WO2021129227A1 - 一种交通信息处理方法及装置 - Google Patents

一种交通信息处理方法及装置 Download PDF

Info

Publication number
WO2021129227A1
WO2021129227A1 PCT/CN2020/129078 CN2020129078W WO2021129227A1 WO 2021129227 A1 WO2021129227 A1 WO 2021129227A1 CN 2020129078 W CN2020129078 W CN 2020129078W WO 2021129227 A1 WO2021129227 A1 WO 2021129227A1
Authority
WO
WIPO (PCT)
Prior art keywords
traffic
model
driver
target
time period
Prior art date
Application number
PCT/CN2020/129078
Other languages
English (en)
French (fr)
Inventor
王萌
胡湘慧
于琦
熊福祥
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP20905917.9A priority Critical patent/EP4060641A4/en
Publication of WO2021129227A1 publication Critical patent/WO2021129227A1/zh
Priority to US17/851,021 priority patent/US20220335820A1/en

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
    • 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
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3691—Retrieval, searching and output of information related to real-time traffic, weather, or environmental conditions
    • 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
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
    • 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
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
    • 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
    • G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
    • G08G1/096716—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information does not generate an automatic action on the vehicle control
    • 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
    • G08G1/096775—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 central station

Definitions

  • the embodiments of the present application relate to the field of artificial intelligence, and in particular to a method and device for processing traffic information.
  • the traffic model (road basic map model, road network curve model, etc.) in the transportation field is used to process traffic information (such as flow, speed, density, etc.) to obtain different road units (such as intersections, road sections or road networks).
  • traffic information such as flow, speed, density, etc.
  • road units such as intersections, road sections or road networks.
  • the processing result of the state of the traffic information, and then the processing result of the traffic information is used to construct a road information system (for example, a traffic signal control system, etc.).
  • the preset traffic model corresponding to the road unit, and then use the traffic data reported by vehicle sensors or road sensors to perform parameter calibration on the preset traffic model (that is, determine the relevant parameters of the preset traffic model), such as basic road
  • the parameters of the graph model reflect the forward propagation speed of traffic; the road information system is then constructed according to the parameters of the traffic model, for example, based on the forward propagation speed of traffic, an optimized signal control scheme, that is, the duration control scheme of traffic lights, is obtained.
  • the preset traffic model may deviate from the actual situation, resulting in a large deviation of the traffic information processing result, and thus the application effect of the constructed road information system is not good.
  • the embodiments of the present application provide a traffic information processing method and device, which can provide a more reasonable and reliable traffic control strategy and improve the quality of traffic services.
  • an embodiment of the present application provides a traffic information processing method, including: using historical traffic data to determine a target traffic model from a plurality of candidate traffic models, the candidate traffic model corresponding to the historical traffic data; and According to the current traffic data, the parameters of the target traffic model are adjusted, the parameters of the target traffic model are used to describe the current traffic operation state, and the current traffic data corresponds to the target traffic model; and based on the adjusted The parameters of the target traffic model generate a traffic control strategy.
  • the candidate traffic model includes at least one of the following: a driver model, a road propagation model, or a road network evaluation model.
  • the historical traffic data includes at least one of the following: traffic data of the driver in the historical time period, traffic data of the target road in the historical time period, or traffic data of the target road network in the historical time period.
  • the current traffic data includes at least one of the following: traffic data of the driver in the current time period, traffic data of the target road in the current time period, or traffic data of the target road network in the current time period.
  • the traffic control strategy includes at least one of the following: driver navigation information, traffic signal control information, or road network boundary control information.
  • the above candidate traffic models correspond to historical traffic data, that is, the types of historical traffic data correspond to the types of candidate traffic models.
  • the historical traffic data is the traffic data of the driver in the historical time period
  • the multiple candidate traffic models are multiple Driver model.
  • the current traffic data corresponds to the target traffic model. For example, if the target traffic model is a target driver model, the traffic data of the driver in the current time period is obtained, and then the parameters of the target driver model are adjusted according to the traffic data of the driver in the current time period .
  • the parameters of the (target) traffic model are used to describe the current traffic operating state, for example, the parameters of the driver model are used to describe the current driving habits of the driver (driving aggressiveness or route choice preferences, etc.), and the road propagation model is used To describe the current traffic operation status of the road, the road network evaluation model is used to describe the current traffic operation status of the road network.
  • the above historical time period refers to the current time (time point) as the starting point, and multiple calculation time windows before the current time.
  • the historical time period corresponds to different time lengths.
  • the length of the historical time period can be set according to actual needs. For example, for the driver, the historical time period can be set to the previous day; for road sections or intersections (that is, roads), the history The time period can be set to the previous day, or a few days, or the previous week, etc.; for the road network, the historical time period can be set to the previous week or two weeks, etc.
  • the current time period refers to a calculation time window before the current time based on the current time (time point) as a starting point. Therefore, the current traffic data refers to traffic data in a calculation time window before the current time.
  • the calculation time window is different, that is, for different statistical objects, the current time period corresponds to different time windows, and the size of the time window can be set according to actual needs, for example,
  • the calculation time window can be set to a small value, for example, set to 1 minute (min)-5min; for road sections or intersections (i.e. roads), the calculation time window can be set to a moderate value, For example, it is set to 15min-30min; for the road network, the calculation time window can be set to a larger value, for example, set to 1 hour (h) or more than 1h.
  • regression analysis for example, gradient descent
  • least squares for example, gradient descent
  • gradient optimization for example, gradient descent
  • other methods can also be used to adjust the parameters of the target traffic model, which is not limited in the embodiment of the present application.
  • the traffic information processing method may use historical traffic data to determine a target traffic model from a plurality of candidate traffic models.
  • the candidate traffic model includes at least one of the following: a driver model, a road propagation model, or a road network Evaluation model; then according to the current traffic data, the parameters of the target traffic model are adjusted, and then based on the adjusted parameters of the target traffic model, a traffic control strategy is generated.
  • the traffic control strategy includes at least one of the following: driver navigation information, Traffic signal control information or road network boundary control information can provide more reasonable and reliable traffic control strategies and improve the quality of traffic services.
  • the historical traffic data is the traffic data of the driver in the historical time period
  • the target traffic model is the target driver model
  • the driver’s traffic data includes traffic data of the vehicle driven by the driver or The driver’s travel habit data
  • the traffic data of the vehicle driven by the driver in the historical time period includes the acceleration and the vehicle speed of the vehicle driven by the driver in the historical time period
  • the driver’s travel habit data in the historical time period includes all The travel probability of one or more trips of the driver in the historical time period and the selection probability of one or more routes corresponding to each trip are described.
  • the traffic data of the driver in the current time period includes the acceleration of the vehicle driven by the driver in the current time period and the speed of the vehicle; the travel habit data of the driver in the current time period includes one of the driver’s information in the current time period.
  • the driver's driving can be extracted from the vehicle's trajectory data (that is, the data reported by the sensor, such as the data reported by the position sensor in the vehicle the previous day or the data reported by other sensors such as electronic police) during the historical time period.
  • the location and license plate number of the vehicle combined with the location and license plate number of the vehicle near the driver's vehicle (for example, the vehicle in front), determine the acceleration and speed of the vehicle driven by the driver.
  • the historical time period here may be a time in days, such as 10 days, 20 days, or 30 days, etc.
  • the travel probability of one or more itineraries of the driver and the selection probability of one or more routes corresponding to each itinerary are calculated according to the travel data of the driver in the historical time period.
  • the traffic control strategy is the driver navigation information
  • the generation of the traffic control strategy based on the adjusted parameters of the target traffic model includes: based on the adjusted target driver model Set the weight of the path on the navigation map, and the parameters of the target driver model are used to describe the current driving habits of the driver; and generate the driver's navigation information according to the weight of the path on the navigation map.
  • the traffic information processing method provided by the embodiments of the present application uses the driver’s traffic data in a historical time period from the perspective of the vehicle being driven by the driver, determines the target driver model from a variety of candidate driver models, and uses the current time
  • the traffic data of the driver in the segment adjusts the parameters of the target driver model to generate driver navigation information. In this way, a more comprehensive and practical personalized navigation service can be provided to the driver.
  • the historical traffic data is traffic data of a target road in a historical time period
  • the target traffic model is a target road propagation model
  • the traffic data of a target road in the historical time period includes a historical time period At least two of the flow, speed, and density of the internal target road
  • the traffic data of the target road in the current time period includes at least two of the flow, speed, and density of the target road in the current time period.
  • the road propagation model may be a road curve model, such as a basic road map model, and the road propagation model may also be a model of other forms, which is not limited in the embodiment of the present application.
  • the basic road map model is a curve model reflecting the relationship between flow-density-speed of the road.
  • the basic road map model can be a three-dimensional curve or a two-dimensional curve (that is, taking the flow, density, or speed). Two types of curves, such as the flow-density curve formed by road flow and density).
  • the traffic control strategy is the traffic signal control information
  • the generation of the traffic control strategy based on the adjusted parameters of the target traffic model includes: based on the adjusted target road propagation model
  • the parameters of the target road propagation model are used to describe the current traffic operation status of the target road; and the signal control constraint conditions are used as the optimization conditions of the traffic signal control model to generate the
  • the signal control constraint condition is determined by the adjusted road propagation model.
  • the traffic information processing method uses traffic data of the target road in the historical time period from the perspective of the road, determines the target road propagation model from a variety of candidate road propagation models, and adopts the target road propagation model in the current time period.
  • the traffic data of the road adjusts the parameters of the target road propagation model to generate traffic signal control information. Because the parameters of the target road propagation model are adjusted according to the traffic data of the target road in the current time period (which can be understood as real-time traffic data) Adjusted to take the regularity and randomness of traffic flow propagation and the heterogeneity between roads into consideration, and the road propagation model obtained is more reliable. In this way, traffic signal control can be performed adaptively and more accurately.
  • the historical traffic data is traffic data of a target road network in a historical time period
  • the target traffic model is a target road network evaluation model
  • the traffic data of a target road network in the historical time period includes At least two of the flow, speed, and density of the target road network in the historical time period
  • the traffic data of the target road network in the current time period includes at least two of the flow, speed, and density of the target road network in the current time period .
  • the above-mentioned road network evaluation model may be a road network curve model, and the road network evaluation model may also be a model of other forms, which is not limited in the embodiment of the present application.
  • the road network curve model is a curve model reflecting the relationship between the traffic-density-speed of the road network.
  • the road network curve model can be a three-dimensional curve or a two-dimensional curve (that is, taking the flow, density, or speed). Two types of curves, such as the dense-speed curve formed by the speed and density of the road network).
  • the traffic control strategy is the road network boundary control information
  • the generation of the traffic control strategy based on the adjusted parameters of the target traffic model includes: based on the adjusted target
  • the parameters of the road network evaluation model and the macro traffic flow model determine the capacity or flow of the target road network, and the parameters of the target road network evaluation model are used to describe the current traffic operation status of the target road network; and
  • the capacity or traffic of the target road network generates the road network boundary control information.
  • the capacity or flow of the target road network can reflect the congestion degree of the traffic state of the target road network. Therefore, according to the capacity or flow of the target road network, the road network boundary control information is generated to realize the traffic control of the road network. . For example, if the density (namely capacity) of the target road network is close to the cutoff density of the target road network, indicating that the target road network is relatively congested, then the vehicles on the target road network can be directed to other road networks that are not congested.
  • the traffic information processing method uses the traffic data of the target road network in the historical time period from the perspective of the road network, determines the target road network evaluation model from a variety of candidate road network evaluation models, and uses the current time According to the traffic data of the target road network in the segment, the parameters of the target road network evaluation model are adjusted to generate road network boundary control information, because according to the traffic data of the target road network in the current time period (which can be understood as real-time traffic data) The parameters of the target road network propagation model are adjusted, and the regularity and randomness of the traffic system are taken into consideration. The resulting road network evaluation model is more reliable. In this way, it is possible to adaptively and more accurately perform traffic control at the road network boundary.
  • the traffic data of the target road network is determined by the traffic data of the road sections included in the target road network.
  • the traffic data of the target road network is determined by the traffic data of the road sections included in the target road network, that is, the traffic data of the road sections included in the target road network are aggregated to obtain the traffic data of the target road network. Traffic data.
  • the traffic data of the road sections included in the target road network can be aggregated in the following manner:
  • q is the traffic of the target road network
  • q i is the traffic of the i-th road segment included in the target road network
  • n is the number of road segments included in the target road network.
  • v is the target speed of the road network
  • v i is the velocity of the target road network comprising the i-th segment.
  • k is the density of the target road network
  • k i is the density of the i-th road section included in the target road network.
  • the traffic information processing method provided by the embodiment of the present application further includes: presenting different levels of traffic information according to different scales, and the different levels of traffic information are respectively the driver’s traffic information and the target road’s traffic information.
  • Traffic information and traffic information of the target road network wherein the traffic information of the driver includes the traffic data of the driver in the current time period and the parameters of the target driver model; the traffic information of the target road includes all The traffic data of the target road in the current time period and the parameters of the target road propagation model; the traffic information of the target road network includes the traffic data of the target road network in the current time period and the parameters of the target road network evaluation model parameter.
  • the above-mentioned different levels of traffic information are displayed according to different scales, and can be switched and displayed according to different scales (for example, zoom in or zoom out) through UI operations.
  • it is displayed on micro, meso and macro scales.
  • the micro traffic information is vehicle traffic information (that is, the driver’s traffic information)
  • the meso traffic information is road traffic information
  • the macro traffic information is Traffic information on the road network.
  • the different levels of traffic information are presented in one or more of the following ways: a display screen, an electronic map, or a projection.
  • different levels of traffic information can be displayed on display screens (such as urban brains), on-board terminal screens and mobile phone screens, etc., or different levels of traffic information can be projected on the front windshield of the vehicle, etc. , Or display different levels of traffic information in electronic maps such as navigation software.
  • an embodiment of the present application provides a traffic information processing device, including a model determination module, a parameter adjustment module, and a traffic management strategy generation module; the model determination module is used to use historical traffic data to obtain data from multiple candidate traffic models.
  • the candidate traffic model includes at least one of the following: a driver model, a road propagation model, or a road network evaluation model, and the historical traffic data includes at least one of the following: Traffic data, traffic data of the target road in the historical time period, or traffic data of the target road network in the historical time period, the candidate traffic model corresponds to the historical traffic data;
  • the parameter adjustment module is used for the current traffic data ,
  • the parameters of the target traffic model are adjusted; the parameters of the target traffic model are used to describe the current traffic operating state, and the current traffic data includes at least one of the following: traffic of vehicles driven by the driver in the current time period Data or, the traffic data of the target road in the current time period or the traffic data of the target road network in the current time period, where the current traffic data corresponds to the target traffic
  • the historical traffic data is the traffic data of the driver in the historical time period
  • the target traffic model is the target driver model
  • the driver’s traffic data includes traffic data of the vehicle driven by the driver or The driver’s travel habit data
  • the traffic data of the vehicle driven by the driver in the historical time period includes the acceleration and the vehicle speed of the vehicle driven by the driver in the historical time period
  • the driver’s travel habit data in the historical time period includes all The travel probability of one or more trips of the driver in the historical time period and the selection probability of one or more routes corresponding to each trip
  • the driver’s traffic data in the current time period includes the current time period
  • the travel habit data of the driver in the current time period includes the travel probability of one or more trips of the driver in the current time period and one corresponding to each trip Or the selection probability of multiple routes.
  • the traffic control strategy is the driver’s navigation information; the traffic control strategy generation module is specifically used to set the route on the navigation map based on the adjusted parameters of the target driver model Weight; and according to the weight of the path on the navigation map, the driver navigation information is generated, and the parameters of the target driver model are used to describe the current driving habits of the driver.
  • the historical traffic data is traffic data of a target road in a historical time period
  • the target traffic model is a target road propagation model
  • the traffic data of a target road in the historical time period includes a historical time period At least two of the flow, speed, and density of the internal target road
  • the traffic data of the target road in the current time period includes at least two of the flow, speed, and density of the target road in the current time period.
  • the traffic control strategy is the traffic signal control information; the traffic control strategy generation module is specifically configured to determine signal control constraints based on the adjusted parameters of the target road propagation model; and
  • the signal control constraint is used as the optimization condition of the traffic signal control model to generate the traffic signal control information, the parameters of the target road propagation model are used to describe the current traffic operation state of the target road, and the signal control constraint The condition is determined by the adjusted road propagation model.
  • the historical traffic data is traffic data of a target road network in a historical time period
  • the target traffic model is a target road network evaluation model
  • the traffic data of a target road network in the historical time period includes At least two of the flow, speed, and density of the target road network in the historical time period
  • the traffic data of the target road network in the current time period includes at least two of the flow, speed, and density of the target road network in the current time period .
  • the traffic control strategy is the road network boundary control information; the traffic control strategy generation module is specifically configured to be based on the parameters of the adjusted target road network evaluation model and macroscopic traffic flow Model to determine the capacity or flow of the target road network; and generate the road network boundary control information according to the capacity or flow of the target road network, and the parameters of the target road network evaluation model are used to describe the target road The current traffic operation status of the network.
  • the traffic data of the target road network is determined by the traffic data of the road sections included in the target road network.
  • the traffic information device provided in this embodiment of the application further includes a display module; the display module is used to present different levels of traffic information according to different scales, and the different levels of traffic information are drivers.
  • the traffic information of the target road and the traffic information of the target road network wherein the traffic information of the driver includes the traffic data of the driver in the current time period and the parameters of the target driver model;
  • the traffic information of the target road includes the traffic data of the target road in the current time period and the parameters of the target road propagation model;
  • the traffic information of the target road network includes the traffic data and all the traffic data of the target road network in the current time period.
  • the parameters of the target road network evaluation model are described.
  • the different levels of traffic information are presented in one or more of the following ways: a display screen, an electronic map, or a projection.
  • an embodiment of the present application provides a traffic information processing device, including a processor and a memory coupled to the processor; the memory is used to store computer instructions, and when the device is running, the processor executes the memory
  • the stored computer instructions enable the apparatus to execute the method described in any one of the foregoing first aspect and its various possible implementation manners.
  • the embodiments of the present application provide a traffic information processing device, the traffic information processing device exists in the form of a chip product, and the structure of the traffic information processing device includes a processor and a memory, and the memory is used for coupling with the processor, The memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory, so that the traffic information processing device executes the method described in any one of the foregoing first aspect and its possible implementation manners.
  • an embodiment of the present application provides a computer-readable storage medium.
  • the computer-readable storage medium may include computer instructions. When the computer instructions run on a computer, they can execute the first aspect and its possible possibilities. Implement the method described in any one of the modes.
  • FIG. 1 is a schematic structural diagram of a traffic information communication system provided by an embodiment of this application.
  • FIG. 2 is a schematic diagram of hardware of a server for processing traffic information provided by an embodiment of the application
  • FIG. 3 is a schematic diagram 1 of a traffic information processing method provided by an embodiment of this application.
