WO2020191701A1 - 一种路况预测方法、装置、设备和计算机存储介质 - Google Patents

一种路况预测方法、装置、设备和计算机存储介质 Download PDF

Info

Publication number
WO2020191701A1
WO2020191701A1 PCT/CN2019/080043 CN2019080043W WO2020191701A1 WO 2020191701 A1 WO2020191701 A1 WO 2020191701A1 CN 2019080043 W CN2019080043 W CN 2019080043W WO 2020191701 A1 WO2020191701 A1 WO 2020191701A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
user
time
road section
currently processed
Prior art date
Application number
PCT/CN2019/080043
Other languages
English (en)
French (fr)
Inventor
黄际洲
张昊
Original Assignee
北京百度网讯科技有限公司
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 北京百度网讯科技有限公司 filed Critical 北京百度网讯科技有限公司
Priority to KR1020207029830A priority Critical patent/KR102457803B1/ko
Priority to JP2020556771A priority patent/JP7106794B2/ja
Priority to US17/042,834 priority patent/US11823574B2/en
Priority to EP19920910.7A priority patent/EP3767605A4/en
Priority to PCT/CN2019/080043 priority patent/WO2020191701A1/zh
Publication of WO2020191701A1 publication Critical patent/WO2020191701A1/zh

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
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of 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
    • G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
    • G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
    • G08G1/096844—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route where the complete route is dynamically recomputed based on new data
    • 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
    • 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
    • G01C21/3626—Details of the output of route guidance instructions
    • G01C21/3641—Personalized guidance, e.g. limited guidance on previously travelled routes
    • 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
    • G08G1/0125—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
    • G08G1/09—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
    • 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 present invention relates to the field of computer application technology, in particular to a road condition prediction method, device, equipment and computer storage medium.
  • Existing navigation tools are all provided based on road condition information at the current moment (ie, the user's query moment). However, it is often a long time process from the moment of inquiry to the process of traveling, and the road conditions change very frequently due to the fast driving speed of the vehicle, and the road conditions may change greatly during this time. Therefore, the existing navigation tools provide users with inaccurate road condition information for each section of the navigation path, resulting in inaccurate estimated arrival time and unable to help users make correct decisions.
  • the present invention provides a road condition prediction method, device, equipment and computer storage medium, so as to provide more accurate road condition information.
  • the present invention provides a road condition prediction method, which includes:
  • the travel time of the user on the currently processed road segment is estimated.
  • the determining the moment when the user arrives at the currently processed road section includes:
  • the user's departure time is taken as the time when the user arrives at the currently processed road segment
  • the time when the user arrives at the previous road section and the estimated travel time of the user on the previous road section are used to determine the time when the user arrives at the currently processed road section.
  • estimating the road condition information of the currently processed road section at the determined moment includes:
  • the currently processed road section information, the duration, and the characteristics of external factors are input into a pre-trained road condition model to obtain road condition information of the currently processed road section at the determined moment.
  • the road condition model is obtained by pre-training in the following manner:
  • the road condition information corresponding to each historical time point of the road segment is used as the output of the classification model, and the classification model is trained to obtain the road condition model.
  • estimating the travel time of the user on the currently processed road segment includes:
  • the general features and the personalized driving features are input into a pre-trained regression model to obtain the travel time of the user on the currently processed road section.
  • the regression model is obtained by pre-training in the following manner:
  • the general characteristics of different users on each road segment and the personalized driving characteristics of the user through each road segment are used as input, and the travel time of the user through each road segment is used as the output to train the regression model.
  • the general feature further includes at least one of the following:
  • Section length road grade, number of traffic lights, waiting time for traffic lights, characteristics of external factors.
  • the external factor characteristics include at least one of the following:
  • the personalized driving feature includes at least one of the following:
  • the historical number of passes of the user on the currently processed road segment The historical number of passes of the user on the currently processed road segment, the vehicle information of the user, and the variance of the historical driving speed of the user on the currently processed road segment and the public driving speed.
  • the method further includes:
  • the method further includes:
  • the mapping the estimated road condition information of each road section and each time, and dynamically displaying the mapping result on the interface includes:
  • the method further includes:
  • the vehicle position and road condition information corresponding to the time axis position dragged by the user is displayed on the interface.
  • the present invention also provides a road condition prediction device, which includes:
  • the road section determining unit is used to determine at least two consecutive road sections obtained by dividing the navigation path;
  • the prediction processing unit is configured to execute the following processing for each road segment one by one from the starting point of the navigation path until the end of the navigation path:
  • the travel time of the user on the currently processed road segment is estimated.
  • the prediction processing unit includes:
  • the arrival time determination subunit is used to use the user’s departure time as the time when the user arrives at the currently processed road section for the road segment starting from the starting point of the navigation route; for other road segments, use the user’s arrival time and estimate of the previous road segment
  • the obtained travel time of the user on the previous road segment determines the time when the user arrives at the currently processed road segment.
  • the prediction processing unit includes:
  • the road condition estimation subunit is used to determine the length of time between the time when the user arrives at the currently processed road segment and the current time; input the currently processed road segment information, the duration and the characteristics of external factors into the pre-trained road condition model to obtain the Road condition information of the currently processed road section at the determined moment.
  • the prediction processing unit further includes:
  • the first training subunit is used to pre-train the road condition model in the following manner:
  • the road condition information corresponding to each historical time point of the road segment is used as the output of the classification model, and the classification model is trained to obtain the road condition model.
  • the prediction processing unit includes:
  • the travel time estimation subunit is used to determine the general features of the currently processed road section, and the general features include the road condition information; from the user’s historical driving record, extract the user’s current process
  • the personalized driving characteristics of the road section; the general characteristics and the personalized driving characteristics are input into a pre-trained regression model to obtain the travel time of the user on the currently processed road section.
  • the prediction processing unit further includes:
  • the second training subunit is used to pre-train the regression model in the following manner:
  • the general characteristics of different users on each road segment and the personalized driving characteristics of the user through each road segment are used as input, and the travel time of the user through each road segment is used as the output to train the regression model.
  • the device further includes: a terminal time determination unit or a transit time determination unit;
  • the end time determining unit is configured to determine the end time when the user reaches the navigation path
  • the transit time determination unit is configured to determine the estimated transit time of the user on the navigation path.
  • the device further includes:
  • the dynamic display unit is used to map the estimated road condition information of each road section and each time, and dynamically display the mapping result on the interface.
  • the present invention provides a device, which includes:
  • One or more processors are One or more processors;
  • Storage device for storing one or more programs
  • the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.
  • the present invention provides a storage medium containing computer-executable instructions, which are used to execute the above-mentioned method when executed by a computer processor.
  • the present invention calculates the time when the user arrives at each road section one by one from the start of the navigation path and predicts the road conditions of the road section at that time, and determines the travel time of the user on each road section based on the predicted road conditions until the end of the navigation path.
  • This kind of road condition prediction method can estimate the road condition at the time when the user arrives at each road section in the future, and can provide more accurate road condition information compared with the road condition estimation method based on the user's query time.
  • Figure 1 is a flowchart of a main method provided by an embodiment of the present invention.
  • Figure 2 is a flow chart of the specific implementation of step 102 in Figure 1;
  • FIG. 3 is a schematic diagram of the principle of an implementation process provided by an embodiment of the present invention.
  • 4a, 4b, and 4c are exemplary diagrams of dynamic display of road conditions provided by an embodiment of the present invention.
  • Figure 5 is a structural diagram of an apparatus provided by an embodiment of the present invention.
  • Figure 6 shows a block diagram of an exemplary computer system/server suitable for implementing embodiments of the present invention.
  • the core idea of the present invention is to calculate the time when the user arrives at each road section one by one starting from the start of the navigation path and predict the road conditions of the road section at that time with the road section as the unit, and determine the travel time of the user on each road section based on the predicted road conditions until the navigation path end.
  • the present invention will be described in detail below in conjunction with embodiments.
  • Fig. 1 is a flowchart of the main method provided by an embodiment of the present invention. As shown in Fig. 1, the method mainly includes the following steps:
  • At least two consecutive road sections obtained by dividing the navigation path are determined.
  • the method provided in the embodiment of the present invention may be executed for each navigation path obtained by matching to perform road condition prediction, or the method provided in the embodiment of the present invention may be performed on only a few selected navigation paths.
  • the navigation application matches the map database to obtain 10 navigation paths, and the method provided in the embodiment of the present invention can be executed for the 10 navigation paths to predict road conditions.
  • the method provided in the embodiment of the present invention can be executed for the three navigation paths to perform road condition prediction.
  • the method provided in the embodiment of the present invention may be executed to predict the road condition only for the navigation path selected by the user. The present invention does not impose restrictions on this.
  • a navigation path can be divided to obtain at least two consecutive road sections.
  • the so-called road section refers to a section of road that does not contain a fork, and is the smallest unit of the road network.
  • the information of the continuous road sections obtained by dividing the navigation route can be obtained from the road network database. The present invention does not limit this, and only needs to obtain and use the result obtained by the division.
