WO2019114432A1 - 路况生成方法、装置、设备和存储介质 - Google Patents

路况生成方法、装置、设备和存储介质 Download PDF

Info

Publication number
WO2019114432A1
WO2019114432A1 PCT/CN2018/112322 CN2018112322W WO2019114432A1 WO 2019114432 A1 WO2019114432 A1 WO 2019114432A1 CN 2018112322 W CN2018112322 W CN 2018112322W WO 2019114432 A1 WO2019114432 A1 WO 2019114432A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
information
state
probability
traffic
Prior art date
Application number
PCT/CN2018/112322
Other languages
English (en)
French (fr)
Inventor
阳勇
孙立光
赵红超
江红英
Original Assignee
腾讯科技（深圳）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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2019114432A1 publication Critical patent/WO2019114432A1/zh
Priority to US16/659,138 priority Critical patent/US11423774B2/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
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • 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
    • 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
    • G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
    • 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
    • G08G1/09—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
    • G08G1/09675—Systems involving transmission of highway information, e.g. weather, speed limits where a selection of the information might take place where a selection from the received information takes place in the 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Definitions

  • the embodiments of the present application relate to the field of computers, and in particular, to a road condition generation method, apparatus, device, and storage medium.
  • real-time traffic condition information as a basic function can not only facilitate the user to know the road congestion situation, plan the travel route to arrange the action plan reasonably, but also help the city to construct traffic warning and dispatch the urban transportation system.
  • Accurate road conditions provide better ETS (Estimated Time of Arrival) services and path planning, saving urban road resources and user time.
  • the first aspect of the embodiment of the present application discloses a road condition generating method, which is executed by a computing device, and includes:
  • the road condition status information is output.
  • the second aspect of the embodiment of the present application discloses a road condition generating apparatus, including:
  • An obtaining unit configured to obtain current driving condition information
  • the information generating unit is configured to generate, according to the current driving condition information, the road state information according to the transition information between the road state states extracted from the historical road condition data, and the correspondence between the road state and the road traffic capability information;
  • An output unit configured to output the road state information.
  • a third aspect of the embodiments of the present application discloses a road condition generating device, including a processor, an input device, an output device, and a memory, wherein the processor, the input device, the output device, and the memory are connected to each other, wherein the memory is used for storing Program code, the processor being configured to invoke the program code to perform the method of the first aspect above.
  • a fourth aspect of embodiments of the present application discloses a computer readable storage medium storing a computer program, the computer program comprising program instructions, the program instructions, when executed by a processor, The processor performs the method of the first aspect as described above.
  • FIG. 1 is a schematic structural diagram of a system for generating a road condition according to an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a method for generating a road condition according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of a principle of road condition generation provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram showing the principle of state transition of a hidden Markov model provided by an embodiment of the present application.
  • FIG. 5 is a schematic flowchart diagram of another embodiment of a road condition generating method provided by the present application.
  • FIG. 6 is a schematic structural diagram of a road condition generating apparatus according to an embodiment of the present application.
  • FIG. 6b is a schematic structural diagram of an information generating unit according to an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a capacity generation unit provided by an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a road condition generating apparatus according to an embodiment of the present application.
  • the term “if” can be interpreted as “when” or “on” or “in response to determining” or “in response to detecting” depending on the context. .
  • the phrase “if determined” or “if detected [condition or event described]” may be interpreted in context to mean “once determined” or “in response to determining” or “once detected [condition or event described] ] or “in response to detecting [conditions or events described]”.
  • the terminal described in the embodiments of the present application includes, but is not limited to, other portable devices such as a mobile phone, a laptop computer or a tablet computer with a touch sensitive surface (for example, a touch screen display and/or a touch pad).
  • a touch sensitive surface for example, a touch screen display and/or a touch pad.
  • the device is not a portable communication device, but a desktop computer having a touch sensitive surface (eg, a touch screen display and/or a touch pad).
  • the terminal including a display and a touch sensitive surface is described.
  • the terminal can include one or more other physical user interface devices such as a physical keyboard, mouse, and/or joystick.
  • the embodiment of the present application provides a road condition generating method, a road condition generating device, a road condition generating device, and a computer readable storage medium.
  • Embodiments of the present application are configured to obtain current driving situation information, and according to the current driving situation information, according to the transition information between the respective road state states extracted from the historical road condition data, and the correspondence between the road state and the road capacity information, Generating the state information of the road state; outputting the state information of the road condition avoids the phenomenon that the continuous abnormal sudden change is easily caused when the road condition is directly determined according to the traffic speed of the single road segment, and the transfer information between the state of each road state extracted by the historical road condition data is And the correspondence between the road condition state and the road capacity information ensures the smoothness of the road state transition on the geospatial sequence, and solves the aforementioned road condition generation method or the road condition determination method is affected by the abnormal traffic speed, and the road condition is calculated or determined.
  • FIG. 1 is a schematic structural diagram of a system for generating a road condition according to an embodiment of the present application.
  • the system architecture can include one or more servers and multiple terminals (or devices), where:
  • the server may include, but is not limited to, a background server, a component server, a traffic generation server, etc., and the server may communicate with a plurality of terminals via the Internet.
  • the server can perform road condition analysis, traffic warning, path planning, etc., and can display road conditions in any platform or product of real-time traffic conditions, such as digital big screen, map service application, taxi software, logistics dispatch system, etc., which can be terminal Timely and dynamic display of road conditions changes, convenient for users to plan and schedule.
  • the terminal can be installed and run with the associated client (Client).
  • a client for example, including a map service client, etc. refers to a program that corresponds to a server and provides a local service to the client.
  • the local service may include, but is not limited to, performing road condition analysis, traffic warning, path planning, and the like.
  • the client may include: a locally running application, a function running on a web browser (also called a Web App), a small program embedded in an email, and a small embedded in the client software of the instant messaging. Programs, as well as features embedded in other applications (such as developers or merchants based on application accounts applied on the public platform).
  • the server needs to run the corresponding server-side program to provide the corresponding services, such as database services, data calculation, decision execution and so on.
  • the user uses the terminal to perform related operations on the traffic road condition on the corresponding platform, such as road condition viewing, path planning, and the like.
  • the server uses the real-time traffic condition information as a basic function to transmit the traffic condition information to the map service client on the user side, and the map service client installed and operated by the user through the terminal can not only be very It is convenient to know the road congestion situation, plan the travel route to arrange the action plan reasonably, and help the traffic control department to construct traffic warning and dispatch the urban transportation system.
  • the terminal in the embodiment of the present application may include, but is not limited to, any smart operating system-based handheld electronic product, which can perform human-computer interaction with a user through an input device such as a keyboard, a virtual keyboard, a touch panel, a touch screen, and a voice control device. , such as smartphones, tablets, personal computers, etc.
  • the smart operating system includes, but is not limited to, any operating system that enriches device functions by providing various mobile applications to mobile devices, such as Android, IOS, Windows Phone, and the like.
  • the system architecture of the road condition generation method provided by the embodiment of the present application may further include other devices, such as a third-party server, for example, for collecting or collecting information such as current driving situation information, in preparation for the road condition generation server.
  • a third-party server for example, for collecting or collecting information such as current driving situation information, in preparation for the road condition generation server.
  • information such as current driving situation information is acquired from the third party server.
  • FIG. 2 is a schematic flowchart of a method for generating a road condition according to an embodiment of the present application, and describes how to generate road condition information from a server side (ie, a road condition generating device or device). , can include the following steps.
  • Step S200 Acquire current driving condition information.
  • the current driving situation information in the embodiment of the present application may include a road type of the current vehicle driving (eg, may be classified by the road speed limit information), traffic accident information of the current road, traffic control information of the current road, current driving Status information (which may include driving experience, driving habits, etc.), etc., is used to characterize the current driving scene or current driver's condition information, or the current driving scene and current driver's condition information.
  • a road type of the current vehicle driving eg, may be classified by the road speed limit information
  • traffic accident information of the current road e.g., may be classified by the road speed limit information
  • traffic control information of the current road e.g., traffic control information of the current road
  • current driving Status information which may include driving experience, driving habits, etc.
  • the current driving situation information may include current driving scene information and driver driving behavior status information
  • the current driving scene information that is, the multi-change information of the road situation, is generally brought about by the surrounding facility properties, and the current driving scene information objectively limits the traffic capacity of the specific road section.
  • the current driving scene in the embodiment of the present application may include at least one of the following: vehicle positioning information, road speed limit information (for example, a highway, an entrance ramp, or a city expressway, etc.), traffic control information, traffic accident information, Whether it is a traffic light section, whether it is a tunnel section, whether it is a subway section, whether it is a ground road, whether it is an overpass section, etc.
  • the driving behavior state information of the driver is equivalent to the personalized driving information of the driver (generally referred to as a person), and belongs to the driver's own driving behavior, which brings a certain vehicle speed to a certain extent, and the driving in the embodiment of the present application
  • the driving behavior status information may include at least one of the following: driver driving age information, whether abnormal parking, driving habit information (including, for example, whether or not to like braking, whether to overtake frequently, whether to frequently follow the driving, etc.).
  • the server in the embodiment of the present application is not limited to how to obtain the current driving situation information.
  • the server may be provided with a database for collecting or collecting information about the stored road scene and behavior status information of different drivers, according to the current
  • the current driving situation information can be directly extracted from the database.
  • the current driving situation information is saved on a third-party device (such as a third-party server, etc.)
  • the current driving capability information of the link needs to be generated according to the current driving situation information
  • the current driving situation may be obtained from the third-party device. information.
  • Step S202 Generate, for the current driving situation information, road state information according to the transition information between the respective road state states extracted from the historical road condition data, and the correspondence between the road state and the road capacity information.
  • the current traffic capacity information of the road segment in the embodiment of the present application is information for characterizing the current traffic capacity of a road or a road segment, and may include at least one of the following: traffic speed, traffic flow, average transit duration, traffic light waiting period, and the like.
  • the current traffic capacity information of the road section may be 50 km / h - 60 km / h, or 40 km / h - 50 km / h, and so on.
  • the current traffic capacity information of the road section can be 50 vehicles/hour/lane-70 vehicles/hour/lane, or 200 vehicles/hour/lane-220 vehicles/hour/lane, and the like.
  • the current traffic capacity information of the road section may be 35 seconds/km-40 seconds/km, or 300 seconds/km-350 seconds/km, and the like.
  • the current traffic capacity information of the road segment can be 1 signal period, or 2 signal periods, and so on.
  • the state of the road condition in the embodiment of the present application may include, but is not limited to, a state of congestion, slowness, smoothness, etc., and the transition information between the state of each road state, that is, the transition information of the state of the road state from the first state to the second state, for example, from congestion to Slow transition probability information, transfer probability information from smooth to slow transition, and so on.
  • the corresponding relationship between the road state and the road capacity information in the embodiment of the present application may be 1 km/h-5 km/hour for the congestion state, or 50 vehicles/hour/lane-70 vehicles/hour for the congestion state.
  • the lane, or the unblocked state corresponds to 60 km / h - 70 km / h, and so on.
  • step S202 may specifically obtain historical road condition data, and then analyze the historical road condition data, and extract, by using a preset extraction algorithm, transfer information between each road state, and a correspondence between each road state and road segment communication capability information, and The transfer information between the respective road state states and the correspondence relationship between each road state and the road segment communication capability information are stored.
