signal intersection refers to a section between two continuous traffic signal intersections (marked as front traffic signal and rear traffic signal), that is, the geographic location when the object 140 leaves the front traffic signal intersection and the object 140 enters the rear traffic signal intersection
  • the distance between the geographical location of the road is marked as S2.
  • the object 140 leaving the traffic signal intersection means that the object 140 leaves the intersection where the road is located within a preset range (for example, three hundred meters). For example, when leaving a traffic signal intersection from a certain road, when the object 140 is 300 meters away from the stop line, it means that the object 140 leaves the traffic signal intersection.
  • the object 140 when the object 140 is out of the range extending 300 meters from the center point of the intersection, it means that the object 140 leaves the intersection of the traffic signal. For another example, when the object 140 leaves the range determined by the traffic instruction line on the road surface, it means that the object 140 leaves the intersection of the traffic signal.
  • the prediction module 330 may predict the length of time that the object 140 passes the non-traffic signal intersection in the road segment to be predicted through the traffic state information of the non-traffic signal intersection.
  • the traffic state information includes traffic congestion information, historical trajectory data, and the moving speed of the object 140, such as the current moving speed (marked as Vc).
  • the prediction module 330 may predict the moving speed of the object 140 (marked as Vp) according to the traffic congestion information. Then, based on S2 and Vp, the prediction module 330 may predict the length of time that the object 140 passes the non-traffic signal intersection in the road segment to be predicted.
  • the prediction module 330 may predict the length of time that the object 140 passes the non-traffic signal intersection in the road segment to be predicted according to historical trajectory data (for example, the object movement trajectory graph 600). As an example, the prediction module 330 may predict the length of time that the object 140 passes the non-traffic signal intersection in the road segment to be predicted at the same specific time according to the historical time when the object 140 passes the non-traffic signal intersection in the road segment to be predicted at a specific time.
  • the historical duration may be the duration of passage in the past period (for example, one week, half month, one month, and one quarter). In some embodiments, the historical duration corresponding to a specific moment is related to a specific date.
  • the historical duration corresponding to 15:00 pm on May 1st, 2018 is related to the passage duration on May 1st or April 24th, 2017 (ie, last Wednesday).
  • the historical duration corresponding to 18:00 pm on Friday is related to the communication duration of 18:00 pm on each Friday in the past month.
  • the prediction module 330 may directly predict the length of time that the object 140 passes the intersection of the non-traffic signal in the road segment to be predicted according to the current moving speed Vc of the object 140. For example, the prediction module 330 may predict, based on S2 and Vc, the length of time that the object 140 passes the intersection of the non-traffic signal in the road segment to be predicted.
  • the prediction module 330 can separately predict the duration of the object 140 passing through the traffic signal intersection in the road section to be predicted and the duration of passing the non-traffic signal intersection in the road section to be predicted, thereby predicting the total length of the object 140 passing the road section to be predicted.
  • the total road segment is divided into multiple road segments to be predicted (or referred to as sub-road segments).
  • the prediction module 330 may predict the passage time of the total road section based on the passage time of each road section to be predicted.
  • the prediction module 330 may dynamically update the transit time of the road segment. For example, when the moving speed of the object 140 (for example, Vp and Vc), the traffic congestion information of the road segment, and the historical trajectory data change, the prediction module 330 may use the changed moving speed of the object 140, the traffic congestion information of the road segment, and the historical trajectory The data dynamically updates the transit time of the link. For another example, the prediction module 330 may dynamically update the passage duration of the link periodically.
  • the prediction module 330 may determine the transit time of the object through the road segment based on the transit time prediction model.
  • the traffic duration prediction model may be a machine learning model, for example, a neural network model, based on historical traffic information status information generated by all objects passing through the road segment within a period of time (eg, within a week), including but not limited to historical traffic congestion information , Trajectory data of historical objects, traffic signal period, historical moving speed of objects, historical passing time of objects passing through road sections, etc. or any combination thereof, obtained after training.
  • the training process of the traffic duration prediction model may be performed by the training module 350.
  • the training module 350 may use the historical traffic information state information to train the passing time prediction model.
  • the training module 350 may also use data generated when the object passes through the sub-segments, for example, the duration of traffic, traffic congestion information, trajectory data, traffic signal period, moving speed, etc., for the duration of traffic The prediction model is updated.
  • the sending module 340 may send information. In some embodiments, the sending module 340 may send prompt information to the object 140. For example, when the prediction module 330 predicts that the traffic signal at the intersection of the traffic light at which the object 140 is about to enter is at the red light stage, the sending module 340 may send a prompt message to the object 140 to remind the traffic signal at the intersection of the traffic signal at which the object 140 is about to enter at the red light stage. For another example, when congestion occurs on the current side road segment, the sending module 340 may send a prompt message to the object 140, indicating that the object 140 is about to enter the congested road segment.
  • the prediction module 330 may predict the length of time that the object 140 passes the traffic signal intersection in the road segment to be predicted based on the traffic congestion information of the traffic signal intersection, the historical trajectory data, and the moving speed of the object 140.
  • the prediction module 330 may make an overall prediction of the passing time of the predicted road segment, instead of dividing the passing time of the road segment to be predicted into the length of the object 140 passing the traffic signal intersection in the road segment to be predicted and passing the non-traffic signal lamp in the road segment to be predicted The length of the intersection.
  • FIG. 4 is an exemplary flowchart of a method for predicting a passing time according to some embodiments of the present application.
  • the passing time prediction method 400 may be executed by the predicting passing time system 300.
  • the traffic duration prediction method 400 may include:
  • the determination module 320 may determine the stage of the first traffic signal when the object 140 enters the intersection of the first traffic signal.
  • the determination module 320 may determine the stage of the first traffic signal 130 when the object 140 enters the first traffic signal intersection based at least on the initial time when the object 140 moves on the sub-segment.
  • the sub-segment is regarded as a road segment to be predicted, and the sub-segment includes the first traffic signal intersection.
  • the acquisition module 310 acquires the initial time when the object 140 moves on the sub-segment.
  • the determining module 320 may determine the stage of the first traffic signal 130 when the object 140 enters the first traffic signal intersection based at least on the initial time.
  • the initial time for the object 140 to move in the sub-segment is the time when the object 140 enters the first traffic signal intersection.
  • the determination module 320 may determine the stage in which the traffic signal 130 is located based only on the initial time when the object 140 moves on the sub-segment.
  • the prediction module 330 may predict the length of time that the object 140 passes through the sub-segment based at least on the stage where the first traffic signal is.
  • the duration of the object 140 passing through the sub-section may be divided into the duration of the object 140 passing through the intersection of the traffic signal in the sub-section and the duration of passing through the intersection of the non-traffic signal in the sub-section.
  • the prediction module 330 may predict the duration of the object 140 passing through the sub-segment by predicting the duration of the object 140 passing through the intersection of the traffic signal in the sub-segment and the duration of the object 140 passing through the intersection of the non-traffic signal in the sub-segment.
  • the sub-segment may include a traffic signal intersection.
  • the prediction module 330 may predict the length of time that the object 140 passes through the traffic signal intersection in the sub-segment based on the stage the traffic signal is at when the object 140 enters the traffic signal intersection.
  • the sub-segment may include two traffic signal intersections, marked as a first traffic signal intersection and a second traffic signal intersection.
  • the prediction module 330 may predict the length of time that the object 140 passes the first traffic signal intersection based on the stage where the first traffic signal lamp is when the object 140 enters the first traffic signal intersection. Further, the prediction module 330 may predict the stage of the second traffic signal when the object enters the intersection of the first traffic signal based on the stage of the object 140 when entering the intersection of the first traffic signal. Then, the prediction module 330 may predict the length of time the object 140 passes through the second traffic signal intersection based on the predicted stage at which the object 140 enters the second traffic signal intersection. Based on the length of time that the object 140 passes through the first traffic signal intersection and the second traffic signal intersection, the prediction module 330 may predict the length of time that the object 140 passes through the traffic signal intersection in the sub-segment.
  • the sub-segments may include three or more traffic signal intersections, labeled as the first traffic signal intersection, the second traffic signal intersection, the third traffic signal intersection, ..., the N-1th traffic signal Intersection, Nth traffic signal intersection.
  • the prediction module 330 may predict the stage of the second traffic signal when the object enters the intersection of the first traffic signal based on the stage of the object 140 entering the intersection of the first traffic signal.
  • the prediction module 330 may predict the stage of the third traffic signal when the object enters the intersection of the third traffic signal based on the stage of the object 140 entering the intersection of the second traffic signal.
  • the prediction module 330 may predict the stage of the Nth traffic signal when the object enters the Nth traffic signal intersection based on the stage of the N-1 traffic signal when the object 140 enters the N-1 traffic signal intersection.
  • the prediction module 330 may predict the length of time that the object 140 passes through each traffic light intersection based on the stage at which each traffic signal is located, and then predict the length of time that the object 140 passes through the traffic signal intersection in the sub-segment.
  • the stage where the front traffic signal for example, the first traffic signal
  • the stage where the rear traffic signal for example, the second traffic signal
  • the prediction module 330 may predict the length of time that the object 140 passes through the non-traffic signal intersection in the sub-segment.
  • the prediction module 330 may predict the length of time that the object 140 passes the non-traffic signal intersection in the sub-segment based on the traffic congestion information of the non-traffic signal intersection, historical trajectory data and the current moving speed of the object 140. For a specific prediction of the length of time an object passes through a non-traffic signal intersection in a sub-segment, refer to the related description in FIG. 3.
  • the prediction module 330 can separately predict the duration of the object 140 passing through the traffic signal intersection in the sub-segment and the duration of passing the non-traffic signal intersection in the sub-segment, thereby predicting the total duration of the object 140 passing through the sub-segment.
  • the prediction module 330 may predict the passing time of the object through the sub-segment based on the passing time prediction model and the stage of the traffic signal when the object passes through the sub-segment.
  • the traffic duration prediction model can be obtained after training based on historical data using the training module 350.
  • the historical data may be historical traffic state information of objects passing through the road segment, including but not limited to historical traffic congestion information, historical object trajectory data, traffic signal period, historical moving speed of the object, and the object passing road Historical transit time, etc. or any combination thereof.
  • the historical traffic congestion information may be a traffic congestion situation of the road section in a specific period of time in the past (for example, one day, one week, etc.).
  • the historical object trajectory data may be trajectory data of all objects passing through the road segment within a certain period of time in the past (for example, one day, one week, etc.).
  • the traffic signal period may be the period of the traffic signal of the road section.
  • the historical moving speed of the object may be the speed and change of each object passing through the road segment in a specific period of time in the past (for example, one day, one week, etc.).
  • the traffic duration prediction model may be a machine learning model, including but not limited to Support Vector Machine (Support Vector Machine (SVM), Naive Bayes (NB), k nearest neighbor (k- Nearest Neighbor (kNN), Decision Tree (DT), Artificial Neural Network (ANN), etc. or any combination thereof.
  • SVM Support Vector Machine
  • NB Naive Bayes
  • kNN k nearest neighbor
  • DT Decision Tree
  • the training module 350 may use the historical traffic state information as input to train the model.
  • the model meets certain conditions, for example, the training times reach a predetermined value and / or the model converges, the training may be stopped.
  • the trained model may be designated as the traffic duration prediction model.
  • the prediction module 330 may input the stage of the traffic lights when the object passes through the road segment and the initial time when the object moves on the sub-segment to the traffic duration prediction model to directly obtain the object passing through the sub-segment The duration of travel is required. For a total road segment with multiple sub-segments, the prediction module 330 may separately predict the length of time that an object passes through each sub-segment based on the passing time model, and finally obtain the total length of time passing through the total road segment.
  • the training module 350 may obtain data generated during the movement of the object, for example, the duration of travel, traffic jam information, trajectory data, traffic signal period, and moving speed. Every other specific time (for example, one day), the training module 350 may use the above-mentioned data of objects passing through the road segment acquired during the time to update the traffic duration prediction model to improve the accuracy of the model prediction.
  • the above-mentioned sub-section may be a section selected from the candidate movement trajectories based on the current movement trajectory of the object 140.
  • the above-mentioned sub-segment may be a part divided by the obtaining module 310 from the total segment.
  • the prediction module 330 may dynamically update the length of time that the object 140 passes through the sub-segment.
  • the prediction module 330 may perform an overall prediction on the transit time of the sub-segment instead of separately predicting the duration of the object 140 passing through the traffic signal intersection in the sub-segment and the duration of passing the non-traffic signal intersection in the sub-segment. .
  • FIG. 5 is an exemplary flowchart of a method for predicting a passing time according to some embodiments of the present application.
  • the passing time prediction method 500 may be executed by the predicting passing time system 300.
  • the traffic duration prediction method 500 may be a further development of the traffic duration prediction method 400. As shown in FIG. 5, the traffic duration prediction method 500 may include:
  • the prediction module 330 may predict the stage of the second traffic signal when the object 140 enters the intersection of the first traffic signal based on the stage of the object 140 entering the intersection of the first traffic signal.
  • the first traffic signal intersection and the second traffic signal intersection may be two adjacent traffic signal intersections or two non-adjacent two traffic signal intersections
  • a specific moment corresponds to a specific stage of a traffic signal.
  • the above-described prediction of the stage where the first traffic signal is at when the object 140 enters the first traffic light intersection may be equivalent to, based on the object 140 at the stage when the object 140 enters the second traffic signal intersection
  • the time corresponding to entering the first traffic signal intersection predicts the time corresponding to the object 140 entering the second traffic signal intersection.
  • the prediction module 330 may predict the object 140 from the first traffic signal intersection to the second traffic signal according to the current speed (or predicted speed) of the object 140 and the distance between the above first traffic signal intersection and the second traffic signal intersection The length of time required at the intersection.
  • the prediction module 330 may predict the time corresponding to the object 140 entering the second traffic signal intersection. Furthermore, the prediction module 330 can predict the stage of the second traffic signal when the object 140 enters the intersection of the second traffic signal.
  • the first traffic signal and the second traffic signal may be set according to specific traffic signal setting rules.
  • the traffic signal setting rule may be that the first traffic signal and the second traffic signal each include three phases, namely a green light, a yellow light, and a red light; when the first traffic signal is in the initial stage of the green light, the second The traffic signal is in the late stage of the red light; when the first traffic signal is in the late stage of the green light, the second traffic signal is in the initial stage of the red light.
  • the prediction module 330 may predict the following prediction.
  • the object 140 passes the first traffic signal intersection, the first traffic signal is in the early stage of the green light, the object 140 passes the second traffic signal intersection, the second traffic signal is in the green light stage; when the object 140 passes the first traffic signal intersection, the first traffic signal is in the green light At a later stage, the body 140 passes the second traffic signal intersection and the second traffic signal is in the red light stage.
  • the prediction module 330 may predict the length of time that the object 140 passes through the sub-segment based at least on the stage where the second traffic signal is.
  • the duration of the object 140 passing through the sub-section may be divided into the duration of the object 140 passing through the intersection of the traffic signal in the sub-section and the duration of passing through the intersection of the non-traffic signal in the sub-section.
  • the prediction module 330 may predict the duration of the object 140 passing through the sub-segment by predicting the duration of the object 140 passing through the intersection of the traffic signal in the sub-segment and the duration of the object 140 passing through the intersection of the non-traffic signal in the sub-segment.
  • the above-mentioned sub-segments may only include the first traffic signal intersection and the second traffic signal intersection.
  • the prediction module 330 may predict the length of time that the object 140 passes the first traffic signal intersection based on the stage where the first traffic signal lamp is when the object 140 enters the first traffic signal intersection. Then, the prediction module 330 may predict the length of time the object 140 passes through the second traffic signal intersection based on the predicted stage at which the object 140 enters the second traffic signal intersection. Based on the length of time that the object 140 passes through the first traffic signal intersection and the second traffic signal intersection, the prediction module 330 may predict the length of time that the object 140 passes through the traffic signal intersection in the sub-segment.
  • the above-mentioned sub-segments may include a first traffic signal intersection, a second traffic signal intersection, and other traffic signal intersections. Other traffic signal intersections may be marked as third traffic signal intersections, ..., N-1th traffic signal intersections, and Nth traffic signal intersections.
  • the prediction module 330 may predict the stage of the third traffic signal when the object enters the intersection of the third traffic signal based on the stage of the object 140 entering the intersection of the second traffic signal. By analogy, the prediction module 330 may predict the stage of the Nth traffic signal when the object enters the Nth traffic signal intersection based on the stage of the N-1 traffic signal when the object 140 enters the N-1 traffic signal intersection.
  • the prediction module 330 may predict the length of time that the object 140 passes through each traffic signal intersection based on the stage where each traffic signal is located, and then predict the length of time that the object 140 passes through the traffic signal intersection in the sub-segment.
  • the prediction module 330 may predict the length of time that the object 140 passes through the non-traffic signal intersection in the sub-segment.
  • the prediction module 330 may predict the length of time that the object 140 passes the non-traffic signal intersection in the sub-segment based on the traffic congestion information of the non-traffic signal intersection, historical trajectory data, and the current moving speed of the object 140. For a specific prediction of the length of time an object passes through a non-traffic signal intersection in a sub-segment, refer to the related description in FIG. 3.
  • the prediction module 330 can separately predict the duration of the object 140 passing through each traffic signal intersection in the sub-segment and the duration of the object 140 passing through the non-traffic signal intersection in the sub-segment, thereby predicting the total duration of the object 140 passing through the sub-segment.
  • Step 530 When it is predicted that the object 140 is passing through the intersection of the second traffic signal and the second traffic signal is in a red light stage, the sending module 340 sends a prompt message.
  • the prompting signal may include prompting that the traffic signal at the intersection of the second traffic signal that the object 140 is about to enter is in the red light stage.
  • the above description of the traffic duration prediction method 500 is for convenience of description only, and cannot limit the application to the scope of the illustrated embodiments. It can be understood that, for those skilled in the art, after understanding the principle of the method, multiple variations and modifications may be made without departing from this principle. However, these variations and modifications do not deviate from the scope of protection of this application.
  • the prediction module 330 may dynamically update the length of time that the object 140 passes through the sub-segment.
  • the prediction module 330 may perform an overall prediction on the transit time of the sub-segment instead of separately predicting the duration of the object 140 passing through the traffic signal intersection in the sub-segment and the duration of passing the non-traffic signal intersection in the sub-segment.
  • step 530 may be omitted.
  • the prediction of the travel time of the object through the road section to be predicted is more accurate.
  • the possible beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.
  • the present application uses specific words to describe the embodiments of the present application.
  • “one embodiment”, “one embodiment”, and / or “some embodiments” mean a certain feature, structure, or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that “one embodiment” or “one embodiment” or “an alternative embodiment” mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment .
  • certain features, structures, or characteristics in one or more embodiments of the present application may be combined as appropriate.
  • the computer-readable signal medium may contain a propagated data signal containing a computer program code, for example, on baseband or as part of a carrier wave.
  • the propagated signal may have multiple manifestations, including electromagnetic, optical, etc., or a suitable combination.
  • the computer-readable signal medium may be any computer-readable medium except the computer-readable storage medium, and the medium may be connected to an instruction execution system, apparatus, or device to communicate, propagate, or transmit a program for use.
  • Program code located on a computer-readable signal medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the foregoing.
  • the computer program codes required for the operation of various parts of this application can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C ++, C #, VB.NET and Python Etc., conventional programming languages such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP and ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages.
  • the program code may run entirely on the user's computer, or as an independent software package on the user's computer, or partly on the user's computer, partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any form of network, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (eg, via the Internet), or in a cloud computing environment, or as a service Use as software as a service (SaaS).
  • LAN local area network
  • WAN wide area network
  • SaaS software as a service
  • Some embodiments use numbers describing the number of components and attributes. It should be understood that such numbers used in embodiment descriptions use the modifiers "about”, “approximately”, or “generally” in some examples. Grooming. Unless otherwise stated, “approximately”, “approximately” or “substantially” indicates that the figures allow a variation of ⁇ 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and the approximate values may be changed according to characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of general digit retention. Although the numerical fields and parameters used to confirm the breadth of their ranges in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values is as accurate as possible within the feasible range.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Atmospheric Sciences (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种预测通行时长的方法和系统，方法包括确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段（410）；至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长（420），其中，一个交通信号灯周期至少包括两个阶段，所述子路段包括所述第一交通信号灯路口。该预测方法在进行时间预测时利用了物体通过路口时交通信号灯所处阶段，使得预测更加准确。