  • the following processing is performed for each successive road segment one by one until the end of the navigation path: determine the time when the user reaches the currently processed road segment; estimate the road condition information of the currently processed road segment at the determined time ; Based on the road condition information of the currently processed road section at the determined moment, the travel time of the user in the currently processed road section is estimated.
  • step 102 may be as shown in FIG. 2, and specifically includes the following steps:
  • the road segment starting from the starting point of the navigation route is taken as the road segment currently being processed, and the departure time of the user is taken as the time when the user arrives at the current processing road segment.
  • the road condition information of the currently processed road section at the determined moment is estimated.
  • the so-called road conditions can be understood as the congestion condition of the road section, which can be reflected in the degree of congestion.
  • the specific representation can be in multiple forms, for example, it can be represented in the form of percentage, congestion level, etc., or can be represented in the form of classification such as unblocked, slow, congested, and extremely congested.
  • the road condition model based on the classification model is used.
  • Each historical time point may adopt a preset time unit, for example, in minutes. It is also possible to obtain the road section where each vehicle identifier is located at each historical time point, that is, which vehicles are on each road section at each historical time point.
  • the road condition information corresponding to the road segment at each historical time point is determined as the output of the classification model.
  • the characteristics of external factors may include, but are not limited to, time characteristics, week characteristics, seasonal characteristics, and weather characteristics.
  • week characteristics can be used such as with For continuous expression, m is the week. For example, Monday corresponds to m is 0, Tuesday corresponds to m is 1, and so on.
  • Weather characteristics can be classified into categories such as sunny, cloudy, light rain, heavy rain, light snow, heavy snow, severe, etc., and expressed in the form of one-hot (one-hot code). For example, when it is sunny, the weather feature is represented as 1,0,0,0,0,0. When it is cloudy, the weather feature is expressed as 0,1,0,0,0,0,0.
  • Seasonal characteristics can be divided into four categories: spring, summer, autumn and winter, and can also be expressed in one-hot form. For example, in spring, the seasonal characteristics are expressed as 1,0,0,0. In summer, the seasonal characteristics are expressed as 0,1,0,0.
  • the classification model is trained to obtain the road condition model.
  • the road condition model is composed of a module that performs the above-mentioned feature extraction and the above-mentioned classification model.
  • the classification model can use a classification algorithm such as KNN (k-Nearest Neighbor).
  • KNN k-Nearest Neighbor
  • the above model training process is an offline process.
  • the road condition estimation of the road section based on the road condition model obtained by the above training is an online process.
  • the obtained road condition model obtains the road condition information of the currently processed road section at the moment when the currently processed road section is reached.
  • the travel time of the user on the currently processed road section is estimated.
  • the general characteristics of the currently processed road section may be determined first, where the general characteristics may include the road condition information of the road section (that is, the road condition information predicted in step 202). It may further include, but is not limited to, characteristics such as road section length, road grade, number of traffic lights, waiting time for traffic lights, and external factors. Wherein, the external factor characteristics may include at least one of time characteristics, week characteristics, seasonal characteristics, and weather characteristics.
  • the personalized characteristics of the user may be further combined when the travel time is estimated. Because the user's personalized characteristics are very obvious in the length of the road section, the driving habits of different users on the same road section may cause a difference of more than 20% in the effect. Therefore, from the user's historical driving records, the personalized driving characteristics of the road section currently processed by the user can be extracted.
  • the personalized driving feature may include at least one of the following: the user's historical pass times on the currently processed road segment, the user's vehicle information, and the variance between the user's historical driving speed on the currently processed road segment and the public driving speed.
  • the extracted general features and personalized driving features are input into the pre-trained regression model to obtain the travel time of the user on the road section currently being processed.
  • the travel time of the user in the currently processed road segment refers to the estimated time required for the user to pass the currently processed road segment, that is, the time from the start point of the currently processed road segment to the end point.
  • the general characteristics of different users on each road segment, the personalized driving characteristics of the user through each road segment, and the travel time of the user through each road segment are used as training samples; the general characteristics of different users on each road segment and the user’s personalized driving through each road segment
  • the feature is used as input, and the travel time of the user through each road section is used as output to train the regression model.
  • the general features and personalized driving features used when training the regression model have the same dimensions as the general features and personalized driving features used when using the training model to estimate travel time. I won't repeat them here.
  • step 204 it is judged whether the currently processed road section has reached the end of the navigation route, and if so, the process of step 102 is ended. Otherwise, go to 205.
  • the time when the user arrives at the currently processed road section and the travel time of the user on the currently processed road section are used to determine the time when the user arrives at the next road section.
  • next road section is regarded as the road section currently being processed, and the process goes to step 202.
  • the principle of the foregoing implementation process can be as shown in FIG. 3, from the navigation path is divided into various road sections, starting from the starting point for each road section, the process shown in FIG. 2 is executed.
  • road section i the time t i when the user arrives at road section i is used to determine the length of time t i from the current time as the traceback time, and the road section information, traceback time and external factor characteristics are input into the road condition model to obtain road condition information for road section i.
  • Use t i and ⁇ t i to obtain the time t i+1 when the user arrives at the next segment i+1 .
  • the above process is performed in turn for each road section until the end point.
  • the time when the user reaches the end of the navigation path is determined.
  • This step can use the following two methods:
  • the first method using the user's departure time and the estimated travel time of each road segment to determine the user's arrival time of the navigation route.
  • the second way using the determined time when the user arrives at the last leg and the estimated travel time of the user on the last leg to determine the time when the user arrives at the end of the navigation path.
  • the end point of the navigation path can be used to provide the user with the estimated time of arrival of the navigation path. For example, on the navigation interface, the user is provided with "the navigation path is expected to reach the end point at 10:26:00".
  • the estimated travel time of the user on the entire navigation path can also be determined, that is, the travel time of each road section is accumulated and provided to the user. For example, on the navigation interface, the user is provided with "the navigation path is estimated to take 22 minutes".
  • the estimated time of reaching the end of the navigation path or the user's estimated travel time on the entire navigation path can be used by the system to select the navigation path for feedback to the user, or displayed on the navigation interface for the user to select the navigation path.
  • the system can select three navigation paths with the shortest expected travel time to feed back to the user on the navigation interface. Further, the estimated travel time of the three navigation paths will also be displayed on the navigation interface, so that the user can select one navigation path from them as the final navigation path.
  • the estimated road condition information of each road section and each time are mapped, and the mapping result is dynamically displayed on the navigation interface.
  • the display method in the prior art can be used, for example, the road condition information of each road section in the navigation result is distinguished by different colors, which is often static.
  • the method shown in 104 can be used to dynamically display the road conditions of each road section.
  • the estimated road condition information of each road section can be mapped on the time axis, and the time-varying vehicle position and road condition information can be dynamically displayed on the navigation interface.
  • Figure 4a is an example diagram of an interface for starting to play. When starting to play, the vehicle position is at the starting point, and the travel time of the user is indicated on the time axis (playing progress bar).
  • Figure 4b is an example of the interface during playback.
  • the vehicle position on the interface changes in the corresponding road section according to the time change, and uses different colors to display the road condition information of the road section at the current moment.
  • the time axis (playing progress bar) also follows the instructions The corresponding moment.
  • Figure 4c is an example diagram of the interface where the playback ends.
  • the vehicle position on the interface is at the end point, and the time when the user reaches the end point is indicated on the time axis (playing progress bar).
  • the above-mentioned entire playback process can be executed based on user triggers. For example, after the user selects one of the navigation paths or clicks the play button, a dynamic process with a length of 2 to 5 seconds is automatically played. It can also automatically play a dynamic process with a length of 2 to 5 seconds for the navigation path displayed by default.
  • the user can also manually drag on the time axis (playing progress bar) to observe the vehicle position at a specified time and the road conditions at that time. That is, the user's drag operation on the time axis is acquired, and the vehicle position and road condition information corresponding to the time axis position dragged by the user is displayed on the interface.
  • the above is a detailed description of the method provided by the present invention, and the following is a detailed description of the road condition prediction device provided by the embodiment of the present invention.
  • the road condition prediction device is used to perform the operations in the foregoing method embodiment.
  • the device may be located in the application of the local terminal, or may also be a functional unit such as a plug-in or a software development kit (SDK) located in the application of the local terminal, or may also be located on the server side. This is not particularly limited.
  • FIG. 5 is a structural diagram of an apparatus provided by an embodiment of the present invention.
  • the apparatus may include: a road section determination unit 00 and a prediction processing unit 10, and may further include an end time determination unit 20, a transit time determination unit 30, At least one of the dynamic display units 40.
  • the above units are included as an example.
  • the road section determination unit 00 is responsible for determining at least two consecutive road sections obtained by dividing the navigation path.
  • a navigation path can be divided to obtain at least two consecutive road sections.
  • the information of the continuous road sections obtained by dividing the navigation route can be obtained from the road network database, and the present invention does not impose restrictions on this, and the road section determining unit 00 only needs to obtain and use the result obtained by the division.