  • the current road state information is generated for the current driving situation information by the stored transition information between the respective road state states and the correspondence between each road state and the road segment communication capability information.
  • Step S204 Output the road condition status information.
  • Embodiments of the present application are configured to obtain current driving situation information, and according to the current driving situation information, according to the transition information between the respective road state states extracted from the historical road condition data, and the correspondence between the road state and the road capacity information, Generating road condition status information; outputting the road condition status information, avoiding the phenomenon that continuous abnormal abrupt changes are easily caused when the road condition is directly determined according to the traffic speed of the single road segment, and the transfer information between the various road condition states extracted by the historical road condition data, and Correspondence between road condition and road traffic capacity information ensures the smoothness of road state transition on the geospatial sequence, and solves the problem that the conventional road condition generation method or road condition determination method is affected by the abnormal traffic speed and will give the calculation or decision zone of the road condition.
  • step S202 can be implemented as follows:
  • the current driving capability information of the link may be generated according to the current driving situation information
  • the server may generate the current traffic capacity information of the link according to the current traffic capacity information algorithm of the relevant road segment.
  • the current traffic capacity information of the road segment takes the traffic speed as an example.
  • the server can combine the vehicle positioning information, the road speed limit information, and whether the driver stops abnormally. Each parameter can correspond to the respective weight coefficient, and then calculate the current traffic speed of the road segment.
  • the observed sequence in the embodiment of the present application is a random sequence visible in the field of hidden Markov model problems.
  • Hidden Markov Model is a probabilistic model for sequences. It describes the random generation of unobservable state random sequences from a hidden Markov chain, and then generates observations from various states to produce observation random sequences. process.
  • the state-random sequence randomly generated by the hidden Markov model is called a state sequence; each state generates an observation, and the resulting observation random sequence is called an observation sequence.
  • the current traffic capacity information of the road segment is taken as an example of the traffic speed. Then, the range of the traffic flow speed can be used as an observation sequence.
  • ACBDFE sequence is generated, where A-[0,10], B-(10,20) , C-(20, 40], D-(40, 60), E-(60, 70], F-(70, 80], G-(80, 120).
  • observation sequence is input into the hidden Markov model to generate a road state sequence.
  • the hidden Markov model in the embodiment of the present application includes a first probability matrix and a second probability matrix of the road segment extracted according to the statistical historical road condition data, where the first probability matrix is used to indicate the transition between the respective road state states. Probability, the second probability matrix is used to indicate that the correspondence between the road state and the road capacity information is determined in the form of a probability.
  • the specific model may be a hidden Markov model, an initial road state probability distribution, the first probability matrix (such as a road state transition probability matrix), and the second probability matrix (such as a road state to an observed output probability matrix or an observed probability)
  • the matrix is composed of a sequence of ACBDFEs in which the traffic speed belongs to the real-time description of the road segment capacity in step S202.
  • the model output is the final road state sequence, that is, the corresponding road state sequence with the highest probability for a given existing observation sequence.
  • the sequence of road conditions along the direction of traffic flow is: congestion
  • Hidden Markov models can be described by five elements, including two state sets and three probability matrices:
  • Associated with the implied state in the model can be obtained by direct observation (for example, O1, O2, O3, etc., the number of observable states does not have to be consistent with the number of implied states.).
  • N the number of implied states and M for the number of observable states:
  • Bij P(Oi
  • the probability that the observation state is Oi at the time t and the implicit state is Sj.
  • the embodiment of the present application can be solved by the Viterbi algorithm, that is, the dynamic maximum path (optimal path) is obtained by dynamic programming, and one path corresponds to a road state sequence.
  • the embodiment of the present application combines the marking problem (that is, the prediction problem that the input variable and the output variable are both variable sequences), and the hidden Markov model composed of the first probability matrix and the second probability matrix of the road segment extracted from the statistical historical road data.
  • the most reasonable sequence of road state is generated.
  • a large amount of accurate historical road condition information is essential for road condition generation.
  • the generated road state sequence can be as close as possible to the actual situation, thus avoiding the determination of the road condition directly based on the traffic speed of the single road segment. It is prone to the phenomenon of continuous abnormal abrupt change, and the smooth transition of the state transition of the road condition state is ensured by the statistical state transition state probability in the historical road condition data, and the conventional road condition generation method or the road condition determination method is affected by the abnormal traffic flow speed.
  • the road condition generation method provided by the embodiment of the present application is described in detail below with reference to the schematic diagram of the principle of road condition generation provided by the embodiment of the present application. According to FIG. 3, the principle of road condition generation can be divided into the following four steps.
  • Step S300 the server (or the road condition generating device or device) may obtain the statistical historical road condition data from the truth value system that records the actual traffic road condition; and then extract the transition probability between the respective road condition states according to the statistical historical road condition data; According to the historical road condition data of the statistics, the correspondence between the road state and the road capacity information is determined in the form of probability.
  • Step S302 collecting positioning information of the vehicle that performs positioning and navigation on the road system; acquiring driver driving behavior state information corresponding to the vehicle according to the vehicle identification, and the positioning information and the acquired driver driving behavior state information, and the road network The links in the data are associated.
  • Step S304 Generate current road capacity information of the road segment according to the current driving situation information.
  • Step S306 Generate a traffic state sequence based on the hidden Markov model.
  • FIG. 4 a schematic flowchart of another embodiment of the road condition generating method provided by the embodiment of the present application, which is shown in FIG. 4, details the principle of road condition generation provided by the embodiment of the present application.
  • the road condition generation method shown in FIG. 4 includes the following steps:
  • Step S400 The server (or the road condition generating device or device) acquires the statistical historical road condition data from the truth value system in which the actual traffic condition is recorded.
  • Step S402 The server extracts the transition probability between the respective road state states according to the historical historical road condition data; and determines the correspondence between the road state state and the road segment capacity information according to the historical road condition data of the statistics.
  • the server can return a large number of accurate systems from the true value system such as road test verification, internal feedback, manual labeling, and machine measurement.
  • Historical road condition information, statistical road state transition probability matrix and observation probability matrix for hidden Markov models A large number of accurate historical road condition information is very important for road condition production, which determines two elements of the hidden Markov model: the road state transition probability matrix and the observation probability matrix.
  • O1, O2, O3...O8 in Fig. 5 are visible observation states (or observable states).
  • the statistical road state change probability distribution (ie, the road state transition probability matrix) is as shown in Table 1 below:
  • Table 1 shows that, from the actual traffic conditions, the probability that the adjacent road section is smoothly transferred to the slow line according to the traffic flow direction is 0.25, the probability of the slow transition to the congestion is 0.35, the probability that the congestion transition is unblocked is 0.20, and so on.
  • the embodiment of the present application ensures the smoothness of the state transition of the road condition state through the historical road condition data, and ensures the error caused by the calculation of the traffic flow speed to a certain extent, and solves the conventional road condition generation method or road condition.
  • the determination method is affected by the abnormal traffic flow speed, which will bring errors to the calculation or determination of the road condition, which will cause technical problems of inaccurate road conditions and enhance the tolerance of the system to abnormal noise.
  • determining the correspondence between the road state and the road capacity information in the form of a probability may specifically include: combining the historical road data according to the statistics, and combining a plurality of different road scene information to the probability The form determines the correspondence between the road condition and the road capacity information.
  • the probability distribution of the traffic state and the traffic velocity can be as shown in Table 2 below:
  • Table 2 shows that the probability of traffic flow speed at (60,70] km/h is 0.32 when the actual traffic is unblocked, and the probability of traffic flow at (20,40] km/h is 0.15 during actual congestion, etc.
  • Ground, lack of data source, incomplete analysis of user driving behavior or other unknown anomalies may lead to the inconsistency between the calculated real-time description of the road capacity and the actual road conditions, and the difference in the scene, so that the road conditions have different performances.
  • the application embodiment statistically determines the correspondence between the road state determined by the probabilistic form and the real-time description of the road traffic capacity from the historical data, and to some extent not only tolerates the corresponding observation noise information but also satisfies the road condition determination scenario in an extended state set manner. Diversified demand, and wide road coverage, highways, urban expressways, other grades of roads can be involved, effectively taking into account traffic accidents, regulations, etc. when the road conditions spread.
  • a road section counts 100 times, 98 times are unobstructed, and 2 times of congestion.
  • the situation that the road section is congested can be regarded as observation noise.
  • the probability of patency is high, and the probability of congestion is very low. Therefore, the congestion situation can be almost ignored, that is, the corresponding observation noise information can be tolerated.
  • different road conditions such as high-speed road sections, community road sections or traffic light road sections can be extended.
  • the parameters of smooth, slow-moving and congestion defined by different road conditions can be different, for example, the speed of the high-speed section is above 60 km/h or 70 thousand. Meters/hour or more can be considered as smooth, and the traffic speed of traffic lights at 30 km/h or 40 km/h is smooth, and so on. Therefore, it is possible to meet the diverse needs of the road condition determination scenario.
  • Step S404 The server collects positioning information of the vehicle that performs positioning and navigation on the road system.
  • Step S406 The server acquires driver driving behavior state information corresponding to the vehicle according to the vehicle identifier, and associates the positioning information and the acquired driver driving behavior state information with the road segment in the road network data.
  • GPS positioning data on the device can be collected, such as: a map application software in the navigation behavior, a driver in the delivery process, and a logistics that is transporting the goods. Cars, as well as many brands of private cars on the move, etc.
  • the GPS positioning data includes information such as a road section where the vehicle is located (ie, vehicle position information), a moving speed of the vehicle, and the like.
  • the driver's driving behavior is connected in series according to the vehicle identification (ID), that is, the ID of each vehicle can be provided, and the driver information corresponding to the ID of each vehicle, the driver The information may include driver's driving behavior status information.
  • ID vehicle identification
  • the vehicle ID can be connected in series with the corresponding driver driving behavior state information, and then the corresponding road matching algorithm can be used to associate the GPS point (ie, the vehicle position information) with the actual road network data.
  • the GPS point ie, the vehicle position information
  • Step S408 The server generates current road capacity information of the road segment according to the current driving situation information.
  • the current driving situation information (which may also be collectively referred to as user driving behavior analysis or driver driving behavior analysis) may be analyzed according to the associated road segment information, and the current driving situation information may include current driving scene information and driver driving.
  • the current driving situation information may include current driving scene information and driver driving.
  • the current traffic capacity information of the generated road segment is discretized to obtain an observation sequence.
  • the steps S404 and S406 may be integrated into the step S408, that is, the generating the current traffic capacity information of the road segment according to the current driving situation information in step S408 may specifically include: collecting positioning information of the vehicle for positioning and positioning on the road system. Obtaining driver driving behavior state information corresponding to the vehicle according to the vehicle identifier, and correlating the positioning information and the acquired driver driving behavior state information with the road segment in the road network data.
  • Step S410 Generate a traffic state sequence based on the hidden Markov model.
  • the server generates a road state sequence corresponding to the maximum probability path according to the input observation sequence, the initial road state probability distribution, the first probability matrix, and the second probability matrix, and generates a road state sequence to indicate the state according to the road state.
  • the sequence displays the probability maximum path in the map; the road state sequence indicates road condition information of each road segment in the maximum probability path.
  • step S204 in the foregoing embodiment of FIG. 2, and details are not described herein.
  • Step S412 Output a sequence of road condition states.
  • the server may send the road state sequence to the terminal, so that the terminal displays the smoothness or congestion degree of the road condition in the map software according to the road state sequence, which may be displayed by different colors.
  • the green road segment indicates that the road segment is clear and yellow.
  • the road section indicates that the road section is slow, the bright red road section indicates that the road section is congested, and the brown red road section indicates that the road section is heavily congested.