Description

预测通行时长的方法和系统
交叉引用
本申请要求于2018年11月16日提交的申请号为201811372599.6的中国申请的优先权，其内容通过引用结合于此。
技术领域
本申请涉及数据处理，尤其是涉及一种预测通行时长的方法和系统。
背景技术
随着经济的发展，道路上的车辆越来越多。车流量的增大，道路复杂度的增加(例如，设置交通信号灯、交叉路口)，使得预测车辆通行时间需要考虑的因素越来越多。为了更加准确的预测车辆的通行时间，一种精细的预测方法是十分必要的。
发明内容
为达到上述目标，本申请提供的技术方案如下。
本申请的一方面提供一种预测通行时长的方法，所述方法可以包括以下至少一个操作。可以确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段。可以至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长。其中，一个交通信号灯周期至少包括两个阶段，所述子路段包括所述第一交通信号灯路口。
在一些实施例中，所述确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段包括以下至少一个操作。可以获取所述物体在所述子路段移动的初始时间和所述第一交通信号灯周期。可以至少基于所述初始时间和所述第一交通信号灯周期，确定所述物体进入所述第一交通信号灯路口时所述第一交通信号灯所处的阶段。
在一些实施例中，所述子路段的起点为所述第一交通信号灯路口，所述初 始时间为所述物体进入所述第一交通信号灯路口的时间。
在一些实施例中，所述子路段进一步包括第二交通信号灯路口，所述至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长可以包括以下至少一个操作。可以基于所述第一交通信号灯所处的阶段，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段；可以至少基于所述第一交通信号灯所处的阶段与所述第二交通信号灯所处的阶段，预测所述物体通过所述子路段的时长。
在一些实施例中，一个交通信号灯周期至少包括红灯阶段、绿灯阶段；所述方法可以进一步包括以下至少一个操作。可以当预测所述物体通过所述第二交通信号灯路口所述第二交通信号灯处于红灯阶段时，发送提示信息，所述提示信息包括所述第二交通信号灯处于红灯阶段。
在一些实施例中，所述基于所述第一交通信号灯所处的阶段，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段可以包括以下至少一个操作。可以基于所述第一交通信号灯所处的阶段以及设置所述第一交通信号灯和所述第二交通信号灯的交通信号灯规则，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段。
在一些实施例中，一个交通信号灯周期至少包括红灯阶段、绿灯阶段，所述绿灯阶段至少包括绿灯初期阶段和绿灯后期阶段。所述方法可以进一步包括以下至少一个操作。当所述物体进入所述第一交通信号灯路口第一交通信号灯处于绿灯初期阶段时，可以预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯处于绿灯阶段。当所述物体进入所述第一交通信号灯路口第一交通信号灯处于绿灯后期阶段时，可以预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯处于红灯阶段。
在一些实施例中，所述方法可以进一步包括以下至少一个操作。可以获取所 述子路段的交通状态信息；所述交通状态信息包括以下中的至少一个：交通拥堵信息、所述子路段的历史物体轨迹数据或所述物体的移动速度。可以至少基于所述第一交通信号灯所处的阶段以及所述交通状态信息，预测所述物体通过所述子路段的时长。
在一些实施例中，所述方法可以进一步包括以下至少一个操作。可以获取通过一个总路段的历史交通状态信息；所述历史交通状态信息包括以下中的至少一个：历史交通拥堵信息、历史物体轨迹数据、交通信号灯周期、物体的历史移动速度、物体通过所述总路段的历史通行时长；所述总路段包括至少一个子路段，每个子路段包括至少一个交通信号灯路口。可以基于所述历史交通状态信息，确定通行时长预测模型。可以至少基于物体通过每个子路段时所述交通信号灯所处的阶段以及所述通行时长预测模型，预测物体通过所述总路段的通行时长。
在一些实施例中，所述方法可以进一步包括以下至少一个操作。至少基于所述物体通过所述总路段的通行时长，动态更新所述通行时长预测模型。
在一些实施例中，所述方法可以进一步包括以下至少一个操作。可以获取所述物体的候选移动轨迹。可以基于所述物体当前的移动轨迹，从所述候选移动轨迹中选择所述子路段。
在一些实施例中，所述方法可以进一步包括以下至少一个操作。可以将总路段划分为多个子路段，所述多个子路段中的至少一个子路段包括至少一个交通信号灯路口。可以基于每个子路段的通行时长，预测所述总路段的通行时长。
在一些实施例中，所述方法可以进一步包括以下至少一个操作。可以动态地更新所述总路段的通行时长。
本申请的另一方面提供一种预测通行时长的系统。所述系统包括确定模块和预测模块。所述确定模块用于确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段。所述预测模块用于，至少基于所述第一交通信号灯所处的阶段， 预测所述物体通过子路段的时长。其中，一个交通信号灯周期至少包括两个阶段，所述子路段包括所述第一交通信号灯路口。
在一些实施例中，所述系统进一步包括获取模块，所述获取模块用于获取所述物体在所述子路段移动的初始时间和所述第一交通信号灯周期。所述确定模块还用于至少基于所述初始时间和所述第一交通信号灯周期，确定所述物体进入所述第一交通信号灯路口时所述第一交通信号灯所处的阶段。
在一些实施例中，所述子路段的起点为所述第一交通信号灯路口，所述初始时间为所述物体进入所述第一交通信号灯路口的时间。
在一些实施例中，所述子路段进一步包括第二交通信号灯路口；所述预测模块还用于基于所述第一交通信号灯所处的阶段，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段。所述预测模块还用于至少基于所述第一交通信号灯所处的阶段与所述第二交通信号灯所处的阶段，预测所述物体通过所述子路段的时长。
在一些实施例中，所述预测模块还用于基于所述第一交通信号灯所处的阶段以及设置所述第一交通信号灯和所述第二交通信号灯的交通信号灯规则，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段。
在一些实施例中，一个交通信号灯周期至少包括红灯阶段、绿灯阶段。所述系统进一步包括发送模块，所述发送模块用于当预测所述物体通过所述第二交通信号灯路口所述第二交通信号灯处于红灯阶段时，发送提示信息，所述提示信息包括所述第二交通信号灯处于红灯阶段。
在一些实施例中，一个交通信号灯周期至少包括红灯阶段、绿灯阶段，所述绿灯阶段至少包括绿灯初期阶段和绿灯后期阶段。所述预测模块还用于当所述物体进入所述第一交通信号灯路口第一交通信号灯处于绿灯初期阶段时，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯处于绿灯阶段；当所述 物体进入所述第一交通信号灯路口第一交通信号灯处于绿灯后期阶段时，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯处于红灯阶段。
在一些实施例中，所述获取模块还用于获取所述子路段的交通状态信息；所述交通状态信息包括以下中的至少一个：交通拥堵信息、所述子路段的历史物体轨迹数据或所述物体的移动速度。所述预测模块还用于至少基于所述第一交通信号灯所处的阶段以及所述交通状态信息，预测所述物体通过所述子路段的时长。
在一些实施例中，所述系统还包括训练模块，所述训练模块用于确定通行时长预测模型，确定方法可以包括以下至少一个操作。可以获取通过一个总路段的历史交通状态信息；所述历史交通状态信息包括以下中的至少一个：交通拥堵信息、所述总路段的历史物体轨迹数据、交通信号灯周期、物体的移动速度；所述总路段包括至少一个子路段，每个子路段包括至少一个交通信号灯路口。可以基于所述历史交通状态信息，确定通行时长预测模型。所述预测模块还用于至少基于物体通过每个子路段时所述交通信号灯所处的阶段以及所述通行时长预测模型，预测物体通过每个子路段的通行时长。
在一些实施例中，所述训练模块还用于基于所述物体通过所述总路段的通行时长，动态更新所述通行时长预测模型。
在一些实施例中，所述获取模块还用于获取所述物体的候选移动轨迹，以及基于所述物体当前的移动轨迹，从所述候选移动轨迹中选择所述子路段。
在一些实施例中，所述获取模块还用于将总路段划分为多个子路段，所述多个子路段中的至少一个子路段包括至少一个交通信号灯路口。所述预测模块还用于基于每个子路段的通行时长，预测所述总路段的通行时长。
在一些实施例中，所述预测模块还用于动态地更新所述总路段的通行时长。
本申请的另一个方面提供了一种计算机可读存储介质，所述存储介质存储指令，所述指令被执行时进行以下至少一个操作。可以确定物体进入第一交通信号 灯路口时第一交通信号灯所处的阶段。可以至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长。其中，一个交通信号灯周期至少包括两个阶段，所述子路段包括所述第一交通信号灯路口。
本申请的另一方面提供了一种预测通行时长的装置，所述装置包括处理器，所述处理运行时执行以下至少一个操作。可以确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段。可以至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长。其中，一个交通信号灯周期至少包括两个阶段，所述子路段包括所述第一交通信号灯路口。
本申请的一部分附加特性可以在下面的描述中进行说明。通过对以下描述和相应附图的检查或者对实施例的生产或操作的了解，本申请的一部分附加特性对于本领域技术人员是明显的。本披露的特性可以通过对以下描述的具体实施例的各种方面的方法、手段和组合的实践或使用得以实现和达到。
附图说明
在此所述的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的限定。各图中相同的标号表示相同的部件：
图1是根据本申请的一些实施例所示的示例性预测通行时长的应用场景示意图；
图2是根据本申请的一些实施例所示的示例性计算设备的示例性硬件组件和/或软件组件的示意图；
图3是根据本申请的一些实施例所示的示例性预测通行时长系统的功能模块框图；
图4所示为根据本申请一些实施例所示的通行时长预测方法的示例性流程图；
图5是根据本申请的一些实施例所示的通行时长预测方法的示例性流程图；
图6是一种根据本申请的一些实施例所示的示例性物体移动轨迹图。
具体实施方式
为了更清楚地说明本申请的实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单的介绍。显而易见地，下面描述中的附图仅仅是本申请的一些示例或实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图将本申请应用于其它类似情景。除非从语言环境中显而易见或另做说明，图中相同标号代表相同结构或操作。
如本申请和权利要求书中所示，除非上下文明确提示例外情形，“一”、“一个”、“一种”和/或“该”等词并非特指单数，也可包括复数。一般说来，术语“包括”与“包含”仅提示包括已明确标识的步骤和元素，而这些步骤和元素不构成一个排它性的罗列，方法或者设备也可能包含其它的步骤或元素。