  • the prediction processing unit 10 is responsible for executing the following processing for each road segment one by one from the starting point of the navigation path to the end of the navigation path: determining the time when the user reaches the currently processed road segment; estimating the road condition information of the currently processed road segment at the determined time; Based on the road condition information of the currently processed road segment at the determined moment, the travel time of the user on the currently processed road segment is estimated.
  • the prediction processing unit 10 may include: an arrival time determination subunit 11, a road condition estimation subunit 12, a first training subunit 13, a transit time estimation subunit 14, and a second training subunit 15.
  • the arrival time determining subunit 11 is responsible for determining the time when the user arrives at the currently processed road section. Specifically, for the road section starting from the starting point of the navigation route, the user’s departure time can be taken as the time when the user arrives at the currently processed road section; for other road sections, the time when the user arrives at the previous road section and the estimated user’s previous time The travel time of the road section determines the time when the user arrives at the road section currently being processed.
  • the road condition estimation subunit 12 is responsible for determining the distance between the time when the user arrives at the currently processed road section and the current time; the currently processed road section information, duration, and external factor characteristics are input into the pre-trained road condition model, and the current road section is determined Traffic information at the moment.
  • the first training subunit 13 is responsible for pre-training the road condition model in the following manner:
  • the road condition model includes a module for performing extraction of the above-mentioned features and the above-mentioned classification model.
  • the characteristics of external factors may include, but are not limited to, time characteristics, week characteristics, seasonal characteristics, and weather characteristics.
  • time characteristics may include, but are not limited to, time characteristics, week characteristics, seasonal characteristics, and weather characteristics.
  • the classification model can use a classification algorithm such as KNN (k-Nearest Neighbor).
  • the travel time estimation subunit 14 is responsible for determining the general features of the currently processed road section, the general features including road condition information; extracting the user’s personalized driving characteristics of the road section currently being processed from the user’s historical driving records; and personalizing the general features
  • the driving feature is input to the regression model obtained by pre-training to obtain the travel time of the user on the road section currently being processed.
  • the second training subunit 15 pre-trains the regression model in the following manner:
  • the general characteristics of different users on each road segment and the personalized driving characteristics of the user through each road segment are used as input, and the travel time of the user through each road segment is used as the output to train the regression model.
  • the aforementioned general features may include the road condition information of the road section (that is, the road condition information predicted by the road condition estimation subunit 12). It may further include, but is not limited to, characteristics such as road section length, road grade, number of traffic lights, waiting time for traffic lights, and external factors. Wherein, the external factor characteristics may include at least one of time characteristics, week characteristics, seasonal characteristics, and weather characteristics.
  • the personalized driving feature may include at least one of the following: the user's historical number of passes on the currently processed road segment, the user's vehicle information, and the variance between the user's historical driving speed on the currently processed road segment and the public driving speed.
  • the end time determining unit 20 is responsible for determining the end time when the user reaches the navigation route. Specifically, the following two methods can be used:
  • the first method using the user's departure time and the estimated travel time of each road segment to determine the user's arrival time of the navigation route.
  • the second way using the determined time when the user arrives at the last leg and the estimated travel time of the user on the last leg to determine the time when the user arrives at the end of the navigation path.
  • the transit time determining unit 30 is responsible for determining the estimated transit time of the user on the navigation path. Specifically, the estimated travel time of the user on the entire navigation path can be determined, that is, the travel time of each road section is accumulated and provided to the user.
  • the dynamic display unit 40 is responsible for mapping the estimated road condition information of each road section and each time, and dynamically displaying the mapping result on the interface. Specifically, the estimated road condition information of each road section can be mapped on the time axis, and the time-varying vehicle position and road condition information can be dynamically displayed on the navigation interface.
  • the user can also manually drag on the time axis (playing progress bar) to observe the vehicle position at the specified time and the road conditions at that time. That is, the dynamic display unit 40 acquires the user's drag operation on the time axis, and displays the vehicle position and road condition information corresponding to the time axis position dragged by the user on the interface.
  • the display can also be combined with some other designs. For example, during the playback process, different colors show the predicted road conditions of the road section the user is currently or about to arrive, and the road conditions of the road section the user walks will be set to gray.
  • Figure 6 shows a block diagram of an exemplary computer system/server 012 suitable for implementing embodiments of the present invention.
  • the computer system/server 012 shown in FIG. 6 is only an example, and should not bring any limitation to the function and application scope of the embodiment of the present invention.
  • the computer system/server 012 is represented in the form of a general-purpose computing device.
  • the components of the computer system/server 012 may include, but are not limited to: one or more processors or processing units 016, a system memory 028, and a bus 018 connecting different system components (including the system memory 028 and the processing unit 016).
  • the bus 018 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any bus structure among multiple bus structures.
  • these architectures include but are not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and peripheral component interconnection ( PCI) bus.
  • ISA industry standard architecture
  • MAC microchannel architecture
  • VESA Video Electronics Standards Association
  • PCI peripheral component interconnection
  • the computer system/server 012 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer system/server 012, including volatile and nonvolatile media, removable and non-removable media.
  • the system memory 028 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 030 and/or cache memory 032.
  • the computer system/server 012 may further include other removable/non-removable, volatile/nonvolatile computer system storage media.
  • the storage system 034 can be used to read and write non-removable, non-volatile magnetic media (not shown in FIG. 6, but generally referred to as a "hard drive").
  • a disk drive for reading and writing to removable non-volatile disks such as "floppy disks"
  • a removable non-volatile disk such as CD-ROM, DVD-ROM
  • other optical media read and write optical disc drives.
  • each drive can be connected to the bus 018 through one or more data media interfaces.
  • the memory 028 may include at least one program product, and the program product has a set (for example, at least one) program modules, which are configured to perform the functions of the embodiments of the present invention.
  • a program/utility tool 040 with a set of (at least one) program module 042 can be stored in, for example, the memory 028.
  • Such program module 042 includes, but is not limited to, an operating system, one or more application programs, and other programs Modules and program data, each of these examples or some combination may include the realization of a network environment.
  • the program module 042 generally executes the functions and/or methods in the described embodiments of the present invention.
  • the computer system/server 012 can also communicate with one or more external devices 014 (such as a keyboard, pointing device, display 024, etc.).
  • the computer system/server 012 communicates with an external radar device, and can also communicate with one or Multiple devices that enable users to interact with the computer system/server 012, and/or communicate with any devices that enable the computer system/server 012 to communicate with one or more other computing devices (such as network cards, modems, etc.) Communication. This communication can be performed through an input/output (I/O) interface 022.
  • I/O input/output
  • the computer system/server 012 can also communicate with one or more networks (for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 020.
  • networks for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet
  • the network adapter 020 communicates with other modules of the computer system/server 012 through the bus 018.
  • other hardware and/or software modules can be used in conjunction with the computer system/server 012, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems , Tape drives and data backup storage systems.
  • the processing unit 016 executes various functional applications and data processing by running programs stored in the system memory 028, for example, to implement the method flow provided by the embodiment of the present invention.
  • the above-mentioned computer program may be set in a computer storage medium, that is, the computer storage medium is encoded with a computer program.
  • the program is executed by one or more computers, one or more computers can execute the above-mentioned embodiments of the present invention.
  • the method flow and/or device operation For example, the process of the method provided in the embodiment of the present invention is executed by the one or more processors described above.
  • the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.
  • the computer-readable storage medium may be, for example, but not limited to, an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above.
  • computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.
  • the computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and computer-readable program code is carried therein. This propagated data signal can take many forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including, but not limited to, wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
  • the computer program code used to perform the operations of the present invention can be written in one or more programming languages or a combination thereof.
  • the programming languages include object-oriented programming languages-such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "C" language or similar programming language.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect to the user's computer) connection).
  • LAN local area network
  • WAN wide area network
  • the present invention calculates the time when the user arrives at each road section one by one from the starting point of the navigation path, predicts the road section road conditions at that time, and determines the user's travel time on each road section based on the predicted road conditions until the end of the navigation path.
  • This kind of road condition prediction method can estimate the road condition at the time when the user arrives at each road section in the future, and can provide more accurate road condition information compared with the road condition estimation method based on the user's query time.
  • the road condition estimation method provided by the present invention for each road section can accurately predict the road condition change for a period of time in the future according to the road condition law learned in history.
  • the present invention When estimating the travel time for each road section, the present invention considers the user's driving behavior and habits, and integrates the user's personalized driving characteristics into the travel time estimation, thereby providing users with more accurate estimation results.
  • the present invention combines the driving position and road conditions of the vehicle on the navigation path to display and dynamically play on the time axis. The user can also manually drag the progress bar to observe the vehicle position and road conditions at each time.