  • the user is planned to plan the optimal path from the starting point to the ending point (ie, the maximum path of probability), and can display the smoothness or congestion degree of each section of the optimal path, and can display the duration of the optimal path, etc. information.
  • Embodiments of the present application generate a traffic state sequence by generating a current capacity information of a road segment according to current driving situation information; and then inputting a hidden sequence by inputting a hidden sequence obtained by discretizing the current traffic capacity information of the road segment; wherein
  • the hidden Markov model includes a first probability matrix and a second probability matrix of the road segment extracted according to the statistical historical road condition data, the first probability matrix is used to indicate a transition probability between the respective road state states, and the second probability matrix is used for The indication determines the correspondence between the road state and the road capacity information in the form of probability, and avoids the phenomenon that the continuous abnormal sudden change is easy to be directly determined according to the traffic speed of the single road segment, and the state transition state probability is ensured by the historical road condition data.
  • the smoothness of the state transition of the road condition on the geospatial sequence, and the error caused by the calculation of the traffic flow speed is allowed to some extent, and the conventional road condition generation method or the road condition determination method is affected by the abnormal traffic flow speed, and the road condition calculation or determination is solved. Bring errors and cause road conditions Accurate technical problems, the system can enhance the tolerance for abnormal noise. Moreover, if the sensor or the coil is deployed on the road through the traffic control department, and the traffic flow on the road is sensed by the sensor to determine the traffic congestion situation, the engineering quantity is huge, and the coverage of the road is narrow, except for the highway or the urban expressway. Technical problems that are difficult to cover on other roads.
  • the hidden Markov model is used to generate the most suitable observation sequence through the transition probability between invisible road conditions and the observation probability of adaptable multi-scene.
  • the excellent sequence of road conditions makes the road conditions more reasonable and more realistic, and the road coverage is wide.
  • the highways and urban expressways can be involved in other grades, effectively taking into account the roadway of traffic accidents, regulations, etc.
  • the solution is flexible, and the shortcomings of strategy optimization can be overcome when solving bad cases (BadCase).
  • the embodiments of the present application can provide better ETA services and path planning, and save urban road resources and user time.
  • the embodiment of the present application further provides a road condition generating device and a road condition generating device, which are described in detail below with reference to the accompanying drawings:
  • FIG. 6a is a schematic structural diagram of a road condition generating apparatus according to an embodiment of the present application, and the road condition generating apparatus 60 may include a unit in an embodiment for executing the road condition generating method.
  • the road condition generating device 60 may include: an obtaining unit 600, an information generating unit 602, and an output unit 604, wherein
  • the obtaining unit 600 is configured to obtain current driving condition information
  • the information generating unit 602 is configured to generate, according to the current driving situation information, the road state information according to the transition information between the respective road state states extracted from the historical road condition data, and the correspondence between the road state and the road traffic capacity information;
  • the output unit 604 is configured to output the road state information.
  • the information generating unit 602 may include: a traffic capability generating unit 6020, a discretization unit 6022, and a sequence generating unit 6024, where
  • the capacity generating unit 6020 is configured to generate current road capacity information according to the current driving situation information
  • the discretization unit 6022 is configured to discretize the current capacity information of the road segment to obtain an observation sequence
  • the sequence generating unit 6024 is configured to input the observation sequence into the hidden Markov model, and output a road state sequence; wherein the hidden Markov model includes a first probability matrix and a second probability matrix of the segment extracted according to the statistical historical road condition data.
  • the first probability matrix is used to indicate a transition probability between the respective road state
  • the second probability matrix is used to indicate that the correspondence between the road state and the road capacity information is determined in the form of a probability.
  • the current driving condition information includes current driving scene information and driver driving behavior status information
  • the current driving scene information includes at least one of the following: vehicle positioning information, road speed limit information, traffic control information, traffic accident information, whether a traffic light section, whether a tunnel section, a subway section, or a ground road;
  • the driver driving behavior status information includes at least one of the following: driver driving age information, whether abnormal parking, driving habit information.
  • FIG. 7 is a schematic structural diagram of a capacity generation unit 6020 according to an embodiment of the present application.
  • the capacity generation unit 6020 may include an acquisition unit 60200, an association unit 60202, and an information generation unit 60204.
  • the collecting unit 60200 is configured to collect positioning information of the vehicle for positioning and positioning on the road system
  • the association unit 60202 is configured to acquire driver driving behavior state information corresponding to the vehicle according to the vehicle identifier, and associate the positioning information and the acquired driver driving behavior state information with the road segment in the road network data;
  • the information generating unit 60204 is configured to generate the current traffic capacity information of the link according to the associated link information.
  • the current traffic capacity information of the road segment includes at least one of the following:
  • Traffic speed traffic flow
  • average transit duration traffic light waiting period.
  • the road condition generating device 60 may further include an acquiring unit, a first extracting unit, and a second extracting unit, where
  • the obtaining unit is configured to obtain statistical historical road condition data from a truth value system that records actual traffic conditions;
  • the first extracting unit is configured to extract a transition probability between each road state according to the historical historical road data of the statistics
  • the second extracting unit is configured to determine, according to the statistical historical road condition data, a correspondence relationship between the road state and the road capacity information in the form of a probability. Specifically, according to the historical historical road condition data, combined with a plurality of different road condition scene information, the correspondence between the road condition state and the road section capacity capability information is determined in the form of probability.
  • sequence generating unit 6024 is specifically configured to generate, according to the input sequence of the observation, the initial road state probability distribution, the first probability matrix, and the second probability matrix, a dynamic state planning to generate a road state sequence corresponding to the maximum probability path;
  • the road condition status sequence is output to indicate that the probability maximum path is displayed in the map according to the road condition status sequence; the road condition status sequence indicates road condition information of each road section in the probability maximum path.
  • the traffic generation device 60 may be a computing device such as a server, including but not limited to a computer or the like.
  • the schematic diagram of the road condition generating device may include: at least one processor 801, such as a CPU, an input module 802, an output module 803, and a memory 804. At least one communication bus 805 and a communication module 806. Among them, the communication bus 805 is used to implement connection communication between these components.
  • the memory 804 may be a high speed RAM memory or a non-volatile memory such as at least one disk memory, and the memory 804 includes the flash in the embodiment of the present application. In some embodiments of the present application, the memory 804 may also be at least one storage system located away from the aforementioned processor 801; the communication module 806 is configured to perform data communication with an external device. As shown in FIG. 8, the memory 804 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an implementation program for road condition generation.
  • the processor 801 can be used to call an implementation of the road condition generation stored in the memory 804, and perform the following operations:
  • the current driving condition information can be obtained through the communication module 806;
  • the road condition status information is output through the output module 803.
  • the processor 801 generates, according to the current driving situation information, the road state information according to the transition information between the state of the road state extracted from the historical road condition data and the relationship between the road state and the road capacity information, which may include:
  • the hidden Markov model includes a first probability matrix and a second probability matrix of the road segment extracted according to the statistical historical road condition data, the first probability matrix It is used to indicate a transition probability between each road state, and the second probability matrix is used to indicate that the correspondence between the road state and the road capacity information is determined in the form of a probability.
  • the current driving situation information includes current driving scene information and driver driving behavior status information
  • the current driving scene information includes at least one of the following: vehicle positioning information, road speed limit information, traffic control information, traffic accident information, whether a traffic light section, whether a tunnel section, a subway section, or a ground road;
  • the driver driving behavior status information includes at least one of the following: driver driving age information, whether abnormal parking, driving habit information.
  • the current driving scene information of the processor 801 includes vehicle positioning information
  • the generating current road capacity information of the road segment according to the current driving situation information includes:
  • the control collection module collects positioning information of the vehicle for positioning and navigation on the road system; the collection module may be disposed on the road condition generating device 80 or other external device;
  • the current traffic capacity information of the link is generated according to the associated link information.
  • the current capacity information of the road segment includes at least one of the following:
  • Traffic speed traffic flow
  • average transit duration traffic light waiting period.
  • the processor 801 inputs the observation sequence into the hidden Markov model to generate a traffic state sequence, and may further perform:
  • the correspondence between the road state and the road capacity information is determined in the form of probability.
  • the processor 801 determines, according to the historical historical road condition data of the statistics, the correspondence between the road state and the road capacity information in the form of a probability, including:
  • the correspondence relationship between the road condition state and the road section capacity information is determined in the form of probability.
  • the processor 801 inputs the observation sequence into the hidden Markov model to generate a road state sequence, including:
  • the dynamic state planning According to the input observation sequence, the initial road state probability distribution, the first probability matrix and the second probability matrix, the dynamic state planning generates a road state sequence corresponding to the maximum probability path;
  • the outputting the road state information by the processor 801 includes: outputting the road state sequence to indicate that the probability maximum path is displayed in the map according to the road state sequence; the road state sequence indicates the road condition of each segment in the probability maximum path information.
  • the road condition generating device 80 may send the road condition status sequence to the terminal by using the communication module 806 to indicate that the probability maximum path is displayed in the map according to the road condition status sequence; the road condition status sequence indicates each road segment in the probability maximum path. Traffic information.
  • the traffic generation device 80 can be a computing device such as a server, including but not limited to a computer or the like.
  • Embodiments of the present application are configured to generate a current state capability information of a road segment according to current driving situation information; and then input a hidden Markov model by using an observation sequence obtained by discretizing the current traffic capacity information of the road segment, and output a road state sequence;
  • the hidden Markov model includes a first probability matrix and a second probability matrix of the road segment extracted according to the statistical historical road condition data, the first probability matrix is used to indicate a transition probability between the respective road state states, and the second probability matrix is used for The indication determines the correspondence between the road state and the road capacity information in the form of probability, and avoids the phenomenon that the continuous abnormal sudden change is easy to be directly determined according to the traffic speed of the single road segment, and the state transition state probability is ensured by the historical road condition data.
  • the smoothness of the state transition of the road condition on the geospatial sequence, and the error caused by the calculation of the traffic flow speed is allowed to some extent, and the conventional road condition generation method or the road condition determination method is affected by the abnormal traffic flow speed, and the road condition calculation or determination is solved. Bring errors and cause road conditions Inaccurate technical issues can enhance the system's tolerance for abnormal noise.
  • the sensor or the coil is deployed on the road through the traffic control department, and the traffic flow on the road is sensed by the sensor to determine the traffic congestion situation, the engineering quantity is huge, and the coverage of the road is narrow, except for the highway or the urban expressway. Technical problems that are difficult to cover on other roads.
  • the hidden Markov model is used to generate the most suitable observation sequence through the transition probability between invisible road conditions and the observation probability of adaptable multi-scene.
  • the excellent sequence of road conditions makes the road conditions more reasonable and more realistic, and the road coverage is wide.
  • the highways and urban expressways can be involved in other grades, effectively taking into account the roadway of traffic accidents, regulations, etc.
  • the solution is flexible, and the shortcomings of strategy optimization can be overcome when solving bad cases (BadCase).
  • the embodiments of the present application can provide better ETA services and path planning, and save urban road resources and user time.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Business, Economics & Management (AREA)
  • Chemical & Material Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Artificial Intelligence (AREA)
  • Probability & Statistics with Applications (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Analysis (AREA)
  • Algebra (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Atmospheric Sciences (AREA)
  • Traffic Control Systems (AREA)