  • FIG. 4 is a schematic diagram 2 of a traffic information processing method provided by an embodiment of this application.
  • FIG. 5 is a third schematic diagram of a traffic information processing method provided by an embodiment of this application.
  • FIG. 6 is a schematic diagram of a traffic route provided by an embodiment of this application.
  • FIG. 7 is a fourth schematic diagram of a traffic information processing method provided by an embodiment of this application.
  • Fig. 8 is a schematic diagram of a flow-density curve provided by an embodiment of the application.
  • FIG. 9 is a schematic diagram of parameters of a flow-density curve provided by an embodiment of the application.
  • FIG. 10 is a schematic diagram 5 of a traffic information processing method provided by an embodiment of this application.
  • FIG. 11 is a schematic diagram of a road provided by an embodiment of the application.
  • FIG. 12 is a sixth schematic diagram of a traffic information processing method provided by an embodiment of this application.
  • FIG. 13 is a schematic diagram 7 of a traffic information processing method provided by an embodiment of this application.
  • FIG. 14 is a schematic diagram of displaying different levels of traffic information according to an embodiment of this application.
  • 15 is a schematic structural diagram 1 of a traffic information processing device provided by an embodiment of this application.
  • FIG. 16 is a second structural diagram of a traffic information processing device provided by an embodiment of this application.
  • words such as “exemplary” or “for example” are used as examples, illustrations, or illustrations. Any embodiment or design solution described as “exemplary” or “for example” in the embodiments of the present application should not be construed as being more preferable or advantageous than other embodiments or design solutions. To be precise, words such as “exemplary” or “for example” are used to present related concepts in a specific manner.
  • multiple processing units refer to two or more processing units; multiple systems refer to two or more systems.
  • Traffic model In the traffic system, mathematical models are used to describe the state of traffic. These mathematical models are called traffic models. Traffic models can be used to analyze the traffic status of vehicles, drivers and pedestrians, roads, and road networks. Whether the traffic is congested in each location, whether the road is unblocked, and whether there are traffic accidents, so as to effectively carry out traffic planning, traffic organization and management.
  • the driver model Used to describe the driving state of individual vehicles.
  • the driver model is a microscopic traffic model.
  • Road propagation model used to describe the propagation state of road traffic flow, such as propagation speed, etc.
  • the road propagation model may be a road curve model (such as a basic road map model), and the road propagation model may also be other forms of models , It is not limited here.
  • the road propagation model is a mesoscopic traffic model.
  • Road network evaluation model used to describe the traffic state of the road network, such as the road network is in a congested state, the road network is in a smooth state, etc.
  • the road network evaluation model is a macroscopic traffic model.
  • Road section refers to the road between two adjacent intersections, that is, the road section should not have other intersections connected to other roads except for the intersections at both ends.
  • Road network refers to a road system that is interconnected and interwoven into a network of various roads (roads including road sections and intersections) in a certain area. It should be understood that a road network composed of all levels of roads is called a road network.
  • the urban road network composed of various roads within a city is called an urban road network.
  • the embodiments of the present application provide a traffic information processing method and device, which can use historical traffic data to determine a target traffic model from multiple candidate traffic models, and the candidate traffic model includes at least one of the following: Driver model, road propagation model or road network evaluation model; then according to the current traffic data, the parameters of the target traffic model are adjusted.
  • the parameters of the target traffic model are used to describe the current traffic operation state, and then based on the adjusted target traffic model To generate a traffic control strategy.
  • the traffic control strategy includes at least one of the following: driver navigation information, traffic signal control information, or road network boundary control information.
  • FIG. 1 is a schematic diagram of the architecture of the traffic information communication system provided in the embodiments of the application.
  • the schematic diagram of the architecture of the traffic information communication system in the embodiment of the present application may include two types.
  • the traffic information communication system shown in (a) in FIG. 1 includes at least one sensor terminal ((a) in FIG. 1) Denoted as sensor terminal 1 to sensor terminal N) and the traffic center side, the traffic center side may include a central server or a central cloud.
  • the sensor side includes a variety of sensors, such as electronic police (cameras) installed on the road, cross-section detectors (detection coils, geomagnetism, radar, etc.) and other road sensors, vehicle sensors (GPS positioning device or driver's mobile phone positioning device) Etc.
  • the traffic data obtained by the electronic police may include data such as the license plate number of the vehicle, the location of the vehicle, the length of the queue of the vehicle, etc.
  • the traffic data detected by the section detector may include data such as the flow of the vehicle, and the traffic data obtained by the vehicle sensor may include Data such as the location of the vehicle.
  • the sensor terminal in the traffic information communication system can report the traffic data it obtains to the traffic center side, and then the equipment (central server or central cloud) on the traffic center side analyzes and processes the traffic data to obtain traffic control strategies.
  • the traffic information communication system shown in (b) in Fig. 1 includes at least one sensor end ((a) in Fig. 1 is marked as sensor end 1 to sensor end N), and at least one edge side ((in Fig. 1) b) Marked as edge side device terminal 1 to edge side K) and traffic center side, where the edge side includes edge service units (such as edge servers), and the edge service units on the edge side are mainly used for preprocessing the traffic data of each sensor terminal , Such as gathering the traffic data of various sensors, the validity detection of the traffic data, etc.
  • Each sensor terminal first sends the traffic data it acquires to its respective edge side (for example, in (b) in Figure 1, sensor terminal 1 and sensor 2 send the traffic data they acquire to edge side 1, and sensor terminal 3 sends the traffic data it acquires).
  • the traffic data it obtains is sent to the edge side 2, and the sensor terminal N sends the traffic data it obtains to the edge side K).
  • each edge side reports the traffic data to the traffic center side, and the equipment on the traffic center side (center The server or central cloud) analyzes and processes traffic data to obtain traffic control strategies.
  • the data transmission from the sensor end to the edge side and then to the traffic center side adopts an active reporting method.
  • Each sensor in the communication system sends traffic data to the edge side, and the edge side transmits the traffic data according to
  • the data report format is aggregated, and then sent to the traffic center side according to the format.
  • the format for reporting traffic data on the edge side may include two types:
  • the first data format is reported in units of sensors in a certain area, for example, data from sensor 1 in the area, data from sensor 2 in the area, ..., data from sensor N in the area.
  • the second data format is reported in units of roads in a certain area, for example, data of road 1 in the area, data of road 2 in the area, ..., data of road M in the area.
  • the traffic information processing device provided by the embodiment of the present application may be a server (for example, the central server shown in FIG. 1) or a cloud server (for example, the central cloud shown in FIG. 1), and the traffic information processing device is used as the server below.
  • a server for example, the central server shown in FIG. 1
  • a cloud server for example, the central cloud shown in FIG. 1
  • each component of the server for processing traffic information provided by an embodiment of the present application will be specifically introduced with reference to FIG. 2.
  • the server 10 may include: a processor 11, a memory 12, a communication interface 13, and the like.
  • Processor 11 is the core component of server 10, used to run the operating system of server 10 and applications (including system applications and third-party applications) on server 30. For example, processor 11 runs network quality on the server. Monitoring methods and procedures to monitor network quality.
  • the processor 11 may specifically be a central processing unit (CPU), a general-purpose processor, a digital signal processor (digital signal processor, DSP), or an application-specific integrated circuit (ASIC). ), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof, which can implement or execute the contents disclosed in the embodiments of the present application.
  • CPU central processing unit
  • DSP digital signal processor
  • ASIC application-specific integrated circuit
  • FPGA field programmable gate array
  • Exemplary logical blocks, modules and circuits; the processor may also be a combination of computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.
  • the memory 12 can be used to store software programs and modules.
  • the processor 11 executes various functional applications and data processing of the server 10 by running the software programs and modules stored in the memory 12.
  • the memory 12 may include one or more computer-readable storage media.
  • the memory 12 includes a storage program area and a storage data area.
  • the storage program area can store an operating system, an application program required by at least one function, etc.
  • the storage data area can store data created by the server 10, etc., in the embodiment of the present application, the storage 12 may include storing historical traffic data and current traffic data.
  • the memory 12 may specifically include a volatile memory (volatile memory), such as a random-access memory (random-access memory, RAM); the memory may also include a non-volatile memory (non-volatile memory) , Such as read-only memory (ROM), flash memory (flash memory), hard disk (HDD) or solid-state drive (SSD); the memory may also include the above types The combination of memory.
  • volatile memory such as a random-access memory (random-access memory, RAM
  • non-volatile memory non-volatile memory
  • ROM read-only memory
  • flash memory flash memory
  • HDD hard disk
  • SSD solid-state drive
  • Communication interface 13 an interface circuit used for communication between the server 10 and other devices.
  • the communication interface can be a transceiver, a transceiver circuit, and other structures with transceiver functions.
  • the communication interface 13 on the server 10 can be a vehicle sensor Or traffic data sent by road sensors (such as electronic police, cross-section detectors, etc.).
  • the traffic information processing method provided by the embodiment of the present application may include S101-S103:
  • the candidate traffic model may include at least one of the following: a driver model, a road propagation model, or a road network evaluation model;
  • the historical traffic data includes at least one of the following: traffic data of drivers in a historical time period, and traffic data in a historical time period The traffic data of the target road or the traffic data of the target road network in the historical time period.
  • the above candidate traffic models correspond to historical traffic data, that is, the types of historical traffic data correspond to the types of candidate traffic models.
  • the historical traffic data is the traffic data of the driver in the historical time period
  • the multiple candidate traffic models are multiple Driver model.
  • the candidate traffic model mentioned above is a variety of commonly used traffic models in the transportation field.
  • the use of historical traffic data to determine the target traffic model from multiple candidate traffic models refers to the use of historical traffic data for traffic model matching. Choose a traffic model that best matches the historical traffic data from a variety of candidate traffic models as the target traffic model for subsequent traffic data analysis.
  • methods such as global error matching method, feature matching method, probability map matching method, etc. may be used to select the traffic model with the smallest error or the most similar characteristics from multiple candidate traffic models as
  • the target traffic model can also use other matching methods to determine the target traffic model from multiple candidate traffic models, which is not limited in the embodiment of the present application.
  • the above historical time period refers to the current time (time point) as the starting point, and multiple calculation time windows before the current time.
  • the historical time period corresponds to different time lengths.
  • the length of the historical time period can be set according to actual needs. For example, for the driver, the historical time period can be set to the previous day; for road sections or intersections (that is, roads), the history The time period can be set to the previous day, or a few days, or the previous week, etc.; for the road network, the historical time period can be set to the previous week or two weeks, etc.
  • S102 Adjust the parameters of the target traffic model according to the current traffic data.
  • the current traffic data may include at least one of the following: traffic data of the driver in the current time period, traffic data of the target road in the current time period, or traffic data of the target road network in the current time period.
  • the current time period refers to the current time (time point) as the starting point, and a calculation time window before the current time. Therefore, the current traffic data refers to the time before the current time.
  • a calculation time window of traffic data For different statistical objects (ie individual vehicles, roads or road networks), the calculation time window is different, that is, for different statistical objects, the current time period corresponds to different time windows, and the size of the time window can be set according to actual needs, for example, For the driver, the calculation time window can be set to a small value, for example, set to 1 minute (min)-5min; for road sections or intersections (i.e. roads), the calculation time window can be set to a moderate value, For example, it is set to 15min-30min; for the road network, the calculation time window can be set to a larger value, for example, set to 1 hour (h) or more than 1h.
  • the current traffic data corresponds to the target traffic model.
  • the target traffic model is a target driver model, then the traffic data of the driver in the current time period is obtained, and then the traffic data of the driver in the current time period is adjusted.
  • the parameters of the target driver model are used to describe the current traffic operating state, for example, the parameters of the driver model are used to describe the current driving habits of the driver (driving aggressiveness or route choice preferences, etc.), and the road propagation model is used To describe the current traffic operation status of the road, the road network evaluation model is used to describe the current traffic operation status of the road network.
  • the parameters of the target traffic model can be calibrated).
  • other methods can also be used to adjust the parameters of the target traffic model, which is not limited in the embodiment of this application.
  • S103 Generate a traffic control strategy based on the adjusted parameters of the target traffic model.
  • the above-mentioned traffic control strategy includes at least one of the following: driver navigation information, traffic signal control information, or road network boundary control information.
  • the traffic control strategy provides driver navigation information to provide personalized navigation services for different drivers;
  • the traffic control strategy It is traffic signal control information (for example, the control time of traffic lights at intersections), which can adaptively realize traffic signal control according to the current traffic operation status of the target road;
  • the traffic control strategy is a road network Boundary control information (for example, the control duration of traffic lights at the boundary of the road network), in this way, the traffic signal control at the boundary of the road network can be performed according to the current traffic operation status of the target road network.
  • the traffic information processing method may use historical traffic data to determine a target traffic model from a plurality of candidate traffic models.
  • the candidate traffic model includes at least one of the following: a driver model, a road propagation model, or a road network Evaluation model; then according to the current traffic data, the parameters of the target traffic model are adjusted, and then based on the adjusted parameters of the target traffic model, a traffic control strategy is generated.
  • the traffic control strategy includes at least one of the following: driver navigation information, Traffic signal control information or road network boundary control information can provide more reasonable and reliable traffic control strategies and improve the quality of traffic services.
  • the traffic information processing method can be used to process traffic information of different scales (micro, meso, and macro), for example, the traffic data of the above-mentioned driver (micro), road traffic
  • the following embodiments respectively introduce the process of processing the traffic data of the driver, the traffic data of the road, and the traffic data of the road network.
  • the above historical traffic data is the traffic data of the driver in the historical time period
  • the current traffic data is the traffic data of the driver in the current time period.
  • One candidate traffic model is multiple driver models
  • the target traffic model is the target driver model
  • the traffic control strategy is driver navigation information.
  • the traffic information processing method provided by the embodiment of the present application may include S201-S203:
  • the traffic data of the driver includes the traffic data of the vehicle driven by the driver or the travel habit data of the driver.
  • the traffic data of the vehicle driven by the driver in the historical time period includes the acceleration of the vehicle driven by the driver in the historical time period and the speed of the vehicle;
  • the travel habit data of the driver in the historical time period includes the driver’s or The travel probability of various itineraries and the selection probability of one or more routes corresponding to each itinerary.
  • the driver's driving can be extracted from the vehicle's trajectory data (that is, the data reported by the sensor, such as the data reported by the position sensor in the vehicle the previous day or the data reported by other sensors such as electronic police) during the historical time period.
  • the location and license plate number of the vehicle combined with the location and license plate number of the vehicle near the driver's vehicle (for example, the vehicle in front), determine the acceleration and speed of the vehicle driven by the driver.
  • Table 1 is an example of the trajectory data of a vehicle collected by an electronic police (camera) on the road where the vehicle passes
  • Table 2 is an example of the trajectory data of a vehicle collected by a position sensor on the vehicle somewhere on the road.
  • the license plate number of the vehicle can be obtained according to the encrypted information of the license plate of the vehicle, and then the trajectory data that is the same as the license plate number of the vehicle driven by the driver can be found from the massive data collected by the electronic police (that is, the data in Table 1 ), the ID of the detector is the location of the electronic policeman who collected the trajectory data of the vehicle, that is, the location of the vehicle is considered, and the time is the time when the trajectory data of the vehicle is collected.
  • time 12409 represents the total number of seconds from 0:00:00 to the current moment
  • 12409s represents the time 3:26:49.
  • multiple sets of trajectory data similar to those shown in Table 2 can also be collected from the position sensor of the vehicle, and the position (longitude and latitude) of the vehicle can also be extracted from the trajectory data of the vehicle. And time information, and the speed of the vehicle can be extracted, and then combined with the position, time information and speed of the adjacent vehicle of the vehicle, the acceleration and speed of the vehicle can be obtained.
  • the trajectory data of the vehicle may also be obtained by other methods, so as to calculate the acceleration and speed of the vehicle, which is not limited here.
  • the multiple target driver models may be the acceleration and speed of various vehicles. Relationship equations. Table 3 illustrates three commonly used driving models of acceleration equations.
  • Using the traffic data of the driver in the historical time period to determine the target driver model (ie, model matching) from multiple driver models may specifically include: using the acceleration and speed of the vehicle in the historical time period, and the vehicle adjacent to the vehicle.
  • the acceleration and speed of the vehicle calibrate the parameters of a variety of driver models (that is, the parameters of the driver model), and the acceleration of the vehicle (called the calculated acceleration) is solved according to the speed of the vehicle and the parameters of the model, and the calculated acceleration
  • the acceleration is compared with the acceleration of the vehicle (called the measured acceleration) determined according to the trajectory data to determine the target driver model.
  • the global matching method can be used.
  • the cumulative error corresponding to each driver model ie the sum of the difference between multiple sets of calculated acceleration and measured acceleration
  • the cumulative error is determined as the target driver model.
  • the historical time period here may be a time in days, such as 10 days, 20 days, or 30 days, etc.
  • the travel probability of one or more itineraries of the driver and the selection probability of one or more routes corresponding to each itinerary are calculated according to the travel data of the driver in the historical time period.
  • the travel probability of each type of trip of the driver is: the ratio of the number of trips of each type of the driver to the sum of the number of trips of all the trips.
  • itinerary in the past 30 days includes 4 trips from home to work, from work to home, from work to train station, and from home to shopping center.
  • Table 4 below is a statistical 4 The number of trips for one itinerary and the trip probabilities for four itineraries.
  • the selection probability of each route corresponding to the trip is: the ratio of the number of times the driver selects each route to the sum of the number of times the driver selects all the routes corresponding to the trip.
  • the traffic data of the driver in the historical time period is the travel probability of one or more trips of the driver in the historical time period and the selection probability of one or more routes corresponding to each trip.
  • the multiple target driver models mentioned above may be probability distribution models. According to the travel probability of one or more trips of the driver in the historical time period, the target driver model is matched from multiple probability distribution models related to the trip, or according to The selection probability of one or more routes corresponding to each trip in the historical time period is matched with the target driver model from a variety of probability distribution models about the route.
  • the above-mentioned model matching method is the same as the above-mentioned matching according to the acceleration and speed of the vehicle The idea of obtaining the target driver model is similar.
  • S202 Adjust the parameters of the target driver model according to the traffic data of the driver in the current time period.
  • the driver’s traffic data in the current time period may include the acceleration of the vehicle driven by the driver in the current time period and the speed of the vehicle; the driver’s traffic data in the current time period
  • the travel habit data includes the travel probability of one or more trips of the driver in the current time period and the selection probability of one or more routes corresponding to each trip.
  • the regression analysis method can be used to obtain the output (such as acceleration) and actual measurement of the target driver model based on the driver’s traffic data in the current time period.
  • the parameter with the smallest error of the data (such as acceleration) is used as the final adjusted parameter.
  • the target driver model is one of the acceleration equations shown in Table 3
  • the parameters of the target driver model can be referred to the examples in Table 3; when the target driver model is a probability distribution model, the The parameters of the target driver model can be the mean or variance of the probability distribution model.
  • the parameters of the target driver model are used to describe the current driving habits of the driver, and the driving habits of the driver may include the driver's aggressiveness or the driver's preference for choosing a certain route.
  • the target driver model is the driver model proposed by Newell (1961) in Table 3 above
  • the parameters of the driver model are c and d
  • the parameter c is used to describe whether the driver pursues high acceleration
  • the parameter d is To describe whether the driver frequently changes lanes, for example, the value of parameter c is 0.7 indicates that the driver pursues high acceleration, and the value of parameter d is 0.8 indicates that the driver frequently changes lanes. It can be seen that the driver’s driving habits are aggressive, so it is inferred The driver is driving fast and overtaking frequently.
  • the variance can reflect the travel preference of the driver for a certain type of trip (for example, the variance is small, indicating that they prefer to choose this type of trip) or The driver's preference for a certain route (for example, a smaller variance indicates a preference for choosing this route).
  • the above-mentioned adjustment of the parameters of the target driver model based on the driver’s traffic data (which can be understood as real-time traffic data) in the current time period can better obtain the driver’s driving habits and reduce the regularity and randomness of the driver’s driving.
  • the heterogeneity between drivers and drivers (which can be understood as different drivers have different driving styles) are taken into consideration, and the resulting driver model is more reliable.
  • S203 Generate driver navigation information based on the adjusted parameters of the target driver model.
  • the driver's navigation information is a navigation route with individual characteristics generated for the driver's driving habits.
  • S203 may be specifically implemented through S2031-S2032:
  • the above-mentioned adjusted parameters of the target driver model can be used to calculate the weight of the route in the navigation map.
  • a major road main road or expressway
  • a primary road Higher weight For example, Fig. 6 is the planning of the route from the starting point 1 to the end point 3. It can be seen that the route from the starting point 1 to the end point 3 can include two candidate routes, which are:
  • Route 1 1 ⁇ 2 ⁇ 3, including path 1 ⁇ 2 and path 2 ⁇ 3, where path 1 ⁇ 2 is a small road with a length of 5 kilometers (km), and the path 2 ⁇ 3 is also a small road with a length of 5km .
  • Route 2 1 ⁇ 4 ⁇ 3, including route 1 ⁇ 4 and route 1 ⁇ 4.
  • 1 ⁇ 4 is an expressway with a length of 12km
  • route 4 ⁇ 3 is a main road with a length of 15km.
  • the target driver model of the driver is the driver model proposed by Pipes (1953) in Table 3, and the parameter c of the driver model is 0.8.
  • the weight of each path in Route 1 and Route 2 is as follows:
  • Route 1 The weight of route 1 ⁇ 2 is 25 (ie 5/(1-0.8)); the weight of route 2 ⁇ 3 is 25 (ie 5/(1-0.8)), so the weight cost of route 1 is 50 (25+25).
  • Route 2 Path 1 ⁇ 4 and the weight is 2.4 (ie 12*(1-0.8)); the weight of path 1 ⁇ 4 is 3 (ie 15*(1-0.8)), so the weight cost of Route 2 is 5.4 .
  • route 2 that is, the route of 1 ⁇ 4 ⁇ 3 is set as the personalized navigation route of the driver, that is, the driver's navigation information is the navigation information corresponding to route 2.
  • the target driver model of the driver is the driver model proposed by Pipes (1953) in Table 3, and the parameter c of the driver model is 0.2.
  • the above The method of determining the weight of the path, the weight of each path in Route 1 and Route 2 is as follows:
  • Route 1 The weight of route 1 ⁇ 2 is 6.25 (ie 5/(1-0.2)); the weight of route 2 ⁇ 3 is 6.25 (ie 5/(1-0.2)), so the weight cost of route 1 is 12.5 (6.25+6.25).
  • Route 2 Path 1 ⁇ 4 and the weight is 9.6 (ie 12*(1-0.2)); the weight of path 1 ⁇ 4 is 12 (ie 15*(1-0.2)), so the weight cost of Route 2 is 21.6 .
  • route 1 that is, the route of 1 ⁇ 2 ⁇ 3 is set as the personalized navigation route of the driver, that is, the driver's navigation information is the navigation information corresponding to route 1.
  • the traffic information processing method provided by the embodiments of the present application uses the driver’s traffic data in a historical time period from the perspective of the vehicle being driven by the driver, determines the target driver model from a variety of candidate driver models, and uses the current time
  • the traffic data of the driver in the segment adjusts the parameters of the target driver model to generate driver navigation information. In this way, a more comprehensive and practical personalized navigation service can be provided to the driver.
  • the above historical traffic data is the traffic data of the target road in the historical time period
  • the current traffic data is the traffic of the target road in the current time period.
  • multiple candidate traffic models are multiple road propagation models
  • the target traffic model is the target road propagation model
  • the traffic control strategy is traffic signal control information.
  • the traffic information processing method provided by the embodiment of the present application may include S301-S303:
  • the traffic data of the target road in the historical time period includes at least two of the flow, speed, and density of the target road in the historical time period, and the target road may include road sections and intersections.
  • the above-mentioned road propagation model may be a road curve model, such as a basic road map model, and the road propagation model may also be a model of other forms, which is not limited in the embodiment of the present application.
  • the basic road map model is a curve model reflecting the relationship between flow-density-speed of the road.
  • the basic road map model can be a three-dimensional curve or a two-dimensional curve (that is, taking the flow, density, or speed). Two types of curves, such as the flow-density curve formed by road flow and density).
  • the (central server) may receive road sensors, for example, the traffic data of the target road in the historical time period collected and reported by the section detector.
  • Table 6 is an example of the traffic data of the target road section collected by the section detector.
  • the traffic data of the target road can be obtained from the traffic data reported by the interrupt surface detector in Table 6. It should be understood that the speed and density of the target road can be detected by other sensors, which are not specifically limited in the embodiment of the present application.
  • multiple section detectors on the target road can collect data similar to that shown in Table 6, thereby obtaining multiple sets of flow and density (that is, the flow and density in the historical time period),
  • multiple sets of flow rates and densities are used to match multiple candidate flow-density curves to determine the flow-density curve of the target road, that is, the target road curve model is obtained.
  • a feature matching method (the feature may be a slope feature or a curvature feature, etc.) is used to determine the flow-density curve from a plurality of candidate flow-density curves.
  • the flow-density curve that best matches the target road.
  • three candidate flow-density curves (curve 1, curve 2 and curve 3 respectively) are illustrated in FIG.
  • curve 1 in Figure 8 is the flow-density curve that best matches the flow and density of the target road in the historical time period.
  • S302 Adjust the parameters of the target road propagation model according to the traffic data of the target road in the current time period.
  • the traffic data of the target road in the current time period includes at least two of the flow, speed, and density of the target road in the current time period.
  • the traffic data of the target road in the current time period please refer to the related description of the traffic data of the target road in the historical time period in S301, which will not be repeated here.
  • the parameters of the target road propagation model are used to describe the current traffic operation status of the target road.
  • the traffic data of the target road in the current time period includes the target The flow and density of the road
  • the parameters of the target road propagation model are the upper limit Q of the flow of the target road, the propagation speed W of the target road, and the overflow speed V of the target road.
  • the least square method is used to adjust the parameters Q, W, and V of the target road propagation model to obtain the adjusted Q, W, and V.
  • the above three parameters in the flow-density curve are shown in FIG. 9.
  • the parameters of the target road propagation model are adjusted according to the traffic data of the target road in the current time period (which can be understood as real-time traffic data), and the regularity and randomness of traffic flow propagation and the heterogeneity between roads are taken into consideration. Range, the road propagation model obtained is more reliable.
  • the transfer learning method can be used to determine the target road propagation model of the target road, that is, the road similarity matching is performed, and the road propagation model of the road similar to the target road is determined as the target road propagation model of the target road.
  • the road characteristics of the target road such as topological characteristics (for example, left-turn lanes), distance (for example, road length), or cell characteristics (for example, whether there is a parking lot near the road), and the road with sensors Match the corresponding features of, and use the road propagation model with the most overlapping features as the target road propagation model of the target road section. Furthermore, the parameters of the most matched road propagation model are used as the parameters of the target road propagation model, and the adjusted parameters of the target road propagation model are further obtained.
  • topological characteristics for example, left-turn lanes
  • distance for example, road length
  • cell characteristics for example, whether there is a parking lot near the road
  • the road with sensors Match the corresponding features of, and use the road propagation model with the most overlapping features as the target road propagation model of the target road section. Furthermore, the parameters of the most matched road propagation model are used as the parameters of the target road propagation model, and the adjusted parameters of the target road propagation model are further obtained.
  • S303 Generate traffic signal control information based on the adjusted parameters of the target road propagation model.
  • the traffic signal control information may be the traffic light control duration of the target road.
  • the signal control constraint is determined by the adjusted road propagation model.
  • the target road is section i
  • the target road propagation model is the flow-density curve described in S302.
  • the parameters of the flow-density curve are flow rate Q, propagation speed W, and overflow speed V.
  • i also called Link i
  • Cell the road section i is divided into m cells, denoted as Cell(i, 1), Cell(i, 2),... , Cell(i,j),...,Cell(i,m)
  • the following four signal control constraints can be determined according to the parameters of the flow-density curve.
  • n i,j (t+1) n i,j (t)+f i,j (t)-f i,j+1 (t)
  • n i,j (t+1) Represents the number of vehicles in the j-th cell of road segment i at time t+1
  • n i,j (t) represents the number of vehicles in the j-th cell of road segment i at time t
  • f i,j (t) Represents the number of vehicles that flow into the j-th cell of the road segment i at time t
  • f i,j+1 (t) represents the number of vehicles that flow into the j+1-th cell from the j-th cell of the road segment i at time t
  • the constraint condition 1 indicates that for a cell, the number of vehicles in the cell at t+1 is equal to the number of vehicles in the cell at t plus the number of vehicles entering the cell at time t, minus the number of vehicles leaving the cell.
  • f i,j (t) represents the number of vehicles flowing into the j-th Cell of the road section i at time t
  • n i ,j-1 (t) represents the number of vehicles in the j-1th Cell of road section i at time t.
  • the constraint condition 2 indicates that for a cell, the number of vehicles flowing into the cell at time t is less than or equal to the number of vehicles in the previous cell of the cell at time t.
  • Qi ,j (t) represents the upper limit of the flow rate of the j-th Cell of road section i at time t.
  • the constraint condition 3 indicates that for a cell, the number of vehicles flowing into the cell at time t is less than or equal to the upper limit of the flow of the cell at time t.
  • f i,j (t) represents the number of vehicles flowing into the j-th cell of the road section i at time t
  • W represents the propagation speed
  • V represents the overflow speed
  • Ni ,j is the capacity of a cell specified in the traffic manual
  • the upper limit, n i,j (t) represents the number of vehicles in the j-th Cell of road section i at time t.
  • the above-mentioned four signal control constraints are used as the optimization conditions of the traffic signal control model (ie, objective function) of the target road to solve the optimization problem, that is, to solve the traffic signal control model to obtain traffic signal control information, namely traffic lights Control duration.
  • the traffic signal control model of the target road section may be a model related to f i,j (t) in the prior art.
  • the above four signal control constraints are used as the constraints of the traffic signal control model. Condition, get traffic signal control information.
  • the road includes 4 road sections and 1 crossroad.
  • the control time of traffic lights in the east-west direction can be obtained by analyzing the traffic data of road section 1 and road section 2 to obtain the signal corresponding to road section 1.
  • the control constraint condition and the signal control constraint condition corresponding to section 2 are solved, and the traffic signal control model is solved based on the signal control constraint condition to obtain the duration of traffic lights in the east-west direction.
  • the control time of traffic lights in the north-south direction can be obtained by analyzing the traffic data of road section 3 and road section 4 to obtain the signal control constraint conditions corresponding to road section 3 and the signal control constraint conditions corresponding to road section 4.
  • the traffic signal control model is solved to obtain the duration of traffic lights in the north-south direction. Or, based on the signal control constraint equation corresponding to road segment 1, the signal control constraint condition corresponding to road segment 2, the signal control constraint condition corresponding to road segment 3, and the signal control constraint condition corresponding to road segment 4, the traffic signal control model is solved to obtain the east-west direction , The duration of each traffic light in the north-south direction.
  • the traffic information processing method uses traffic data of the target road in the historical time period from the perspective of the road, determines the target road propagation model from a variety of candidate road propagation models, and adopts the target road propagation model in the current time period.
  • the road traffic data adjusts the parameters of the target road propagation model to generate traffic signal control information. In this way, traffic signal control can be adaptively and more accurately performed.
  • the above historical traffic data is the traffic data of the target road network in the historical time period
  • the current traffic data is the traffic data of the target road network in the current time period.
  • the candidate traffic models are multiple road network evaluation models
  • the target traffic model is the target road network evaluation model
  • the traffic control strategy is road network boundary control information.
  • the traffic information processing method provided by the embodiment of the present application may include S401-S403:
  • the traffic data of the target road network in the historical time period includes at least two of the flow, speed, and density of the target road network in the historical time period (e.g., one week or two weeks).
  • the traffic data of the target road network is determined by the traffic data of the road sections included in the target road network, that is, the traffic data of the road sections included in the target road network are aggregated to obtain the traffic data of the target road network. Traffic data.
  • the traffic data of the road sections included in the target road network can be aggregated in the following manner:
  • q is the traffic of the target road network
  • q i is the traffic of the i-th road segment included in the target road network
  • n is the number of road segments included in the target road network.
  • v is the target speed of the road network
  • v i is the velocity of the target road network comprising the i-th segment.
  • k is the density of the target road network
  • k i is the density of the i-th road section included in the target road network.
  • the above-mentioned road network evaluation model may be a road network curve model, and the road network evaluation model may also be a model of other forms, which is not limited in the embodiment of the present application.
  • the road network curve model is a curve model reflecting the relationship between the traffic-density-speed of the road network.
  • the road network curve model can be a three-dimensional curve or a two-dimensional curve (that is, taking the flow, density, or speed). Two types of curves, such as the dense-speed curve formed by the speed and density of the road network).
  • the probability graph matching method is used to select the dense-speed curve with the highest matching probability among multiple candidate dense-speed curves.
  • the speed curve is determined as the density-speed curve of the target road network, that is, as the target road network evaluation model.
  • S402 Adjust the parameters of the target road network evaluation model according to the traffic data of the target road network in the current time period.
  • the traffic data of the target road network in the current time period includes at least two of the flow, speed, and density of the target road network in the current time period.
  • the traffic data of the target road network in the current time period please refer to the related description of the traffic data of the target road network in the historical time period in S401, which will not be repeated here.
  • the parameters of the target road network propagation model are adjusted, and the regularity and randomness of the traffic system are taken into consideration to obtain the road network evaluation
  • the model is more reliable.
  • S403 Generate road network boundary control information based on the adjusted parameters of the target road network propagation model.
  • the road network boundary control information is information such as traffic light control duration at the road network boundary.
  • the macro-traffic flow model is a mathematical model that describes the operating characteristics of the traffic flow from the perspective of traffic flow, speed, and density.
  • the macro-traffic flow model may include the basic traffic flow model, the vehicle party model, and the conservation of traffic flow. Model (can also be called the conservation condition of traffic flow) and so on.
  • the embodiment of the present application takes the macroscopic traffic flow model as the traffic flow conservation condition as an example for description.
  • k t is the partial derivative of the density function k(t,x) with respect to t
  • q t is the partial derivative of the flow function q(t,x) with respect to x
  • t is the time
  • x is the displacement.
  • the function expression of V(k) can be obtained.
  • Solving the LWR equation can obtain the density function k(t,x) and the flow function. q(t,x).
  • the limit value of the density function k(t,x) of the target road network can reflect the capacity state of the target road network.
  • other indicators can also be used to reflect the capacity of the target road network;
  • the flow function q of the target road network The limit value of (t,x) can reflect the traffic state of the target road network.
  • the capacity or flow of the target road network can reflect the congestion degree of the traffic state of the target road network. Therefore, according to the capacity or flow of the target road network, the road network boundary control information is generated to realize the traffic control of the road network. . For example, if the density (namely capacity) of the target road network is close to the cutoff density of the target road network, indicating that the target road network is relatively congested, then the vehicles on the target road network can be directed to other road networks that are not congested.
  • the road network boundary control scheme can be : Increase the green light time from road network 1 to road network 2, reduce the green light time from road network 2 to road network 1, road network boundary control information is the green light time from road network 1 to road network 2, road network 2 to road network The green light duration of 1.
  • the traffic information processing method uses the traffic data of the target road network in the historical time period from the perspective of the road network, determines the target road network evaluation model from a variety of candidate road network evaluation models, and uses the current time
  • the traffic data of the target road network in the segment adjusts the parameters of the target road network evaluation model to generate road network boundary control information. In this way, the traffic control of the road network boundary can be adaptively and more accurately performed.
  • the traffic information processing method further includes: presenting different levels of traffic information according to different scales, and dividing the traffic Information visualization.
  • the above-mentioned different levels of traffic information are respectively the driver’s traffic information, the target road’s traffic information, and the target road network’s traffic information; where the driver’s traffic information includes the driver’s traffic data in the current time period (for example, the above-mentioned driver’s driving The acceleration and speed of the vehicle) and the parameters of the target driver model (for example, c in the acceleration equation proposed by Pipes (1953) above);
  • the traffic information of the target road includes the traffic data of the target road in the current time period (for example, the target road
  • the traffic information of the target road network includes the traffic data of the target road network in the current time period (for example, the traffic data of the target road network) At least two of them) and the parameters of the target road network evaluation model.
  • different levels of traffic information may be presented in one or more of the following ways: a display screen, an electronic map, or a projection.
  • display screens such as urban brains
  • display screens of vehicle-mounted terminals such as LCD
  • display screens of mobile phones etc.
  • project traffic information on the front windshield of the vehicle or display it on electronic maps such as navigation software.
  • the above-mentioned different levels of traffic information are displayed according to different scales, and can be switched and displayed according to different scales (for example, zoom in or zoom out) through UI operations.
  • it is displayed on micro, meso and macro scales.
  • the micro traffic information is vehicle traffic information (that is, the driver’s traffic information)
  • the meso traffic information is road traffic information
  • the macro traffic information is For the traffic information of the road network, take the electronic map as an example.
  • the traffic information of the road network can be displayed after the electronic map is zoomed out ((a) in Figure 14), and the traffic information of the road can be displayed after the electronic map is enlarged ( Figure 14(b)), the electronic map can display the traffic information of the vehicle after being further enlarged ( Figure 14(c)), so that it can display traffic information of different scales, which is practical and flexible.
  • the traffic information processing method provided in the embodiments of the present application can be executed by a traffic information processing device (for example, the above-mentioned central server), and the traffic information processing device is divided into functional modules according to the above method examples.
  • a traffic information processing device for example, the above-mentioned central server
  • each functional module can be divided corresponding to each function, It is also possible to integrate two or more functions into one processing module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. It should be noted that the division of modules in the embodiments of the present application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.
  • FIG. 15 shows a possible structural schematic diagram of the traffic information processing device involved in the foregoing embodiment.
  • the traffic information processing device may include: The model determination module 1001, the parameter adjustment module 1002, and the traffic control strategy generation module 1003.
  • the model determination module 1001 can be used to support the traffic information processing device to execute S101, S201, S301, and S401 in the above method embodiment;
  • the parameter adjustment module 1002 can be used to support the traffic information processing device to execute the above method embodiment S102, S202, S302, and S402;
  • the traffic control strategy generation module 1003 can be used to support the traffic information processing device to execute S103, S203 (including S2031-S2032), S303 (including S3031-S3032) and S403 ( Including S4031-S4032).
  • S203 including S2031-S2032
  • S303 including S3031-S3032
  • S403 Including S4031-S4032
  • the traffic information processing device may further include a display module 1004, which is used to support the traffic information processing device to display multi-level traffic information.
  • the information is the traffic information of the driver, the traffic information of the target road, and the traffic information of the target road network.
  • FIG. 16 shows a possible structural schematic diagram of the traffic information processing device involved in the foregoing embodiment.
  • the traffic information processing device may include: a processing module 2001 and a communication module 2002.
  • the processing module 2001 can be used to control and manage the actions of the traffic information processing device.
  • the processing module 2001 can be used to support the traffic information processing device to execute S101-S103, S201-S203 (wherein, S203) in the foregoing method embodiment. Including S2031-S2032), S301-S303 (wherein S303 includes S3031-S3032), and S401-S403 (wherein S403 includes S4031-S4032), and/or other processes used in the technology described herein.
  • the communication module 2002 can be used to support communication between the traffic information processing device and other network entities.
  • the traffic information processing device may further include a storage module 2003 for storing program codes and data of the traffic information processing device.
  • the processing module 2001 may be a processor or a controller (for example, the processor 11 shown in FIG. 2), for example, a CPU, a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, transistor Logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in conjunction with the disclosure of the embodiments of the present application.
  • the foregoing processor may also be a combination for realizing calculation functions, for example, including a combination of one or more microprocessors, a combination of DSP and microprocessor, and so on.
  • the communication module 2002 may be a transceiver, a transceiver circuit or a communication interface (for example, it may be the communication interface 13 shown in FIG. 2).
  • the storage module 2003 may be a memory (for example, it may be the above-mentioned memory 12 shown in FIG. 2).
  • the processing module 2001 is a processor
  • the communication module 2002 is a transceiver
  • the storage module 2003 is a memory
  • the processor, the transceiver, and the memory may be connected by a bus.
  • the bus may be a peripheral component interconnect standard (PCI) bus or an extended industry standard architecture (EISA) bus, etc.
  • PCI peripheral component interconnect standard
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the above embodiments it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • a software program it can be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions.
  • the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instruction may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the computer instruction may be transmitted from a website, a computer, a server, or a data center through a cable (Such as coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (such as infrared, wireless, microwave, etc.) to another website, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrated with one or more available media.
  • the usable medium can be a magnetic medium (for example, a floppy disk, a magnetic disk, a tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid state drive (SSD)), etc. .
  • a magnetic medium for example, a floppy disk, a magnetic disk, a tape
  • an optical medium for example, a digital video disc (DVD)
  • DVD digital video disc
  • SSD solid state drive
  • the disclosed system, device, and method can be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, for example, multiple units or components may be divided. It can be combined or integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor execute all or part of the steps of the method described in each embodiment of the present application.
  • the aforementioned storage media include: flash memory, mobile hard disk, read-only memory, random access memory, magnetic disk or optical disk and other media that can store program codes.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Atmospheric Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Environmental Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • Ecology (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