Landscapes

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

Abstract

一种路况预测方法、装置、设备和计算机存储介质。其中方法包括：确定导航路径被划分得到的至少两个连续的路段（步骤101）；从该导航路径的起点开始逐一针对各路段分别执行以下处理直至该导航路径的终点：确定用户到达当前处理的路段的时刻；预估该当前处理的路段在确定出的时刻的路况信息；基于该当前处理的路段在确定出的时刻的路况信息，预估该用户在该当前处理的路段的通行时长（步骤102）。该路况预测方式能够对用户到达各路段的时刻的路况进行预估，相比较基于用户查询时刻进行路况预估的方式，能够提供更加准确的路况信息。

Description

一种路况预测方法、装置、设备和计算机存储介质 技术领域
本发明涉及计算机应用技术领域，特别涉及一种路况预测方法、装置、设备和计算机存储介质。
背景技术
本部分旨在为权利要求书中陈述的本发明的实施方式提供背景或上下文。此处的描述不因为包括在本部分中就被认为是现有技术。
随着城市人口和城市车辆交通量的增加，城市特别是大城市的道路拥堵的问题已经成为驾车出行最关注的焦点之一。在北京、深圳等特大城市，高峰期的道路拥堵会造成70％以上的出行成本增加。对于每一位司机来说，如果能够准确地预估出未来一段时间内的路况信息，以辅助司机判断出应该如何选择出行时刻和出行路线来躲避拥堵，将会大大的提高出行效率。
现有导航工具均是以当前时刻(即用户的查询时刻)的路况信息为基准提供的。然而，从查询时刻到行进过程中往往是一个较长的时间过程，由于车辆行驶速度很快导致路况变化也会非常频繁，在该时间过程中路况可能会发生很大变化。因此现有导航工具向用户提供的导航路径中各路段的路况信息是不准确的，导致据此预估的到达时间也是不准确的，无法帮助用户做出正确的决策。
发明内容
有鉴于此，本发明提供了一种路况预测方法、装置、设备和计算机存储介质，以便于提供更加准确的路况信息。
第一方面，本发明提供了一种路况预测方法，该方法包括：
确定导航路径被划分得到的至少两个连续的路段；
从所述导航路径的起点开始逐一针对各路段分别执行以下处理直至所述导航路径的终点：
确定用户到达当前处理的路段的时刻；
预估所述当前处理的路段在确定出的时刻的路况信息；
基于所述当前处理的路段在确定出的时刻的路况信息，预估所述用户在所述当前处理的路段的通行时长。
根据本发明一优选实施方式，所述确定用户到达当前处理的路段的时刻包括：
对于从所述导航路径的起点开始的路段，将用户的出发时刻作为用户到达当前处理的路段的时刻；
对于其他路段，利用用户到达上一路段的时刻和预估得到的所述用户在所述上一路段的通行时长，确定用户到达当前处理的路段的时刻。
根据本发明一优选实施方式，预估所述当前处理的路段在确定出的时刻的路况信息包括：
确定用户到达当前处理的路段的时刻距离当前时刻的时长；
将所述当前处理的路段信息、所述时长以及外部因素特征输入预先训练得到的路况模型，得到所述当前处理的路段在所述确定出的时刻的路况信息。
根据本发明一优选实施方式，所述路况模型采用如下方式预先训练得到：
收集各路段的历史车流信息作为训练数据；
分别针对各路段执行以下处理：
依据路段在各历史时间点的车流信息确定该路段分别在各历史时间点对应的路况信息；
在各历史时间点回溯预设时长，确定在各历史时间点在该路段上行驶的用户分别来自的路段及其路况信息以及在各历史时间点回溯预设时长的外部因素特征作为分类模型的输入，将该路段分别在各历史时间点对应的路况信息作为分类模型的输出，训练所述分类模型，得到所述路况模型。
根据本发明一优选实施方式，基于所述当前处理的路段在确定出的时刻的路况信息，预估所述用户在所述当前处理的路段的通行时长包括：
确定所述当前处理的路段的通用特征，所述通用特征包括所述路况信息；
从所述用户的历史驾驶记录中，抽取所述用户通过所述当前处理的路段的个性化驾驶特征；
将所述通用特征和所述个性化驾驶特征输入预先训练得到的回归模型，得到用户在所述当前处理的路段的通行时长。
根据本发明一优选实施方式，所述回归模型采用如下方式预先训练得到：
将不同用户在各路段的通用特征、用户通过各路段的个性化驾驶特征以及用户通过各路段的通行时长作为训练样本；
将不同用户在各路段的通用特征和用户通过各路段的个性化驾驶特征作为输入，用户通过各路段的通行时长作为输出，训练回归模型。
根据本发明一优选实施方式，所述通用特征还包括以下至少一种：
路段长度、道路等级、交通灯数量、交通灯等待时长、外部因素特征。
根据本发明一优选实施方式，所述外部因素特征包括以下至少一种：
时间特征、星期特征、季节特征和天气特征。
根据本发明一优选实施方式，所述个性化驾驶特征包括以下至少一种：
用户在所述当前处理的路段的历史通行次数、所述用户的车辆信息、所述用户在所述当前处理的路段的历史驾驶速度与大众驾驶速度的方差。
根据本发明一优选实施方式，该方法还包括：
确定所述用户到达所述导航路径的终点时刻；或者，
确定所述用户在所述导航路径上的预计通行时长。
根据本发明一优选实施方式，该方法还包括：
将预估得到的各路段的路况信息和各时刻进行映射，在界面上对映射结果进行动态展现。
根据本发明一优选实施方式，所述将预估得到的各路段的路况信息和各时刻进行映射，在界面上对映射结果进行动态展现包括：
将预估得到的各路段的路况信息在时间轴上进行映射，在界面上动态展现依时间变化的车辆位置和路况信息。
根据本发明一优选实施方式，该方法还包括：
获取到用户在所述时间轴上的拖动操作；
在所述界面上展示用户拖动到的时间轴位置所对应的车辆位置和路况信息。
第二方面，本发明还提供了一种路况预测装置，该装置包括：
路段确定单元，用于确定导航路径被划分得到的至少两个连续的路段；
预测处理单元，用于从所述导航路径的起点开始逐一针对各路段分别执行以下处理直至所述导航路径的终点：
确定用户到达当前处理的路段的时刻；
预估所述当前处理的路段在确定出的时刻的路况信息；
基于所述当前处理的路段在确定出的时刻的路况信息，预估所述用户在所述当前处理的路段的通行时长。
根据本发明一优选实施方式，所述预测处理单元包括：
到达时刻确定子单元，用于对于从所述导航路径的起点开始的路段，将用户的出发时刻作为用户到达当前处理的路段的时刻；对于其他路段，利用用户到达上一路段的时刻和预估得到的所述用户在所述上一路段的通行时长，确定用户到达当前处理的路段的时刻。
根据本发明一优选实施方式，所述预测处理单元包括：
路况预估子单元，用于确定用户到达当前处理的路段的时刻距离当前时刻的时长；将所述当前处理的路段信息、所述时长以及外部因素特征输入预先训练得到的路况模型，得到所述当前处理的路段在所述确定出的时刻的路况信息。
根据本发明一优选实施方式，所述预测处理单元还包括：
第一训练子单元，用于采用如下方式预先训练所述路况模型：
收集各路段的历史车流信息作为训练数据；
分别针对各路段执行以下处理：
依据路段在各历史时间点的车流信息确定该路段分别在各历史时间点对应的路况信息；
在各历史时间点回溯预设时长，确定在各历史时间点在该路段上行驶的用户分别来自的路段及其路况信息以及在各历史时间点回溯预设时长的外部因素特征作为分类模型的输入，将该路段分别在各历史时间点对应的路况信息作为分类模型的输出，训练所述分类模型，得到所述路况模型。
根据本发明一优选实施方式，所述预测处理单元包括：
通行时长预估子单元，用于确定所述当前处理的路段的通用特征，所述通用特征包括所述路况信息；从所述用户的历史驾驶记录中，抽取所述用户通过所述当前处理的路段的个性化驾驶特征；将所述通用特征和所述个性化驾驶特征输入预先训练得到的回归模型，得到用户在所述当前处理的路段的通行时长。
根据本发明一优选实施方式，所述预测处理单元还包括：
第二训练子单元，用于采用如下方式预先训练所述回归模型：
将不同用户在各路段的通用特征、用户通过各路段的个性化驾驶特征以及用户通过各路段的通行时长作为训练样本；
将不同用户在各路段的通用特征和用户通过各路段的个性化驾驶特征作为输入，用户通过各路段的通行时长作为输出，训练回归模型。
根据本发明一优选实施方式，该装置还包括：终点时刻确定单元或通行时长确定单元；
所述终点时刻确定单元，用于确定所述用户到达所述导航路径的终点时刻；
所述通行时长确定单元，用于确定所述用户在所述导航路径上的预计通行时长。
根据本发明一优选实施方式，该装置还包括：
动态展现单元，用于将预估得到的各路段的路况信息和各时刻进行映射，在界面上对映射结果进行动态展现。
第三方面，本发明提供了一种设备，所述设备包括：
一个或多个处理器；
存储装置，用于存储一个或多个程序，
当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如上所述的方法。
第四方面，本发明提供了一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行如上所述的方法。
由以上技术方案可以看出，本发明从导航路径起点开始逐个计算用户到达各路段的时刻并预测该时刻的路段路况，并基于预测的路况确定用户在各路段的通行时长，直至导航路径终点。这种路况预测方式能够对未来用户到达各路段的时刻进行路况预估，相比较基于用户查询时刻进行路况预估的方式，能够提供更加准确的路况信息。
附图说明
图1为本发明实施例提供的主要方法流程图；
图2为图1中步骤102的具体实现流程图；
图3为本发明实施例提供的实现流程的原理示意图；
图4a、图4b和图4c为本发明实施例提供的路况动态展现的示例图；
图5为本发明实施例提供的装置结构图；
图6出了适于用来实现本发明实施方式的示例性计算机系统/服务器的框图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面结合附图和具体实施例对本发明进行详细描述。
本发明的核心思想在于，以路段为单位，从导航路径起点开始逐个计算用户到达各路段的时刻并预测该时刻的路段路况，并基于预测的路况确定用户在各路段的通行时长，直至导航路径终点。下面结合实施例对本发明进行详细描述。
图1为本发明实施例提供的主要方法流程图，如图1中所示，该方法主要包括以下步骤：
在101中，确定导航路径被划分得到的至少两个连续的路段。
当用户在导航类应用中输入起点和终点进行导航路径的查询时，会匹配得到一条或者两条以上的导航路径。可以针对匹配得到的各条导航路径分别执行本发明实施例提供的方法进行路况预测，也可以仅对其中被选择出的若干条导航路径分别执行本发明实施例提供的方法进行路况预测。