Abstract

本申请实施例公开了一种路况生成方法、装置、设备和存储介质，该方法由计算设备执行，包括：获取当前驾驶状况信息；针对所述当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息；输出所述路况状态信息。

Description

路况生成方法、装置、设备和存储介质
本申请要求于2017年12月13日提交中国专利局、申请号为201711335748.7，申请名称为“路况生成方法、相关装置和设备”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
本申请实施例涉及计算机领域，尤其涉及路况生成方法、装置、设备和存储介质。
背景技术
在地图服务中，实时交通路况信息作为基础功能，不仅能够方便用户知晓道路拥堵情况，规划出行路线合理安排行动计划，还能帮助城市构建交通预警，调度城市交通系统。准确的路况，可提供更加优质的ETA(Estimated Time of Arrival)服务和路径规划，节省城市道路资源和用户时间。
发明内容
本申请实施例第一方面公开了一种路况生成方法，由计算设备执行，包括：
获取当前驾驶状况信息；
针对所述当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息；
输出所述路况状态信息。
本申请实施例第二方面公开了一种路况生成装置，包括：
获取单元，用于获取当前驾驶状况信息；
信息生成单元，用于针对该当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能 力信息的对应关系，生成路况状态信息；
输出单元，用于输出该路况状态信息。
本申请实施例第三方面公开了一种路况生成设备，包括处理器、输入设备、输出设备和存储器，所述处理器、输入设备、输出设备和存储器相互连接，其中，所述存储器用于存储程序代码，所述处理器被配置用于调用所述程序代码，执行如上述第一方面的方法。
本申请实施例第四方面公开了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行如上述第一方面的方法。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的路况生成方法的系统构架示意图；
图2是本申请实施例提供的一种路况生成方法的示意流程图；
图3是本申请实施例提供的路况生成的原理示意图；
图4是本申请实施例提供的隐马尔可夫模型的状态转移的原理示意图；
图5是本申请提供的路况生成方法的另一实施例的流程示意图；
图6a是本申请实施例提供的路况生成装置的结构示意图；
图6b是本申请实施例提供的信息生成单元的结构示意图；
图7是本申请实施例提供的通行能力生成单元的结构示意图；
图8是本申请实施例提供的路况生成设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案 进行描述。
应当理解，当在本说明书和所附权利要求书中使用时，术语“包括”和“包含”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。
还应当理解，在此本申请说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本申请。如在本申请说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
还应当进一步理解，在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。
如在本说明书和所附权利要求书中所使用的那样，术语“如果”可以依据上下文被解释为“当...时”或“一旦”或“响应于确定”或“响应于检测到”。类似地，短语“如果确定”或“如果检测到[所描述条件或事件]”可以依据上下文被解释为意指“一旦确定”或“响应于确定”或“一旦检测到[所描述条件或事件]”或“响应于检测到[所描述条件或事件]”。
具体实现中，本申请实施例中描述的终端包括但不限于诸如具有触摸敏感表面(例如，触摸屏显示器和/或触摸板)的移动电话、膝上型计算机或平板计算机之类的其它便携式设备。还应当理解的是，在某些实施例中，所述设备并非便携式通信设备，而是具有触摸敏感表面(例如，触摸屏显示器和/或触摸板)的台式计算机。
在接下来的讨论中，描述了包括显示器和触摸敏感表面的终端。然而，应当理解的是，终端可以包括诸如物理键盘、鼠标和/或控制杆的一个或多个其它物理用户接口设备。
如今，大多数地图生产厂商通过采集道路上车辆全球定位系统(Global Positioning System，GPS)定位点信息，计算车辆在各路段上 的实时速度，并融合多车在同一路段上的速度，通过速度的快慢来确定路段拥堵情况。然而，该方法直接根据单路段的车流速度判定路况时很容易出现连续异常突变的现象，异常突变的出现来自异常车流速度，例如车辆行为异常导致速度值过低或过高等。也就是说，上述的路况生成方法或路况判定方法受异常车流速度的影响，会给路况的计算或判定带来误差，造成路况不准确。
有鉴于此，本申请实施例提供了一种路况生成方法、一种路况生成装置、一种路况生成设备以及一种计算机可读存储介质。实施本申请实施例，通过获取当前驾驶状况信息；针对所述当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息；输出该路况状态信息，避免了前述的直接根据单路段的车流速度判定路况时很容易出现连续异常突变的现象，通过历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，保证了地理空间序列上路况状态过渡的平滑性，解决了前述的路况生成方法或路况判定方法受异常车流速度的影响，会给路况的计算或判定带来误差，造成路况不准确的技术问题。并且解决了若通过交管部门将传感器或线圈部署在道路上，通过传感器感应道路上车流量以确定交通的拥堵情况时，工程量巨大，对道路的覆盖面窄，除了高速路或城市快速路以外，其它道路难以覆盖的技术问题。
为了更好的理解本申请实施例提供的一种路况生成方法、路况生成装置以及路况生成设备，下面先对本申请实施例适用的路况生成方法的系统构架进行描述。参阅图1，图1是本申请实施例提供的路况生成方法的系统构架示意图。如图1所示，系统构架可以包括一个或多个服务器以及多个终端(或设备)，其中：
服务器可以包括但不限于后台服务器、组件服务器、路况生成服务器等，服务器可以通过互联网与多个终端进行通信。服务器可以进行路况分析、交通预警、路径规划等，并可以将路况展示于实时交通路况的 任何平台或产品中，如数字大屏、地图服务应用、打车软件、物流调度系统等等，可以为终端及时动态显示路况变化，方便用户规划调度及决策。
终端(或设备)可以安装并运行有相关的客户端(Client)。客户端(Client)(例如包括地图服务客户端等)是指与服务器相对应，为客户提供本地服务的程序。这里，该本地服务可包括但不限于：进行路况分析、交通预警、路径规划等等。
具体的，客户端可包括：本地运行的应用程序、运行于网络浏览器上的功能(又称为Web App)、嵌入于电子邮件中的小程序、嵌入于即时通讯的客户端软件中的小程序，以及嵌入在其他应用程序中的功能(如开发者或商家基于公众平台上申请的应用账号)等。对于客户端，服务器上需要运行有相应的服务器端程序来提供相应的服务，如数据库服务，数据计算、决策执行等等。用户使用终端在该相应平台上进行针对交通路况的相关操作，例如路况查看，路径规划等操作。
例如，在地图服务客户端中，服务器以实时交通路况信息作为基础功能，将交通路况信息发送给用户侧的该地图服务客户端，用户通过该终端上安装并运行的地图服务客户端不仅能够很方便地知晓道路拥堵情况，规划出行路线合理安排行动计划；另外还能帮助交管部门构建交通预警，调度城市交通系统。
本申请实施例中的终端可以包括但不限于任何一种基于智能操作系统的手持式电子产品，其可与用户通过键盘、虚拟键盘、触摸板、触摸屏以及声控设备等输入设备来进行人机交互，诸如智能手机、平板电脑、个人电脑等。其中，智能操作系统包括但不限于任何通过向移动设备提供各种移动应用来丰富设备功能的操作系统，诸如安卓(Android)、IOS、Windows Phone等。
不限于图1所示，本申请实施例提供的路况生成方法的系统构架还可以包括其他设备，例如第三方服务器，例如用于统计或采集存储当前驾驶状况信息等信息，以备路况生成服务器需要根据生成路况时，从该 第三方服务器获取当前驾驶状况信息等信息。
基于图1所示的路况生成方法的系统构架，参见图2，是本申请实施例提供一种路况生成方法的示意流程图，从服务器侧(即路况生成装置或设备)来描述如何生成路况信息，可以包括以下步骤。
步骤S200：获取当前驾驶状况信息。
具体地，本申请实施例中的当前驾驶状况信息可以包括当前车辆驾驶的道路类型(例如可以通过路段限速信息来进行分类)、当前道路的交通事故信息、当前道路的交通管制信息、当前驾驶者的状态信息(可以包括驾龄、驾驶习惯等信息)等等，用于表征当前驾驶场景或当前驾驶者的状况信息，或者当前驾驶场景和当前驾驶者的状况信息。
进一步地，该当前驾驶状况信息可以包括当前驾驶场景信息和驾驶者驾驶行为状态信息；
该当前驾驶场景信息，即道路情形的多变化信息，一般是道路周边设施属性带来的，当前驾驶场景信息从客观上限制了特定路段的通行能力。本申请实施例中的当前驾驶场景可以包括以下至少一项：车辆定位信息、路段限速信息(例如是高速路、还是出入口匝道、还是城市快速路等等)、交通管制信息、交通事故信息、是否红绿灯路段、是否隧道路段、是否地铁口路段、是否地面道路、是否立交桥路段等等。
该驾驶者驾驶行为状态信息，相当于驾驶者(一般指人)的个性化驾驶信息，属于驾驶者自身的驾驶行为，在一定程度上会带来不同的车辆速度，本申请实施例中的驾驶者驾驶行为状态信息可以包括以下至少一项：驾驶者驾龄信息、是否异常停车、驾驶习惯信息(例如包括是否喜欢飙车、是否经常超车、是否经常尾随行驶等等)。
本申请实施例中的服务器不限定于如何获取上述当前驾驶状况信息，例如该服务器可以设有一数据库，用于统计或采集存储道路场景的信息以及不同驾驶者的行为状态信息，在需要根据该当前驾驶状况信息生成路段当前通行能力信息时，可以直接从该数据库中提取该当前驾驶状况信息。或者，又如该当前驾驶状况信息在第三方设备(如第三方服 务器等)上保存，那么当需要根据该当前驾驶状况信息生成路段当前通行能力信息时，可以向该第三方设备获取当前驾驶状况信息。
步骤S202：针对所述当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息。
具体地，本申请实施例的路段当前通行能力信息是用于表征一条道路或路段当前通行能力的信息，可以包括以下至少一项：车流速度、车流量、平均通行时长、红绿灯等待周期等。
以车流速度为例，路段当前通行能力信息可以为50千米/小时-60千米/小时，或40千米/小时-50千米/小时，等等。以车流量为例，路段当前通行能力信息可以为50辆/时/车道-70辆/时/车道，或200辆/时/车道-220辆/时/车道，等等。以平均通行时长为例，路段当前通行能力信息可以为35秒/千米-40秒/千米，或300秒/千米-350秒/千米，等等。以红绿灯等待周期为例，路段当前通行能力信息可以为1个信号周期，或2个信号周期，等等。
本申请实施例中的路况状态可以包括但不限于拥堵、缓行、畅通等状态，各个路况状态之间的转移信息即路况状态从第一状态转移到第二状态的转移信息，比如从拥堵转移为缓行的转移概率信息、从畅通转移为缓行的转移概率信息等等。本申请实施例中的路况状态与路段通行能力信息的对应关系，可以为拥堵状态对应1千米/小时-5千米/小时，或者拥堵状态对应50辆/时/车道-70辆/时/车道，或者畅通状态对应60千米/小时-70千米/小时，等等。
那么步骤S202具体可以为先获取历史路况数据，然后分析该历史路况数据，通过预设的提取算法提取各个路况状态之间的转移信息，以及每个路况状态与路段通信能力信息的对应关系，并存储该各个路况状态之间的转移信息以及每个路况状态与路段通信能力信息的对应关系。在获取到当前驾驶状况信息后，针对该当前驾驶状况信息，通过存储的该各个路况状态之间的转移信息以及每个路况状态与路段通信能力信 息的对应关系，生成当前的路况状态信息。