本申请涉及人工智能领域，提供一种交通信息处理方法及装置，能够提供更加合理、可靠的交通管控策略，提升交通服务质量。该方法包括：采用历史交通数据，从多个候选交通模型中确定目标交通模型；该候选交通模型包括下述至少一种：驾驶员模型、道路传播模型或路网评价模型，该候选交通模型与历史交通数据相对应；并且跟据当前交通数据，对目标交通模型的参数进行调整，该目标交通模型的参数用于描述当前交通运行状态；以及基于调整后的目标交通模型的参数，生成交通管控策略，该交通管控策略包括下述至少一种：驾驶员导航信息、交通信号控制信息或路网边界控制信息。

Description

一种交通信息处理方法及装置
本申请要求于2019年12月27日提交国家知识产权局、申请号为201911380305.9、申请名称为“一种交通信息处理方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及人工智能领域，尤其涉及一种交通信息处理方法及装置。
背景技术
目前，采用交通领域的交通模型(道路基本图模型、路网曲线模型等)对交通信息(例如流量、速度、密度等信息)进行处理得到可以反映不同道路单元(例如路口、路段或路网)的状态的处理结果，进而将交通信息的处理结果用于构建道路信息系统(例如交通信号控制系统等)。
具体的，首先确定道路单元对应的预设交通模型，然后采用由车辆传感器或道路传感器等上报的交通数据对预设交通模型进行参数标定(即确定预设交通模型的相关参数)，例如道路基本图模型的参数反映交通前向传播速度；进而根据交通模型的参数构建道路信息系统，例如根据交通前向传播速度，得到优化的信号控制方案，即红绿灯的时长控制方案。
然而，上述方法中，预设交通模型可能与实际情况有偏差，从而导致交通信息处理结果偏差较大，进而构建的道路信息系统的应用效果不佳。
发明内容
本申请实施例提供一种交通信息处理方法及装置，能够提供更加合理、可靠的交通管控策略，提升交通服务质量。
为达到上述目的，本申请实施例采用如下技术方案：
第一方面，本申请实施例提供一种交通信息处理方法，包括：采用历史交通数据，从多个候选交通模型中确定目标交通模型，所述候选交通模型与所述历史交通数据相对应；并且根据当前交通数据，对所述目标交通模型的参数进行调整，所述目标交通模型的参数用于描述当前交通运行状态，所述当前交通数据与所述目标交通模型相对应；以及基于调整后的所述目标交通模型的参数，生成交通管控策略。
本申请实施例中，所述候选交通模型包括下述至少一种：驾驶员模型、道路传播模型或路网评价模型。所述历史交通数据包括下述至少一种：历史时间段内驾驶员的交通数据、历史时间段内目标道路的交通数据或历史时间段内目标路网的交通数据。所述当前交通数据包括下述至少一种：当前时间段内驾驶员的交通数据、当前时间段内目标道路的交通数据或当前时间段内目标路网的交通数据。所述交通管控策略包括下述至少一种：驾驶员导航信息、交通信号控制信息或路网边界控制信息。
上述候选交通模型与历史交通数据相对应，即历史交通数据的种类与候选交通模型的种类相对应，例如历史交通数据为历史时间段内驾驶员的交通数据，则多种候选交通模型为多种驾驶员模型。当前交通数据与目标交通模型相对应，例如目标交通模 型为目标驾驶员模型，则获取当前时间段内驾驶员的交通数据，进而根据当前时间段内驾驶员的交通数据调整目标驾驶员模型的参数。应理解，(目标)交通模型的参数用于描述当前交通运行状态，例如，驾驶员模型的参数用于描述驾驶员当前的驾驶习惯(驾驶激进程度或路线选择的偏好等)，道路传播模型用于描述道路当前的交通运行状态，路网评价模型用于描述路网当前的交通运行状态。
需要说明的是，上述历史时间段指的是以当前时刻(时间点)为起点，在该当前时刻之前的多个计算时间窗，同理，对于不同的统计对象(即个体车辆、道路或路网)，历史时间段对应的时间长度不同，历史时间段的长度可以根据实际需求设定，例如，对于驾驶员，历史时间段可以设定为前一天；对于路段或路口(即道路)，历史时间段可以设定为前一天，或者前几天，或者前一周等；对于路网，历史时间段可以设定为前一周或者前两周等。
当前时间段指的是以当前时刻(时间点)为起点，在该当前时刻之前的一个计算时间窗，从而，当前交通数据指的是当前时刻之前的一个计算时间窗内的交通数据。对于不同的统计对象(即个体车辆、道路或路网)，计算时间窗不同，即对于不同的统计对象，当前时间段对应的时间窗不同，时间窗的大小可以根据实际需求设定，例如，对于驾驶员，其计算时间窗可以设定为较小的值，例如设定为1分钟(min)-5min；对于路段或路口(即道路)，其计算时间窗可以设定为适中的值，例如设定为15min-30min；对于路网，其计算时间窗可以设定为较大的值，例如设定为1小时(h)或1h以上。
本申请实施例中，根据当前交通数据，可以采用回归分析法、最小二乘法或梯度优化法(例如梯度下降法)对目标交通模型的参数进行调整(也可以称为对目标交通模型的参数进行参数标定)，当然，也可以采用其他方法对目标交通模型的参数进行调整，本申请实施例不作限定。
本申请实施例提供的交通信息处理方法，可以采用历史交通数据，从多个候选交通模型中确定目标交通模型，该候选交通模型包括下述至少一种：驾驶员模型、道路传播模型或路网评价模型；然后根据当前交通数据，对目标交通模型的参数进行调整，进而基于调整后的目标交通模型的参数，生成交通管控策略，该交通管控策略包括下述至少一种：驾驶员导航信息、交通信号控制信息或路网边界控制信息，能够提供更加合理、可靠的交通管控策略，提升交通服务质量。
一种可能的实现方式中，所述历史交通数据为历史时间段内驾驶员的交通数据，所述目标交通模型为目标驾驶员模型，驾驶员的交通数据包括驾驶员驾驶的车辆的交通数据或驾驶员的出行习惯数据；历史时间段内驾驶员驾驶的车辆的交通数据包括所述历史时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；历史时间段内驾驶员的出行习惯数据包括所述历史时间段内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率。当前时间段内驾驶员的交通数据包括所述当前时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；当前时间段内驾驶员的出行习惯数据包括所述当前时间段内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率。
本申请实施例中，可以根据历史时间段内车辆的轨迹数据(即传感器上报的数据， 例如车辆中的位置传感器前一天所上报数据或电子警察等其他传感器上报的数据)中提取该驾驶员驾驶的车辆的位置和车牌号，再结合该驾驶员驾驶的车辆附近的车辆(例如前方车辆)的位置和车牌号等数据，确定该驾驶员驾驶的车辆的加速度以及速度。
本申请实施例中，可以收集某一驾驶员在历史时间段内(需注意，此处的历史时间段可以为以天为单位的时间，例如10天、20天或者30天等)的出行数据(例如行程和路线)，根据该驾驶员在历史时间段内的出行数据计算得到驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率。
一种可能的实现方式中，所述交通管控策略为所述驾驶员导航信息，所述基于调整后的所述目标交通模型的参数，生成交通管控策略，包括：基于调整后的目标驾驶员模型的参数，设置导航地图上的路径的权重，所述目标驾驶员模型的参数用于描述驾驶员当前的驾驶习惯；并且根据所述导航地图上的路径的权重，生成所述驾驶员导航信息。
本申请实施例提供的交通信息的处理方法，从驾驶员驾驶的车辆的角度，采用历史时间段内驾驶员的交通数据，从多种候选驾驶员模型中确定目标驾驶员模型，并且采用当前时间段内该驾驶员的交通数据，对目标驾驶员模型的参数进行调整，从而生成驾驶员导航信息，如此，能够为驾驶员提供更加全面且实用的个性化导航服务。
一种可能的实现方式中，所述历史交通数据为历史时间段内目标道路的交通数据，所述目标交通模型为目标道路传播模型；所述历史时间段内目标道路的交通数据包括历史时间段内目标道路的流量、速度以及密度中的至少两种；所述当前时间段内目标道路的交通数据包括当前时间段内目标道路的流量、速度以及密度中的至少两种。
需要说明的是，道路传播模型可以为道路曲线模型，例如道路基本图模型，道路传播模型也可以为其他形态的模型，本申请实施例不作限定。
本申请实施例中，道路基本图模型是反映道路的流量-密度-速度关系的曲线模型，该道路基本图模型可以是三维曲线，也可以为二维曲线(即取流量、密度或速度中的两种形成的曲线，例如道路的流量和密度形成的流-密曲线)。
一种可能的实现方式中，所述交通管控策略为所述交通信号控制信息，所述基于调整后的所述目标交通模型的参数，生成交通管控策略，包括：基于调整后的目标道路传播模型的参数，确定信号控制约束条件，所述目标道路传播模型的参数用于描述所述目标道路当前的交通运行状态；并且将所述信号控制约束条件作为交通信号控制模型的优化条件，生成所述交通信号控制信息，所述信号控制约束条件是通过所述调整后的道路传播模型确定的。
上述。本申请实施例提供的交通信息的处理方法，从道路的角度，采用历史时间段内目标道路的交通数据，从多种候选道路传播模型中确定目标道路传播模型，并且采用当前时间段内该目标道路的交通数据，对目标道路传播模型的参数进行调整，从而生成交通信号控制信息，由于根据当前时间段内目标道路的交通数据(可以理解为实时的交通数据)对目标道路传播模型的参数进行调整，将交通流传播的规律性、随机性以及道路之间的异构性纳入考虑范围，得到的道路传播模型更加可靠。如此，能够自适应地、并且更加准确地进行交通信号控制。
一种可能的实现方式中，所述历史交通数据为历史时间段内目标路网的交通数据， 所述目标交通模型为目标路网评价模型；所述历史时间段内目标路网的交通数据包括历史时间段内目标路网的流量、速度以及密度中的至少两种；所述当前时间段内目标路网的交通数据包括当前时间段内目标路网的流量、速度以及密度中的至少两种。
需要说明的是，上述路网评价模型可以为路网曲线模型，路网评价模型也可以为其他形态的模型，本申请实施例不作限定。
本申请实施例中，路网曲线模型是反映路网的流量-密度-速度关系的曲线模型，该路网曲线模型可以是三维曲线，也可以为二维曲线(即取流量、密度或速度中的两种形成的曲线，例如路网的速度和密度形成的密-速曲线)。
一种可能的实现方式中，所述交通管控策略为所述路网边界控制信息，所述基于调整后的所述目标交通模型的参数，生成交通管控策略，包括：基于所述调整后的目标路网评价模型的参数以及宏观交通流模型，确定所述目标路网的容量或流量，所述目标路网评价模型的参数用于描述所述目标路网当前的交通运行状态；并且根据所述目标路网的容量或流量，生成所述路网边界控制信息。
本申请实施例中，目标路网的容量或者流量可以反映该目标路网的交通状态的拥堵程度，因此根据目标路网的容量或者流量，生成路网边界控制信息，实现对路网的交通管控。例如，目标路网的密度(即容量)已接近该目标路网的截止密度，说明该目标路网比较拥堵，那么可以将该目标路网的车辆引导至其他不拥堵的路网。
本申请实施例提供的交通信息的处理方法，从路网的角度，采用历史时间段内目标路网的交通数据，从多种候选路网评价模型中确定目标路网评价模型，并且采用当前时间段内该目标路网的交通数据，对目标路网评价模型的参数进行调整，从而生成路网边界控制信息，由于根据当前时间段内目标路网的交通数据(可以理解为实时的交通数据)对目标路网传播模型的参数进行调整，将交通系统的规律性、随机性纳入考虑范围，得到的路网评价模型更加可靠。如此，能够自适应地、并且更加准确地进行路网边界的交通管控。
一种可能的实现方式中，所述目标路网的交通数据是通过所述目标路网所包含的路段的交通数据确定。
本申请实施例中，目标路网的交通数据是通过该目标路网所包含的路段的交通数据确定，也就是说，将目标路网包含的路段的交通数据进行汇聚，得到该目标路网的交通数据。在一种实现方式中，可以通过如下方式汇聚目标路网包含的路段的交通该数据：
Figure PCTCN2020129078-appb-000001
其中，q为目标路网的流量，q i为目标路网包含的第i个路段的流量，n为该目标路网包含的路段的数量。
Figure PCTCN2020129078-appb-000002
其中，v为目标路网的速度，v i为目标路网包含的第i个路段的速度。
Figure PCTCN2020129078-appb-000003
其中，k为目标路网的密度，k i为目标路网包含的第i个路段的密度。
一种可能的实现方式中，本申请实施例提供的交通信息处理方法还包括：按照不 同的比例尺呈现不同层次的交通信息，所述不同层次的交通信息分别为驾驶员的交通信息、目标道路的交通信息以及目标路网的交通信息；其中，所述驾驶员的交通信息包括所述当前时间段内驾驶员的交通数据和所述目标驾驶员模型的参数；所述目标道路的交通信息包括所述当前时间段内目标道路的交通数据和所述目标道路传播模型的参数；所述目标路网的交通信息包括所述当前时间段内目标路网的交通数据和所述目标路网评价模型的参数。
在本申请实施例中，上述不同层次的交通信息按照不同的比列尺进行显示，并且可以通过UI操作按照不同的比例尺进行切换显示(例如，放大或缩小)。示例性的，按照微观、中观以及宏观的尺度进行显示，微观的交通信息是车辆的交通信息(即驾驶员的交通信息)，中观的交通信息是道路的交通信息，宏观的交通信息是路网的交通信息。
一种可能的实现方式中，通过下述一种或多种方式呈现所述不同层次的交通信息：显示屏、电子地图或投影。
可选的，可以在展示屏(例如城市大脑)、车载终端的显示屏以及手机的显示屏等上显示不同层次的交通信息，或者将不同层次的交通信息投影在车辆的前挡风玻璃等位置，或者在导航软件等电子地图中显示不同层次的交通信息。
第二方面，本申请实施例提供一种交通信息处理装置，包括模型确定模块、参数调整模块、交通管控策略生成模块；所述模型确定模块，用于采用历史交通数据，从多个候选交通模型中确定目标交通模型；所述候选交通模型包括下述至少一种：驾驶员模型、道路传播模型或路网评价模型，所述历史交通数据包括下述至少一种：历史时间段内驾驶员的交通数据、历史时间段内目标道路的交通数据或历史时间段内目标路网的交通数据，所述候选交通模型与所述历史交通数据相对应；所述参数调整模块，用于根据当前交通数据，对所述目标交通模型的参数进行调整；所述目标交通模型的参数用于描述当前交通运行状态，所述当前交通数据包括下述至少一种：当前时间段内驾驶员驾驶的车辆的交通数据或、当前时间段内目标道路的交通数据或当前时间段内目标路网的交通数据，所述当前交通数据与所述目标交通模型相对应；所述交通管控策略生成模块，用于基于调整后的所述目标交通模型的参数，生成交通管控策略；所述交通管控策略包括下述至少一种：驾驶员导航信息、交通信号控制信息或路网边界控制信息。
一种可能的实现方式中，所述历史交通数据为历史时间段内驾驶员的交通数据，所述目标交通模型为目标驾驶员模型，驾驶员的交通数据包括驾驶员驾驶的车辆的交通数据或驾驶员的出行习惯数据；历史时间段内驾驶员驾驶的车辆的交通数据包括所述历史时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；历史时间段内驾驶员的出行习惯数据包括所述历史时间段内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率；当前时间段内驾驶员的交通数据包括所述当前时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；当前时间段内驾驶员的出行习惯数据包括所述当前时间段内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率。
一种可能的实现方式中，所述交通管控策略为所述驾驶员导航信息；所述交通管 控策略生成模块，具体用于基于调整后的目标驾驶员模型的参数，设置导航地图上的路径的权重；且根据所述导航地图上的路径的权重，生成所述驾驶员导航信息，所述目标驾驶员模型的参数用于描述驾驶员当前的驾驶习惯。
一种可能的实现方式中，所述历史交通数据为历史时间段内目标道路的交通数据，所述目标交通模型为目标道路传播模型；所述历史时间段内目标道路的交通数据包括历史时间段内目标道路的流量、速度以及密度中的至少两种；所述当前时间段内目标道路的交通数据包括当前时间段内目标道路的流量、速度以及密度中的至少两种。
一种可能的实现方式中，所述交通管控策略为所述交通信号控制信息；所述交通管控策略生成模块，具体用于基于调整后的目标道路传播模型的参数，确定信号控制约束条件；并且将所述信号控制约束条件作为交通信号控制模型的优化条件，生成所述交通信号控制信息，所述目标道路传播模型的参数用于描述所述目标道路当前的交通运行状态，所述信号控制约束条件是通过所述调整后的道路传播模型确定的。
一种可能的实现方式中，所述历史交通数据为历史时间段内目标路网的交通数据，所述目标交通模型为目标路网评价模型；所述历史时间段内目标路网的交通数据包括历史时间段内目标路网的流量、速度以及密度中的至少两种；所述当前时间段内目标路网的交通数据包括当前时间段内目标路网的流量、速度以及密度中的至少两种。
一种可能的实现方式中，所述交通管控策略为所述路网边界控制信息；所述交通管控策略生成模块，具体用于基于所述调整后的目标路网评价模型的参数以及宏观交通流模型，确定所述目标路网的容量或流量；并且根据所述目标路网的容量或流量，生成所述路网边界控制信息，所述目标路网评价模型的参数用于描述所述目标路网当前的交通运行状态。
一种可能的实现方式中，所述目标路网的交通数据是通过所述目标路网所包含的路段的交通数据确定。
一种可能的实现方式中，本申请实施例提供的交通信息装置还包括显示模块；所述显示模块，用于按照不同比例尺呈现不同层次的交通信息，所述不同层次的交通信息分别为驾驶员的交通信息、目标道路的交通信息以及目标路网的交通信息；其中，所述驾驶员的交通信息包括所述当前时间段内驾驶员的交通数据和所述目标驾驶员模型的参数；所述目标道路的交通信息包括所述当前时间段内目标道路的交通数据和所述目标道路传播模型的参数；所述目标路网的交通信息包括所述当前时间段内目标路网的交通数据和所述目标路网评价模型的参数。
一种可能的实现方式中，通过下述一种或多种方式呈现所述不同层次的交通信息：显示屏、电子地图或投影。
第三方面，本申请实施例提供一种交通信息处理装置，包括处理器和与所述处理器耦合连接的存储器；所述存储器用于存储计算机指令，当所述装置运行时，处理器执行存储器存储的所述计算机指令，以使得所述装置执行上述第一方面以及其各种可能的实现方式中任意之一所述的方法。
第四方面，本申请实施例提供一种交通信息处理装置，该交通信息处理装置以芯片的产品形态存在，该交通信息处理装置的结构中包括处理器和存储器，存储器用于与处理器耦合，存储器用于存储计算机指令，处理器用于执行存储器中存储的计算机 指令，使得该交通信息处理装置执行上述第一方面及其可能的实现方式中任意之一所述的方法。
第五方面，本申请实施例提供一种计算机可读存储介质，所述计算机可读存储介质可以包括计算机指令，当所述计算机指令在计算机上运行时，以执行上述第一方面及其可能的实现方式中任意之一所述的方法。
应当理解的是，本申请实施例的第二方面至第五方面技术方案及对应的可能的实施方式所取得的有益效果可以参见上述对第一方面及其对应的可能的实施方式的技术效果，此处不再赘述。
附图说明
图1为本申请实施例提供的一种交通信息通信系统的架构示意图；
图2为本申请实施例提供的一种处理交通信息的服务器的硬件示意图；
图3为本申请实施例提供的一种交通信息处理方法示意图一；
图4为本申请实施例提供的一种交通信息处理方法示意图二；
图5为本申请实施例提供的一种交通信息处理方法示意图三；
图6为本申请实施例提供的一种交通路线示意图；
图7为本申请实施例提供的一种交通信息处理方法示意图四；
图8为本申请实施例提供的流-密曲线示意图；
图9为本申请实施例提供的流-密曲线的参数示意图；
图10为本申请实施例提供的一种交通信息处理方法示意图五；
图11为本申请实施例提供的一种道路示意图；
图12为本申请实施例提供的一种交通信息处理方法示意图六；
图13为本申请实施例提供的一种交通信息处理方法示意图七；
图14为本申请实施例提供的一种不同层次的交通信息的显示示意图；
图15为本申请实施例提供的一种交通信息处理装置的结构示意图一；
图16为本申请实施例提供的一种交通信息处理装置的结构示意图二。
具体实施方式
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。
在本申请实施例中，“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请实施例中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其它实施例或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。
在本申请实施例的描述中，除非另有说明，“多个”的含义是指两个或两个以上。例如，多个处理单元是指两个或两个以上的处理单元；多个系统是指两个或两个以上的系统。
首先对本申请实施例提供的一种交通信息处理方法及装置中涉及的一些概念做解释说明。
交通模型：在交通系统中，采用数学模型来描述交通运行状态，这些数学模型称 为交通模型，交通模型可以用于分析车辆、驾驶员和行人、道路以及路网等的交通状态，例如对某个位置交通是否拥堵、道路是否畅通、有无出现交通事故，从而有效地进行交通规划、交通组织与管理等。
驾驶员模型：用于描述个体车辆的驾驶状态，驾驶员模型是一种微观交通模型。
道路传播模型：用于描述道路交通流传播状态，如传播速度等，本申请实施例中，道路传播模型可以是道路曲线模型(例如道路基本图模型)，道路传播模型也可以为其他形式的模型，在此不做限定。道路传播模型是一种中观交通模型。
路网评价模型：用于描述路网的通行状态，如路网处于拥堵态、路网处于畅通态等。路网评价模型是一种宏观交通模型。