例如，用户输入起点和终点后，导航类应用在地图数据库中匹配得到10条导航路径，可以针对这10条导航路径分别执行本发明实施例提供的方法进行路况预测。再例如，若其中3条导航路径的距离最近，则可以针对该3条导航路径分别执行本发明实施例提供的方法进行路况预 测。在例如，若用户从这10条导航路径中选择出一条导航路径，则也可以仅针对用户选择出的该条导航路径执行本发明实施例提供的方法进行路况预测。本发明对此并不加以限制。
在本发明实施例中，一条导航路径可以被划分得到至少两个连续的路段。所谓路段指的是一段不包含分岔路口的道路，是路网的最小组成单元。导航路径被划分得到的连续路段的信息可以从路网数据库中获取，本发明对此不加以限制，仅需要获取并利用划分得到的结果即可。
在102中，从导航路径的起点开始逐一针对各连续的路段分别执行以下处理直至导航路径的终点：确定用户到达当前处理的路段的时刻；预估当前处理的路段在确定出的时刻的路况信息；基于当前处理的路段在确定出的时刻的路况信息，预估用户在当前处理的路段的通行时长。
作为其中一种具体的实施方式，上述步骤102的具体实现方式可以如图2中所示，具体包括以下步骤：
在201中，将导航路径起点开始的路段作为当前处理的路段，将用户的出发时刻作为用户到达当前处理路段的时刻。
在202中，预估当前处理的路段在确定出的时刻的路况信息。
所谓路况可以理解为路段的拥堵状况，可以体现为拥堵的程度。具体表示形式可以采用多种，例如可以以百分率、拥堵级别等形式表示，也可以以诸如畅通、缓行、拥堵、极度拥堵等分类的形式表示。
本步骤中，预估路段的路况信息时，使用基于分类模型实现的路况模型。为了方便理解，首先对路况模型的训练过程进行介绍。
首先，收集各路段的历史车流信息作为训练数据。从各路段的历史车流信息中可以获取到在各历史时间点各路段的车流状况，从而确定出 各路段在各历史时间点的路况信息。其中各历史时间点可以采用预设的时间单位，例如以分钟为单位。还可以获取到各车辆标识在各历史时间点所在的路段，即在各历史时间点各路段上有哪些车辆。
分别针对各路段执行以下处理：
依据路段在各历史时间点的车流信息确定该路段分别在各历史时间点对应的路况信息，作为分类模型的输出。
在各历史时间点回溯预设时长(例如回溯1分钟、2分钟、3分钟、4分钟、5分钟)，提取在各历史时间点在该路段上行驶的用户分别来自的路段及其路况信息。举个例子，在历史时间点t，路段L上的所有用户在5分钟前只可能来自于路段L1和L2，5分钟前路段L1上有3个用户，路段L2上有5个用户。将此作为分类模型的第一输入特征。
还可以提取在各历史时间点回溯预设时长的外部因素特征作为分类模型的第二输入特征。其中外部因素特征可以包括但不限于时间特征、星期特征、季节特征和天气特征。
时间特征的表达可以采用诸如
Figure PCTCN2019080043-appb-000001
和
Figure PCTCN2019080043-appb-000002
进行连续性表达。其中，x是小时，y是分钟，z是秒钟。比如，早晨8：00：30时，x＝8，y＝0，z＝30，代入公式计算出两个值，共同作为时间特征进行记录。
星期特征的表达可以采用诸如
Figure PCTCN2019080043-appb-000003
和
Figure PCTCN2019080043-appb-000004
进行连续性表达，m是星期。比如，星期一对应m是0，星期二对应m是1，以此类推。
天气特征可以分为诸如晴天、阴天、小雨、大雨、小雪、大雪、恶劣等分类，使用one-hot(独热码)形式进行表达。比如，晴天时，天气特征表示为1,0,0,0,0,0,0。阴天时，天气特征表示为0,1,0,0,0,0,0。
季节特征可以分为春、夏、秋、冬四种分类，同样可以使用one-hot形式进行表达。比如，春季时，季节特征表示为1,0,0,0。夏季时，季节特征表示为0,1,0,0。
确定出输入特征和输出后，进行分类模型的训练，得到路况模型。其中路况模型由执行上述特征提取的模块和上述分类模型构成。其中分类模型可以采用诸如KNN(k-NearestNeighbor，K临近)分类算法等。训练得到的路况模型能够依据路段标识和回溯时间，得到该路段的路况信息。
上述模型训练过程为离线过程。基于上述训练得到的路况模型进行路段的路况预估是在线过程。
在进行路况预估时，首先确定用户到达当前处理的路段的时刻距离当前时刻的时长(即对应上面模型训练过程中的回溯时间)；将当前处理的路段信息、时长以及外部因素特征输入预先训练得到的路况模型，得到当前处理的路段在到达当前处理的路段的时刻的路况信息。其中，路况模型的处理过程原理参见训练过程中的描述，在此不再赘述。
在203中，基于当前处理的路段在确定出的时刻的路况信息，预估用户在当前处理的路段的通行时长。
具体地，可以首先确定当前处理的路段的通用特征，其中通用特征可以包括该路段的路况信息(即步骤202中预测得到的路况信息)。还可以进一步包括但不限于诸如路段长度、道路等级、交通灯数量、交通灯等待时长、外部因素特征。其中，外部因素特征可以包括时间特征、星期特征、季节特征和天气特征等中至少一种。
可以基于通用特征来预估用户在当前处理的路段的通行时长，这种 方式已是比较成熟的。但作为本发明实施例的一种优选的实施方式，在通行时长预估时，除了路段的通用特征之外，还可以进一步结合用户的个性化特征。因为用户的个性化特征在路段的通行时长上体现得非常明显，同一路段，不同用户的驾驶习惯可能导致20％以上的效果差异。因此可以从用户的历史驾驶记录中，抽取该用户通过当前处理的路段的个性化驾驶特征。
其中，个性化驾驶特征可以包括以下至少一种：用户在当前处理的路段的历史通行次数、用户的车辆信息、用户在当前处理的路段的历史驾驶速度与大众驾驶速度的方差。
然后，将提取的上述通用特征和个性化驾驶特征输入预先训练得到的回归模型，得到用户在当前处理的路段的通行时长。
其中用户在当前处理的路段的通行时长指的是预估出的用户通过当前处理的路段所需要的时长，即用户从当前处理的路段的起点开始到达终点的时长。
下面对上述回归模型的训练过程进行简单介绍。
首先将不同用户在各路段的通用特征、用户通过各路段的个性化驾驶特征以及用户通过各路段的通行时长作为训练样本；将不同用户在各路段的通用特征和用户通过各路段的个性化驾驶特征作为输入，用户通过各路段的通行时长作为输出，训练回归模型。
其中在训练回归模型时采用的通用特征和个性化驾驶特征与上述利用训练模型进行通行时长预估时采用的通用特征和个性化驾驶特征具有相同的维度。在此不做赘述。
在204中，判断当前处理的路段是否到达导航路径终点，如果是， 则结束步骤102的流程。否则，执行205。
在205中，利用用户到达当前处理路段的时刻以及用户在当前处理的路段的通行时长，确定用户到达下一路段的时刻。
在206中，将下一路段作为当前处理的路段，转至步骤202。
上述实现流程的原理可以如图3中所示，从导航路径被划分成各路段，从起点开始针对每个路段执行如图2所示的流程。对于路段i而言，利用用户到达路段i的时刻t i确定出t i距离当前时刻的时长作为回溯时间，将路段信息、回溯时间以及外部因素特征输入路况模型，得到路段i的路况信息。将包含路段i的路况信息的通用特征与用户在该路段i的特性化特征输入回归模型，得到用户在路段i的通行时长Δt i。利用t i和Δt i得到用户到达下一路段i+1的时刻t i+1。针对每个路段依次执行上述过程，直至终点。
继续参见图1，还可以进一步执行以下步骤：
在103中，确定用户到达导航路径的终点时刻。
本步骤可以采用以下两种方式：
第一种方式：利用用户的出发时刻，以及预估得到的各路段的通行时长，确定用户到达导航路径的终点时刻。
第二种方式：利用确定出的用户到达最后一路段的时刻以及预估得到的用户在最后一路段的通行时长，确定用户到达导航路径的终点时刻。
该到达导航路径的终点时刻可以用于向用户提供导航路径的预计到达时间。例如在导航界面上向用户提供“该导航路径预计10:26:00到达终点”。
除了103之外，也可以确定用户在整个导航路径上的预计通行时长， 即将各路段的通行时长进行累加，并提供给用户。例如在导航界面上向用户提供“该导航路径预计用时22分钟”。
上述预估的到达导航路径的终点时刻或用户在整个导航路径上的预计通行时长可以用于系统选择导航路径以向用户反馈，也可以用于显示于导航界面上以供用户选择导航路径。
例如，系统计算出多条导航路径的预计通行时长后，可以从中选择3条预计通行时长最短的导航路径以在导航界面上反馈给用户。进一步地，这3条导航路径的预计通行时长也会显示在导航界面上，以便用户从中选择一条导航路径作为最终采用的导航路径。
在104中，将预估得到的各路段的路况信息和各时刻进行映射，在导航界面上对映射结果进行动态展现。
对于导航界面上的路况信息的预估结果展现，可以采用现有技术中的展现方式，例如以不同颜色区分导航结果中各路段的路况信息，这种展现方式往往是静态的。
但作为一种更优选的实施方式，可以采用104中所示的方式，对各路段的路况进行动态展现。具体地，可以将预估得到的各路段的路况信息在时间轴上进行映射，在导航界面上动态展现依时间变化的车辆位置和路况信息。
如图4a中所示，用户在导航应用中输入起点和终点后，针对匹配得到的各导航路径分别执行本发明实施例的上述方法流程后，得到各导航路径的通行时长，可以选取通行时长最短的三条导航路径作为三个方案供用户选择。若用户选择其中一条导航路径，则将预估得到的该导航路径各路段的路况信息在时间轴上进行映射，在导航界面上动态展现依时 间变化的车辆位置和路况信息。图4a为开始播放的界面示例图，开始播放时，车辆位置在起点位置，在时间轴(播放进度条)上指示用户出行时间。图4b为播放过程中的界面示例图，界面上车辆位置依据时间变化位于对应的路段，并采用不同的颜色展现当前时刻该路段的路况信息，在时间轴(播放进度条)上也随着指示相应的时刻。图4c为播放结束的界面示例图，界面上车辆位置在终点，在时间轴(播放进度条)上指示用户到达终点的时间。上述整个播放过程可以依据用户触发执行，例如用户在选择了其中一个导航路径，或者点击播放按钮后，自动播放长度在2～5秒的动态过程。也可以对于默认展现的导航路径自动播放长度在2～5秒的动态过程。
更进一步地，用户也可以手工在时间轴(播放进度条)上进行拖动操作，观察指定时刻的车辆位置和该时刻的路况。即获取到用户在时间轴上的拖动操作，则在界面上展示用户拖动到的时间轴位置所对应的车辆位置和路况信息。
以上是对本发明所提供的方法进行的详细描述，下面对本发明实施例提供的路况预测装置进行详细描述。该路况预测装置用以执行上述方法实施例中的操作。该装置可以位于本地终端的应用，或者还可以为位于本地终端的应用中的插件或软件开发工具包(Software Development Kit，SDK)等功能单元，或者，还可以位于服务器端，本发明实施例对此不进行特别限定。