步骤S204：输出该路况状态信息。
实施本申请实施例，通过获取当前驾驶状况信息；针对所述当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息；输出所述路况状态信息，避免了直接根据单路段的车流速度判定路况时很容易出现连续异常突变的现象，通过历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，保证了地理空间序列上路况状态过渡的平滑性，解决了常规的路况生成方法或路况判定方法受异常车流速度的影响，会给路况的计算或判定带来误差，造成路况不准确的技术问题。并且解决了若通过交管部门将传感器或线圈部署在道路上，通过传感器感应道路上车流量以确定交通的拥堵情况时，工程量巨大，对道路的覆盖面窄，除了高速路或城市快速路以外，其它道路难以覆盖的技术问题。
在本申请的一个实施例中，步骤S202可以通过如下方式来实现：
在获取到当前驾驶状况信息以后，可以先根据该当前驾驶状况信息生成路段当前通行能力信息；
服务器在获取到当前驾驶状况信息后，可以根据相关的路段当前通行能力信息算法生成路段当前通行能力信息。例如，路段当前通行能力信息以车流速度为例，服务器可以结合车辆定位信息、路段限速信息以及驾驶者是否异常停车，每一个参数可以对应各自的权重系数，然后计算出路段当前的车流速度。
然后将该路段当前通行能力信息进行离散化处理，得到观测序列；
具体地，本申请实施例中的观测序列为隐马尔科夫模型问题领域中可见的随机序列。隐马尔科夫模型(Hidden Markov Model，HMM)是一个关于序列的概率模型，描述由一个隐藏的马尔可夫链随机生成不可观测的状态随机序列，再由各个状态生成观测而产生观测随机序列的过 程。隐马尔科夫模型随机生成的状态随机序列，称为状态序列；每个状态生成一个观测，由此产生的观测随机序列，称为观测序列。比如：路段当前通行能力信息以车流速度为例，那么可将车流速度所属范围作为观测序列，进行离散化处理后，生成ACBDFE序列，其中A-[0,10]，B-(10,20]，C-(20,40]，D-(40,60]，E-(60,70]，F-(70,80]，G-(80,120]。
最后将该观测序列输入隐马尔可夫模型，生成路况状态序列。
具体地，本申请实施例中的隐马尔可夫模型包括根据统计的历史路况数据提取的路段的第一概率矩阵和第二概率矩阵，该第一概率矩阵用于指示各个路况状态之间的转移概率，该第二概率矩阵用于指示以概率的形式确定路况状态与路段通行能力信息的对应关系。
需要说明的是，本申请实施例求取的是模型不可见的状态序列，需要已知具体模型及观测序列。该具体模型可以为隐马尔可夫模型，由初始路况状态概率分布、该第一概率矩阵(如路况状态转移概率矩阵)和该第二概率矩阵(如路况状态至观测的输出概率矩阵或观测概率矩阵)组成，该观测序列为步骤S202由路段通行能力实时描述经离散化后得到，例如上述车流速度所属范围序列ACBDFE。模型输出即为最终路况状态序列，也就是对于给定的已有观测序列，求使其概率最大的对应的路况状态序列。比如沿车流方向上的路况状态序列为：拥堵|缓行|拥堵|畅通|畅通|畅通。
一般的，可以用λ＝(A,B,π)三元组来简洁的表示一个隐马尔可夫模型。隐马尔可夫模型可以用五个元素来描述，包括2个状态集合和3个概率矩阵：
1.隐含状态S
这些状态之间满足马尔可夫性质，是马尔可夫模型中实际所隐含的状态。这些状态通常无法通过直接观测而得到(例如S1、S2、S3等等)。
2.可观测状态O
在模型中与隐含状态相关联，可通过直接观测而得到(例如O1、O2、O3等等，可观测状态的数目不一定要和隐含状态的数目一致。)。
3.初始状态概率矩阵π
表示隐含状态在初始时刻t＝1的概率矩阵，(例如t＝1时，P(S1)＝p1、P(S2)＝P2、P(S3)＝p3，则初始状态概率矩阵π＝[p1 p2 p3]。
4.隐含状态转移概率矩阵A
描述了HMM模型中各个状态之间的转移概率。
其中Aij＝P(Sj|Si),1≤i,,j≤N.
表示在t时刻、状态为Si的条件下，在t+1时刻状态是Sj的概率。
5.观测状态转移概率矩阵B
令N代表隐含状态数目，M代表可观测状态数目，则：
Bij＝P(Oi|Sj),1≤i≤M,1≤j≤N.
表示在t时刻、隐含状态是Sj条件下，观测状态为Oi的概率。
那么，给定观测序列和模型参数λ＝(A,B,π)，怎样有效计算某一观测序列的概率，进而可对该HMM做出相关评估。本申请实施例可以通过维特比算法求解，即：采用动态规划求概率最大路径(最优路径)，而一条路径对应着一个路况状态序列。
本申请实施例结合标记问题(即输入变量与输出变量均为变量序列的预测问题)，以及根据统计的历史路况数据提取的路段的第一概率矩阵和第二概率矩阵构成的隐马尔可夫模型，生成最合理的路况状态序列，大量的准确的历史路况信息对路况生成至关重要，生成的路况状态序列可以尽可能的符合实际情况，从而避免了直接根据单路段的车流速度判定路况时很容易出现连续异常突变的现象，通过历史路况数据中统计路况状态转移概率，保证了地理空间序列上路况状态过渡的平滑性，解决了常规的路况生成方法或路况判定方法受异常车流速度的影响，会给路况的计算或判定带来误差，造成路况不准确的技术问题。并且解决了若通过交管部门将传感器或线圈部署在道路上，通过传感器感应道路上车流量以确定交通的拥堵情况时，工程量巨大，对道路的覆盖面窄，除了高速路或城市快速路以外，其它道路难以覆盖的技术问题。
进一步地，下面结合图3示出的本申请实施例提供的路况生成的原理示意图，来再次详细说明本申请实施例提供的路况生成方法。根据图3所示，路况生成的原理可以分成以下4个步骤。
步骤S300：服务器(或路况生成装置或设备)可以从记录了实际交通路况的真值系统中获取统计的历史路况数据；然后根据该统计的历史路况数据提取各个路况状态之间的转移概率；以及根据该统计的历史路况数据，以概率的形式确定路况状态与路段通行能力信息的对应关系。
步骤S302：采集道路系统上进行定位导航的车辆的定位信息；根据车辆标识获取车辆对应的驾驶者驾驶行为状态信息，将所述定位信息和获取的所述驾驶者驾驶行为状态信息，与路网数据中的路段进行关联。
步骤S304：根据当前驾驶状况信息生成路段当前通行能力信息。
步骤S306：基于隐马尔可夫模型生成路况状态序列。
具体地，结合图4示出的本申请实施例提供的路况生成方法的另一实施例的流程示意图，详细说明本申请实施例提供的路况生成的原理。图4示出的路况生成方法包括如下步骤：
步骤S400：服务器(或路况生成装置或设备)从记录了实际交通路况的真值系统中获取统计的历史路况数据。
步骤S402：服务器根据该统计的历史路况数据提取各个路况状态之间的转移概率；以及根据该统计的历史路况数据，以概率的形式确定路况状态与路段通行能力信息的对应关系。
具体地，如图5示出的本申请实施例提供的隐马尔可夫模型的状态转移的原理示意图，服务器可以从路测验证、内部反馈、人工标注、机测等真值系统返回大量准确的历史路况信息，统计用于隐马尔可夫模型的路况状态转换概率矩阵和观测概率矩阵。大量准确的历史路况信息对路况生产至关重要，决定了隐马尔可夫模型三要素中的两要素：路况状态转移概率矩阵和观测概率矩阵。图5中的O1、O2、O3…O8即为可见观测状态(或可观测状态)。
例如，假设路况状态包括畅通、缓行和拥堵。基于大量准确的历史 路况信息，统计的路况状态变化概率分布(即路况状态转移概率矩阵)，如下表1所示：
  畅通 缓行 拥堵
畅通 0.6 0.25 0.15
缓行 0.3 0.35 0.35
拥堵 0.2 0.38 0.42
表1
表1表明，从实际交通路况中，根据车流方向统计相邻路段畅通转移为缓行的概率为0.25，缓行转移为拥堵的概率为0.35，拥堵转移为畅通的概率为0.20，等等。本申请实施例通过历史路况数据中统计路况状态转移概率，保证了地理空间序列上路况状态过渡的平滑性，并且一定程度地允许车流速度计算带来的误差，解决了常规的路况生成方法或路况判定方法受异常车流速度的影响，会给路况的计算或判定带来误差，造成路况不准确的技术问题，能增强系统对异常噪声的容忍度。
另外，根据该统计的历史路况数据，以概率的形式确定路况状态与路段通行能力信息的对应关系时可以具体包括：根据该统计的历史路况数据，并结合多个不同的路况场景信息，以概率的形式确定路况状态与路段通行能力信息的对应关系。
例如：基于大量准确的历史路况信息，从实际交通路况中，统计路况状态与车流速度的概率分布(即观测概率矩阵)，可以如下表2所示：
  [0,10] (10,20] (20,40] ... (60,70] (70,80] (80,120]
畅通 0.001 0.02 0.05 ... 0.32 0.2 0.15
缓行 0.08 0.22 0.46 ... 0.008 0.003 0
拥堵 0.26 0.38 0.15 ... 0.003 0.002 0.001
表2
表2表明，实际畅通时车流速度处在(60,70]千米/小时的概率为0.32， 实际拥堵时车流速度处在(20,40]千米/小时的概率为0.15，等等。具体地，数据源缺少、用户驾驶行为分析不全面或其他未知异常等原因，可能会导致计算出来的路段通行能力实时描述与真实路况不一致，同时场景的差异，让路况又存在不同的表现。而本申请实施例从历史数据中统计以概率形式确定的路况状态与路段通行能力实时描述对应关系，在一定程度上不仅容忍了相应的观测噪声信息而且还能以扩展状态集合的方式满足路况判定场景的多样化需求，并且道路覆盖面广，高速路城市快速路其他等级道路均能涉及，有效地兼顾交通事故、管制等发生时路况的扩散途径。
例如，某路段统计100次，98次都是通畅、2次拥堵，可以把该路段为拥堵的情况看作是观测噪声，以概率的形式来说通畅的概率很高，拥堵的概率就很低，因此几乎可以忽略拥堵的情况，也就是说可以容忍相应的观测噪声信息。另外，可以扩展出高速路段、小区路段或红绿灯路段等不同路况场景，每个不同路况场景定义的畅通、缓行和拥堵的参数可以不同，例如高速路段车流速度在60千米/小时以上或70千米/小时以上才能算畅通，而红绿灯路段车流速度在30千米/小时或40千米/小时以上就算畅通，等等。因此可以满足路况判定场景的多样化需求。
步骤S404：服务器采集道路系统上进行定位导航的车辆的定位信息。
步骤S406：服务器根据车辆标识获取车辆对应的驾驶者驾驶行为状态信息，将所述定位信息和获取的所述驾驶者驾驶行为状态信息，与路网数据中的路段进行关联。
具体地，只要有连续驾驶行为、导航过程中的车辆，均可采集其设备上的GPS定位数据，如：处于导航行为中的地图应用软件、处于送客过程中的司机、正在运送货物的物流车、以及行进中的众多品牌私家车辆等等。该GPS定位数据包括车辆所在路段(即车辆位置信息)、车辆的移动速度等等信息。在获取到GPS定位数据后，根据车辆标识(ID)将驾驶者驾驶行为串联起来，也就是说可以设有每一辆车的ID，以及每 一辆车的ID对应的驾驶者信息，驾驶者信息可以包括驾驶者的驾驶行为状态信息。那么在获取到GPS定位数据后，即可根据车辆ID与其对应的驾驶者驾驶行为状态信息串联起来，然后可以采用相应的道路匹配算法将GPS点(即车辆位置信息)关联到路网数据中实际的道路段上，以便后续在特定场景下对用户驾驶行为进行分析。
步骤S408：服务器根据当前驾驶状况信息生成路段当前通行能力信息。
具体地，可以根据关联后的路段信息分析得出当前驾驶状况信息(也可以统称为用户驾驶行为分析，或驾驶者驾驶行为分析)，该当前驾驶状况信息可以包括当前驾驶场景信息和驾驶者驾驶行为状态信息；具体可以参考上述图2实施例中的步骤S200，这里不进行赘述。将生成的路段当前通行能力信息进行离散化处理，得到观测序列。
本申请的其中一个实施例，步骤S404、S406可以融合到步骤S408中，即步骤S408中根据当前驾驶状况信息生成路段当前通行能力信息可以具体包括：采集道路系统上进行定位导航的车辆的定位信息；根据车辆标识获取车辆对应的驾驶者驾驶行为状态信息，将该定位信息和获取的该驾驶者驾驶行为状态信息，与路网数据中的路段进行关联。
步骤S410：基于隐马尔可夫模型生成路况状态序列。
具体地，服务器根据输入的观测序列、初始路况状态概率分布、第一概率矩阵和第二概率矩阵，采用动态规划生成概率最大路径对应的路况状态序列；生成路况状态序列以指示根据所述路况状态序列在地图中显示所述概率最大路径；路况状态序列指示概率最大路径中各个路段的路况信息。具体地，可以参考上述图2实施例中的步骤S204，这里不进行赘述。
步骤S412：输出路况状态序列。
具体地，服务器可以将路况状态序列发送给终端，以使终端根据路况状态序列在地图软件中展示路况的畅通或拥堵程度，具体可以通过不同的颜色来展示，例如绿色路段表示该路段畅通、黄色路段表示该路段 缓行、鲜红色路段表示该路段拥堵、褐红色路段表示该路段严重拥堵等等。或者根据路况状态序列帮助用户规划从起点到终点的最优路径(即概率最大路径)，并可以显示该最优路径的各个路段的畅通或拥堵程度，以及可以显示该最优路径通行的时长等信息。
实施本申请实施例，通过根据当前驾驶状况信息生成路段当前通行能力信息；然后将该路段当前通行能力信息进行离散化后得到的观测序列输入隐马尔可夫模型，生成路况状态序列；其中，该隐马尔可夫模型包括根据统计的历史路况数据提取的路段的第一概率矩阵和第二概率矩阵，该第一概率矩阵用于指示各个路况状态之间的转移概率，该第二概率矩阵用于指示以概率的形式确定路况状态与路段通行能力信息的对应关系，避免了直接根据单路段的车流速度判定路况时很容易出现连续异常突变的现象，通过历史路况数据中统计路况状态转移概率，保证了地理空间序列上路况状态过渡的平滑性，并且一定程度地允许车流速度计算带来的误差，解决了常规的路况生成方法或路况判定方法受异常车流速度的影响，会给路况的计算或判定带来误差，造成路况不准确的技术问题，能增强系统对异常噪声的容忍度。并且解决了若通过交管部门将传感器或线圈部署在道路上，通过传感器感应道路上车流量以确定交通的拥堵情况时，工程量巨大，对道路的覆盖面窄，除了高速路或城市快速路以外，其它道路难以覆盖的技术问题。
由于本申请实施例从标注问题及概率生成模型角度出发，采用隐马尔可夫模型对已有给定的观测序列，通过不可见路况状态间的转移概率及可适应多场景的观测概率产出最优的路况状态序列，使得路况发布更合理、更符合实际情况，并且道路覆盖面广，高速路、城市快速路其他等级道路均能涉及，有效地兼顾交通事故、管制等发生时路况的扩散途径；并且方案灵活，在解决坏案例(BadCase)时可克服策略优化顾此失彼的缺点。本申请实施例通过提供准确的路况，可提供更加优质的ETA服务和路径规划，节省城市道路资源和用户时间。
为了便于更好地实施本申请实施例的上述方案，本申请实施例还对应提供了一种路况生成装置、一种路况生成设备，下面结合附图来进行详细说明：
如图6a示出的本申请实施例提供的路况生成装置的结构示意图，路况生成装置60可以包括执行上述路况生成方法的实施例中的单元。具体地，路况生成装置60可以包括：获取单元600、信息生成单元602，输出单元604，其中
获取单元600，用于获取当前驾驶状况信息；
信息生成单元602，用于针对该当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息；
输出单元604，用于输出该路况状态信息。
具体地，如图6b示出的本申请实施例提供的信息生成单元的结构示意图，信息生成单元602可以包括：通行能力生成单元6020、离散化单元6022和序列生成单元6024，其中，
通行能力生成单元6020用于根据当前驾驶状况信息生成路段当前通行能力信息；
离散化单元6022用于将该路段当前通行能力信息进行离散化处理，得到观测序列；
序列生成单元6024用于将该观测序列输入隐马尔可夫模型，输出路况状态序列；其中，该隐马尔可夫模型包括根据统计的历史路况数据提取的路段的第一概率矩阵和第二概率矩阵，该第一概率矩阵用于指示各个路况状态之间的转移概率，该第二概率矩阵用于指示以概率的形式确定路况状态与路段通行能力信息的对应关系。
该当前驾驶状况信息包括当前驾驶场景信息和驾驶者驾驶行为状态信息；
该当前驾驶场景信息包括以下至少一项：车辆定位信息、路段限速信息、交通管制信息、交通事故信息、是否红绿灯路段、是否隧道路段、 是否地铁口路段、是否地面道路；
该驾驶者驾驶行为状态信息包括以下至少一项：驾驶者驾龄信息、是否异常停车、驾驶习惯信息。
如图7示出的本申请实施例提供的通行能力生成单元6020的结构示意图，通行能力生成单元6020可以包括采集单元60200、关联单元60202和信息生成单元60204，其中，
采集单元60200用于采集道路系统上进行定位导航的车辆的定位信息；
关联单元60202用于根据车辆标识获取车辆对应的驾驶者驾驶行为状态信息，将所述定位信息和获取的所述驾驶者驾驶行为状态信息，与路网数据中的路段进行关联；
信息生成单元60204用于根据关联后的路段信息生成路段当前通行能力信息。
所述路段当前通行能力信息包括以下至少一项：
车流速度、车流量、平均通行时长、红绿灯等待周期。
具体地，路况生成装置60还可以包括获取单元、第一提取单元和第二提取单元，其中，
获取单元用于从记录了实际交通路况的真值系统中获取统计的历史路况数据；
第一提取单元用于根据该统计的历史路况数据提取各个路况状态之间的转移概率；
第二提取单元用于根据该统计的历史路况数据，以概率的形式确定路况状态与路段通行能力信息的对应关系。具体地，根据所述统计的历史路况数据，并结合多个不同的路况场景信息，以概率的形式确定路况状态与路段通行能力信息的对应关系。
进一步地，序列生成单元6024具体用于根据输入的该观测序列，初始路况状态概率分布、该第一概率矩阵和该第二概率矩阵，采用动态规划生成概率最大路径对应的路况状态序列；
输出该路况状态序列，以指示根据该路况状态序列在地图中显示该概率最大路径；该路况状态序列指示该概率最大路径中各个路段的路况信息。
需要说明的是，本申请实施例中的路况生成装置60中各模块的功能可对应参考上述各方法实施例中图1至图5任意实施例的具体实现方式，这里不再赘述。路况生成装置60可以为服务器等计算设备，包括但不限于计算机等。
再进一步地，如图8示出的本申请实施例提供的路况生成设备的结构示意图，路况生成设备80可以包括：至少一个处理器801，例如CPU，输入模块802，输出模块803，存储器804，至少一个通信总线805以及通信模块806。其中，通信总线805用于实现这些组件之间的连接通信。存储器804可以是高速RAM存储器，也可以是非易失性的存储器(non-volatile memory)，例如至少一个磁盘存储器，存储器804包括本申请实施例中的flash。在本申请一些实施例中，存储器804还可以是至少一个位于远离前述处理器801的存储系统；通信模块806用于与外部设备进行数据通信。如图8所示，作为一种计算机存储介质的存储器804中可以包括操作系统、网络通信模块、用户接口模块以及路况生成的实现程序。
在图8所示的路况生成设备80中，处理器801可以用于调用存储器804中存储的路况生成的实现程序，并执行以下操作：
可以通过通信模块806获取当前驾驶状况信息；
针对该当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息；
通过输出模块803输出该路况状态信息。
具体地，处理器801针对该当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能 力信息的对应关系，生成路况状态信息，可以包括：
根据该当前驾驶状况信息生成路段当前通行能力信息；
将该路段当前通行能力信息进行离散化处理，得到观测序列；
将该观测序列输入隐马尔可夫模型，生成路况状态序列；其中，该隐马尔可夫模型包括根据统计的历史路况数据提取的路段的第一概率矩阵和第二概率矩阵，该第一概率矩阵用于指示各个路况状态之间的转移概率，该第二概率矩阵用于指示以概率的形式确定路况状态与路段通行能力信息的对应关系。
具体地，该当前驾驶状况信息包括当前驾驶场景信息和驾驶者驾驶行为状态信息；
该当前驾驶场景信息包括以下至少一项：车辆定位信息、路段限速信息、交通管制信息、交通事故信息、是否红绿灯路段、是否隧道路段、是否地铁口路段、是否地面道路；
该驾驶者驾驶行为状态信息包括以下至少一项：驾驶者驾龄信息、是否异常停车、驾驶习惯信息。
具体地，处理器801当前驾驶场景信息包括车辆定位信息；所述根据当前驾驶状况信息生成路段当前通行能力信息，包括：
控制采集模块采集道路系统上进行定位导航的车辆的定位信息；该采集模块可以设置在路况生成设备80上，或者其他外部设备上；
根据车辆标识获取车辆对应的驾驶者驾驶行为状态信息，将该定位信息和获取的该驾驶者驾驶行为状态信息，与路网数据中的路段进行关联；
根据关联后的路段信息生成路段当前通行能力信息。
具体地，该路段当前通行能力信息包括以下至少一项：
车流速度、车流量、平均通行时长、红绿灯等待周期。
具体地，处理器801将该观测序列输入隐马尔可夫模型，生成路况状态序列之前，还可以执行：
从记录了实际交通路况的真值系统中获取统计的历史路况数据；
根据该统计的历史路况数据提取各个路况状态之间的转移概率；
根据该统计的历史路况数据，以概率的形式确定路况状态与路段通行能力信息的对应关系。
具体地，处理器801根据该统计的历史路况数据，以概率的形式确定路况状态与路段通行能力信息的对应关系，包括：
根据该统计的历史路况数据，并结合多个不同的路况场景信息，以概率的形式确定路况状态与路段通行能力信息的对应关系。
具体地，处理器801将该观测序列输入隐马尔可夫模型，生成路况状态序列，包括：
根据输入的该观测序列，初始路况状态概率分布、该第一概率矩阵和该第二概率矩阵，采用动态规划生成概率最大路径对应的路况状态序列；
处理器801通过输出模块803输出该路况状态信息包括：输出该路况状态序列，以指示根据该路况状态序列在地图中显示该概率最大路径；该路况状态序列指示该概率最大路径中各个路段的路况信息。
具体地，路况生成设备80可以通过通信模块806将该路况状态序列发送给终端，以指示根据该路况状态序列在地图中显示该概率最大路径；该路况状态序列指示该概率最大路径中各个路段的路况信息。
需要说明的是，本申请实施例中的路况生成设备80中各模块的功能可对应参考上述各方法实施例中图1至图5任意实施例的具体实现方式，这里不再赘述。路况生成设备80可以为服务器等计算设备，包括但不限于计算机等。
实施本申请实施例，通过根据当前驾驶状况信息生成路段当前通行能力信息；然后将该路段当前通行能力信息进行离散化后得到的观测序列输入隐马尔可夫模型，输出路况状态序列；其中，该隐马尔可夫模型包括根据统计的历史路况数据提取的路段的第一概率矩阵和第二概率矩阵，该第一概率矩阵用于指示各个路况状态之间的转移概率，该第二概率矩阵用于指示以概率的形式确定路况状态与路段通行能力信息的 对应关系，避免了直接根据单路段的车流速度判定路况时很容易出现连续异常突变的现象，通过历史路况数据中统计路况状态转移概率，保证了地理空间序列上路况状态过渡的平滑性，并且一定程度地允许车流速度计算带来的误差，解决了常规的路况生成方法或路况判定方法受异常车流速度的影响，会给路况的计算或判定带来误差，造成路况不准确的技术问题，能增强系统对异常噪声的容忍度。并且解决了若通过交管部门将传感器或线圈部署在道路上，通过传感器感应道路上车流量以确定交通的拥堵情况时，工程量巨大，对道路的覆盖面窄，除了高速路或城市快速路以外，其它道路难以覆盖的技术问题。
由于本申请实施例从标注问题及概率生成模型角度出发，采用隐马尔可夫模型对已有给定的观测序列，通过不可见路况状态间的转移概率及可适应多场景的观测概率产出最优的路况状态序列，使得路况发布更合理、更符合实际情况，并且道路覆盖面广，高速路、城市快速路其他等级道路均能涉及，有效地兼顾交通事故、管制等发生时路况的扩散途径；并且方案灵活，在解决坏案例(BadCase)时可克服策略优化顾此失彼的缺点。本申请实施例通过提供准确的路况，可提供更加优质的ETA服务和路径规划，节省城市道路资源和用户时间。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等。
以上所揭露的仅为本申请较佳实施例而已，当然不能以此来限定本申请之权利范围，因此依本申请权利要求所作的等同变化，仍属本申请所涵盖的范围。

Claims (11)

  1. 一种路况生成方法，由计算设备执行，包括：
    获取当前驾驶状况信息；
    针对所述当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息；
    输出所述路况状态信息。
  2. 如权利要求1所述的方法，所述针对所述当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息，包括：
    根据所述当前驾驶状况信息生成路段当前通行能力信息；
    将所述路段当前通行能力信息进行离散化处理，得到观测序列；
    将所述观测序列输入隐马尔可夫模型，生成路况状态序列；其中，所述隐马尔可夫模型包括根据统计的历史路况数据提取的路段的第一概率矩阵和第二概率矩阵，所述第一概率矩阵用于指示各个路况状态之间的转移概率，所述第二概率矩阵用于指示以概率的形式确定路况状态与路段通行能力信息的对应关系。
  3. 如权利要求2所述的方法，所述当前驾驶状况信息包括当前驾驶场景信息和驾驶者驾驶行为状态信息；
    所述当前驾驶场景信息包括以下至少一项：车辆定位信息、路段限速信息、交通管制信息、交通事故信息、是否红绿灯路段、是否隧道路段、是否地铁口路段、是否地面道路；
    所述驾驶者驾驶行为状态信息包括以下至少一项：驾驶者驾龄信息、是否异常停车、驾驶习惯信息。
  4. 如权利要求3所述的方法，所述当前驾驶场景信息包括车辆定 位信息；所述根据当前驾驶状况信息生成路段当前通行能力信息，包括：
    采集道路系统上进行定位导航的车辆的定位信息；
    根据车辆标识获取车辆对应的驾驶者驾驶行为状态信息，将所述定位信息和获取的所述驾驶者驾驶行为状态信息，与路网数据中的路段进行关联；
    根据关联后的路段信息生成路段当前通行能力信息。
  5. 如权利要求2-4任一项所述的方法，所述路段当前通行能力信息包括以下至少一项：
    车流速度、车流量、平均通行时长、红绿灯等待周期。
  6. 如权利要求2所述的方法，所述将所述观测序列输入隐马尔可夫模型，生成路况状态序列之前，还包括：
    从记录了实际交通路况的真值系统中获取统计的历史路况数据；
    根据所述统计的历史路况数据提取各个路况状态之间的转移概率；
    根据所述统计的历史路况数据，以概率的形式确定路况状态与路段通行能力信息的对应关系。
  7. 如权利要求6所述的方法，所述根据所述统计的历史路况数据，以概率的形式确定路况状态与路段通行能力信息的对应关系，包括：
    根据所述统计的历史路况数据，并结合多个不同的路况场景信息，以概率的形式确定路况状态与路段通行能力信息的对应关系。
  8. 如权利要求2所述的方法，所述将所述观测序列输入隐马尔可夫模型，生成路况状态序列，包括：
    根据输入的所述观测序列，初始路况状态概率分布、所述第一概率矩阵和所述第二概率矩阵，采用动态规划生成概率最大路径对应的路况状态序列；
    所述输出所述路况状态信息包括：输出所述路况状态序列，以指示根据所述路况状态序列在地图中显示所述概率最大路径；所述路况状态序列指示所述概率最大路径中各个路段的路况信息。
  9. 一种路况生成装置，包括：
    获取单元，用于获取当前驾驶状况信息；
    信息生成单元，用于针对该当前驾驶状况信息，根据从历史路况数据中提取的各个路况状态之间的转移信息，以及路况状态与路段通行能力信息的对应关系，生成路况状态信息；
    输出单元，用于输出该路况状态信息。
  10. 一种路况生成设备，包括处理器、输入设备、输出设备和存储器，所述处理器、输入设备、输出设备和存储器相互连接，其中，所述存储器用于存储程序代码，所述处理器被配置用于调用所述程序代码，执行如权利要求1-8任一项所述的方法。
  11. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行如权利要求1-8任一项所述的方法。
PCT/CN2018/112322 2017-12-13 2018-10-29 路况生成方法、装置、设备和存储介质 WO2019114432A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/659,138 US11423774B2 (en) 2017-12-13 2019-10-21 Road condition generation method, apparatus and device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711335748.7 2017-12-13
CN201711335748.7A CN109919347B (zh) 2017-12-13 2017-12-13 路况生成方法、相关装置和设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/659,138 Continuation US11423774B2 (en) 2017-12-13 2019-10-21 Road condition generation method, apparatus and device, and storage medium