路段：指的是相邻的两个路口之间的道路，即路段除两端路口外不应该有其他路口与其他道路相连通。
路网：指的是在一定区域内，由各种道路(道路包含路段和路口)组成的相互联络、交织成网状分布的道路系统。应理解，全部由各级公路组成的称公路网。在城市范围内由各种道路组成的称城市道路网。
基于背景技术存在的问题，本申请实施例提供一种交通信息处理方法及装置，可以采用历史交通数据，从多个候选交通模型中确定目标交通模型，该候选交通模型包括下述至少一种：驾驶员模型、道路传播模型或路网评价模型；然后根据当前交通数据，对目标交通模型的参数进行调整，该目标交通模型的参数用于描述当前交通运行状态，进而基于调整后的目标交通模型的参数，生成交通管控策略，该交通管控策略包括下述至少一种：驾驶员导航信息、交通信号控制信息或路网边界控制信息，采用本申请实施例提供的技术方案，能够提供更加合理、可靠的交通管控策略，提升交通服务质量。
本申请实施例提供的交通信息处理方法及装置可以应用于交通信息通信系统中，如图1所示为本申请实施例提供的交通信息通信系统的架构示意图。本申请实施例中的交通信息通信系统的架构示意图可以包括两种，具体的，在图1中的(a)所示的交通信息通信系统中包括至少一个传感器端(图1中的(a)记为传感器端1至传感器端N)和交通中心侧，该交通中心侧可以包括中心服务器或中心云。其中，传感器端包括多种传感器，例如道路上安装的电子警察(摄像头)、断面检测器(检测线圈、地磁、雷达等)等道路传感器，车辆传感器(GPS定位装置或驾驶员的手机定位装置)等等，电子警察获取的交通数据可以包括车辆的车牌号、车辆的位置、车辆排队长度等数据，断面检测器检测到的交通数据可以包括车辆的流量等数据，车辆传感器获取的交通数据可以包括车辆的位置等数据。交通信息通信系统中的传感器端可以将其获取的交通数据上报至交通中心侧，进而交通中心侧的设备(中心服务器或中心云)对交通数据进行分析处理，得到交通管控策略。
在图1中的(b)所示的交通信息通信系统中包括至少一个传感器端(图1中的(a)记为传感器端1至传感器端N)、至少一个边缘侧(图1中的(b)记为边缘侧器端1至边缘侧K)和交通中心侧，其中，边缘侧包括边缘服务单元(例如边缘服务器)，边缘侧的边缘服务单元主要用于各个传感器端的交通数据进行预处理，例如汇聚各个传感器的交通数据、交通数据的有效性检测等。各个传感器端首先将其获取的交通数 据发送至各自的边缘侧(例如在图1中的(b)中，传感器端1和传感器2将其获取的交通数据发送至边缘侧1，传感器端3将其获取的交通数据发送至边缘侧2，传感器端N将其获取的交通数据发送至边缘侧K)，然后，各个边缘侧再将交通数据上报至交通中心侧，由交通中心侧的设备(中心服务器或中心云)对交通数据进行分析处理，得到交通管控策略。
结合上述交通信息通信系统的架构，传感器端到边缘侧再到交通中心侧的数据传输均采用主动上报的方式，该通信系统中的各个传感器将交通数据发送至边缘侧，边缘侧将交通数据按照数据上报格式进行汇聚，再按照该格式发送至交通中心侧。可选的，本申请实施例中，边缘侧上报交通数据的格式可以包括两种类型：
第一种数据格式是以某一区域内的传感器为单位进行上报，例如，区域内传感器1的数据、区域内传感器2的数据、……、区域内传感器N的数据。
第二种数据格式是以某一区域内的道路为单位进行上报，例如，区域内道路1的数据、区域内道路2的数据、......、区域内道路M的数据。
本申请实施例提供的交通信息处理装置可以为一台服务器(例如图1中所示的中心服务器)或云服务器(例如图1中所示的中心云)，下面以该交通信息处理装置为服务器为例，结合图2具体介绍本申请实施例提供的用于处理交通信息的服务器的各个部件。如图2所示，该服务器10可以包括：处理器11、存储器12和通信接口13等。
处理器11：是服务器10的核心部件，用于运行服务器10的操作系统与服务器30上的应用程序(包括系统应用程序和第三方应用程序)，例如处理器11通过运行该服务器上的网络质量监控的方法程序，对网络质量进行监控。
本申请实施例中，处理器11具体可以为中央处理器(central processing unit，CPU)，通用处理器，数字信号处理器(digital signal processor，DSP)，专用集成电路(application-specific integrated circuit，ASIC)，现场可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合，其可以实现或执行结合本申请实施例公开的内容所描述的各种示例性的逻辑方框，模块和电路；处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和微处理器的组合等。
存储器12：可用于存储软件程序以及模块，处理器11通过运行存储在存储器12里的软件程序以及模块，从而执行服务器10的各种功能应用以及数据处理。存储器12可包含一个或多个计算机可读存储介质。存储器12包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序等，存储数据区可存储服务器10创建的数据等，本申请实施例中，存储器12中可以包括用于存储历史交通数据和当前交通数据等。
本申请实施例中，存储器12具体可以包括易失性存储器(volatile memory)，例如随机存取存储器(random-access memory，RAM)；该存储器也可以包括非易失性存储器(non-volatile memory)，例如只读存储器(read-only memory，ROM)，快闪存储器(flash memory)，硬盘(hard disk drive，HDD)或固态硬盘(solid-state drive，SSD)；该存储器还可以包括上述种类的存储器的组合。
通信接口13：用于服务器10与其他设备进行通信的接口电路，通信接口可以为收发器、收发电路等具有收发功能的结构，本申请实施例中，通过服务器10上的通信接口13可以车辆传感器或者道路传感器(例如电子警察、断面检测器等)发送的交通数据。
如图3所示，本申请实施例提供的交通信息处理方法可以包括S101-S103：
S101、采用历史交通数据，从多个候选交通模型中确定目标交通模型。
其中，候选交通模型可以包括下述至少一种：驾驶员模型、道路传播模型或路网评价模型；历史交通数据包括下述至少一种：历史时间段内驾驶员的交通数据、历史时间段内目标道路的交通数据或历史时间段内目标路网的交通数据。
上述候选交通模型与历史交通数据相对应，即历史交通数据的种类与候选交通模型的种类相对应，例如历史交通数据为历史时间段内驾驶员的交通数据，则多种候选交通模型为多种驾驶员模型。
本申请实施例中，上述候选交通模型是交通领域的多种常用的交通模型，上述采用历史交通数据，从多个候选交通模型中确定目标交通模型指的是采用历史交通数据进行交通模型匹配，从多种候选交通模型中选择一种与历史交通数据最匹配的交通模型作为目标交通模型，以用于后续的交通数据分析。
可选的，本申请实施例中，根据历史交通数据，可以采用全局误差匹配法、特征匹配法、概率图匹配法等方法从多个候选交通模型中选取误差最小或者特征最相似的交通模型作为目标交通模型，当然，也可以采用其他的匹配方法从多个候选交通模型中确定目标交通模型，本申请实施例不作限定。
需要说明的是，上述历史时间段指的是以当前时刻(时间点)为起点，在该当前时刻之前的多个计算时间窗，同理，对于不同的统计对象(即个体车辆、道路或路网)，历史时间段对应的时间长度不同，历史时间段的长度可以根据实际需求设定，例如，对于驾驶员，历史时间段可以设定为前一天；对于路段或路口(即道路)，历史时间段可以设定为前一天，或者前几天，或者前一周等；对于路网，历史时间段可以设定为前一周或者前两周等。
S102、根据当前交通数据，对目标交通模型的参数进行调整。
其中，当前交通数据可以包括下述至少一种：当前时间段内驾驶员的交通数据、当前时间段内目标道路的交通数据或当前时间段内目标路网的交通数据。
需要说明的是，本申请实施例中，当前时间段指的是以当前时刻(时间点)为起点，在该当前时刻之前的一个计算时间窗，从而，当前交通数据指的是当前时刻之前的一个计算时间窗内的交通数据。对于不同的统计对象(即个体车辆、道路或路网)，计算时间窗不同，即对于不同的统计对象，当前时间段对应的时间窗不同，时间窗的大小可以根据实际需求设定，例如，对于驾驶员，其计算时间窗可以设定为较小的值，例如设定为1分钟(min)-5min；对于路段或路口(即道路)，其计算时间窗可以设定为适中的值，例如设定为15min-30min；对于路网，其计算时间窗可以设定为较大的值，例如设定为1小时(h)或1h以上。
本申请实施例中，当前交通数据与目标交通模型相对应，例如目标交通模型为目标驾驶员模型，则获取当前时间段内驾驶员的交通数据，进而根据当前时间段内驾驶 员的交通数据调整目标驾驶员模型的参数。应理解，(目标)交通模型的参数用于描述当前交通运行状态，例如，驾驶员模型的参数用于描述驾驶员当前的驾驶习惯(驾驶激进程度或路线选择的偏好等)，道路传播模型用于描述道路当前的交通运行状态，路网评价模型用于描述路网当前的交通运行状态。
可选的，本申请实施例中，根据当前交通数据，可以采用回归分析法、最小二乘法或梯度优化法(例如梯度下降法)对目标交通模型的参数进行调整(也可以称为对目标交通模型的参数进行参数标定)，当然，也可以采用其他方法对目标交通模型的参数进行调整，本申请实施例不作限定。
S103、基于调整后的目标交通模型的参数，生成交通管控策略。
其中，上述交通管控策略包括下述至少一种：驾驶员导航信息、交通信号控制信息或路网边界控制信息。例如，目标交通模型为目标驾驶员模型时，该交通管控策略为驾驶员导航信息，以实现为不同的驾驶员提供个性化的导航服务；目标交通模型为目标道路传播模型时，该交通管控策略为交通信号控制信息(例如路口的红绿灯控制时长)，能够根据目标道路的当前的交通运行状态自适应的实现交通信号控制；目标驾驶员模型为路网评价模型时，该交通管控策略为路网边界控制信息(例如路网边界的红绿灯控制时长)，如此，能够根据目标路网当前的交通运行状态进行路网边界的交通信号控制。
本申请实施例提供的交通信息处理方法，可以采用历史交通数据，从多个候选交通模型中确定目标交通模型，该候选交通模型包括下述至少一种：驾驶员模型、道路传播模型或路网评价模型；然后根据当前交通数据，对目标交通模型的参数进行调整，进而基于调整后的目标交通模型的参数，生成交通管控策略，该交通管控策略包括下述至少一种：驾驶员导航信息、交通信号控制信息或路网边界控制信息，能够提供更加合理、可靠的交通管控策略，提升交通服务质量。
需要说明的是，本申请实施例提供的交通信息处理方法可以用于对不同尺度(微观、中观以及宏观)的交通信息的处理，例如对上述驾驶员的交通数据(微观)、道路的交通数据(中观)或路网的交通数据(宏观)中的至少一种交通数据的处理，进而生成对应的交通管控策略，实现多尺度道路信息系统(例如个性化导航系统、信号控制分析系统以及路网边界控制分析系统中的至少一种)。以下实施例分别介绍处理驾驶员的交通数据、道路的交通该数据以及路网的交通数据的过程。
可以理解的是，对于某一驾驶员(也可以理解为某一车辆)，上述历史交通数据为历史时间段内驾驶员的交通数据，当前交通数据为当前时间段内驾驶员的交通数据，多个候选交通模型为多个驾驶员模型，目标交通模型为目标驾驶员模型，交通管控策略为驾驶员导航信息。如图4所示，本申请实施例提供的交通信息处理方法可以包括S201-S203：
S201、采用历史时间段内驾驶员的交通数据，从多个驾驶员模型中确定目标驾驶员模型。
应理解，驾驶员的交通数据包括驾驶员驾驶的车辆的交通数据或驾驶员的出行习惯数据。历史时间段内驾驶员驾驶的车辆的交通数据包括历史时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；历史时间段内驾驶员的出行习惯数据包括历史时间段 内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率。
本申请实施例中，可以根据历史时间段内车辆的轨迹数据(即传感器上报的数据，例如车辆中的位置传感器前一天所上报数据或电子警察等其他传感器上报的数据)中提取该驾驶员驾驶的车辆的位置和车牌号，再结合该驾驶员驾驶的车辆附近的车辆(例如前方车辆)的位置和车牌号等数据，确定该驾驶员驾驶的车辆的加速度以及速度。
表1为车辆经过的道路上的1个电子警察(摄像头)采集的车辆的轨迹数据的示例，表2为在道路某处车辆上的位置传感器采集的车辆的轨迹数据的示例。
表1
车牌加密信息 车辆注册地 ID长度 时间 检测器ID
2D******5B****1 省份A 5 2018-03-19-06:23:39 ***5***1
在上述表1中，根据车辆的车牌加密信息可以得到车辆的车牌号，进而从电子警察采集的海量数据中找到与该驾驶员驾驶的车辆的车牌号相同的轨迹数据(即表1中的数据)，检测器的ID为采集该车辆轨迹数据的电子警察的位置，即认为是该车辆的位置，时间是采集该车辆的轨迹数据的时间。
应理解，在车辆行驶的过程中，车辆经过的路段或路口的多个电子警察均可以采集与上表1类似的多组车辆的轨迹数据，如表2所示，从而根据多个电子警察采集的电子设备的位置、时间信息，再结合该车辆邻近车辆的位置和时间信息，计算该车辆的加速度和速度。
表2
日期 时间 车牌号 经度 纬度 速度 方向角
20190401 12409 **C***4 114.184059 22.648478 9.0 74
应理解，一天一共有86400秒(s)，在表2中，时间12409代表的是从0点0分0秒开始到当前时刻的总计秒数，12409s代表时刻3点26分49秒。
同理，在上述表2中，从上述车辆的位置传感器也可以采集多组类似于表2中所示的轨迹数据，并且从车辆的轨迹数据中也可以提取该车辆的位置(经度和纬度)和时间信息，并且可以提取车辆的速度，再结合该车辆邻近车辆的位置、时间信息以及速度，得到该车辆的加速度和速度。
本申请实施例中，也可以通过其他的方法获取车辆的轨迹数据，从而计算车辆的加速度和速度，在此不做限定。
在一种实现方式中，历史时间段内驾驶员的交通数据为该历史时间段内驾驶员驾驶的车辆的加速度和速度时，上述多个目标驾驶员模型可以为多种车辆的加速度和速度的关系方程，表3中示例了3种常用的加速度方程的驾驶模型。
表3
Figure PCTCN2020129078-appb-000004
Figure PCTCN2020129078-appb-000005
上述采用历史时间段内驾驶员的交通数据，从多个驾驶员模型中确定目标驾驶员模型(即模型匹配)具体可以包括：采用历史时间段内车辆的加速度和速度，以及与该车辆邻近的车辆的加速度和速度对多种驾驶员模型的参数进行标定(即求解驾驶员模型的参数)，并且根据车辆的速度和模型的参数求解车辆的加速度(称为计算的加速度)，并将计算的加速度与上述根据轨迹数据确定的车辆的加速度(称为测量的加速度)进行比较，以确定出目标驾驶员模型。例如，可以采用全局匹配法，对于车辆的多组加速度和速度，可以得到每一种驾驶员模型对应的累计误差(即多组计算的加速度与测量的加速度的差值之和)，并且将累计误差最小的驾驶员模型确定为目标驾驶员模型。
本申请实施例中，可以收集某一驾驶员在历史时间段内(需注意，此处的历史时间段可以为以天为单位的时间，例如10天、20天或者30天等)的出行数据(例如行程和路线)，根据该驾驶员在历史时间段内的出行数据计算得到驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率。
具体的，驾驶员的每一种行程的出行概率为：该驾驶员的每一种行程的出行次数与所有行程的出行次数之和的比值。示例性的，假设驾驶员在过去的30天内的行程包括从家到工作单位，从工作单位到家、从工作单位到火车站，从家到购物中心的4种行程，如下表4为统计的4种行程的出行次数以及4种行程的出行概率。
表4
行程 行程内容 出行次数 行程的出行概率
1 从家到工作单位 20 0.4
2 从工作单位到家 20 0.4
3 从工作单位到火车站 5 0.1
4 从家到购物中心 5 0.1
对于驾驶员的一种行程，该行程对应的每一种路线的选择概率为：该驾驶员选择每一种路线的次数与选择该行程对应的所有路线的次数之和的比值。结合上述表4，以上述表4中的行程1(即从家到工作单位)为例，在历史时间段内该驾驶员从家到工作单位可选择的路线有3条，如下表5为统计的行程1的三种路线的选择次数以及3种路线的选择概率。
表5
路线 选择次数 行程的出行概率
1 10 0.5
2 6 0.3
3 4 0.2
本申请实施例中，对于表4中的行程2至行程4对应的多种路线的选择次数和选择概率此处不再一一罗列。
在一种实现方式中，历史时间段内驾驶员的交通数据为该历史时间段内驾驶员的 一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率，上述多个目标驾驶员模型可以为概率分布模型，根据该历史时间段内驾驶员的一种或多种行程的出行概率从多种关于行程的概率分布模型中匹配目标驾驶员模型，或者根据该历史时间段内每一种行程对应的一种或多种路线的选择概率从多种关于路线的概率分布模型中匹配目标驾驶员模型，上述模型匹配的方法与上述根据车辆的加速度和速度匹配得到目标驾驶员模型的方法的思路类似。
S202、根据当前时间段内驾驶员的交通数据，对目标驾驶员模型的参数进行调整。
结合S201中对驾驶员的交通数据的描述，相应的，可知当前时间段内驾驶员的交通数据可以包括当前时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；当前时间段内驾驶员的出行习惯数据包括当前时间段内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率。
对于当前时间段内驾驶员的交通数据的相关描述可以参见上述S201中对于历史时间段内驾驶员的交通数据的相关描述，此处不再赘述。
本申请实施例中，上述S101中确定出目标驾驶员模型之后，根据当前时间段内驾驶员的交通该数据，可以采用回归分析法，得到使得目标驾驶员模型的输出(例如加速度)和实际测量的数据(例如加速度)的误差最小的参数作为最终调整后的参数。应理解，在S201中，目标驾驶员模型为表3所示的加速度方程中的一种时，该目标驾驶员模型的参数可以参见表3的示例；目标驾驶员模型为概率分布模型时，该目标驾驶员模型的参数可以为概率分布模型的均值或方差。
本申请实施例中，目标驾驶员模型的参数用于描述驾驶员当前的驾驶习惯，该驾驶员的驾驶习惯可以包括该驾驶员的激进程度或该驾驶员选择某种路线的偏好。
对于表3中所示的几种驾驶员模型，当驾驶员模型的参数较大时，表示驾驶员的驾驶行为比较激进，当该驾驶员模型的参数较小时，表示驾驶员的驾驶行为比较保守。示例性的，若目标驾驶员模型为上述表3中Newell(1961)提出的驾驶员模型，该驾驶员模型的参数为c和d，参数c用于描述驾驶员是否追求高加速度，参数d用于描述驾驶员是否频繁换道，例如，参数c的值为0.7表明驾驶员追求高加速度，参数d的值为0.8表明驾驶员频繁换道，可见驾驶员的驾驶习惯是激进的，由此推测驾驶员的驾驶速度快，并且在频繁超车。
对于表4和表5对应的概率分布模型，概率分布模型的参数为方差时，该方差可以反映驾驶员对于某一种行程的出行偏好(例如方差较小，表示偏好于选择此种行程)或驾驶员对于某一路线的选择偏好(例如方差较小，表示偏好于选择此种路线)。
上述根据当前时间段内驾驶员的交通数据(可以理解为实时的交通数据)对目标驾驶员模型的参数进行调整，能够较好的获得驾驶员驾驶的习惯，将驾驶员驾驶的规律性、随机性以及驾驶员之间的异构性(可以理解为不同驾驶员具有不同的驾驶风格)纳入考虑范围，得到的驾驶员模型更加可靠。
S203、基于调整后的目标驾驶员模型的参数，生成驾驶员导航信息。
本申请实施例中，该驾驶员导航信息是一种针对于该驾驶员的驾驶习惯而生成的具有个性特征的导航路线。
可选的，结合图4，如图5所示，上述S203具体可以通过S2031-S2032实现：
S2031、基于调整后的目标驾驶员模型的参数，设置导航地图上的路径的权重。
S2032、根据导航地图上的路径的权重，生成驾驶员导航信息。
本申请实施例中，可以将上述调整后的目标驾驶员模型的参数用于导航地图中路径权重的计算，例如，对于激进型的驾驶员将一级道路等大路(主干道或快速干道)设置较高的权重。示例性的，图6为从起始点①至终点③的路线的规划，可见，起点①至终点③的路线可以为包括两条候选的路线，分别为：
路线1：①→②→③，包括路径①→②和路径②→③，其中，路径①→②为小路，长度为5千米(km)，路径②→③的也为小路，长度为5km。
路线2：①→④→③，包括路径①→④和路径①→④，其中，①→④为快速干道，长度为12km，路径④→③为主干道，长度为15km。
结合图6，在一种示例中，假设该驾驶员的目标驾驶员模型为表3中的Pipes(1953)提出的驾驶员模型，该驾驶员模型的参数c为0.8，根据该参数c按照下述方法计算每条路径的权重：对于小路，路径的权重＝路径的长度/(1-目标驾驶员模型的参数c)；对于快速干道和主干道，路径的权重＝路径的长度*(1-目标驾驶员模型的参数c)。路线1和路线2中每条路径的权重如下：
路线1：路径①→②的权重为25(即5/(1-0.8))；路径②→③的权重为25(即5/(1-0.8))，如此，路线1的权重代价为50(25+25)。
路线2：路径①→④和权重为2.4(即12*(1-0.8))；路径①→④的权重为3(即15*(1-0.8))，如此，路线2的权重代价为5.4。
根据路线的权重代价最小原则，将路线2，即①→④→③的路线设定成该驾驶员的个性化导航路线，即驾驶员导航信息为路线2对应的导航信息。
结合图6，在另一种示例中，假设该驾驶员的目标驾驶员模型为表3中的Pipes(1953)提出的驾驶员模型，该驾驶员模型的参数c为0.2，同理，采用上述确定路径权重的方法，路线1和路线2中每条路径的权重如下：