图5为本发明实施例提供的装置结构图，如图5所示，该装置可以包括：路段确定单元00和预测处理单元10，还可以进一步包括终点时刻确定单元20、通行时长确定单元30、动态展现单元40中的至少一种。 图5中以同时包括上述单元为例。
路段确定单元00负责确定导航路径被划分得到的至少两个连续的路段。
在本发明实施例中，一条导航路径可以被划分得到至少两个连续的路段。导航路径被划分得到的连续路段的信息可以从路网数据库中获取，本发明对此不加以限制，路段确定单元00仅需要获取并利用划分得到的结果即可。
预测处理单元10负责从导航路径的起点开始逐一针对各路段分别执行以下处理直至导航路径的终点：确定用户到达当前处理的路段的时刻；预估当前处理的路段在确定出的时刻的路况信息；基于当前处理的路段在确定出的时刻的路况信息，预估用户在当前处理的路段的通行时长。
具体地，预测处理单元10可以包括：到达时刻确定子单元11、路况预估子单元12、第一训练子单元13、通行时长预估子单元14和第二训练子单元15。
其中，到达时刻确定子单元11负责确定用户到达当前处理的路段的时刻。具体地，对于从导航路径的起点开始的路段，可以将用户的出发时刻作为用户到达当前处理的路段的时刻；对于其他路段，利用用户到达上一路段的时刻和预估得到的用户在上一路段的通行时长，确定用户到达当前处理的路段的时刻。
路况预估子单元12负责确定用户到达当前处理的路段的时刻距离当前时刻的时长；将当前处理的路段信息、时长以及外部因素特征输入预先训练得到的路况模型，得到当前处理的路段在确定出的时刻的路况 信息。
第一训练子单元13负责采用如下方式预先训练路况模型：
收集各路段的历史车流信息作为训练数据；
分别针对各路段执行以下处理：
依据路段在各历史时间点的车流信息确定该路段分别在各历史时间点对应的路况信息；
在各历史时间点回溯预设时长，提取在各历史时间点在该路段上行驶的用户分别来自的路段及其路况信息以及在各历史时间点回溯预设时长的外部因素特征作为分类模型的输入，将该路段分别在各历史时间点对应的路况信息作为分类模型的输出，训练分类模型，得到路况模型。该路况模型包括执行提取上述特征的模块以及上述分类模型。
其中外部因素特征可以包括但不限于时间特征、星期特征、季节特征和天气特征。对于各种外部因素特征的表达具体参见方法实施例中的描述。
其中分类模型可以采用诸如KNN(k-NearestNeighbor，K临近)分类算法等。
通行时长预估子单元14负责确定当前处理的路段的通用特征，通用特征包括路况信息；从用户的历史驾驶记录中，抽取用户通过当前处理的路段的个性化驾驶特征；将通用特征和个性化驾驶特征输入预先训练得到的回归模型，得到用户在当前处理的路段的通行时长。
第二训练子单元15采用如下方式预先训练回归模型：
将不同用户在各路段的通用特征、用户通过各路段的个性化驾驶特征以及用户通过各路段的通行时长作为训练样本；
将不同用户在各路段的通用特征和用户通过各路段的个性化驾驶特征作为输入，用户通过各路段的通行时长作为输出，训练回归模型。
上述通用特征可以包括该路段的路况信息(即路况预估子单元12预测得到的路况信息)。还可以进一步包括但不限于诸如路段长度、道路等级、交通灯数量、交通灯等待时长、外部因素特征。其中，外部因素特征可以包括时间特征、星期特征、季节特征和天气特征等中至少一种。
个性化驾驶特征可以包括以下至少一种：用户在当前处理的路段的历史通行次数、用户的车辆信息、用户在当前处理的路段的历史驾驶速度与大众驾驶速度的方差。
终点时刻确定单元20负责确定用户到达导航路径的终点时刻。具体可以采用以下两种方式：
第一种方式：利用用户的出发时刻，以及预估得到的各路段的通行时长，确定用户到达导航路径的终点时刻。
第二种方式：利用确定出的用户到达最后一路段的时刻以及预估得到的用户在最后一路段的通行时长，确定用户到达导航路径的终点时刻。
通行时长确定单元30负责确定用户在导航路径上的预计通行时长。具体可以确定用户在整个导航路径上的预计通行时长，即将各路段的通行时长进行累加，并提供给用户。
动态展现单元40负责将预估得到的各路段的路况信息和各时刻进行映射，在界面上对映射结果进行动态展现。具体地，可以将预估得到的各路段的路况信息在时间轴上进行映射，在导航界面上动态展现依时间变化的车辆位置和路况信息。
更进一步地，用户也可以手工在时间轴(播放进度条)上进行拖动 操作，观察指定时刻的车辆位置和该时刻的路况。即动态展现单元40获取到用户在时间轴上的拖动操作，则在界面上展示用户拖动到的时间轴位置所对应的车辆位置和路况信息。
另外，在展现上还可以结合一些其他设计，例如在播放过程中不同颜色展现的是用户正在或即将到达的路段的预测路况，而用户走过的路段的路况将设置为灰色。
图6示出了适于用来实现本发明实施方式的示例性计算机系统/服务器012的框图。图6显示的计算机系统/服务器012仅仅是一个示例，不应对本发明实施例的功能和使用范围带来任何限制。
如图6所示，计算机系统/服务器012以通用计算设备的形式表现。计算机系统/服务器012的组件可以包括但不限于：一个或者多个处理器或者处理单元016，系统存储器028，连接不同系统组件(包括系统存储器028和处理单元016)的总线018。
总线018表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(ISA)总线，微通道体系结构(MAC)总线，增强型ISA总线、视频电子标准协会(VESA)局域总线以及外围组件互连(PCI)总线。
计算机系统/服务器012典型地包括多种计算机系统可读介质。这些介质可以是任何能够被计算机系统/服务器012访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
系统存储器028可以包括易失性存储器形式的计算机系统可读介 质，例如随机存取存储器(RAM)030和/或高速缓存存储器032。计算机系统/服务器012可以进一步包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统034可以用于读写不可移动的、非易失性磁介质(图6未显示，通常称为“硬盘驱动器”)。尽管图6中未示出，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘(例如CD-ROM,DVD-ROM或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过一个或者多个数据介质接口与总线018相连。存储器028可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本发明各实施例的功能。
具有一组(至少一个)程序模块042的程序/实用工具040，可以存储在例如存储器028中，这样的程序模块042包括——但不限于——操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块042通常执行本发明所描述的实施例中的功能和/或方法。
计算机系统/服务器012也可以与一个或多个外部设备014(例如键盘、指向设备、显示器024等)通信，在本发明中，计算机系统/服务器012与外部雷达设备进行通信，还可与一个或者多个使得用户能与该计算机系统/服务器012交互的设备通信，和/或与使得该计算机系统/服务器012能与一个或多个其它计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口022进行。并且，计算机系统/服务器012还可以通过网络适配器020与一个或者多个网络(例如局域网(LAN)，广域网(WAN)和/或公共网络， 例如因特网)通信。如图所示，网络适配器020通过总线018与计算机系统/服务器012的其它模块通信。应当明白，尽管图6中未示出，可以结合计算机系统/服务器012使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。
处理单元016通过运行存储在系统存储器028中的程序，从而执行各种功能应用以及数据处理，例如实现本发明实施例所提供的方法流程。
上述的计算机程序可以设置于计算机存储介质中，即该计算机存储介质被编码有计算机程序，该程序在被一个或多个计算机执行时，使得一个或多个计算机执行本发明上述实施例中所示的方法流程和/或装置操作。例如，被上述一个或多个处理器执行本发明实施例所提供的方法流程。
随着时间、技术的发展，介质含义越来越广泛，计算机程序的传播途径不再受限于有形介质，还可以直接从网络下载等。可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介 质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括——但不限于——电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括——但不限于——无线、电线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本发明操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
由以上描述可以看出，本发明实施例提供的上述方法、装置设备和计算机存储介质可以具备以下优点：
1)本发明从导航路径起点开始逐个计算用户到达各路段的时刻并预 测该时刻的路段路况，并基于预测的路况确定用户在各路段的通行时长，直至导航路径终点。这种路况预测方式能够对未来用户到达各路段的时刻进行路况预估，相比较基于用户查询时刻进行路况预估的方式，能够提供更加准确的路况信息。
2)基于上述预测方式得到的路况信息，能够更加准确地确定导航路径的终点到达时间和导航路径的通行时长，以帮助用户做出正确的决策。
3)本发明针对各路段提供的路况预估方式，能够针对历史学习到的路况规律，准确地预估出未来一段时间的路况变化情况。
4)本发明针对各路段进行通行时长预估时，考虑到用户的驾驶行为和习惯，将用户的个性化驾驶特征融入通行时长的预估，从而为用户提供更准确的预估结果。
5)本发明将车辆在导航路径上的行驶位置和路况在时间轴上进行结合展现和动态播放，用户也可以手动拖动进度条以观察各时刻的车辆位置和路况。
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明保护的范围之内。