Publications (1)

Publication Number Publication Date
WO2019114432A1 true WO2019114432A1 (zh) 2019-06-20

Family

ID=66820754

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/112322 WO2019114432A1 (zh) 2017-12-13 2018-10-29 路况生成方法、装置、设备和存储介质

Country Status (3)

Country Link
US (1) US11423774B2 (zh)
CN (1) CN109919347B (zh)
WO (1) WO2019114432A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110634295A (zh) * 2019-09-28 2019-12-31 安徽百诚慧通科技有限公司 一种利用优化模型计算道路最佳通行能力的方法
CN112598165A (zh) * 2020-12-11 2021-04-02 湖南大学 基于私家车数据的城市功能区转移流量预测方法及装置
CN113011712A (zh) * 2021-02-25 2021-06-22 长安大学 基于欧氏距离和信息熵的驾驶员驾驶稳定性评估方法
CN114493191A (zh) * 2022-01-07 2022-05-13 东南大学 一种基于网约车数据的驾驶行为建模分析方法
CN116092056A (zh) * 2023-03-06 2023-05-09 安徽蔚来智驾科技有限公司 目标识别方法、车辆控制方法、设备、介质及车辆

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11663514B1 (en) * 2019-08-30 2023-05-30 Apple Inc. Multimodal input processing system
CN112652161B (zh) * 2019-10-12 2023-01-06 阿里巴巴集团控股有限公司 一种车流路径分布信息的处理方法、装置、及电子设备
CN110895882B (zh) * 2019-12-24 2021-11-12 腾讯科技（深圳）有限公司 公路通行能力确定方法及装置
CN111402583B (zh) * 2020-03-19 2022-06-21 阿里巴巴集团控股有限公司 一种交通事件的感知方法、设备及存储介质
CN111597282B (zh) * 2020-04-24 2024-03-19 汉海信息技术(上海)有限公司 挖掘路网数据的方法、装置及电子设备
CN111489553B (zh) * 2020-04-26 2022-02-25 百度在线网络技术（北京）有限公司 一种路线规划方法、装置、设备和计算机存储介质
CN111998866B (zh) * 2020-08-25 2022-08-30 北京百度网讯科技有限公司 为信息点设置车辆入口位置的方法、装置、设备和介质
CN112307090A (zh) * 2020-11-03 2021-02-02 中铁隆工程集团有限公司 基于隧道安全数据的检测方法及系统
CN112398932B (zh) * 2020-11-04 2023-10-24 腾讯科技（深圳）有限公司 获取路况信息的方法、装置、设备及计算机可读存储介质
CN114639233B (zh) * 2020-12-15 2024-02-02 腾讯科技（深圳）有限公司 一种拥堵状态预测方法、装置、电子设备及存储介质
CN112966860B (zh) * 2021-02-23 2022-09-16 武汉育知联信息科技有限公司 一种基于附预链式数据分析预测系统
CN113221975B (zh) * 2021-04-26 2023-07-11 中国科学技术大学先进技术研究院 基于改进马尔可夫分析法的工况构建方法及存储介质
CN115482020A (zh) * 2021-05-31 2022-12-16 英业达科技有限公司 车行纪录路况情资收集反馈之奖励系统及其方法
CN113888872B (zh) * 2021-10-20 2023-07-28 沈阳世纪高通科技有限公司 一种基于浮动车数据计算红绿灯时长的方法
CN116758744A (zh) * 2023-06-21 2023-09-15 山东宜鑫致远信息科技有限公司 基于人工智能的智慧城市运维管理方法、系统及存储介质

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101118693A (zh) * 2006-08-01 2008-02-06 环达电脑(上海)有限公司 路况提示系统以及方法
CN103186986A (zh) * 2011-12-31 2013-07-03 高德软件有限公司 一种用于终端上显示路况的方法、装置及设备

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7813870B2 (en) * 2006-03-03 2010-10-12 Inrix, Inc. Dynamic time series prediction of future traffic conditions
CN103700259B (zh) 2013-12-13 2016-08-17 广东车联网信息科技服务有限公司 实时交通路况判别方法
CN103745106A (zh) * 2014-01-10 2014-04-23 浙江银江研究院有限公司 一种短时交通流预测方法
CN104835319B (zh) * 2015-04-07 2017-02-22 同济大学 一种高等级道路瓶颈区入匝道车辆汇入行为估计方法
CN106652441A (zh) * 2015-11-02 2017-05-10 杭州师范大学 一种基于时空数据的城市道路交通状态预测方法
CN106855878B (zh) * 2016-11-17 2020-03-03 北京京东尚科信息技术有限公司 基于电子地图的历史行车轨迹显示方法和装置

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101118693A (zh) * 2006-08-01 2008-02-06 环达电脑(上海)有限公司 路况提示系统以及方法
CN103186986A (zh) * 2011-12-31 2013-07-03 高德软件有限公司 一种用于终端上显示路况的方法、装置及设备

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110634295A (zh) * 2019-09-28 2019-12-31 安徽百诚慧通科技有限公司 一种利用优化模型计算道路最佳通行能力的方法
CN112598165A (zh) * 2020-12-11 2021-04-02 湖南大学 基于私家车数据的城市功能区转移流量预测方法及装置
CN112598165B (zh) * 2020-12-11 2023-09-26 湖南大学 基于私家车数据的城市功能区转移流量预测方法及装置
CN113011712A (zh) * 2021-02-25 2021-06-22 长安大学 基于欧氏距离和信息熵的驾驶员驾驶稳定性评估方法
CN113011712B (zh) * 2021-02-25 2024-01-19 长安大学 基于欧氏距离和信息熵的驾驶员驾驶稳定性评估方法
CN114493191A (zh) * 2022-01-07 2022-05-13 东南大学 一种基于网约车数据的驾驶行为建模分析方法
CN114493191B (zh) * 2022-01-07 2024-04-30 东南大学 一种基于网约车数据的驾驶行为建模分析方法
CN116092056A (zh) * 2023-03-06 2023-05-09 安徽蔚来智驾科技有限公司 目标识别方法、车辆控制方法、设备、介质及车辆
CN116092056B (zh) * 2023-03-06 2023-07-07 安徽蔚来智驾科技有限公司 目标识别方法、车辆控制方法、设备、介质及车辆

Also Published As

Publication number Publication date
CN109919347B (zh) 2022-01-18
US20200051428A1 (en) 2020-02-13
CN109919347A (zh) 2019-06-21
US11423774B2 (en) 2022-08-23

Similar Documents

Publication Publication Date Title
WO2019114432A1 (zh) 路况生成方法、装置、设备和存储介质
CA3011825C (en) Simplifying gps data for map building and distance calculation
US10672264B2 (en) Predictive incident aggregation
WO2019085807A1 (zh) 一种路况信息获取方法及其设备、存储介质
Goodall et al. Microscopic estimation of freeway vehicle positions from the behavior of connected vehicles
US20160170414A1 (en) Learning Signs From Vehicle Probes
US10198941B2 (en) Method and apparatus for evaluating traffic approaching a junction at a lane level
US11270578B2 (en) Method, apparatus, and system for detecting road closures based on probe activity
Ganti et al. Inferring human mobility patterns from taxicab location traces
US10147315B2 (en) Method and apparatus for determining split lane traffic conditions utilizing both multimedia data and probe data
US11393334B2 (en) Method, apparatus, and computer program product for detecting changes in road traffic condition
EP3671126A1 (en) Method, apparatus, and system for providing road closure graph inconsistency resolution
Fu et al. Constructing spatiotemporal driving volatility profiles for connected and automated vehicles in existing highway networks
Bharadwaj et al. Deriving capacity and level-of-service thresholds for intercity expressways in India
AlRajie Investigation of using microscopic traffic simulation tools to predict traffic conflicts between right-turning vehicles and through cyclists at signalized intersections
TWI591493B (zh) Method of Estimating Traffic Speed ​​Using Positioning Trajectory Stop and Traveling Model
US20230349717A1 (en) Electronic map correction method, navigation information setting method, navigation method, and apparatus
Tian et al. Identifying residential and workplace locations from transit smart card data
Ghods et al. Development and evaluation of a microscopic overtaking gap acceptance model for two-lane highways
JP2018180906A (ja) 混雑予測プログラム、混雑予測装置、及び混雑予測方法
CN113570870A (zh) 分布式路口平均延误估计方法、装置、设备及存储介质
Guido et al. A calibration framework of car following models for safety analysis based on vehicle tracking data from smartphone probes
CN113393011A (zh) 预测限速信息的方法、装置、计算机设备和介质
WO2018107611A1 (zh) 城市道路的运行速度的处理方法、装置、设备及非易失性计算机存储介质
US20240104121A1 (en) Method, apparatus, and computer program product for map data conflation

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: 18888166

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18888166

Country of ref document: EP

Kind code of ref document: A1