路线1：路径①→②的权重为6.25(即5/(1-0.2))；路径②→③的权重为6.25(即5/(1-0.2))，如此，路线1的权重代价为12.5(6.25+6.25)。
路线2：路径①→④和权重为9.6(即12*(1-0.2))；路径①→④的权重为12(即15*(1-0.2))，如此，路线2的权重代价为21.6。
根据路线的权重代价最小原则，将路线1，即①→②→③的路线设定成该驾驶员的个性化导航路线，即驾驶员导航信息为路线1对应的导航信息。
本申请实施例提供的交通信息的处理方法，从驾驶员驾驶的车辆的角度，采用历史时间段内驾驶员的交通数据，从多种候选驾驶员模型中确定目标驾驶员模型，并且采用当前时间段内该驾驶员的交通数据，对目标驾驶员模型的参数进行调整，从而生成驾驶员导航信息，如此，能够为驾驶员提供更加全面且实用的个性化导航服务。
可以理解的是，对于某一道路(以下称为目标道路，可以包括路段和路口)，上述历史交通数据为历史时间段内目标道路的交通数据，当前交通数据为当前时间段内目标道路的交通数据，多个候选交通模型为多个道路传播模型，目标交通模型为目标道路传播模型，交通管控策略为交通信号控制信息。如图7所示，本申请实施例提供的交通信息处理方法可以包括S301-S303：
S301、采用历史时间段内目标道路的交通数据，从多个道路传播模型中确定目标道路传播模型。
应理解，历史时间段内(前一天或前一周)目标道路的交通数据包括历史时间段内目标道路的流量、速度以及密度中的至少两种，该目标道路可以包括路段和路口。
需要说明的是，上述道路传播模型可以为道路曲线模型，例如道路基本图模型，道路传播模型也可以为其他形态的模型，本申请实施例不作限定。
本申请实施例中，道路基本图模型是反映道路的流量-密度-速度关系的曲线模型，该道路基本图模型可以是三维曲线，也可以为二维曲线(即取流量、密度或速度中的两种形成的曲线，例如道路的流量和密度形成的流-密曲线)。
示例性的，(中心服务器)可以接收道路传感器，例如断面检测器采集并上报的历史时间段内的目标道路的交通数据，表6为断面检测器采集的目标路段的交通数据的示例。
表6
Figure PCTCN2020129078-appb-000006
从表6中断面检测器上报的交通数据中可以获取目标道路的流量，应理解，可以通过其他的传感器检测目标道路的速度和密度，本申请实施例不作具体限定。
结合表6，在历史时间段内，目标道路上的多个断面检测器均可以采集类似于表6所示的数据，从而得到多组流量和密度(即历史时间段内的流量和密度)，从而采用多组流量和密度，与多个候选的流-密曲线进行匹配，确定目标道路的流-密曲线，即得到目标道路曲线模型。
可选的，本申请实施例中，根据历史时间内目标道路的流量和密度，采用特征匹配方法(该特征可以为斜率特征或曲率特征等)从多个候选的流-密曲线中，确定与该目标道路最匹配的流-密曲线，示例性的，在图8中示例了三种候选的流-密曲线(分别为曲线1、曲线2以及曲线3)，将上述历史时间段内目标道路的流量和密度体现在坐标系中(体现为数据点)，然后将坐标系中的数据点与每一种候选的流-密曲线进行特征误差计算，选取特征误差最小的流-密曲线作为目标道路传播模型，在图8中曲线1是与历史时间段内目标道路的流量和密度最匹配的流-密曲线。
S302、根据当前时间段内目标道路的交通数据，对目标道路传播模型的参数进行调整。
结合S301，相应的，当前时间段内目标道路的交通数据包括当前时间段内目标道路的流量、速度以及密度中的至少两种。对于当前时间段内目标道路的交通数据的相关描述可以参见上述S301中对于历史时间段内目标道路的交通数据的相关描述，此处不再赘述。
本申请实施例中，目标道路传播模型的参数用于描述目标道路当前的交通运行状态，以目标道路传播模型为上述的流-密曲线为例，当前时间段内目标道路的交通数据包括该目标道路的流量和密度，该目标道路传播模型的参数为目标道路的流量上限值Q、目标道路的传播速度W以及目标道路的溢流速度V，如此，根据当前时间段内目 标道路的流量和密度，采用最小二乘法对该目标道路传播模型的参数Q、W以及V进行调整，得到调整后的Q、W以及V。在图9中示出了流-密曲线中的上述三种参数。
上述根据当前时间段内目标道路的交通数据(可以理解为实时的交通数据)对目标道路传播模型的参数进行调整，将交通流传播的规律性、随机性以及道路之间的异构性纳入考虑范围，得到的道路传播模型更加可靠。
需要说明的是，本发明实施例中，若目标道路上没有布设传感器，则无法获取历史时间段内该目标道路的交通数据和当前时间段内该目标道路的交通数据，在这种情况下，可以采用迁移学习的方法确定该目标道路的目标道路传播模型，即：进行道路相似性匹配，将与该目标道路相似的道路的道路传播模型确定为该目标道路的目标道路传播模型。也就是说，将目标道路的道路特征，例如拓扑特征(例如均是左转道)、距离(例如道路长度)或小区特征(例如道路附件是否有停车场)等特征，与有传感器布设的道路的对应的特征进行匹配，将特征重合最多的道路传播模型作为该目标路段的目标道路传播模型。进而，将该最匹配的道路传播模型的参数作为该目标道路传播模型的参数，并进一步得到调整后的目标道路传播模型的参数。
S303、基于调整后的目标道路传播模型的参数，生成交通信号控制信息。
本申请实施例中，该交通信号控制信息可以为目标道路的红绿灯控制时长。
结合图7，如图10所示，上述S303可以通过S3031-S3032实现：
S3031、基于调整后的目标道路传播模型的参数，确定信号控制约束条件。
该信号控制约束条件是通过调整后的道路传播模型确定的。
本申请实施例中，假设目标道路为路段i，目标道路传播模型为上述S302中描述的流-密曲线，该流-密曲线的参数为流量Q、传播速度W以及溢流速度V，将路段i(也可以称为Link i)划分为多个单元(可以记为Cell)，例如将该路段i划分为m个Cell，分别记为Cell(i，1)，Cell(i，2)，…，Cell(i，j)，…，Cell(i，m)，根据该流-密曲线的参数可以确定如下4个信号控制约束条件。
Figure PCTCN2020129078-appb-000007
对于约束条件1：n i,j(t+1)＝n i,j(t)+f i,j(t)-f i,j+1(t)，n i,j(t+1)表示在t+1时刻，路段i的第j个Cell中的车辆数，n i,j(t)表示在t时刻，路段i的第j个Cell中的车辆数，f i,j(t)表示在t时刻流入该路段i的第j个Cell的车辆数，f i,j+1(t)表示在t时刻从该路段i的第j个Cell流入到第j+1个Cell的车辆数(应注意，在约束条件1中，对于一个Cell仅从单方向考虑车辆流入该Cell或者流出该Cell的情况)。
即约束条件1表示对于一个Cell，该Cell在t+1的车辆数等于该Cell在t的车辆数加上t时刻流入该Cell的车辆数，再减去流出该Cell的车辆数。
对于约束条件2：f i,j(t)≤n i,j-1(t)，f i,j(t)表示在t时刻，流入该路段i的第j个Cell的车辆数，n i,j-1(t)表示在t时刻，路段i的第j-1个Cell中的车辆数。
即约束条件2表示对于一个Cell，在t时刻流入该Cell的车辆数小于或者等于t时刻该Cell的上一个Cell中的车辆数。
对于约束条件3：f i,j(t)≤Q i,j(t)，f i,j(t)表示在t时刻，流入该路段i的第j个Cell的车辆数，Q i,j(t)表示在t时刻，路段i的第j个Cell的流量上限。
即约束条件3表示对于一个Cell，在t时刻流入该Cell的车辆数小于或者等于t时刻该Cell的流量上限。
对于约束条件4：
Figure PCTCN2020129078-appb-000008
f i,j(t)表示在t时刻，流入该路段i的第j个Cell的车辆数，W表示传播速度，V表示溢流速度，N i,j为交通手册中规定的一个Cell的容量上限，n i,j(t)表示在t时刻，路段i的第j个Cell中的车辆数。
S3032、将信号控制约束条件作为交通信号控制模型的优化条件，生成交通信号控制信息。
本申请实施例中，将上述4个信号控制约束条件作为目标道路的交通信号控制模型(即目标函数)的优化条件，求解优化问题，即求解交通信号控制模型，得到交通信号控制信息，即红绿灯的控制时长。需要说明的是，上述目标路段的交通信号控制模型可以为现有技术中的与f i,j(t)相关的模型，如此，将上述4个信号控制约束条件作为该交通信号控制模型的约束条件，得到交通信号控制信息。
示例性的，如图11所示的道路，该道路包括4个路段和1个十字路口，对于东西方向的红绿灯的控制时长可以通过分析路段1和路段2的交通数据，得到路段1对应的信号控制约束条件和路段2对应的信号控制约束条件，并基于信号控制约束条件对交通信号控制模型进行求解，得到东西方向的红绿灯的时长。同理的，对于南北方向的红绿灯的控制时长可以通过分析路段3和路段4的交通数据，得到路段3对应的信号控制约束条件和路段4对应的信号控制约束条件，并基于信号控制约束条件对交通信号控制模型进行求解，得到南北方向的红绿灯的时长。或者，基于路段1对应的信号控制约束方程、路段2对应的信号控制约束条件、路段3对应的信号控制约束条件以及路段4对应的信号控制约束条件，对交通信号控制模型进行求解，得到东西方向、南北方向各自的红绿灯时长。
本申请实施例提供的交通信息的处理方法，从道路的角度，采用历史时间段内目标道路的交通数据，从多种候选道路传播模型中确定目标道路传播模型，并且采用当前时间段内该目标道路的交通数据，对目标道路传播模型的参数进行调整，从而生成交通信号控制信息，如此，能够自适应地、并且更加准确地进行交通信号控制。
可以理解的是，对于某一路网(以下称为目标路网)，上述历史交通数据为历史时间段内目标路网的交通数据，当前交通数据为当前时间段内目标路网的交通数据，多个候选交通模型为多个路网评价模型，目标交通模型为目标路网评价模型，交通管控策略为路网边界控制信息。如图12所示，本申请实施例提供的交通信息处理方法可以包括S401-S403：
S401、采用历史时间段内目标路网的交通数据，从多个路网评价模型中确定目标路网评价模型。
应理解，历史时间段内(前一周或前两周)目标路网的交通数据包括历史时间段 内(例如一周或两周)目标路网的流量、速度以及密度中的至少两种。
本申请实施例中，目标路网的交通数据是通过该目标路网所包含的路段的交通数据确定，也就是说，将目标路网包含的路段的交通数据进行汇聚，得到该目标路网的交通数据。在一种实现方式中，可以通过如下方式汇聚目标路网包含的路段的交通该数据：
Figure PCTCN2020129078-appb-000009
其中，q为目标路网的流量，q i为目标路网包含的第i个路段的流量，n为该目标路网包含的路段的数量。
Figure PCTCN2020129078-appb-000010
其中，v为目标路网的速度，v i为目标路网包含的第i个路段的速度。
Figure PCTCN2020129078-appb-000011
其中，k为目标路网的密度，k i为目标路网包含的第i个路段的密度。
需要说明的是，上述路网评价模型可以为路网曲线模型，路网评价模型也可以为其他形态的模型，本申请实施例不作限定。
本申请实施例中，路网曲线模型是反映路网的流量-密度-速度关系的曲线模型，该路网曲线模型可以是三维曲线，也可以为二维曲线(即取流量、密度或速度中的两种形成的曲线，例如路网的速度和密度形成的密-速曲线)。
可选的，以路网评价模型为密-速曲线为例，根据历史时间内目标路网的密度和速度，采用概率图匹配法将多个候选的密-速曲线中，匹配概率最的密-速曲线确定为该目标路网的密-速曲线，即作为目标路网评价模型。
S402、根据当前时间段内目标路网的交通数据，对目标路网评价模型的参数进行调整。
结合S401，相应的，当前时间段内目标路网的交通数据包括当前时间段内目标路网的流量、速度以及密度中的至少两种。对于当前时间段内目标路网的交通数据的相关描述可以参见上述S401中对于历史时间段内目标路网的交通数据的相关描述，此处不再赘述。
本申请实施例中，目标路网评价模型的参数用于描述目标路网当前的交通运行状态，若目标路网评价模型为密-速曲线，将目标路网的速度与密度的关系表示为：v＝V(k)，v为速度，k为密度，V(k)为密-速曲线的函数表达式，则当前时间段内目标路网的交通数据位当前时间段内目标路网的速度和密度，如此，根据当前时间段内目标路网的速度和密度，采用梯度优化法得到调整后的密-速曲线V(k)的参数。
上述根据当前时间段内目标路网的交通数据(可以理解为实时的交通数据)对目标路网传播模型的参数进行调整，将交通系统的规律性、随机性纳入考虑范围，得到的路网评价模型更加可靠。
S403、基于调整后的目标路网传播模型的参数，生成路网边界控制信息。
本申请实施例中，该路网边界控制信息为路网边界的红绿灯控制时长等信息。
结合图12，如图13所示，上述S403可以通过S4031-S4032实现：
S4031、基于调整后的目标路网评价模型的参数以及宏观交通流模型，确定目标路 网的容量或流量。
本申请实施例中，宏观交通流模型是从交通流的流量、速度、密度的角度描述交通流运行特性的数学模型，宏观交通流模型可以包括交通流基本图模型、车辆派对模型、交通流守恒模型(也可以称为交通流守恒条件)等。本申请实施例以该宏观交通流模型为交通流守恒条件为例进行说明。
上述交通流守恒条件可以为LWR方程：
Figure PCTCN2020129078-appb-000012
其中，k t是密度函数k(t,x)对t的偏导数，q t是流量函数q(t,x)对x的偏导数，t为时间，x为位移。在LWR方程中，v＝V(k)为已知，通过S402进行参数调整后即可得到V(k)的函数表达式，求解该LWR方程可以得到密度函数k(t,x)和流量函数q(t,x)。
应理解，目标路网的密度函数k(t,x)的极限值可以反映目标路网的容量状态，当然，也可以采用其他的指标来反映目标路网的容量；目标路网的流量函数q(t,x)的极限值可以反映该目标路网的流量状态。
S4032、根据目标路网的容量或流量，生成路网边界控制信息。
本申请实施例中，目标路网的容量或者流量可以反映该目标路网的交通状态的拥堵程度，因此根据目标路网的容量或者流量，生成路网边界控制信息，实现对路网的交通管控。例如，目标路网的密度(即容量)已接近该目标路网的截止密度，说明该目标路网比较拥堵，那么可以将该目标路网的车辆引导至其他不拥堵的路网。
示例性的，以路网1和路网2的容量(密度)为例，假设路网1的密度函数的极限值为40，路网2的密度函数的极限值为20，并且路网1和路网2的截止密度为50，可知，路网1的密度已经临近截止密度，可能处于拥堵状态，而路网2的密度较小，处于自由流状态，此时，路网边界控制方案可以为：增加路网1至路网2的绿灯时长，减小路网2至路网1的绿灯时长，路网边界控制信息即为路网1至路网2的绿灯时长，路网2至路网1的绿灯时长。
本申请实施例提供的交通信息的处理方法，从路网的角度，采用历史时间段内目标路网的交通数据，从多种候选路网评价模型中确定目标路网评价模型，并且采用当前时间段内该目标路网的交通数据，对目标路网评价模型的参数进行调整，从而生成路网边界控制信息，如此，能够自适应地、并且更加准确地进行路网边界的交通管控。
综上所述，完成对驾驶员驾驶的车辆、道路以及路网的交通数据的分析之后，本申请实施例提供的交通信息处理方法还包括：按照不同的比例尺呈现不同层次的交通信息，将交通信息可视化。
上述不同层次的交通信息分别为驾驶员的交通信息、目标道路的交通信息以及目标路网的交通信息；其中，驾驶员的交通信息包括当前时间段内驾驶员的交通数据(例如上述驾驶员驾驶的车辆的加速度和速度)和目标驾驶员模型的参数(例如上述Pipes(1953)提出的加速度方程中的c)；目标道路的交通信息包括当前时间段内目标道路的交通数据(例如，目标道路的流量、密度或速度中的至少两种)和目标道路传播 模型的参数；目标路网的交通信息包括当前时间段内目标路网的交通数据(例如，目标路网的流量、密度或速度中的至少两种)和目标路网评价模型的参数。
可选的，本申请实施例中，可以通过以下一种或多种方式呈现不同层次的交通信息：显示屏、电子地图或投影。例如展示屏(例如城市大脑)、车载终端的显示屏以及手机的显示屏等，或者，将交通信息投影在车辆的前挡风玻璃等位置，或者在导航软件等电子地图中显示。
在本申请实施例中，上述不同层次的交通信息按照不同的比列尺进行显示，并且可以通过UI操作按照不同的比例尺进行切换显示(例如，放大或缩小)。示例性的，按照微观、中观以及宏观的尺度进行显示，微观的交通信息是车辆的交通信息(即驾驶员的交通信息)，中观的交通信息是道路的交通信息，宏观的交通信息是路网的交通信息，以电子地图为例，在图14中，电子地图缩小之后可以显示路网的交通信息(图14中的(a))，该电子地图放大之后可以显示道路的交通信息(图14中的(b))，该电子地图在进一步放大之后可以显示车辆的交通信息(图14中的(c))，从而可以显示不同尺度的交通信息，实用且灵活。
本申请实施例提供的交通信息处理方法可以由交通信息处理装置(例如上述中心服务器)执行，根据上述方法示例对交通信息处理装置进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
在采用对应各个功能划分各个功能模块的情况下，图15示出了上述实施例中所涉及的交通信息处理装置的一种可能的结构示意图，如图15所示，交通信息处理装置可以包括：模型确定模块1001、参数调整模块1002以及交通管控策略生成模块1003。其中，模型确定模块1001可以用于支持该交通信息处理装置执行上述方法实施例中的S101、S201、S301以及S401；参数调整模块1002可以用于支持该交通信息处理装置执行上述方法实施例中的S102、S202、S302以及S402；交通管控策略生成模块1003可以用于支持该交通信息处理装置执行上述方法实施例中的S103、S203(包括S2031-S2032)、S303(包括S3031-S3032)以及S403(包括S4031-S4032)。其中，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描述，在此不再赘述。
可选的，如图15所示，本申请实施例提供的交通信息处理装置还可以包括显示模块1004，该显示模块用于支持该交通信息处理装置显示多层次的交通信息，该多层次的交通信息分别为驾驶员的交通信息、目标道路的交通信息以及目标路网的交通信息。
在采用集成的单元的情况下，图16示出了上述实施例中所涉及的交通信息处理装置的一种可能的结构示意图。如图16所示，交通信息处理装置可以包括：处理模块2001和通信模块2002。处理模块2001可以用于对该交通信息处理装置的动作进行控制管理，例如，处理模块2001可以用于支持该交通信息处理装置执行上述方法实施例中的S101-S103、S201-S203(其中，S203包括S2031-S2032)、S301-S303(其中，S303包括S3031-S3032)以及S401-S403(其中，S403包括S4031-S4032)，和/或用 于本文所描述的技术的其它过程。通信模块2002可以用于支持该交通信息处理装置与其他网络实体的通信。可选的，如图16所示，该交通信息处理装置还可以包括存储模块2003，用于存储该交通信息处理装置的程序代码和数据。
其中，处理模块2001可以是处理器或控制器(例如可以是上述如图2所示的处理器11)，例如可以是CPU、通用处理器、DSP、ASIC、FPGA或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合。其可以实现或执行结合本申请实施例公开内容所描述的各种示例性的逻辑方框、模块和电路。上述处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和微处理器的组合等等。通信模块2002可以是收发器、收发电路或通信接口等(例如可以是上述如图2所示的通信接口13)。存储模块2003可以是存储器(例如可以是上述如图2所示的存储器12)。
当处理模块2001为处理器，通信模块2002为收发器，存储模块2003为存储器时，处理器、收发器和存储器可以通过总线连接。总线可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended Industry standard architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件程序实现时，可以全部或部分地以计算机程序产品的形式实现。该计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行该计算机指令时，全部或部分地产生按照本申请实施例中的流程或功能。该计算机可以是通用计算机、专用计算机、计算机网络或者其他可编程装置。该计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，该计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))方式或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心传输。该计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包括一个或多个可用介质集成的服务器、数据中心等数据存储设备。该可用介质可以是磁性介质(例如，软盘、磁盘、磁带)、光介质(例如，数字视频光盘(digital video disc，DVD))、或者半导体介质(例如固态硬盘(solid state drives，SSD))等。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：快闪存储器、移动硬盘、只读存储器、随机存取存储器、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何在本申请揭露的技术范围内的变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (22)