Claims (23)

  1. 一种路况预测方法，其特征在于，该方法包括：
    确定导航路径被划分得到的至少两个连续的路段；
    从所述导航路径的起点开始逐一针对各路段分别执行以下处理直至所述导航路径的终点：
    确定用户到达当前处理的路段的时刻；
    预估所述当前处理的路段在确定出的时刻的路况信息；
    基于所述当前处理的路段在确定出的时刻的路况信息，预估所述用户在所述当前处理的路段的通行时长。
  2. 根据权利要求1所述的方法，其特征在于，所述确定用户到达当前处理的路段的时刻包括：
    对于从所述导航路径的起点开始的路段，将用户的出发时刻作为用户到达当前处理的路段的时刻；
    对于其他路段，利用用户到达上一路段的时刻和预估得到的所述用户在所述上一路段的通行时长，确定用户到达当前处理的路段的时刻。
  3. 根据权利要求1所述的方法，其特征在于，预估所述当前处理的路段在确定出的时刻的路况信息包括：
    确定用户到达当前处理的路段的时刻距离当前时刻的时长；
    将所述当前处理的路段信息、所述时长以及外部因素特征输入预先训练得到的路况模型，得到所述当前处理的路段在所述确定出的时刻的路况信息。
  4. 根据权利要求3所述的方法，其特征在于，所述路况模型采用如下方式预先训练得到：
    收集各路段的历史车流信息作为训练数据；
    分别针对各路段执行以下处理：
    依据路段在各历史时间点的车流信息确定该路段分别在各历史时间点对应的路况信息；
    在各历史时间点回溯预设时长，确定在各历史时间点在该路段上行 驶的用户分别来自的路段及其路况信息以及在各历史时间点回溯预设时长的外部因素特征作为分类模型的输入，将该路段分别在各历史时间点对应的路况信息作为分类模型的输出，训练所述分类模型，得到所述路况模型。
  5. 根据权利要求1所述的方法，其特征在于，基于所述当前处理的路段在确定出的时刻的路况信息，预估所述用户在所述当前处理的路段的通行时长包括：
    确定所述当前处理的路段的通用特征，所述通用特征包括所述路况信息；
    从所述用户的历史驾驶记录中，抽取所述用户通过所述当前处理的路段的个性化驾驶特征；
    将所述通用特征和所述个性化驾驶特征输入预先训练得到的回归模型，得到用户在所述当前处理的路段的通行时长。
  6. 根据权利要求5所述的方法，其特征在于，所述回归模型采用如下方式预先训练得到：
    将不同用户在各路段的通用特征、用户通过各路段的个性化驾驶特征以及用户通过各路段的通行时长作为训练样本；
    将不同用户在各路段的通用特征和用户通过各路段的个性化驾驶特征作为输入，用户通过各路段的通行时长作为输出，训练回归模型。
  7. 根据权利要求6所述的方法，其特征在于，所述通用特征还包括以下至少一种：
    路段长度、道路等级、交通灯数量、交通灯等待时长、外部因素特征。
  8. 根据权利要求3、4或7所述的方法，其特征在于，所述外部因素特征包括以下至少一种：
    时间特征、星期特征、季节特征和天气特征。
  9. 根据权利要求5所述的方法，其特征在于，所述个性化驾驶特征包括以下至少一种：
    用户在所述当前处理的路段的历史通行次数、所述用户的车辆信息、所述用户在所述当前处理的路段的历史驾驶速度与大众驾驶速度的方差。
  10. 根据权利要求1所述的方法，其特征在于，该方法还包括：
    确定所述用户到达所述导航路径的终点时刻；或者，
    确定所述用户在所述导航路径上的预计通行时长。
  11. 根据权利要求1或10所述的方法，其特征在于，该方法还包括：
    将预估得到的各路段的路况信息和各时刻进行映射，在界面上对映射结果进行动态展现。
  12. 根据权利要求11所述的方法，其特征在于，所述将预估得到的各路段的路况信息和各时刻进行映射，在界面上对映射结果进行动态展现包括：
    将预估得到的各路段的路况信息在时间轴上进行映射，在界面上动态展现依时间变化的车辆位置和路况信息。
  13. 根据权利要求12所述的方法，其特征在于，该方法还包括：
    获取到用户在所述时间轴上的拖动操作；
    在所述界面上展示用户拖动到的时间轴位置所对应的车辆位置和路况信息。
  14. 一种路况预测装置，其特征在于，该装置包括：
    路段确定单元，用于确定导航路径被划分得到的至少两个连续的路段；
    预测处理单元，用于从所述导航路径的起点开始逐一针对各路段分别执行以下处理直至所述导航路径的终点：
    确定用户到达当前处理的路段的时刻；
    预估所述当前处理的路段在确定出的时刻的路况信息；
    基于所述当前处理的路段在确定出的时刻的路况信息，预估所述用户在所述当前处理的路段的通行时长。
  15. 根据权利要求14所述的装置，其特征在于，所述预测处理单元 包括：
    到达时刻确定子单元，用于对于从所述导航路径的起点开始的路段，将用户的出发时刻作为用户到达当前处理的路段的时刻；对于其他路段，利用用户到达上一路段的时刻和预估得到的所述用户在所述上一路段的通行时长，确定用户到达当前处理的路段的时刻。
  16. 根据权利要求14所述的装置，其特征在于，所述预测处理单元包括：
    路况预估子单元，用于确定用户到达当前处理的路段的时刻距离当前时刻的时长；将所述当前处理的路段信息、所述时长以及外部因素特征输入预先训练得到的路况模型，得到所述当前处理的路段在所述确定出的时刻的路况信息。
  17. 根据权利要求16所述的装置，其特征在于，所述预测处理单元还包括：
    第一训练子单元，用于采用如下方式预先训练所述路况模型：
    收集各路段的历史车流信息作为训练数据；
    分别针对各路段执行以下处理：
    依据路段在各历史时间点的车流信息确定该路段分别在各历史时间点对应的路况信息；
    在各历史时间点回溯预设时长，确定在各历史时间点在该路段上行驶的用户分别来自的路段及其路况信息以及在各历史时间点回溯预设时长的外部因素特征作为分类模型的输入，将该路段分别在各历史时间点对应的路况信息作为分类模型的输出，训练所述分类模型，得到所述路况模型。
  18. 根据权利要求14所述的装置，其特征在于，所述预测处理单元包括：
    通行时长预估子单元，用于确定所述当前处理的路段的通用特征，所述通用特征包括所述路况信息；从所述用户的历史驾驶记录中，抽取所述用户通过所述当前处理的路段的个性化驾驶特征；将所述通用特征 和所述个性化驾驶特征输入预先训练得到的回归模型，得到用户在所述当前处理的路段的通行时长。
  19. 根据权利要求18所述的装置，其特征在于，所述预测处理单元还包括：
    第二训练子单元，用于采用如下方式预先训练所述回归模型：
    将不同用户在各路段的通用特征、用户通过各路段的个性化驾驶特征以及用户通过各路段的通行时长作为训练样本；
    将不同用户在各路段的通用特征和用户通过各路段的个性化驾驶特征作为输入，用户通过各路段的通行时长作为输出，训练回归模型。
  20. 根据权利要求14所述的装置，其特征在于，该装置还包括：终点时刻确定单元或通行时长确定单元；
    所述终点时刻确定单元，用于确定所述用户到达所述导航路径的终点时刻；
    所述通行时长确定单元，用于确定所述用户在所述导航路径上的预计通行时长。
  21. 根据权利要求14或20所述的装置，其特征在于，该装置还包括：
    动态展现单元，用于将预估得到的各路段的路况信息和各时刻进行映射，在界面上对映射结果进行动态展现。
  22. 一种设备，其特征在于，所述设备包括：
    一个或多个处理器；
    存储装置，用于存储一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-13中任一所述的方法。
  23. 一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行如权利要求1-13中任一所述的方法。
PCT/CN2019/080043 2019-03-28 2019-03-28 一种路况预测方法、装置、设备和计算机存储介质 WO2020191701A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
KR1020207029830A KR102457803B1 (ko) 2019-03-28 2019-03-28 도로 상황 예측 방법, 장치, 기기 및 컴퓨터 저장 매체
JP2020556771A JP7106794B2 (ja) 2019-03-28 2019-03-28 道路状況予測方法、装置、機器、プログラム及びコンピュータ記憶媒体
US17/042,834 US11823574B2 (en) 2019-03-28 2019-03-28 Method and apparatus for prediction road condition, device and computer storage medium
EP19920910.7A EP3767605A4 (en) 2019-03-28 2019-03-28 ROAD CONDITION FORECAST METHOD, SYSTEM AND DEVICE AND COMPUTER STORAGE MEDIUM
PCT/CN2019/080043 WO2020191701A1 (zh) 2019-03-28 2019-03-28 一种路况预测方法、装置、设备和计算机存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/080043 WO2020191701A1 (zh) 2019-03-28 2019-03-28 一种路况预测方法、装置、设备和计算机存储介质