虽然本申请对根据本申请的实施例的系统中的某些模块或单元做出了各种引用，然而，任何数量的不同模块或单元可以被使用并运行在客户端和/或服务器上。所述模块仅是说明性的，并且所述系统和方法的不同方面可以使用不同模块。
本申请中使用了流程图用来说明根据本申请的实施例的系统所执行的操作。应当理解的是，前面或下面操作不一定按照顺序来精确地执行。相反，可以按照倒序或同时处理各种步骤。同时，也可以将其他操作添加到这些过程中，或从这些过程移除某一步或数步操作。
图1是根据本申请的一些实施例所示的示例性预测通行时长的应用场景示意图。示例性应用场景100可以包括服务器110、网络120、交通信号灯130、物体140和存储器150。
服务器110可以用于对收集的信息进行分析加工以生成分析结果的系统。 在一些实施例中，服务器110可以分析物体140进入前一个交通信号灯路口时交通信号灯130(例如，交通信号灯130-1)所处的阶段(例如，红灯阶段、绿灯阶段)，预测物体140进入下一个交通信号灯路口时交通信号灯130(例如，交通信号灯130-2)所处的阶段。在一些实施例中，服务器110可以分析道路的交通拥堵信息、历史物体轨迹数据(例如，历史车辆轨迹数据)、物体140的移动速度、物体140进入交通信号灯路口时交通信号灯130所处的阶段等，进而预测物体140在特定时间通过特定路段的时长。服务器110可以是一个服务器，也可以是一个服务器群组。所述服务器群组可以是集中式的，例如数据中心。所述服务器群组也可以是分布式的，例如一个分布式系统。服务器110可以是本地的，也可以是远程的。
服务器110可以包括引擎112。所述引擎112可以用于执行服务器110的指令(程序代码)。例如，引擎112能够执行预测通行时长程序的指令，进而预测物体140在特定时间通过特定路段的时长。所述预测通行时长程序可以以计算机指令的形式存储在计算机可读存储介质(例如，存储器150)中。
网络120可以提供信息交换的渠道。在一些实施例中，服务器110、交通信号灯130、物体140和/或存储器150之间可以通过网络120交换信息。例如，服务器110可以通过网络120获取交通信号灯130的地理位置、在特定时间所处的阶段等。又例如，服务器110可以通过网络120获取物体140的地理位置、移动速度等。再例如，服务器110可以通过网络120从存储器150获取信息(例如，交通信号灯130的地理位置、历史物体轨迹数据)。
网络120可以是单一网络，也可以是多种网络组合的。网络120可以包括但不限于局域网、广域网、公用网络、专用网络、无线局域网、虚拟网络、都市城域网、公用开关电话网络等中的一种或几种的组合。网络120可以包括多种网络接入点，如有线或无线接入点、基站(如120-1，120-2)或网络交换点， 通过以上接入点使数据源连接网络120并通过网络发送信息。
交通信号灯130是指安装在道路、路口处的交通信号灯(或称为红绿灯)。交通信号灯130可以包括多个相位。作为示例，交通信号灯130可以包括三个相位，分别为绿灯、黄灯和红灯。在一些实施例中，一个地区或道路可以包括多个交通信号灯130，例如，交通信号灯130-1、交通信号灯130-2、交通信号灯130-3、……、交通信号灯130-n。
物体140是指可以在道路上移动的物体。作为示例，物体140可以包括车辆(汽车、卡车、公交车、有轨电车、摩托车、自行车)、人、机器人等。在一些实施例中，物体140上可以安装定位装置，例如，GPS定位系统。在一些实施例中，在道路上移动的物体140可以包括物体140-1、物体140-2、物体140-3、……、物体140-n。
存储器150可以泛指具有存储功能的设备。存储器150主要用于存储交通信号灯130和/或物体140相关的数据和服务器110工作中产生的各种数据。例如，存储器150可以存储交通信号灯130的地理位置、交通信号灯130的相位、历史物体轨迹数据。存储器150可以是本地的，也可以是远程的。系统数据库与系统其他模块间的连接或通信可以是有线的，也可以是无线的。在一些实施例中，服务器110可以直接访问存取储存在存储器150的数据信息，也可以直接通过网络120访问存取交通信号灯130和/或物体140的信息。
应该注意的是，关于应用场景100的描述出于说明性目的，并不用于限制本申请的保护范围。对于本领域的技术人员来说，可以在本申请的指示下做出多个变体和修改。然而，这些变体和修改不会脱离本申请的保护范围。例如，存储器150和服务器110可以是本地连接，而不是通过网络120进行连接。
图2是根据本申请的一些实施例所示的示例性计算设备的示例性硬件组件和/或软件组件的示意图。如图2所示，计算设备200可以包括处理器210、存储 器220、输入/输出接口230和通信通信端口240。
处理器210可以执行计算指令(程序代码)并执行本发明描述的服务器110的功能。所述计算指令可以包括程序、对象、组件、数据结构、过程、模块和功能(所述功能指本发明中描述的特定功能)。例如，处理器210可以处理应用场景100中道路的交通拥堵信息、历史物体轨迹数据、物体140的移动速度、物体140进入交通信号灯路口时交通信号灯130所处的阶段，预测物体140在通过特定路段的时间。又例如，处理器210可以分析物体140通过前一个交通信号灯路口时交通信号灯130所处的阶段，预测物体140通过下一个交通信号灯路口时交通信号灯130所述的阶段。
在一些实施例中，处理器210可以包括微控制器、微处理器、精简指令集计算机(RISC)、专用集成电路(ASIC)、应用特定指令集处理器(ASIP)、中央处理器(CPU)、图形处理单元(GPU)、物理处理单元(PPU)、微控制器单元、数字信号处理器(DSP)、现场可编程门阵列(FPGA)、高级RISC机(ARM)、可编程逻辑器件以及能够执行一个或多个功能的任何电路和处理器等，或其任意组合。仅为了说明，图2中的计算设备200只描述了一个处理器，但需要注意的是本发明中的计算设备200还可以包括多个处理器。
存储器220可以存储从应用场景100中任何主体获得的数据/信息，例如，交通信号灯130的相关信息(例如，相位、周期)、物体140的地理位置。在一些实施例中，存储器220可以包括大容量存储器、可移动存储器、易失性读取和写入存储器和只读存储器(ROM)等，或其任意组合。示例性大容量存储器可以包括磁盘、光盘和固态驱动器等。可移动存储器可以包括闪存驱动器、软盘、光盘、存储卡、压缩盘和磁带等。易失性读取和写入存储器可以包括随机存取存储器(RAM)。RAM可以包括动态RAM(DRAM)、双倍速率同步动态RAM(DDR SDRAM)、静态RAM(SRAM)、晶闸管RAM(T-RAM)和零电容(Z- RAM)等。ROM可以包括掩模ROM(MROM)、可编程ROM(PROM)、可擦除可编程ROM(PEROM)、电可擦除可编程ROM(EEPROM)、光盘ROM(CD-ROM)和数字通用盘ROM等。
输入/输出接口230可以用于输入或输出信号、数据或信息。在一些实施例中，输入/输出接口230可以使操作者与服务器110进行联系。在一些实施例中，输入/输出接口230可以包括输入装置和输出装置。示例性输入装置可以包括键盘、鼠标、触摸屏和麦克风等，或其任意组合。示例性输出设备可以包括显示设备、扬声器、打印机、投影仪等，或其任意组合。示例性显示装置可以包括液晶显示器(LCD)、基于发光二极管(LED)的显示器、平板显示器、曲面显示器、电视设备、阴极射线管(CRT)等，或其任意组合。
通信端口240可以连接到网络以便数据通信。所述连接可以是有线连接、无线连接或两者的组合。有线连接可以包括电缆、光缆或电话线等，或其任意组合。无线连接可以包括蓝牙、Wi-Fi、WiMax、WLAN、ZigBee、移动网络(例如，3G、4G或5G等)等，或其任意组合。在一些实施例中，通信端口240可以是标准化端口，如RS232、RS485等。在一些实施例中，通信端口240可以是专门设计的端口。
图3是根据本申请的一些实施例所示的示例性预测通行时长系统的功能模块框图。预测通行时长系统300可以包括获取模块310、确定模块320、预测模块330和发送模块340。
获取模块310可以获取路段及其相关信息、交通信号灯130的相关信息和物体140的相关信息。
在一些实施例中，获取模块310可以获取路段。所述路段可以作为待预测路段。所述待预测路段可以具有特定的长度的路段，例如，3千米，或者所述待测路段可以是具有特定的通行时长的路段，例如，十分钟。当车辆的速度为预 设速度时，该车辆通过所述待预测路段所需要的时长为特定的通行时长。
例如，获取模块310可以获取物体140的候选移动轨迹，然后基于物体140当前的移动轨迹，从候选移动轨迹中选择待预测路段。作为示例，获取模块310可以获取物体140的候选移动轨迹，以物体140的当前位置为起点，选取预设长度的候选移动轨迹作为待预测路段。所述候选移动轨迹可以是预测通行时长系统300为物体140规划的移动轨迹、物体140自动规划的移动轨迹。
又例如，获取模块310可以获取物体140的候选移动轨迹，或称为总路段。获取模块310可以将总路段划分为多个子路段，所述子路段可以作为待预测路段。子路段可以包括至少一个交通信号灯路口。在一些实施例中，子路段的起点为交通信号灯路口。
在一些实施例中，获取模块310可以获取路段的相关信息，例如，交通拥堵信息、物体轨迹数据、路段限速信息。例如，获取模块310可以获取路段在当前时间的交通拥堵信息或未来时段的预计交通拥堵信息。又例如，获取模块310可以获取路段的历史物体轨迹数据和当前时间的物体轨迹数据。所述交通拥堵信息可以反映路段的拥堵情况。所述物体轨迹数据(例如，车辆轨迹数据)可以反映路段的物体流量(例如，车流量)。进而，物体轨迹数据可以反映路段的拥堵情况。所述路段限速信息可以包括允许物体140通过该路段的最大速度和/或最小速度。
在一些实施例中，获取模块310可以获取交通信号灯130的相关信息，例如，位置信息、相位、每个相位的配时、周期。每个相位的配时是指每个相位持续的时长。交通信号灯130的配时是指所有相位的配时总和。作为示例，获取模块310可以获取交通信号灯130的地理位置(比如，经纬度信息)；交通信号130的三个相位，分别为绿灯、黄灯和红灯；三个相位的配时，分别为30秒、3秒和50秒；交通信号灯130的周期，为83秒，即(30+3+50)秒。在一些实施 例中，获取模块310可以基于通过路段的物体的历史轨迹数据(比如，速度、停留时间、运动时间等)确定交通信号灯130的周期。例如，获取模块310可以对一周内通过该路段的物体的轨迹数据进行统计分析，确定交通信号灯130的周期。在一些实施例中，获取模块130可以通过交通安全综合服务平台直接获取交通信号灯130的周期。所述交通平台可以用于监测、控制道路通行安全和为交通工具提供服务的平台。
在一些实施例中，获取模块310可以获取物体140的相关信息，例如，时间信息、位置信息、速度信息。例如，获取模块310可以获取物体140在待预测路段移动的初始时间、物体140移动的当前时间。又例如，获取模块310可以获取物体140的地理位置(比如，经纬度信息)、移动轨迹。物体140的地理移动轨迹可以由物体140的多个地理位置组成。再例如，获取模块310可以获取物体140的移动速度。
确定模块320可以确定交通信号灯130所处的阶段。一个交通信号灯周期可以包括两个以上的阶段。每个阶段可以反映特定时刻交通信号灯周期的进程。
为了说明交通信号灯所处的阶段，举例如下。交通信号灯130具有三个相位，分别为绿灯、黄灯和红灯，对应的配时分别是30秒、3秒和50秒。交通信号灯130周期包括四个阶段，分别为绿灯初始阶段、绿灯后期阶段、红灯初始阶段和红灯后期阶段。绿灯初始阶段可以反映特定时刻该交通信号灯周期的进程为绿灯初期。例如，可以将绿灯的前15秒划分为绿灯初始阶段。绿灯后期阶段可以反映特定时刻该交通信号灯周期的进程为绿灯后期。例如，可以将绿灯的后15秒划分为绿灯后期阶段。红灯初始阶段可以反映特定时刻该交通信号灯周期的进程为黄灯时期和/或红灯初期。例如，可以将黄灯时期的3秒和红灯的前24秒划分为红灯初始阶段。红灯后期阶段可以反映特定时刻该交通信号灯周期的进程为红灯后期。例如，可以将红灯的后26秒划分为红灯后期阶段。
在一些实施例中，交通信号灯130的阶段与交通信号灯130的相位可以一一对应。例如，当交通信号灯130处于上述绿灯初始阶段或绿灯后期阶段时，该交通信号灯130的相位为绿灯。又例如，当交通信号灯130处于上述红灯后期阶段时，该交通信号灯的相位为红灯。
在一些实施例中，交通信号灯130的阶段与交通信号130的相位可以不一一对应。例如，当交通信号灯130处于上述红灯初始阶段时，该交通信号灯130的相位为黄灯和红灯。
需要注意的是，交通信号灯130包括的阶段是可变的，可以根据具体规则进行划分；每个阶段的含义是可变的，可以根据具体的规则进行定义。在一些实施例中，可以根据历史物体轨迹数据划分阶段。在一些实施例中，交通信号灯130的一个周期可以包括三个阶段，比如红灯阶段、绿灯初期阶段和绿灯后期阶段。绿灯初期阶段和绿灯后期阶段可以合称为绿灯阶段。
应当理解的是，当交通信号灯130的周期被划分为具体的阶段时，一个特定的时刻对应一个具体的阶段。那么，确定模块310可以确定当前时刻或特定行为发生时交通信号灯130所处的阶段。作为示例，确定模块320可以确定物体140进入交通信号灯路口时交通信号灯130所处的阶段。所述物体140进入路口是指物体140进入路口所在的道路预设范围(例如，三百米)内。例如，从某道路进入路口时，距离停止线300米以内的范围都算是路口。又例如，以路口中心点为中心向外延伸300米的范围算是路口。再例如，可以是道路路面上交通指示线确定的范围为路口，例如十字路口，四个方向道路的停止线围成的区域为路口。以上仅为对路口的示例性说明，不应理解为对路口定义的限制，在其他实施例中，可以根据实际需要设置路口的具体范围。例如，所述范围可以是10米、50米、100米、150米、200米等。
在上述示例中，确定模块320可以至少基于物体140在待预测路段移动的 初始时间确定物体140进入交通信号灯路口时交通信号灯130所处的阶段。例如，确定模块320可以根据物体140的当前移动速度和物体140的当前位置与交通信号灯路口的距离，预测物体140从待预测路段的初始位置进入交通信号灯路口所需要的时长。结合物体140在待预测路段移动的初始时间，确定模块320可以预测物体140进入交通信号灯路口时的时间。然后，确定模块320可以基于物体140进入交通信号灯路口时的时间确定交通信号灯130所处的阶段。例如，物体140进入交通信号灯路口时是上午10：00：00整，交通信号灯的周期为1分钟，假定交通信号灯的在一个周期内的相位变化是绿灯、黄灯、红灯，则此时交通信号灯处于刚开始的绿灯阶段(也可称为绿灯初始阶段)。
在上述示例中，待预测路段(例如，上文出现的子路段)的起点可以为一个交通信号灯路口。那么，物体140在待预测路段移动的初始时间为物体140进入交通信号灯路口时的时间。此时，确定模块320可以仅根据物体140在待预测路段移动的初始时间确定交通信号灯130所处的阶段。确定方法可参考上述示例。
预测模块330可以至少基于物体140进入交通信号灯路口时交通信号灯130所处的阶段，预测物体140通过待预测路段的时长。所述待预测路段包括所述交通信号灯路口。
为了便于说明，可以将物体140通过待预测路段的时长分为物体140通过待预测路段中交通信号灯路口的时长和通过待预测路段中非交通信号灯路口的时长。进而，预测模块330可以通过预测物体140通过待预测路段中交通信号灯路口的时长和预测物体140通过待预测路段中非交通信号灯路口的时长，预测物体140通过待预测路段的时长。
在一些实施例中，待预测路段可能包括一个交通信号灯路口。预测模块330可以基于物体140进入交通信号灯路口时该交通信号灯所处的阶段，预测物体140通过待预测路段中交通信号灯路口的时长。例如，当物体140进入交通信 号灯路口时该交通信号灯处于绿灯阶段(例如，绿灯初始阶段、绿灯后期阶段)，物体140可以直接通过所述交通信号灯路口，不做停留。预测模块330可以，基于物体140进入所述交通信号灯路口时的地理位置与物体140离开所述交通信号灯路口时的地理位置之间的距离(标记为S1)和物体140的移动速度(标记为V)，预测物体140通过所述交通信号灯路口的时间。又例如，当物体140进入交通信号灯路口时该交通信号灯处于红灯初始阶段或红灯后期阶段，物体140不可以直接通过所述交通信号灯路口，需要等待一段时间(标记为tw)。预测模块330可以基于S1、V和tw预测物体140通过所述交通信号灯路口的时间。
在一些实施例中，待预测路段可能包括两个交通信号灯路口，标记为第一交通信号灯路口和第二交通信号灯路口。预测模块330可以基于物体140进入第一交通信号灯路口时第一交通信号灯所处的阶段，预测物体140通过第一交通信号灯路口的时长。进一步，预测模块330可以基于物体140进入第一交通信号灯路口时第一交通信号灯所处的阶段预测物体进入第二交通信号灯路口时第二交通信号灯所处的阶段。然后，预测模块330可以基于预测的物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段，预测物体140通过第二交通信号灯路口的时长。基于物体140通过第一交通信号灯路口和第二交通信号灯路口的时长，预测模块330可以预测物体140通过待预测路段中交通信号灯路口的时长。
在一些实施例中，待预测路段可能包括三个或三个以上的交通信号灯路口，标记为第一交通信号灯路口、第二交通信号灯路口、第三交通信号灯路口、……、第N-1交通信号灯路口、第N交通信号灯路口。预测模块330可以基于物体140进入第一交通信号灯路口时第一交通信号灯所处的阶段预测物体进入第二交通信号灯路口时第二交通信号灯所处的阶段。预测模块330可以基于物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段预测物体进入第三交通信号灯路口时第三交通信号灯所处的阶段。以此类推，预测模块330可以基 于物体140进入第N-1交通信号灯路口时第N-1交通信号灯所处的阶段预测物体进入第N交通信号灯路口时第N交通信号灯所处的阶段。预测模块330可以基于以上每个交通信号灯所处的阶段预测物体140通过每个交通信号灯路口的时长，进而预测物体140通过待预测路段中交通信号灯路口的时长。
在上述的实施例中，预测模块330可以采用多种方法预测物体140通过每个交通信号灯路口的时长。作为示例，预测模块330可以基于物体140进入交通信号灯路口的地理位置(即，进入该交通信号灯路口预设范围时的地理位置)和离开该交通信号灯路口的地理位置(即，离开该交通信号灯路口预设范围时的地理位置)之间的距离和物体140当前的速度预测物体140通过所述距离的时间(标记为t1)。预测模块330可以根据物体进入该交通信号灯路口时交通信号灯所处的阶段，预测物体140等待的时间(标记为t2)。基于t1和t2，预测模块330可以预测物体140通过该交通信号灯路口的时长。
如上文所述，特定的时刻对应交通信号灯特定的阶段。在一些实施例中，上述基于物体140进入一个交通信号灯路口时交通信号灯(标记为前交通信号灯)所处的阶段预测物体140进入另一个交通信号灯路口时交通信号灯(标记为后交通信号灯)所处的阶段可以等同于，基于物体140进入前交通信号灯路口对应的时刻预测物体140进入后交通信号灯路口对应的时刻。作为示例，预测模块330可以根据物体140的当前速度(或预测速度)和上述两个交通信号灯路口之间的距离，预测物体140从前交通信号灯路口到后交通信号灯路口所需要的时长。结合物体140进入前交通信号灯路口时对应的时刻以及预测的物体140通过前交通信号灯路口的时长，预测模块330可以预测物体140进入后交通信号灯路口对应的时刻。进而，预测模块330可以预测物体140进入后交通信号灯路口时后交通信号灯所处的阶段。
在一些实施例中，多个交通信号灯130可以根据特定的交通信号灯规则设 置。例如，道路上连续的两个交通信号灯130，标记为前交通信号灯(例如，第一交通信号灯)和后交通信号灯(例如，第二交通信号灯)，可以根据特定的交通信号灯规则设置。所述交通信号灯规则可以反映交通信号灯的相位、交通信号灯每个相位的配时、同一时刻不同交通信号灯周期进程(例如，交通信号灯所处的阶段)之间的对应关系。那么，预测模块330可以依据所述交通信号灯规则预测物体140进入交通信号灯路口时交通信号灯所处的阶段。
作为示例，所述交通信号灯设置规则可以是，第一交通信号灯和第二交通信号灯均包括三个相位，分别是绿灯、黄灯和红灯；当第一交通信号灯处于绿灯初始阶段时，第二交通信号灯处于绿灯后期阶段；当第一交通信号灯处于绿灯后期阶段时，第二交通信号灯处于红灯初始阶段。当物体140以预设速度移动时，预测模块330可以进行以下预测。当物体140通过第一交通信号灯路口第一交通信号灯处于绿灯初期阶段时，物体140通过第二交通信号灯路口第二交通信号灯处于绿灯阶段；当物体140通过第一交通信号灯路口第一交通信号灯处于绿灯后期阶段时，物体140通过第二交通信号灯路口第二交通信号灯处于红灯阶段。在一些实施例中，所述物体140的预设速度可以是特定时刻该道路上所有车辆的平均速度，也可以是道路限速范围内的平均速度(例如，最大限速和最小限速的平均值)。
为了说明物体140进入交通信号灯路口时交通信号灯130所处的阶段对物体140通过所述交通信号灯路口的时长影响，结合图6举例如下。
图6是一种根据本申请的一些实施例所示的示例性物体移动轨迹图。物体移动轨迹图600的横坐标为时间，纵坐标为距离。物体移动轨迹图600包括多条物体移动轨迹，例如，移动轨迹640和移动轨迹650。
移动轨迹640描述的是第一物体从第一交通信号灯路口610，途径第二交通信号灯路口620，移动至第三交通信号灯路口630形成的移动轨迹。移动轨迹 650描述的第二物体从第一交通信号灯路口610，途径第二交通信号灯路口620，移动至第三交通信号灯路口630形成的移动轨迹。第一物体和第二物体移动的速率是相同的或相当的，均是介于预设速度范围内。
交通信号灯路口610设置的交通信号灯有三个相位，分别为绿灯611、黄灯612和红灯613。交通信号灯路口620设置的交通信号灯有三个相位，分别为绿灯621、黄灯622和红灯623。交通信号灯路口630设置的交通信号灯有三个相位，分别为绿灯631、黄灯632和红灯633。
交通信号灯路口610、交通信号灯路口620和交通信号灯路口630处的交通信号灯是按照一定的交通信号灯设置规则设置的。当第一物体经过第一交通信号灯路口610第一交通信号灯为绿灯611(或称为绿灯初始阶段)时，第一物体经过第二交通信号灯路口620第二交通信号灯为绿灯621(或称为绿灯阶段)，第一物体经过第三交通信号灯路口630第三交通信号灯为绿灯631(或称为绿灯阶段)。此时，第一物体通过移动轨迹640的通行时长为T1。当第二物体经过第一交通信号灯路口610第一交通信号灯为绿灯611(或称为绿灯后期阶段)时，第二物体经过第二交通信号灯路口620第二交通信号灯为红灯623(或称为红灯阶段)，第二物体经过第三交通信号灯路口630第三交通信号灯为红灯633(或称为红灯阶段)。此时，第二物体通过移动轨迹650的通行时长为T2。
如图6所示，当第一物体和第二物体的移动距离相同或相当，通过路段的移动的速度相同或相当，T1远远小于T2。由此可见，物体140进入交通信号灯路口时交通信号灯130所处的阶段对物体140通过所述交通信号灯路口的时长有较大的影响。结合特定的交通信号灯设置规则，当物体140进入第一交通信号灯路口第一交通信号灯处于绿灯初始阶段时，物体140通过待预测路段的时长较短；当物体140进入第一交通信号灯路口第一交通信号灯处于绿灯后期阶段时，物体140通过待预测路段的时长较长。
在一些实施例中，预测模块330还可以预测物体140通过待预测路段中非交通信号灯路口的时长。所述非交通信号灯路口是指两个连续交通信号灯路口(标记为前交通信号灯和后交通信号灯)之间的路段，即物体140离开前交通信号灯路口时的地理位置与物体140进入后交通信号灯路口的地理位置之间的路段，其距离标记为S2。所述物体140离开交通信号路口是指物体140离开路口所在的道路预设范围(例如，三百米)内。例如，从某道路离开交通信号路口时，当物体140距离停止线300米以外时表示物体140离开交通信号灯路口。又例如，当物体140距离以路口中心点为中心向外延伸300米的范围外时表示物体140离开交通信号灯路口。再例如，当物体140离开道路路面上交通指示线确定的范围外时表示物体140离开交通信号灯路口。
在一些实施例中，预测模块330可以通过非交通信号路口的交通状态信息预测物体140通过待预测路段中非交通信号灯路口的时长。所述交通状态信息包括交通拥堵信息、历史轨迹数据和物体140的移动速度，例如当前移动速度(标记为Vc)。
例如，预测模块330可以根据交通拥堵信息预测物体140的移动速度(标记为Vp)。然后，基于S2和Vp，预测模块330可以预测物体140通过待预测路段中非交通信号灯路口的时长。
又例如，预测模块330可以根据历史轨迹数据(例如，物体移动轨迹图600)预测物体140通过待预测路段中非交通信号灯路口的时长。作为示例，预测模块330可以根据物体140在特定时刻通过待预测路段中非交通信号灯路口的历史时长，预测物体140在相同的特定时刻通过所述待预测路段中非交通信号灯路口的时长。在一些具体实施例中，所述历史时长可以是过去一段时期(例如，一个星期、半个月、一个月、一个季度)内的通行时长。在一些实施例中，特定时刻对应的历史时长与特定的日期有关。例如，2018年5月1号(例如，五 一劳动节、周三)15:00pm对应的历史时长与2017年5月1号或者4月24号(即，上周三)的通行时长有关。又例如，周五18:00pm对应的历史时长与过去一个月内的各个周五的18:00pm的通信时长有关。
再例如，预测模块330可以直接根据物体140的当前移动速度Vc预测物体140通过待预测路段中非交通信号灯路口的时长。例如，预测模块330可以基于S2和Vc，预测物体140通过待预测路段中非交通信号灯路口的时长。
综上，预测模块330可以分别预测物体140通过待预测路段中交通信号灯路口的时长和通过待预测路段中非交通信号灯路口的时长，从而预测物体140通过待预测路段的总时长。
在一些实施例中，总路段被划分为多个待预测路段(或称为子路段)。预测模块330可以基于每个待预测路段的通行时长，预测所述总路段的通行时长。
在一些实施例中，预测模块330可以动态地更新路段的通行时长。例如，当物体140的移动速度(例如，Vp和Vc)、路段的交通拥堵信息、历史轨迹数据改变时，预测模块330可以根据改变后的物体140的移动速度、路段的交通拥堵信息和历史轨迹数据动态地更新路段的通行时长。又例如，预测模块330可以定期动态地更新路段的通行时长。
在一些实施例中，预测模块330可以基于通行时长预测模型确定物体通过路段的通行时长。所述通行时长预测模型可以是机器学习模型，例如，神经网络模型，基于一段时间内(例如，一周内)通过该路段的所有物体产生的历史交通信息状态信息，包括但不限于历史交通拥堵信息、历史物体轨迹数据、交通信号灯周期、物体的历史移动速度、物体通过路段的历史通行时间等或其任意组合，训练后得到。所述通行时长预测模型的训练过程可以由训练模块350执行。训练模块350可以利用所述历史交通信息状态信息对通行时长预测模型进行训练，在达到预设条件时，例如，训练次数达到预设值或模型已收敛(例如，损失函 数的值小于预设值)，可以输出最终的通行时长预测模型。在一些实施例中，训练模块350还可以利用所述物体通过所述子路段时产生的数据，例如，通行时长，交通拥堵信息、轨迹数据、交通信号灯周期、移动速度等，对所述通行时长预测模型进行更新。
发送模块340可以发送信息。在一些实施例中，发送模块340可以向物体140发送提示信息。例如，当预测模块330预测物体140即将进入的交通信号灯路口的交通信号灯处于红灯阶段时，发送模块340可以向物体140发送提示信息，提示物体140即将进入的交通信号灯路口的交通信号灯处于红灯阶段。又例如，当前方路段出现拥堵时，发送模块340可以向物体140发送提示信息，提示物体140即将进入拥堵路段。
应该注意的是，关于预测通行时长系统300的描述出于说明性目的，并不用于限制本申请的保护范围。对于本领域的技术人员来说，可以在本申请的指示下做出多个变体和修改。然而，这些变体和修改不会脱离本申请的保护范围。例如，预测模块330可以基于交通信号路口的交通拥堵信息、历史轨迹数据和物体140的移动速度预测物体140通过待预测路段中交通信号灯路口的时长。又例如，预测模块330可以对待预测路段的通行时长进行整体的预测，而不是将待预测路段的通行时长分为物体140通过待预测路段中交通信号灯路口的时长和通过待预测路段中非交通信号灯路口的时长。
图4所示为根据本申请一些实施例所示的通行时长预测方法的示例性流程图。通行时长预测方法400可以由预测通行时长系统300执行。如图4所示，通行时长预测方法400可以包括：
步骤410，确定模块320可以确定物体140进入第一交通信号灯路口时第一交通信号灯所处的阶段。
在一些实施例中，确定模块320可以至少基于物体140在子路段移动的初 始时间确定物体140进入第一交通信号灯路口时第一交通信号灯130所处的阶段。所述子路段作为待预测路段，所述子路段包括所述第一交通信号灯路口。
例如，获取模块310获取物体140在子路段移动的初始时间。确定模块320可以至少基于所述初始时间，确定物体140进入第一交通信号灯路口时第一交通信号灯130所处的阶段。
又例如，当子路段(例如，上文出现的子路段)的起点为所述第一交通信号灯路口时，物体140在子路段移动的初始时间为物体140进入第一交通信号灯路口时的时间。此时，确定模块320可以仅根据物体140在子路段移动的初始时间确定交通信号灯130所处的阶段。
上述确定交通信号灯130所处的阶段的具体方法可以参见图3的相关描述。
步骤420，预测模块330可以至少基于所述第一交通信号灯所处的阶段，预测物体140通过子路段的时长。
为了便于说明，可以将物体140通过子路段的时长分为物体140通过子路段中交通信号灯路口的时长和通过子路段中非交通信号灯路口的时长。进而，预测模块330可以通过预测物体140通过子路段中交通信号灯路口的时长和预测物体140通过子路段中非交通信号灯路口的时长，预测物体140通过子路段的时长。
在一些实施例中，子路段可能包括一个交通信号灯路口。预测模块330可以基于物体140进入交通信号灯路口时该交通信号灯所处的阶段，预测物体140通过子路段中交通信号灯路口的时长。
在一些实施例中，子路段可能包括两个交通信号灯路口，标记为第一交通信号灯路口和第二交通信号灯路口。预测模块330可以基于物体140进入第一交通信号灯路口时第一交通信号灯所处的阶段，预测物体140通过第一交通信号灯路口的时长。进一步，预测模块330可以基于物体140进入第一交通信号灯路口 时第一交通信号灯所处的阶段预测物体进入第二交通信号灯路口时第二交通信号灯所处的阶段。然后，预测模块330可以基于预测的物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段，预测物体140通过第二交通信号灯路口的时长。基于物体140通过第一交通信号灯路口和第二交通信号灯路口的时长，预测模块330可以预测物体140通过子路段中交通信号灯路口的时长。
在一些实施例中，子路段可能包括三个或三个以上的交通信号灯路口，标记为第一交通信号灯路口、第二交通信号灯路口、第三交通信号灯路口、……、第N-1交通信号灯路口、第N交通信号灯路口。预测模块330可以基于物体140进入第一交通信号灯路口时第一交通信号灯所处的阶段预测物体进入第二交通信号灯路口时第二交通信号灯所处的阶段。预测模块330可以基于物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段预测物体进入第三交通信号灯路口时第三交通信号灯所处的阶段。以此类推，预测模块330可以基于物体140进入第N-1交通信号灯路口时第N-1交通信号灯所处的阶段预测物体进入第N交通信号灯路口时第N交通信号灯所处的阶段。预测模块330可以基于以上每个交通信号灯所处的阶段预测物体140通过每个交通信号灯路口的时长，进而预测物体140通过子路段中交通信号灯路口的时长。
上述基于物体140进入前交通信号灯路口时前交通信号灯(例如，第一交通信号灯)所处的阶段预测物体140进入后交通信号灯路口时后交通信号灯(例如，第二交通信号灯)所处的阶段可以参见图3和图5的相关描述。
上述预测物体140通过每个交通信号灯路口的时长可以参见图3的相关描述。
在一些实施例中，预测模块330可以预测物体140通过子路段中非交通信号灯路口的时长。预测模块330可以通过非交通信号路口的交通拥堵信息、历史轨迹数据和物体140的当前移动速度预测物体140通过子路段中非交通信号灯路 口的时长。具体预测物体通过子路段中非交通信号灯路口的时长可以参考图3的相关描述。
综上，预测模块330可以分别预测物体140通过子路段中交通信号灯路口的时长和通过子路段中非交通信号灯路口的时长，从而预测物体140通过子路段的总时长。
在一些实施例中，预测模块330可以基于通行时长预测模型和物体通过所述子路段时所述交通信号灯所处的阶段，预测物体通过所述子路段的通行时长。所述通行时长预测模型可以用训练模块350基于历史数据训练后得到。在一些实施例中，所述历史数据可以是通过路段的物体的历史交通状态信息，包括但不限于历史交通拥堵信息、历史物体轨迹数据、交通信号灯周期、物体的历史移动速度、物体通过路段的历史通行时间等或其任意组合。所述历史交通拥堵信息可以是在过去特定的一段的时间内(例如，一天、一周等)所述路段的交通拥堵情况。所述历史物体轨迹数据可以是在过去特定的一段的时间内(例如，一天、一周等)内通过所述路段的所有物体的轨迹数据。所述交通信号灯周期可以是所述路段的交通信号灯的周期。所述物体的历史移动速度可以是在过去特定的一段的时间内(例如，一天、一周等)通过所述路段的每个物体的速度及其变化情况。在一些实施例中，所述通行时长预测模型可以是机器学习模型，包括但不限于支持向量机(Support Vector Machine，SVM)、朴素贝叶斯(Naive Bayes，NB)、k最邻近(k-Nearest Neighbor，kNN)、决策树(Decision Tree，DT)、人工神经网络(Artificial Neural Network，ANN)等或其任意组合。训练模块350可以利用所述历史交通状态信息作为输入对模型进行训练，当模型满足一定条件时，例如，训练次数达到预定值和/或模型收敛，可以停止训练。训练后的模型可以被指定为所述通行时长预测模型。
在一些实施例中，预测模块330可以将物体通过路段时交通信号灯所处的 阶段以及所述物体在所述子路段移动的初始时间输入至所述通行时长预测模型，直接得到物体通过子路段所需通行时长。对于具有多个子路段的总路段，预测模块330可以基于所述通行时长模型分别预测物体通过每个子路段的时长，最终获得通过总路段的总时长。
在一些实施例中，在所述物体通过路段后，训练模块350可以获取物体在运动过程中产生的数据，例如，通行时长，交通拥堵信息、轨迹数据、交通信号灯周期、移动速度等。每隔一个特定的时间(例如，一天，)训练模块350可以利用在该时间内获取的通过该路段的物体的上述数据，对所述通行时长预测模型进行更新，以提升模型预测的准确性。在一些实施例中，上述子路段可以为，获取模块310基于物体140当前的移动轨迹从候选移动轨迹中选择的路段。
在一些实施例中，上述子路段可以为，获取模块310从总路段中划分的一部分。
需要注意的是，以上对于通行时长预测方法400的描述，仅为描述方便，并不能把本申请限制在所举实施例范围之内。可以理解，对于本领域的技术人员来说，在了解该方法的原理后，可能在不背离这一原理的情况下，做出多个变体和修改。然而，这些变体和修改不会脱离本申请的保护范围。例如，预测模块330可以动态地更新物体140通过子路段的时长。又例如，预测模块330可以对子路段的通行时长进行整体的预测，而不是分别预测物体140通过子路段中交通信号灯路口的时长和通过子路段中非交通信号灯路口的时长。。
图5所示为根据本申请的一些实施例所示的通行时长预测方法的示例性流程图。通行时长预测方法500可以由预测通行时长系统300执行。通行时长预测方法500可以为通行时长预测方法400的进一步展开。如图5所示，通行时长预测方法500可以包括：
步骤510，预测模块330可以基于物体140进入第一交通信号灯路口时第 一交通信号灯所处的阶段，预测物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段。所述第一交通信号灯路口和第二交通信号灯路口可以是相邻的两个交通信号灯路口或非相邻的两个交通信号灯路口
如上文所述，特定的时刻对应交通信号灯特定的阶段。在一些实施例中，上述基于物体140进入第一交通信号灯路口时第一交通信号灯所处的阶段预测物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段可以等同于，基于物体140进入第一交通信号灯路口对应的时刻预测物体140进入第二交通信号灯路口对应的时刻。作为示例，预测模块330可以根据物体140的当前速度(或预测速度)和上述第一交通信号灯路口和第二交通信号灯路口之间的距离，预测物体140从第一交通信号灯路口到第二交通信号灯路口所需要的时长。结合物体140进入第一交通信号灯路口时对应的时刻以及预测的物体140通过第一交通信号灯路口的时长，预测模块330可以预测物体140进入第二交通信号灯路口对应的时刻。进而，预测模块330可以预测物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段。
在一些实施例中，上述第一交通信号灯和第二交通信号灯可以根据特定的交通信号灯设置规则设置。作为示例，所述交通信号灯设置规则可以是，第一交通信号灯和第二交通信号灯均包括三个相位，分别是绿灯、黄灯和红灯；当第一交通信号灯处于绿灯初始阶段时，第二交通信号灯处于红灯后期阶段；当第一交通信号灯处于绿灯后期阶段时，第二交通信号灯处于红灯初始阶段。当物体140以预设速度移动时，预测模块330可以预测进行以下预测。当物体140通过第一交通信号灯路口第一交通信号灯处于绿灯初期阶段时，物体140通过第二交通信号灯路口第二交通信号灯处于绿灯阶段；当物体140通过第一交通信号灯路口第一交通信号灯处于绿灯后期阶段时，体140通过第二交通信号灯路口第二交通信号灯处于红灯阶段。
上述预测物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段的具体方法可以参见图3的相关描述。
步骤520，预测模块330可以至少基于所述第二交通信号灯所处的阶段，预测物体140通过子路段的时长。
为了便于说明，可以将物体140通过子路段的时长分为物体140通过子路段中交通信号灯路口的时长和通过子路段中非交通信号灯路口的时长。进而，预测模块330可以通过预测物体140通过子路段中交通信号灯路口的时长和预测物体140通过子路段中非交通信号灯路口的时长，预测物体140通过子路段的时长。
在一些实施例中，上述子路段可能仅包括第一交通信号灯路口和第二交通信号灯路口。预测模块330可以基于物体140进入第一交通信号灯路口时第一交通信号灯所处的阶段，预测物体140通过第一交通信号灯路口的时长。然后，预测模块330可以基于预测的物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段，预测物体140通过第二交通信号灯路口的时长。基于物体140通过第一交通信号灯路口和第二交通信号灯路口的时长，预测模块330可以预测物体140通过子路段中交通信号灯路口的时长。
在一些实施例中，上述子路段可能包括第一交通信号灯路口、第二交通信号灯路口和其他交通信号灯路口。其他交通信号灯路口可以被标记为第三交通信号灯路口、……、第N-1交通信号灯路口和第N交通信号灯路口。预测模块330可以基于物体140进入第二交通信号灯路口时第二交通信号灯所处的阶段预测物体进入第三交通信号灯路口时第三交通信号灯所处的阶段。以此类推，预测模块330可以基于物体140进入第N-1交通信号灯路口时第N-1交通信号灯所处的阶段预测物体进入第N交通信号灯路口时第N交通信号灯所处的阶段。预测模块330可以基于以上每个交通信号灯所处的阶段预测物体140通过每个交通 信号灯路口的时长，进而预测物体140通过子路段中交通信号灯路口的时长。
上述预测物体140通过每个交通信号灯路口的时长可以参见图3的相关描述。
在一些实施例中，预测模块330可以预测物体140通过子路段中非交通信号灯路口的时长。预测模块330可以通过非交通信号路口的交通拥堵信息、历史轨迹数据和物体140的当前移动速度预测物体140通过子路段中非交通信号灯路口的时长。具体预测物体通过子路段中非交通信号灯路口的时长可以参考图3的相关描述。
综上，预测模块330可以分别预测物体140通过子路段中每个交通信号灯路口的时长以及物体140通过子路段中非交通信号灯路口的时长，从而预测物体140通过子路段的总时长。
步骤530，当预测物体140通过所述第二交通信号灯路口所述第二交通信号灯处于红灯阶段时，发送模块340发送提示信息。所述提示信号可以包括提示物体140即将进入的第二交通信号灯路口的交通信号灯处于红灯阶段。
需要注意的是，以上对于通行时长预测方法500的描述，仅为描述方便，并不能把本申请限制在所举实施例范围之内。可以理解，对于本领域的技术人员来说，在了解该方法的原理后，可能在不背离这一原理的情况下，做出多个变体和修改。然而，这些变体和修改不会脱离本申请的保护范围。例如，预测模块330可以动态地更新物体140通过子路段的时长。又例如，预测模块330可以对子路段的通行时长进行整体的预测，而不是分别预测物体140通过子路段中交通信号灯路口的时长和通过子路段中非交通信号灯路口的时长。再例如，步骤530可以被省略。
与现有技术相比，本申请实施例可能带来的有益效果包括但不限于：
一、对于包括交通信号灯路口的待预测路段，至少基于物体进入交通信号 灯路口时交通信号灯所处的阶段，预测物体通过该待预测路段的通行时长时，通行时长的预测更加精确。
二、基于历史轨迹数据构建通行时长预测模型，并结合物体进入交通信号灯路口时交通信号灯的阶段，对物体通过待预测路段的通行时长进行精准预测。
三、通过对行程分段实现长距离行程和非直行路段的时间预测。
需要说明的是，不同实施例可能产生的有益效果不同，在不同的实施例里，可能产生的有益效果可以是以上任意一种或几种的组合，也可以是其他任何可能获得的有益效果。
上文已对基本概念做了描述，显然，对于本领域技术人员来说，上述发明披露仅仅作为示例，而并不构成对本申请的限定。虽然此处并没有明确说明，本领域技术人员可能会对本申请进行各种修改、改进和修正。该类修改、改进和修正在本申请中被建议，所以该类修改、改进和修正仍属于本申请示范实施例的精神和范围。
同时，本申请使用了特定词语来描述本申请的实施例。如“一个实施例”、“一实施例”、和/或“一些实施例”意指与本申请至少一个实施例相关的某一特征、结构或特点。因此，应强调并注意的是，本说明书中在不同位置两次或多次提及的“一实施例”或“一个实施例”或“一替代性实施例”并不一定是指同一实施例。此外，本申请的一个或多个实施例中的某些特征、结构或特点可以进行适当的组合。
此外，本领域技术人员可以理解，本申请的各方面可以通过若干具有可专利性的种类或情况进行说明和描述，包括任何新的和有用的工序、机器、产品或物质的组合，或对他们的任何新的和有用的改进。相应地，本申请的各个方面可以完全由硬件执行、可以完全由软件(包括固件、常驻软件、微码等)执行、也可以由硬件和软件组合执行。以上硬件或软件均可被称为“数据块”、“模 块”、“引擎”、“单元”、“组件”或“系统”。此外，本申请的各方面可能表现为位于一个或多个计算机可读介质中的计算机产品，该产品包括计算机可读程序编码。
计算机可读信号介质可能包含一个内含有计算机程序编码的传播数据信号，例如在基带上或作为载波的一部分。该传播信号可能有多种表现形式，包括电磁形式、光形式等等、或合适的组合形式。计算机可读信号介质可以是除计算机可读存储介质之外的任何计算机可读介质，该介质可以通过连接至一个指令执行系统、装置或设备以实现通信、传播或传输供使用的程序。位于计算机可读信号介质上的程序编码可以通过任何合适的介质进行传播，包括无线电、电缆、光纤电缆、RF、或类似介质、或任何上述介质的组合。
本申请各部分操作所需的计算机程序编码可以用任意一种或多种程序语言编写，包括面向对象编程语言如Java、Scala、Smalltalk、Eiffel、JADE、Emerald、C++、C#、VB.NET和Python等，常规程序化编程语言如C语言、Visual Basic、Fortran 2003、Perl、COBOL 2002、PHP和ABAP，动态编程语言如Python、Ruby和Groovy，或其他编程语言等。该程序编码可以完全在用户计算机上运行、或作为独立的软件包在用户计算机上运行、或部分在用户计算机上运行部分在远程计算机运行、或完全在远程计算机或服务器上运行。在后种情况下，远程计算机可以通过任何网络形式与用户计算机连接，比如局域网(LAN)或广域网(WAN)，或连接至外部计算机(例如通过因特网)，或在云计算环境中，或作为服务使用如软件即服务(SaaS)。
此外，除非权利要求中明确说明，本申请所述处理元素和序列的顺序、数字字母的使用、或其他名称的使用，并非用于限定本申请流程和方法的顺序。尽管上述披露中通过各种示例讨论了一些目前认为有用的发明实施例，但应当理解的是，该类细节仅起到说明的目的，附加的权利要求并不仅限于披露的实 施例，相反，权利要求旨在覆盖所有符合本申请实施例实质和范围的修正和等价组合。例如，虽然以上所描述的系统组件可以通过硬件设备实现，但是也可以只通过软件的解决方案得以实现，如在现有的服务器或移动设备上安装所描述的系统。
同理，应当注意的是，为了简化本申请披露的表述，从而帮助对一个或多个发明实施例的理解，前文对本申请实施例的描述中，有时会将多种特征归并至一个实施例、附图或对其的描述中。但是，这种披露方法并不意味着本申请对象所需要的特征比权利要求中提及的特征多。实际上，实施例的特征要少于上述披露的单个实施例的全部特征。
一些实施例中使用了描述成分、属性数量的数字，应当理解的是，此类用于实施例描述的数字，在一些示例中使用了修饰词“大约”、“近似”或“大体上”来修饰。除非另外说明，“大约”、“近似”或“大体上”表明所述数字允许有±20％的变化。相应地，在一些实施例中，说明书和权利要求中使用的数值参数均为近似值，该近似值根据个别实施例所需特点可以发生改变。在一些实施例中，数值参数应考虑规定的有效数位并采用一般位数保留的方法。尽管本申请一些实施例中用于确认其范围广度的数值域和参数为近似值，在具体实施例中，此类数值的设定在可行范围内尽可能精确。
针对本申请引用的每个专利、专利申请、专利申请公开物和其他材料，如文章、书籍、说明书、出版物、文档或物件等，特此将其全部内容并入本申请作为参考。与本申请内容不一致或产生冲突的申请历史文件除外，对本申请权利要求最广范围有限制的文件(当前或之后附加于本申请中的)也除外。需要说明的是，如果本申请附属材料中的描述、定义和/或术语的使用与本申请所述内容有不一致或冲突的地方，以本申请的描述、定义和/或术语的使用为准。
最后，应当理解的是，本申请中所述实施例仅用以说明本申请实施例的原 则。其他的变形也可能属于本申请的范围。因此，作为示例而非限制，本申请实施例的替代配置可视为与本申请的教导一致。相应地，本申请的实施例不仅限于本申请明确介绍和描述的实施例。

Claims (28)

  1. 一种预测通行时长的方法，其特征在于，所述方法包括：
    确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段；
    至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长；
    其中，一个交通信号灯周期至少包括两个阶段，所述子路段包括所述第一交通信号灯路口。
  2. 根据权利要求1所述的方法，其特征在于，确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段包括：
    获取所述物体在所述子路段移动的初始时间和所述第一交通信号灯周期；
    至少基于所述初始时间和所述第一交通信号灯周期，确定所述物体进入所述第一交通信号灯路口时所述第一交通信号灯所处的阶段。
  3. 根据权利要求2所述的方法，其特征在于，所述子路段的起点为所述第一交通信号灯路口，所述初始时间为所述物体进入所述第一交通信号灯路口的时间。
  4. 根据权利要求1所述的方法，其特征在于，
    所述子路段进一步包括第二交通信号灯路口；
    至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长包括：
    基于所述第一交通信号灯所处的阶段，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段；
    至少基于所述第一交通信号灯所处的阶段与所述第二交通信号灯所处的阶段，预测所述物体通过所述子路段的时长。
  5. 根据权利要求4所述的方法，其特征在于，
    一个交通信号灯周期至少包括红灯阶段和绿灯阶段；
    所述方法进一步包括：
    当预测所述物体通过所述第二交通信号灯路口所述第二交通信号灯处于红灯阶段时，发送提示信息，所述提示信息包括所述第二交通信号灯处于红灯阶段。
  6. 根据权利要求4所述的方法，其特征在于，所述基于所述第一交通信号灯所处的阶段，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段包括：
    基于所述第一交通信号灯所处的阶段以及设置所述第一交通信号灯和所述第二交通信号灯的交通信号灯规则，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段。
  7. 根据权利要求4所述的方法，其特征在于，
    一个交通信号灯周期至少包括红灯阶段和绿灯阶段，所述绿灯阶段至少包括绿灯初期阶段和绿灯后期阶段；
    所述方法进一步包括：
    当所述物体进入所述第一交通信号灯路口第一交通信号灯处于绿灯初期阶段时，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯处于绿灯阶段；
    当所述物体进入所述第一交通信号灯路口第一交通信号灯处于绿灯后期阶段时，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯处于红灯阶段。
  8. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    获取所述子路段的交通状态信息；所述交通状态信息包括以下中的至少一个：交通拥堵信息、所述子路段的历史物体轨迹数据或所述物体的移动速度；
    至少基于所述第一交通信号灯所处的阶段以及所述交通状态信息，预测所述物体通过所述子路段的时长。
  9. 根据权利要求1所述的方法，其特征在于，所述方法进一步包括：
    获取通过一个总路段的历史交通状态信息；所述历史交通状态信息包括以下中的至少一个：历史交通拥堵信息、历史物体轨迹数据、交通信号灯周期、物体的历史移动速度、物体通过所述总路段的历史通行时长；所述总路段包括至少一个子路段，每个子路段包括至少一个交通信号灯路口；
    基于所述历史交通状态信息，确定通行时长预测模型；
    至少基于物体通过每个子路段时所述交通信号灯所处的阶段以及所述通行时长预测模型，预测物体通过所述总路段的通行时长。
  10. 根据权利要求9所述的方法，其特征在于，所述方法进一步包括：
    至少基于所述物体通过所述总路段的通行时长，动态更新所述通行时长预测模型。
  11. 根据权利要求1所述的方法，其特征在于，所述方法进一步包括：
    获取所述物体的候选移动轨迹；
    基于所述物体当前的移动轨迹，从所述候选移动轨迹中选择所述子路段。
  12. 根据权利要求1所述的方法，其特征在于，所述方法进一步包括：
    将总路段划分为多个子路段，所述多个子路段中的至少一个子路段包括至少一个交通信号灯路口；
    基于每个子路段的通行时长，预测所述总路段的通行时长。
  13. 根据权利要求12所述的方法，其特征在于，所述方法进一步包括：动态地更新所述总路段的通行时长。
  14. 一种预测通行时长的系统，其特征在于，所述系统包括确定模块和预测模块；
    所述确定模块用于，确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段；
    所述预测模块用于，至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长；
    其中，一个交通信号灯周期至少包括两个阶段，所述子路段包括所述第一交通信号灯路口。
  15. 根据权利要求14所述的系统，其特征在于，所述系统进一步包括获取模块，
    所述获取模块用于，获取所述物体在所述子路段移动的初始时间和所述第一交通信号灯周期；
    所述确定模块还用于，至少基于所述初始时间和所述第一交通信号灯周期，确定所述物体进入所述第一交通信号灯路口时所述第一交通信号灯所处的阶段。
  16. 根据权利要求15所述的系统，其特征在于，所述子路段的起点为所述第一交通信号灯路口，所述初始时间为所述物体进入所述第一交通信号灯路口的时间。
  17. 根据权利要求14所述的系统，其特征在于，所述子路段进一步包括第二交通信号灯路口；所述预测模块进一步用于：
    基于所述第一交通信号灯所处的阶段，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段；
    至少基于所述第一交通信号灯所处的阶段与所述第二交通信号灯所处的阶段，预测所述物体通过所述子路段的时长。
  18. 根据权利要求17所述的系统，其特征在于，所述预测模块进一步用于：
    基于所述第一交通信号灯所处的阶段以及设置所述第一交通信号灯和所述第二交通信号灯的交通信号灯规则，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯所处的阶段。
  19. 根据权利要求17所述的系统，其特征在于，一个交通信号灯周期至少包括红灯阶段和绿灯阶段；所述系统进一步包括发送模块，
    所述发送模块用于，当预测所述物体通过所述第二交通信号灯路口所述第二交通信号灯处于红灯阶段时，发送提示信息，所述提示信息包括所述第二交通信号灯处于红灯阶段。
  20. 根据权利要求17所述的系统，其特征在于，一个交通信号灯周期至少包括红灯阶段和绿灯阶段，所述绿灯阶段至少包括绿灯初期阶段和绿灯后期阶段；所述预测模块还用于：
    当所述物体进入所述第一交通信号灯路口第一交通信号灯处于绿灯初期阶段时，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯处于绿灯阶段；
    当所述物体进入所述第一交通信号灯路口第一交通信号灯处于绿灯后期阶段时，预测所述物体通过所述第二交通信号灯路口时所述第二交通信号灯处于红灯阶段。
  21. 根据权利要求14所述的系统，其特征在于，
    所述获取模块还用于，获取所述子路段的交通状态信息；所述交通状态信息包括以下中的至少一个：交通拥堵信息、所述子路段的历史物体轨迹数据或所述物体的移动速度；
    所述预测模块还用于，至少基于所述第一交通信号灯所处的阶段以及所述交通状态信息，预测所述物体通过所述子路段的时长。
  22. 根据权利要求14所示的系统，其特征在于，所述系统进一步包括训练模块，所述训练模块，用于确定通行时长预测模型；确定方法包括：
    获取通过一个总路段的历史交通状态信息；所述历史交通状态信息包括以下中的至少一个：交通拥堵信息、所述总路段的历史物体轨迹数据、交通信号灯周期、物体的移动速度；所述总路段包括至少一个子路段，每个子路段包括至少一个交通信号灯路口；
    基于所述历史交通状态信息，确定通行时长预测模型；
    所述预测模块，还用于至少基于物体通过每个子路段时所述交通信号灯所处的阶段以及所述通行时长预测模型，预测物体通过每个子路段的通行时长。
  23. 根据权利要求22所述的系统，其特征在于，所述训练模块还用于：
    基于所述物体通过所述总路段的通行时长，动态更新所述通行时长预测模型。
  24. 根据权利要求14所述的系统，其特征在于，所述获取模块还用于：
    获取所述物体的候选移动轨迹；
    基于所述物体当前的移动轨迹，从所述候选移动轨迹中选择所述子路段。
  25. 根据权利要求14所述的系统，其特征在于，
    所述获取模块还用于，将总路段划分为多个子路段，所述多个子路段中的至少一个子路段包括至少一个交通信号灯路口；
    所述预测模块还用于，基于每个子路段的通行时长，预测所述总路段的通行时长。
  26. 根据权利要求25所述的系统，其特征在于，所述预测模块还用于动态地更新所述总路段的通行时长。
  27. 一种计算机可读存储介质，所述存储介质存储指令，所述指令被执行时：
    确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段；
    至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长；
    其中，一个交通信号灯周期至少包括两个阶段，所述子路段包括所述第一交通信号灯路口。
  28. 一种预测通行时长的装置，其特征在于包括处理器，所述处理器运行时执行以下的方法：
    确定物体进入第一交通信号灯路口时第一交通信号灯所处的阶段；
    至少基于所述第一交通信号灯所处的阶段，预测所述物体通过子路段的时长；
    其中，一个交通信号灯周期至少包括两个阶段，所述子路段包括所述第一交通信号灯路口。
PCT/CN2018/123291 2018-11-16 2018-12-25 预测通行时长的方法和系统 Ceased WO2020098079A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/226,110 US20210241613A1 (en) 2018-11-16 2021-04-09 Methods and systems for predicting travel time

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811372599.6A CN111199642B (zh) 2018-11-16 2018-11-16 预测通行时长的方法和系统
CN201811372599.6 2018-11-16

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/226,110 Continuation US20210241613A1 (en) 2018-11-16 2021-04-09 Methods and systems for predicting travel time

Publications (1)

Publication Number Publication Date
WO2020098079A1 true WO2020098079A1 (zh) 2020-05-22

Family

ID=70731327

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/123291 Ceased WO2020098079A1 (zh) 2018-11-16 2018-12-25 预测通行时长的方法和系统

Country Status (3)

Country Link
US (1) US20210241613A1 (zh)
CN (1) CN111199642B (zh)
WO (1) WO2020098079A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112330962A (zh) * 2020-11-04 2021-02-05 杭州海康威视数字技术股份有限公司 交通信号灯控制方法、装置、电子设备及计算机存储介质

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111932872B (zh) * 2020-06-29 2022-08-02 阿里巴巴集团控股有限公司 一种交通控制方法、装置及电子设备
CN111787491B (zh) * 2020-06-29 2022-09-30 广东小天才科技有限公司 一种辅助定位、系统、可穿戴设备和存储介质
CN113450569A (zh) * 2021-06-30 2021-09-28 阿波罗智联(北京)科技有限公司 确定路口状态的方法、装置、电子设备和存储介质
US11904906B2 (en) * 2021-08-05 2024-02-20 Argo AI, LLC Systems and methods for prediction of a jaywalker trajectory through an intersection
US12128929B2 (en) 2021-08-05 2024-10-29 Argo AI, LLC Methods and system for predicting trajectories of actors with respect to a drivable area
CN115641739A (zh) * 2022-10-20 2023-01-24 星河智联汽车科技有限公司 一种道路交通信息显示方法、装置及车辆

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080319639A1 (en) * 2006-08-18 2008-12-25 Xanavi Informatics Corporation Predictive Traffic Information Creating Method, Predictive Traffic Information Creating Apparatus, and Traffic Information Display Terminal
CN102708679A (zh) * 2012-05-29 2012-10-03 孙健 一种城市信号交叉口短时交通流预测方法
CN104318797A (zh) * 2014-10-16 2015-01-28 广东好帮手电子科技股份有限公司 一种具有城市交通诱导功能的北斗导航车载终端及系统
CN106408975A (zh) * 2016-06-17 2017-02-15 京东方科技集团股份有限公司 车辆行驶预测方法、装置和车载智能系统
CN107025788A (zh) * 2017-05-17 2017-08-08 青岛海信网络科技股份有限公司 一种旅行时间预测方法及装置
CN107144286A (zh) * 2016-03-01 2017-09-08 阿里巴巴集团控股有限公司 导航方法及装置

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19752458A1 (de) * 1997-11-27 1999-06-02 Cit Alcatel Wartezeitvorhersagesystem
CN102737504B (zh) * 2012-07-13 2014-05-14 重庆大学 一种基于驾驶特性的公交车到站时间实时估计方法
CN103440768B (zh) * 2013-09-12 2015-04-15 重庆大学 一种基于动态修正的公交车到达时间实时预测方法
CN114973677A (zh) * 2016-04-18 2022-08-30 北京嘀嘀无限科技发展有限公司 用于确定预计到达时间的方法和设备
US11113957B2 (en) * 2017-03-31 2021-09-07 Traffic Technology Services, Inc. System and method for providing real-time and predictive speed, traffic signal timing, station dwell time, and departure window information to transit vehicle
CN108520633A (zh) * 2018-03-02 2018-09-11 江苏大学 一种缓解交通拥堵的车速引导方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080319639A1 (en) * 2006-08-18 2008-12-25 Xanavi Informatics Corporation Predictive Traffic Information Creating Method, Predictive Traffic Information Creating Apparatus, and Traffic Information Display Terminal
CN102708679A (zh) * 2012-05-29 2012-10-03 孙健 一种城市信号交叉口短时交通流预测方法
CN104318797A (zh) * 2014-10-16 2015-01-28 广东好帮手电子科技股份有限公司 一种具有城市交通诱导功能的北斗导航车载终端及系统
CN107144286A (zh) * 2016-03-01 2017-09-08 阿里巴巴集团控股有限公司 导航方法及装置
CN106408975A (zh) * 2016-06-17 2017-02-15 京东方科技集团股份有限公司 车辆行驶预测方法、装置和车载智能系统
CN107025788A (zh) * 2017-05-17 2017-08-08 青岛海信网络科技股份有限公司 一种旅行时间预测方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112330962A (zh) * 2020-11-04 2021-02-05 杭州海康威视数字技术股份有限公司 交通信号灯控制方法、装置、电子设备及计算机存储介质
CN112330962B (zh) * 2020-11-04 2022-03-08 杭州海康威视数字技术股份有限公司 交通信号灯控制方法、装置、电子设备及计算机存储介质

Also Published As

Publication number Publication date
CN111199642B (zh) 2021-08-03
US20210241613A1 (en) 2021-08-05
CN111199642A (zh) 2020-05-26

Similar Documents

Publication Publication Date Title
WO2020098079A1 (zh) 预测通行时长的方法和系统
CN110709908B (zh) 用于交通系统的状态预测的计算机系统和方法
Nampally Leveraging AI in urban traffic management: Addressing congestion and traffic flow with intelligent systems
JP7625140B2 (ja) 交通予測のための分散マルチタスク機械学習
JP7525618B2 (ja) 車両挙動予測方法及び装置、電子機器、記憶媒体
Hamilton et al. The evolution of urban traffic control: changing policy and technology
CN108734955B (zh) 预测路况状态的方法及装置
Płaczek A self-organizing system for urban traffic control based on predictive interval microscopic model
US20140058652A1 (en) Traffic information processing
US10713941B2 (en) Cognitive traffic signal cycle timer
WO2020132990A1 (zh) 一种识别交叉路口的方法和系统
WO2019047905A1 (zh) 一种交通路况分析系统、方法以及装置
WO2020082284A1 (zh) 一种路口是否存在目标道路设施的判断方法及系统
US20170276504A1 (en) Vehicular Traffic Assistance Based on Traffic Management Decisions
JP2015125775A (ja) システムでの需要の予測のためのマルチタスク学習システムおよび方法
US20230306546A1 (en) Driving timetable generation method and apparatus, and electronic device
JP6685763B2 (ja) 事故予報システム、および事故予報方法
US20250131819A1 (en) Energy-efficient vehicle and/or traffic light control
Zhang et al. Eco-driving for public transit in cyber-physical systems using V2I communication
Lee Transfer learning-based deep reinforcement learning approach for robust route guidance in mixed traffic environment
Kwesiga et al. Adaptive Traffic Signal Control based on Multi-Agent Reinforcement Learning. Case Study on a simulated real-world corridor
CN114781243B (zh) Eta预测及模型训练方法、设备、介质及产品
Apple et al. Green driver: Ai in a microcosm
CN113516843A (zh) 预计到达时间的确定方法和装置、电子设备以及计算机可读存储介质
Aggarwal et al. Data mining techniques for smart mobility—a survey

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18940187

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18940187

Country of ref document: EP

Kind code of ref document: A1