  1. 一种交通信息处理方法，其特征在于，包括：
    采用历史交通数据，从多个候选交通模型中确定目标交通模型；所述候选交通模型包括下述至少一种：驾驶员模型、道路传播模型或路网评价模型，所述历史交通数据包括下述至少一种：历史时间段内驾驶员的交通数据、历史时间段内目标道路的交通数据或历史时间段内目标路网的交通数据，所述候选交通模型与所述历史交通数据相对应；
    根据当前交通数据，对所述目标交通模型的参数进行调整；所述目标交通模型的参数用于描述当前交通运行状态，所述当前交通数据包括下述至少一种：当前时间段内驾驶员的交通数据、当前时间段内目标道路的交通数据或当前时间段内目标路网的交通数据，所述当前交通数据与所述目标交通模型相对应；
    基于调整后的所述目标交通模型的参数，生成交通管控策略；所述交通管控策略包括下述至少一种：驾驶员导航信息、交通信号控制信息或路网边界控制信息。
  2. 根据权利要求1所述的方法，其特征在于，所述历史交通数据为历史时间段内驾驶员的交通数据，所述目标交通模型为目标驾驶员模型，驾驶员的交通数据包括驾驶员驾驶的车辆的交通数据或驾驶员的出行习惯数据；
    历史时间段内驾驶员驾驶的车辆的交通数据包括所述历史时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；历史时间段内驾驶员的出行习惯数据包括所述历史时间段内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率；
    当前时间段内驾驶员的交通数据包括所述当前时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；当前时间段内驾驶员的出行习惯数据包括所述当前时间段内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率。
  3. 根据权利要求1或2所述的方法，其特征在于，所述交通管控策略为所述驾驶员导航信息，所述基于调整后的所述目标交通模型的参数，生成交通管控策略，包括：
    基于调整后的目标驾驶员模型的参数，设置导航地图上的路径的权重，所述目标驾驶员模型的参数用于描述驾驶员当前的驾驶习惯；
    根据所述导航地图上的路径的权重，生成所述驾驶员导航信息。
  4. 根据权利要求1所述的方法，其特征在于，所述历史交通数据为历史时间段内目标道路的交通数据，所述目标交通模型为目标道路传播模型；
    所述历史时间段内目标道路的交通数据包括历史时间段内目标道路的流量、速度以及密度中的至少两种；
    所述当前时间段内目标道路的交通数据包括当前时间段内目标道路的流量、速度以及密度中的至少两种。
  5. 根据权利要求1或4所述的方法，其特征在于，所述交通管控策略为所述交通信号控制信息，所述基于调整后的所述目标交通模型的参数，生成交通管控策略，包括：
    基于调整后的目标道路传播模型的参数，确定信号控制约束条件，所述目标道路传播模型的参数用于描述所述目标道路当前的交通运行状态；
    将所述信号控制约束条件作为交通信号控制模型的优化条件，生成所述交通信号控制信息，所述信号控制约束条件是通过所述调整后的道路传播模型确定的。
  6. 根据权利要求1所述的方法，其特征在于，所述历史交通数据为历史时间段内目标路网的交通数据，所述目标交通模型为目标路网评价模型；
    所述历史时间段内目标路网的交通数据包括历史时间段内目标路网的流量、速度以及密度中的至少两种；
    所述当前时间段内目标路网的交通数据包括当前时间段内目标路网的流量、速度以及密度中的至少两种。
  7. 根据权利要求1或6所述的方法，其特征在于，所述交通管控策略为所述路网边界控制信息，所述基于调整后的所述目标交通模型的参数，生成交通管控策略，包括：
    基于所述调整后的目标路网评价模型的参数以及宏观交通流模型条件，确定所述目标路网的容量或流量，所述目标路网评价模型的参数用于描述所述目标路网当前的交通运行状态；
    根据所述目标路网的容量或流量，生成所述路网边界控制信息。
  8. 根据权利要求6或7所述的方法，其特征在于，
    所述目标路网的交通数据是通过所述目标路网所包含的路段的交通数据确定。
  9. 根据权利要求1至8任一项所述的方法，其特征在于，所述方法还包括：
    按照不同的比例尺呈现不同层次的交通信息，所述不同层次的交通信息分别为驾驶员的交通信息、目标道路的交通信息以及目标路网的交通信息；
    其中，所述驾驶员的交通信息包括所述当前时间段内驾驶员的交通数据和目标驾驶员模型的参数；所述目标道路的交通信息包括所述当前时间段内目标道路的交通数据和目标道路传播模型的参数；所述目标路网的交通信息包括所述当前时间段内目标路网的交通数据和目标路网评价模型的参数。
  10. 根据权利要求9所述的方法，其特征在于，
    通过下述一种或多种方式呈现所述不同层次的交通信息：显示屏、电子地图或投影。
  11. 一种交通信息处理装置，其特征在于，包括模型确定模块、参数调整模块、交通管控策略生成模块；
    所述模型确定模块，用于采用历史交通数据，从多个候选交通模型中确定目标交通模型；所述候选交通模型包括下述至少一种：驾驶员模型、道路传播模型或路网评价模型，所述历史交通数据包括下述至少一种：历史时间段内驾驶员的交通数据、历史时间段内目标道路的交通数据或历史时间段内目标路网的交通数据，所述候选交通模型与所述历史交通数据相对应；
    所述参数调整模块，用于根据当前交通数据，对所述目标交通模型的参数进行调整；所述目标交通模型的参数用于描述当前交通运行状态，所述当前交通数据包括下述至少一种：当前时间段内驾驶员驾驶的车辆的交通数据或、当前时间段内目标道路的交通数据或当前时间段内目标路网的交通数据，所述当前交通数据与所述目标交通模型相对应；
    所述交通管控策略生成模块，用于基于调整后的所述目标交通模型的参数，生成交通管控策略；所述交通管控策略包括下述至少一种：驾驶员导航信息、交通信号控制信息或路网边界控制信息。
  12. 根据权利要求11所述的装置，其特征在于，所述历史交通数据为历史时间段内驾驶员的交通数据，所述目标交通模型为目标驾驶员模型，驾驶员的交通数据包括驾驶员驾驶的车辆的交通数据或驾驶员的出行习惯数据；
    历史时间段内驾驶员驾驶的车辆的交通数据包括所述历史时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；历史时间段内驾驶员的出行习惯数据包括所述历史时间段内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率；
    当前时间段内驾驶员的交通数据包括所述当前时间段内驾驶员驾驶的车辆的加速度以及车辆的速度；当前时间段内驾驶员的出行习惯数据包括所述当前时间段内驾驶员的一种或多种行程的出行概率以及每一种行程对应的一种或多种路线的选择概率。
  13. 根据权利要求11或12所述的装置，其特征在于，所述交通管控策略为所述驾驶员导航信息；
    所述交通管控策略生成模块，具体用于基于调整后的目标驾驶员模型的参数，设置导航地图上的路径的权重；并且根据所述导航地图上的路径的权重，生成所述驾驶员导航信息，所述目标驾驶员模型的参数用于描述驾驶员当前的驾驶习惯。
  14. 根据权利要求11所述的装置，其特征在于，所述历史交通数据为历史时间段内目标道路的交通数据，所述目标交通模型为目标道路传播模型；
    所述历史时间段内目标道路的交通数据包括历史时间段内目标道路的流量、速度以及密度中的至少两种；
    所述当前时间段内目标道路的交通数据包括当前时间段内目标道路的流量、速度以及密度中的至少两种。
  15. 根据权利要求11或14所述的装置，其特征在于，所述交通管控策略为所述交通信号控制信息；
    所述交通管控策略生成模块，具体用于基于调整后的目标道路传播模型的参数，确定信号控制约束条件；并且将所述信号控制约束条件作为交通信号控制模型的优化条件，生成所述交通信号控制信息，所述目标道路传播模型的参数用于描述所述目标道路当前的交通运行状态，所述信号控制约束条件是通过所述调整后的道路传播模型确定的。
  16. 根据权利要求11所述的装置，其特征在于，所述历史交通数据为历史时间段内目标路网的交通数据，所述目标交通模型为目标路网评价模型；
    所述历史时间段内目标路网的交通数据包括历史时间段内目标路网的流量、速度以及密度中的至少两种；
    所述当前时间段内目标路网的交通数据包括当前时间段内目标路网的流量、速度以及密度中的至少两种。
  17. 根据权利要求11或16所述的装置，其特征在于，所述交通管控策略为所述路网边界控制信息；
    所述交通管控策略生成模块，具体用于基于所述调整后的目标路网评价模型的参数以及宏观交通流模型条件，确定所述目标路网的容量或流量；并且根据所述目标路网的容量或流量，生成所述路网边界控制信息，所述目标路网评价模型的参数用于描述所述目标路网当前的交通运行状态。
  18. 根据权利要求16或17所述的装置，其特征在于，
    所述目标路网的交通数据是通过所述目标路网所包含的路段的交通数据确定。
  19. 根据权利要求11至18任一项所述的装置，其特征在于，所述装置还包括显示模块；
    所述显示模块，用于按照不同的比例尺呈现不同层次的交通信息，所述不同层次的交通信息分别为驾驶员的交通信息、目标道路的交通信息以及目标路网的交通信息；
    其中，所述驾驶员的交通信息包括所述当前时间段内驾驶员的交通数据和目标驾驶员模型的参数；所述目标道路的交通信息包括所述当前时间段内目标道路的交通数据和目标道路传播模型的参数；所述目标路网的交通信息包括所述当前时间段内目标路网的交通数据和目标路网评价模型的参数。
  20. 根据权利要求19所述的装置，其特征在于，
    通过下述一种或多种方式呈现所述不同层次的交通信息：显示屏、电子地图或投影。
  21. 一种交通信息处理装置，其特征在于，包括处理器和与所述处理器耦合连接的存储器；所述存储器用于存储计算机指令，当所述装置运行时，处理器执行存储器存储的所述计算机指令，以使得所述装置执行如权利要求1至10任一项所述的方法。
  22. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质可以包括计算机指令，当所述计算机指令在计算机上运行时，以执行如权利要求1至10任一项所述的方法。
PCT/CN2020/129078 2019-12-27 2020-11-16 一种交通信息处理方法及装置 WO2021129227A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20905917.9A EP4060641A4 (en) 2019-12-27 2020-11-16 TRAFFIC INFORMATION PROCESSING METHOD AND DEVICE
US17/851,021 US20220335820A1 (en) 2019-12-27 2022-06-27 Traffic information processing method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911380305.9 2019-12-27
CN201911380305.9A CN110969857B (zh) 2019-12-27 2019-12-27 一种交通信息处理方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/851,021 Continuation US20220335820A1 (en) 2019-12-27 2022-06-27 Traffic information processing method and apparatus

Publications (1)

Publication Number Publication Date
WO2021129227A1 true WO2021129227A1 (zh) 2021-07-01

Family

ID=70036958

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/129078 WO2021129227A1 (zh) 2019-12-27 2020-11-16 一种交通信息处理方法及装置

Country Status (4)

Country Link
US (1) US20220335820A1 (zh)
EP (1) EP4060641A4 (zh)
CN (1) CN110969857B (zh)
WO (1) WO2021129227A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706863A (zh) * 2021-08-05 2021-11-26 青岛海信网络科技股份有限公司 一种道路交通状态预测方法

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110969857B (zh) * 2019-12-27 2021-11-19 华为技术有限公司 一种交通信息处理方法及装置
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
CN112419708B (zh) * 2020-08-17 2022-03-29 腾讯科技（深圳）有限公司 基于交通流激进程度的道路安全策略确定方法及装置
CN112201033B (zh) * 2020-09-08 2022-06-07 同济大学 一种道路交通运行主动管控策略选择方法
CN112863172B (zh) * 2020-12-29 2022-10-28 千方捷通科技股份有限公司 高速公路交通运行状态判定方法、预警方法、装置及终端
CN113053103B (zh) * 2021-02-19 2022-07-05 北京嘀嘀无限科技发展有限公司 交通仿真模型生成方法、交通流量预测方法及相关装置
CN112990758B (zh) * 2021-04-14 2021-09-07 北京三快在线科技有限公司 一种远程控制无人驾驶设备的方法及装置
CN115691094A (zh) * 2021-07-27 2023-02-03 阿里巴巴新加坡控股有限公司 路况信息处理方法、装置、设备及存储介质
CN113747364B (zh) * 2021-09-29 2022-08-16 山东金宇信息科技集团有限公司 一种基于5g网络的智能交通导航方法、设备及介质
CN114038213B (zh) * 2021-10-18 2022-12-23 中国联合网络通信集团有限公司 一种交通管控方法、装置和存储介质

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102521989A (zh) * 2011-12-31 2012-06-27 山西省交通规划勘察设计院 一种动态数据驱动的高速公路出口流量预测方法
CN102682601A (zh) * 2012-05-04 2012-09-19 南京大学 基于优化svm的高速公路交通事件检测方法
CN103871246A (zh) * 2014-02-10 2014-06-18 南京大学 基于路网空间关系约束Lasso的短时交通流预测方法
US20140244158A1 (en) * 2007-01-24 2014-08-28 Tomtom Global Assets B.V. Method and apparatus for providing navigational guidance using the states of traffic signal
US20160189044A1 (en) * 2012-10-23 2016-06-30 University Of Southern California Traffic Prediction Using Real-World Transportation Data
CN110032782A (zh) * 2019-03-29 2019-07-19 银江股份有限公司 一种城市级智能交通信号控制系统及方法
CN110375760A (zh) * 2019-07-29 2019-10-25 北京百度网讯科技有限公司 路线确定方法、装置、设备和介质
CN110390415A (zh) * 2018-04-18 2019-10-29 北京嘀嘀无限科技发展有限公司 一种基于用户出行大数据进行出行方式推荐的方法及系统
CN110969857A (zh) * 2019-12-27 2020-04-07 华为技术有限公司 一种交通信息处理方法及装置

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1402457B1 (en) * 2001-06-22 2011-02-09 Caliper Corporation Traffic data management and simulation system
CN101477747B (zh) * 2009-01-05 2010-06-02 东南大学 一种交通高峰期高密度路网的信号控制方法
JP5585229B2 (ja) * 2010-06-16 2014-09-10 富士通株式会社 車両の挙動推定装置、プログラム、及び、方法
CN103021180B (zh) * 2012-12-30 2014-10-01 西安费斯达自动化工程有限公司 基于修正速度的宏观交通流离散模型的交通拥堵监控预报方法
CN105074793A (zh) * 2013-03-15 2015-11-18 凯利普公司 用于车辆路径规划和交通管理的车道级车辆导航
CN103247177B (zh) * 2013-05-21 2016-01-20 清华大学 大规模路网交通流实时动态预测系统
CN104574967B (zh) * 2015-01-14 2016-08-24 合肥革绿信息科技有限公司 一种基于北斗的城市大面积路网交通感知方法
CN104821080B (zh) * 2015-03-02 2017-04-12 北京理工大学 基于宏观城市交通流的智能车辆行驶速度及时间预测方法
CN106971565B (zh) * 2017-04-22 2019-08-23 高新兴科技集团股份有限公司 基于物联网的区域交通边界控制与诱导协同方法及系统
CN107123265B (zh) * 2017-06-12 2020-01-10 东南大学 一种基于并行计算的高速公路交通状态估计方法
US10636298B2 (en) * 2017-08-11 2020-04-28 Cubic Corporation Adaptive traffic control using object tracking and identity details
CN109064750B (zh) * 2018-09-28 2021-09-24 深圳大学 城市路网交通估计方法及系统
CN109410587B (zh) * 2018-12-18 2021-07-02 北京工业大学 一种城市快速路的宏观交通流参数估计方法
CN109544932B (zh) * 2018-12-19 2021-03-19 东南大学 一种基于出租车gps数据与卡口数据融合的城市路网流量估计方法
CN109584567A (zh) * 2018-12-29 2019-04-05 浙江方大智控科技有限公司 基于车路协同的交通管理方法
CN109887284B (zh) * 2019-03-13 2020-08-21 银江股份有限公司 一种智慧城市交通信号控制推荐方法、系统及装置
CN110428608B (zh) * 2019-06-18 2022-03-04 上海电科智能系统股份有限公司 一种基于交通大数据的道路通行能力提取方法
CN110264725B (zh) * 2019-07-31 2021-08-03 北京世纪高通科技有限公司 路段流量的确定方法及装置

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140244158A1 (en) * 2007-01-24 2014-08-28 Tomtom Global Assets B.V. Method and apparatus for providing navigational guidance using the states of traffic signal
CN102521989A (zh) * 2011-12-31 2012-06-27 山西省交通规划勘察设计院 一种动态数据驱动的高速公路出口流量预测方法
CN102682601A (zh) * 2012-05-04 2012-09-19 南京大学 基于优化svm的高速公路交通事件检测方法
US20160189044A1 (en) * 2012-10-23 2016-06-30 University Of Southern California Traffic Prediction Using Real-World Transportation Data
CN103871246A (zh) * 2014-02-10 2014-06-18 南京大学 基于路网空间关系约束Lasso的短时交通流预测方法
CN110390415A (zh) * 2018-04-18 2019-10-29 北京嘀嘀无限科技发展有限公司 一种基于用户出行大数据进行出行方式推荐的方法及系统
CN110032782A (zh) * 2019-03-29 2019-07-19 银江股份有限公司 一种城市级智能交通信号控制系统及方法
CN110375760A (zh) * 2019-07-29 2019-10-25 北京百度网讯科技有限公司 路线确定方法、装置、设备和介质
CN110969857A (zh) * 2019-12-27 2020-04-07 华为技术有限公司 一种交通信息处理方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706863A (zh) * 2021-08-05 2021-11-26 青岛海信网络科技股份有限公司 一种道路交通状态预测方法
CN113706863B (zh) * 2021-08-05 2022-08-02 青岛海信网络科技股份有限公司 一种道路交通状态预测方法

Also Published As

Publication number Publication date
EP4060641A4 (en) 2023-01-11
US20220335820A1 (en) 2022-10-20
CN110969857B (zh) 2021-11-19
EP4060641A1 (en) 2022-09-21
CN110969857A (zh) 2020-04-07

Similar Documents

Publication Publication Date Title
WO2021129227A1 (zh) 一种交通信息处理方法及装置
US11593344B2 (en) Updating high definition maps based on age of maps
US11988518B2 (en) Updating high definition maps based on lane closure and lane opening
EP3719449A1 (en) Driving condition specific sensor quality index
CN112818497B (zh) 交通仿真方法、装置、计算机设备和存储介质
US11036238B2 (en) Positioning system based on geofencing framework
US10553110B2 (en) Detection and estimation of variable speed signs
US11004334B2 (en) Method, apparatus, and system for automatic verification of road closure reports
US11009366B2 (en) Navigation using dynamic intersection map data
US10198941B2 (en) Method and apparatus for evaluating traffic approaching a junction at a lane level
JP2016513805A (ja) 車両ルート指定および交通管理のための車線レベル車両ナビゲーション
US11270578B2 (en) Method, apparatus, and system for detecting road closures based on probe activity
US11932260B2 (en) Selecting testing scenarios for evaluating the performance of autonomous vehicles
US11682295B2 (en) Adjusting historical probe data for new road geometry
US11887324B2 (en) Cross-modality active learning for object detection
US20210397854A1 (en) Systems and methods for aligning trajectory information derived from different source data
US11348452B2 (en) Method, apparatus, and system for automatic closure verification using multiple possible vehicle paths
WO2019070237A1 (en) VEHICLE AND NAVIGATION SYSTEM
US11867528B2 (en) Method, apparatus, and system for providing road closure graph inconsistency resolution
EP4002322A1 (en) System and method for determining dynamic road capacity data for traffic condition
WO2022231800A1 (en) Vehicle guidance with systemic optimization
US20220170761A1 (en) Method and apparatus for detecting/verifying contraflow lane shift incidents
US20230349717A1 (en) Electronic map correction method, navigation information setting method, navigation method, and apparatus
US20220207993A1 (en) Method, apparatus, and system for verifying a lane closure using probe data
US20220198923A1 (en) Method, apparatus, and computer program product for determining a split lane traffic pattern

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: 20905917

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020905917

Country of ref document: EP

Effective date: 20220614

NENP Non-entry into the national phase

Ref country code: DE