Publications (1)

Publication Number Publication Date
WO2020191701A1 true WO2020191701A1 (zh) 2020-10-01

Family

ID=72608801

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/080043 WO2020191701A1 (zh) 2019-03-28 2019-03-28 一种路况预测方法、装置、设备和计算机存储介质

Country Status (5)

Country Link
US (1) US11823574B2 (zh)
EP (1) EP3767605A4 (zh)
JP (1) JP7106794B2 (zh)
KR (1) KR102457803B1 (zh)
WO (1) WO2020191701A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113665576A (zh) * 2021-08-31 2021-11-19 中国第一汽车股份有限公司 车辆行驶工况预测方法、装置、设备及介质
CN117975745A (zh) * 2024-04-01 2024-05-03 华东交通大学 一种基于车联网的智慧交通监控系统
CN117975745B (zh) * 2024-04-01 2024-05-31 华东交通大学 一种基于车联网的智慧交通监控系统

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102457803B1 (ko) * 2019-03-28 2022-10-20 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. 도로 상황 예측 방법, 장치, 기기 및 컴퓨터 저장 매체
CN113066285B (zh) * 2021-03-15 2022-12-09 北京百度网讯科技有限公司 一种路况信息确定方法、装置、电子设备及存储介质
CN113808401B (zh) * 2021-09-18 2023-02-10 平安普惠企业管理有限公司 交通拥堵预测方法、装置、设备及存储介质
CN115841190B (zh) * 2023-02-14 2023-06-06 中咨公路养护检测技术有限公司 道路pci多步预测方法及装置
CN116312008B (zh) * 2023-02-17 2024-02-06 成都和乐信软件有限公司 一种基于气候信息的高速道路状况预警方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104851298A (zh) * 2015-06-09 2015-08-19 刘光明 预测交通状况和行车时间
CN105139656A (zh) * 2015-09-28 2015-12-09 百度在线网络技术（北京）有限公司 一种道路状态预测方法及装置
CN105910612A (zh) * 2015-12-29 2016-08-31 乐视网信息技术（北京）股份有限公司 一种个性化导航的方法及系统
CN109211253A (zh) * 2017-07-05 2019-01-15 深圳市凯立德科技股份有限公司 一种预估到达时间的方法及导航设备
US20190033083A1 (en) * 2016-01-28 2019-01-31 Nec Corporation Route analysis device, route analysis method, and computer-readable recording medium

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6317686B1 (en) * 2000-07-21 2001-11-13 Bin Ran Method of providing travel time
EP2343694B1 (en) * 2009-12-29 2012-03-14 Research In Motion Limited System and method of sending an arrival time estimate
EP2556339B8 (en) * 2010-04-09 2018-12-26 TomTom Navigation B.V. Method and device for generating a cost function
EP2410294A1 (en) * 2010-07-21 2012-01-25 Harman Becker Automotive Systems GmbH Method and device for providing cost information associated with junctions and method of determining a route
JP2013032949A (ja) 2011-08-01 2013-02-14 Aisin Aw Co Ltd 車両用表示処理システムおよび車両用表示処理方法並びにプログラム
US9122987B2 (en) 2013-01-17 2015-09-01 Mitsubishi Electric Research Laboratories, Inc. Method for predicting future travel time using geospatial inference
CN104567897A (zh) * 2013-10-16 2015-04-29 大陆汽车投资（上海）有限公司 结合路况预测的路径规划方法及导航装置
DE112016003148B4 (de) 2015-07-15 2023-02-23 Mitsubishi Electric Corporation Routen-auswertungseinrichtung und routen-auswertungsverfahren
CN107063278A (zh) * 2017-01-24 2017-08-18 观致汽车有限公司 一种车辆导航系统、导航方法及其车辆
US10698421B1 (en) * 2017-09-25 2020-06-30 State Farm Mutual Automobile Insurance Company Dynamic autonomous vehicle train
US11048271B1 (en) * 2017-10-05 2021-06-29 State Farm Mutual Automobile Insurance Company Dynamic autonomous vehicle train
CN109711591B (zh) * 2017-10-25 2022-02-01 腾讯科技（深圳）有限公司 一种路段速度预测方法、装置、服务器及存储介质
KR102457803B1 (ko) * 2019-03-28 2022-10-20 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. 도로 상황 예측 방법, 장치, 기기 및 컴퓨터 저장 매체
DE102020122010B4 (de) * 2020-08-24 2023-05-04 Bareways GmbH Verfahren und system zur bestimmung einer beschaffenheit einer geografischen linie
US11499516B2 (en) * 2020-11-04 2022-11-15 Ford Global Technologies, Llc Methods and systems for an adaptive stop-start inhibitor

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104851298A (zh) * 2015-06-09 2015-08-19 刘光明 预测交通状况和行车时间
CN105139656A (zh) * 2015-09-28 2015-12-09 百度在线网络技术（北京）有限公司 一种道路状态预测方法及装置
CN105910612A (zh) * 2015-12-29 2016-08-31 乐视网信息技术（北京）股份有限公司 一种个性化导航的方法及系统
US20190033083A1 (en) * 2016-01-28 2019-01-31 Nec Corporation Route analysis device, route analysis method, and computer-readable recording medium
CN109211253A (zh) * 2017-07-05 2019-01-15 深圳市凯立德科技股份有限公司 一种预估到达时间的方法及导航设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3767605A4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113665576A (zh) * 2021-08-31 2021-11-19 中国第一汽车股份有限公司 车辆行驶工况预测方法、装置、设备及介质
CN117975745A (zh) * 2024-04-01 2024-05-03 华东交通大学 一种基于车联网的智慧交通监控系统
CN117975745B (zh) * 2024-04-01 2024-05-31 华东交通大学 一种基于车联网的智慧交通监控系统

Also Published As

Publication number Publication date
KR102457803B1 (ko) 2022-10-20
US20210241618A1 (en) 2021-08-05
EP3767605A4 (en) 2021-06-16
EP3767605A1 (en) 2021-01-20
JP7106794B2 (ja) 2022-07-27
KR20200130439A (ko) 2020-11-18
US11823574B2 (en) 2023-11-21
JP2021519933A (ja) 2021-08-12

Similar Documents

Publication Publication Date Title
WO2020191701A1 (zh) 一种路况预测方法、装置、设备和计算机存储介质
CN109919347B (zh) 路况生成方法、相关装置和设备
US10592936B2 (en) Travel assistance device, travel assistance server, and travel assistance system
CN106969782B (zh) 导航路线的推送方法、装置、设备以及存储介质
JP2013178266A (ja) 車経路案内において目印情報をユーザに提供する方法およびシステム
US20080319660A1 (en) Landmark-based routing
JP5892004B2 (ja) 経路探索システム、経路探索装置、経路探索方法及びコンピュータプログラム
CN103632542A (zh) 交通信息处理方法、装置和相应设备
US20080294337A1 (en) Travel-related information processing system
CN107270923A (zh) 一种路线推送的方法、终端及存储介质
CN114435138A (zh) 一种车辆能耗预测方法、装置、车辆及存储介质
JP6974505B2 (ja) ランドマーク援用ナビゲーション
WO2022199311A1 (zh) 交互方法和交互装置
CN104380047A (zh) 导航系统
JP3507133B2 (ja) 誘導経路探索装置
US10989549B2 (en) Route recommendation in map service
RU2664034C1 (ru) Способ и система создания информации о трафике, которая будет использована в картографическом приложении, выполняемом на электронном устройстве
CN113418531B (zh) 导航路线的确定方法、装置、电子设备和计算机存储介质
US20200333149A1 (en) Route searching device and computer program
US11346683B2 (en) Method and apparatus for providing argumentative navigation routing
CN111854777B (zh) 导航路线行驶时间的更新方法、导航方法、系统及车辆
JP2022517454A (ja) ナビゲーション中に難しい操縦についての追加の命令を提供すること
CN114118582A (zh) 目的地预测方法、装置、电子终端及存储介质
EP3622252A1 (en) Routes on digital maps with interactive turn graphics
CN113420942A (zh) 一种基于深度q学习的环卫车实时路线规划方法

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2020556771

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20207029830

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2019920910

Country of ref document: EP

Effective date: 20201016

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

Ref document number: 19920910

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE