WO2019153745A1 - 信息处理的方法和装置 - Google Patents

信息处理的方法和装置 Download PDF

Info

Publication number
WO2019153745A1
WO2019153745A1 PCT/CN2018/105889 CN2018105889W WO2019153745A1 WO 2019153745 A1 WO2019153745 A1 WO 2019153745A1 CN 2018105889 W CN2018105889 W CN 2018105889W WO 2019153745 A1 WO2019153745 A1 WO 2019153745A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
time
target vehicle
target
travel
Prior art date
Application number
PCT/CN2018/105889
Other languages
English (en)
French (fr)
Inventor
李婧萱
李波
李正兵
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP18905774.8A priority Critical patent/EP3706097A4/en
Publication of WO2019153745A1 publication Critical patent/WO2019153745A1/zh
Priority to US16/927,112 priority patent/US20200342430A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/08—Payment architectures
    • G06Q20/14—Payment architectures specially adapted for billing systems
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
    • G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
    • G07B15/06—Arrangements for road pricing or congestion charging of vehicles or vehicle users, e.g. automatic toll systems
    • G07B15/063—Arrangements for road pricing or congestion charging of vehicles or vehicle users, e.g. automatic toll systems using wireless information transmission between the vehicle and a fixed station
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G06F16/285—Clustering or classification
    • 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
    • G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
    • 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
    • G06Q2240/00—Transportation facility access, e.g. fares, tolls or parking
    • 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
    • G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station

Definitions

  • the present application relates to the field of intelligent transportation and, more particularly, to a method and apparatus for information processing.
  • the electronic toll collection mainly includes a road side unit (RSU) and an onboard unit (OBU).
  • RSU is disposed on the ETC lane
  • OBU is disposed on the vehicle.
  • DSRC dedicated short range communication
  • the ETC system when determining the toll cost of the vehicle, the ETC system mainly determines by reading the vehicle type information recorded in the OBU, that is, the card does not recognize the car, but the model recorded in the OBU is not necessarily the vehicle.
  • Actual models, such as the information submitted by the user when registering, are small cars, but the electronic tag OBU is finally installed on a large car to reduce the high-speed traffic.
  • the present application provides a method and apparatus for information processing that can identify an actual vehicle model with a high accuracy.
  • an information processing method including: acquiring driving data of a target vehicle; and determining an actual vehicle type of the target vehicle according to the first driving data in the driving data.
  • the server identifies the actual vehicle model of the target vehicle based on the analysis of the driving data of the target vehicle. Because the driving data of different models is different, for example, the family car is mainly used in commuting time, the driving time of the truck is relatively uniform, that is, the target. The driving data of the vehicle corresponds to the actual vehicle type, so that the actual vehicle type of the target vehicle can be identified with higher accuracy by the driving data.
  • determining the actual vehicle type of the target vehicle according to the first driving data includes: determining, according to the driving data, a travel time distribution and/or a travel track distribution of the target vehicle Determining an actual vehicle type of the target vehicle based on a travel time distribution and/or a travel trajectory distribution of the target vehicle.
  • determining the actual vehicle type of the target vehicle according to the travel time distribution and/or the travel trajectory distribution of the target vehicle includes: according to at least one travel time distribution and/or travel trajectory distribution A correspondence between the at least one vehicle type and a travel time distribution and/or a travel trajectory distribution of the target vehicle determines an actual vehicle type of the target vehicle.
  • the server may directly find the travel time distribution of the target vehicle according to the predetermined travel time distribution and/or the corresponding relationship between the travel track distribution and the vehicle type. And the vehicle with the corresponding trajectory distribution, so that the actual vehicle model of the target vehicle can be quickly determined.
  • the correspondence is obtained by using the driving data of the sample vehicle in the following manner: according to the driving data of each vehicle in the sample vehicle, the each vehicle is obtained into multiple vehicles. The probability of each vehicle type, and the travel time distribution and/or the travel track distribution of each of the vehicles; determining the vehicle type with the vehicle model probability corresponding to the first vehicle being greater than the first threshold as the actual vehicle model of the first vehicle; The corresponding relationship is obtained by describing the actual vehicle type of the first vehicle and the travel time distribution and/or the travel trajectory distribution of the first vehicle.
  • the target vehicle includes a plurality of vehicles; and the determining, according to the travel time distribution and/or travel time of the target vehicle, determining an actual vehicle type of the target vehicle, including: according to the First driving data of each of the plurality of vehicles, obtaining a probability that each of the vehicles is assigned to each of the plurality of vehicle types, and a travel time distribution and/or a travel time distribution of each of the vehicles; A vehicle type in which a vehicle corresponding vehicle model probability is greater than a first threshold is determined as an actual vehicle model of the first vehicle; and the same travel time distribution and/or driving trajectory in the travel time distribution and/or the travel trajectory distribution of the plurality of vehicles
  • the distribution constitutes a type of travel time distribution and/or travel trajectory distribution; for each type of travel time distribution and/or travel time distribution corresponding to the vehicle, determining the proportion of the first vehicle in each type of vehicle; Determining a vehicle corresponding to each type of travel time distribution and/or travel time distribution, determining a target vehicle model in which the proportion of the
  • the server may determine the vehicle type of the first vehicle as the vehicle model of the second vehicle, so that the number of vehicles of the actual vehicle type that the server can determine under offline conditions Can be significantly increased.
  • determining, according to the first driving data, determining a travel time distribution and/or a travel trajectory distribution of the target vehicle including: identifying, according to the first travel data, the target vehicle a stay point; determining, according to the frequency of occurrence of the stay point, the resident point of the target vehicle in combination with map information, determining a geographic location of the resident point; and based on the geographic location of the resident point, the resident
  • the frequent itemsets in the points are combined and connected to obtain a travel trajectory distribution of the vehicle.
  • the identifying, according to the first driving data, the stopping point of the target vehicle comprising: sequentially determining a circle with a third threshold value as a center of a different positioning point of the target vehicle; Determining a maximum time difference between the positioning points in each circle; comparing the maximum time difference value with a fourth threshold value, and determining the maximum time difference if the maximum time difference value is greater than the fourth threshold value
  • the center of the circle in which the value is located is the candidate stay point; the center point of all candidate stay points is calculated, and the center point is the stay point of the target vehicle.
  • determining the actual vehicle type of the target vehicle according to the first driving data comprising: obtaining, according to the first driving data and the first model, that the target vehicle is assigned to different models Probability, wherein the first model is obtained from a registered vehicle model of the sample vehicle in the onboard unit OBU and the driving data; based on the probability, the actual vehicle model of the target vehicle is determined.
  • the first model obtained according to the registered vehicle model of the sample vehicle generally conforms to the actual vehicle model distribution, so that the accuracy of the actual vehicle model of the target vehicle determined online by the server according to the first model is compared. high.
  • the method further includes: verifying business behavior information of the target vehicle based on the actual vehicle model, or outputting business behavior information of the target vehicle.
  • the method further includes determining, according to the second driving data and the target area in the driving data, a time when the target vehicle drives out of the target area, where the target area is a toll station Area;
  • the verifying the business behavior information of the target vehicle or outputting the business behavior information of the target vehicle based on the actual vehicle model including: verifying the target vehicle at a time when the target vehicle exits the target area Whether to pay the corresponding fee for the actual model.
  • the server can determine the range of the target area according to the diagonal coordinates of the target area, and based on the travel data of the target vehicle, that is, the longitude and latitude of the current time, can determine the coordinates of the target vehicle, and the range of the target area and The coordinates of the target vehicle can automatically identify the behavior of the target vehicle leaving the toll booth, and when the target vehicle leaves the toll booth, it can be determined whether the target vehicle pays the fee. If the payment is made, the target vehicle has been verified based on the determined actual vehicle type. Corresponding models, this can reduce the evasion behavior of the target vehicle.
  • the determining, according to the second driving data and the target area, the moment when the target vehicle exits the target area includes: determining the target vehicle based on the second driving data. Whether the time t and the time t-1 are inside the target area; if the target vehicle t-1 is inside the target area, and t is outside the target area, determining that the time t is the target vehicle The moment of exiting the target area.
  • the determining, according to the second driving data, whether the target vehicle t time and the t-1 time are within the target area including: determining in a horizontal direction or a vertical direction The positioning point of the target vehicle at time t and time t-1 is a ray of the end point; and determining whether the target vehicle t time and the time t-1 are within the target area according to the number of intersections of the ray and the target area .
  • determining, according to the number of intersections of the ray and the target area, whether the target vehicle t time and the time t-1 are within the target area including: if the ray and The number of intersections of the target area is an odd number, and the target vehicle t time or t-1 time is determined to be inside the target area; if the number of intersections of the ray and the target area is an even number, the target vehicle is determined The time or time t-1 is outside the target area.
  • the determining, according to the second driving data, whether the target vehicle t time and the t-1 time are within the target area further comprising: determining, based on the second driving data, The target vehicle t time and the t-1 time are inside a minimum outsourcing area of the target area, and the minimum outsourcing area is a rectangle.
  • the server first determines whether the target vehicle is inside the minimum outsourcing area, and if inside the minimum outsourcing area, determines whether it is inside the target area; if the target vehicle is not inside the minimum outsourcing area, it can directly determine that the target vehicle is outside the target area. Since it is judged whether the target vehicle is faster in the minimum outsourcing area, it is possible to quickly determine whether the target vehicle is inside the target area, so that it is possible to determine in real time whether the target vehicle is to leave the toll booth.
  • the determining, according to the second driving data, that the target vehicle t time and the t-1 time are within a minimum outsourcing area of the target area including: acquiring the minimum outsourcing area a diagonal coordinate; determining a range of the minimum outsourcing area based on the coordinates; obtaining coordinates of the target vehicle at time t and time t-1 based on the second driving data; The coordinates of the time t and the time t-1 and the range of the minimum outsourcing area determine that the target vehicle is inside the minimum outsourcing area at time t and time t-1.
  • the method further includes: establishing a spatial index based on the target area and the minimum outsourced area; the coordinates based on the target vehicle at time t and time t-1 and the Determining a range of the minimum outsourcing area, determining that the target vehicle is inside the minimum outsourcing area at time t and time t-1, including: based on coordinates of the target vehicle at time t and time t-1, the minimum outsourcing area The range and the spatial index determine that the target vehicle is inside the minimum outsourced area at time t and time t-1.
  • the server can quickly determine whether the target vehicle is inside the minimum outsourcing area.
  • the method further includes: verifying business behavior information of the target vehicle based on the actual vehicle model, or outputting business behavior information of the target vehicle, including: verifying based on the actual vehicle model The paid information of the target vehicle, or the information to be paid of the target vehicle.
  • the actual vehicle model of the target vehicle may be output to the roadside device, and the roadside device may charge the target vehicle according to the received actual vehicle model; or the server may verify the payment of the target vehicle. Whether the vehicle model information is consistent with the determined actual vehicle model, if it is inconsistent, a series of measures can be taken for the target vehicle, thereby reducing the loss to the operator caused by the target vehicle's small vehicle bidding behavior.
  • the method further includes: determining, according to the first driving data, a mileage of the target vehicle on a highway within a preset time;
  • the payment of the paid information of the target vehicle, or outputting the to-be-paid information of the target vehicle includes: outputting the to-be-paid information of the target vehicle based on the actual vehicle type and the mileage.
  • the server can identify the actual driving mileage of the target vehicle according to the driving data of the target vehicle, for example, by trajectory tracking, so as to avoid the card reversal behavior of the target vehicle, thereby reducing the evasion behavior of the reversed card to the operator. Economic losses.
  • the paid information includes a registered model issued by the OBU at the time of payment.
  • the method before determining the actual vehicle model of the target vehicle according to the first driving data in the driving data, the method further includes: identifying noise data in the driving data; Determining the driving data according to the noise data, and determining the actual vehicle type of the target vehicle according to the first driving data in the driving data, comprising: according to the first driving data in the corrected driving data Determining the actual vehicle type of the target vehicle.
  • the server since it is determined that the actual vehicle model of the target vehicle is based on the driving data of the target vehicle, the server recognizes and corrects the noise data in the driving data, thereby increasing the accuracy of the driving data, so that the server determines the driving data according to the driving data.
  • the actual vehicle model of the target vehicle is more accurate.
  • the identifying the noise data in the travel data includes: calculating a mean and a variance of the travel data in a time period before and after the time t; and performing the travel data at the time t and the multiple of the variance Comparing, if the travel data at the time t is greater than a multiple of the variance, determining that the travel data at the time t is noise data; and the correcting the noise data includes correcting the noise data based on the average value.
  • the correcting the noise data based on the average value includes: replacing the noise data with the average value to obtain initial correction data; and correcting the initial correction data according to a road in the map .
  • the initial correction data is corrected again in combination with the actual road distribution in the map, and part of the travel data that is not traveling on the road can be corrected to the road.
  • the identifying the noise data in the driving data includes: identifying noise data in the driving data based on a second model, wherein the second model is by using the target The displacement and acceleration of the vehicle are obtained by Kalman filtering; and the correcting the noise data comprises: correcting the noise data based on the second model.
  • the Kalman filter is built on the dynamic equation. Due to the non-mutable nature of the displacement and velocity in the driving data, the state of the current moment can be estimated by the state of the target vehicle at a moment, so that the driving data can be identified. Noise data in.
  • the correcting the noise data based on the second model includes: initializing the noise data based on the second model to obtain initial correction data; combining roads in the map, Correct the initial correction data.
  • the correcting the initial correction data by combining the roads in the map includes: determining a circle centered on the positioning point of the initial correction data and having a radius of a maximum positioning error; determining the The projection distance from the anchor point to the road intersecting the circle; the projection point on the road with the shortest projection distance is determined as the anchor point of the corrected travel data.
  • a method for processing vehicle information comprising: receiving travel data transmitted by a target vehicle; determining, based on the travel data and a target area, a time at which the target vehicle exits the target area And the target area is an area of the toll station; acquiring an actual vehicle type of the target vehicle; determining whether the target vehicle pays a fee corresponding to the actual vehicle type at a time when the target vehicle exits the target area.
  • the server determines the target area, and the range of the target area may be determined according to the diagonal coordinates of the target area, and based on the driving data of the target vehicle, that is, the longitude and the latitude, the coordinates of the target vehicle may be determined, and the range of the target area is
  • the coordinates of the target vehicle can automatically identify the behavior of the target vehicle entering and leaving the toll booth, and according to the actual vehicle model of the acquired target vehicle, when the target vehicle leaves the fare station, it can identify whether the target vehicle pays the corresponding fee of the actual vehicle, such that It can reduce the evasion behavior of the target vehicle.
  • the determining, according to the driving data and the target area, the moment when the target vehicle exits the target area includes: determining, according to the driving data, the target vehicle t time and t Whether the time is 1 inside the target area; if the target vehicle t-1 is inside the target area, and t is outside the target area, determining that the time t is the target vehicle exiting The time of the target area.
  • the determining, according to the driving data, whether the target vehicle t time and the t-1 time are inside the target area including: determining the target vehicle in a horizontal direction or a vertical direction The positioning point at time t and time t-1 is the ray of the end point; and based on the number of intersections of the ray and the target area, it is determined whether the target vehicle t time and the time t-1 are inside the target area.
  • determining, according to the number of intersections of the ray and the target area, whether the target vehicle t time and the time t-1 are within the target area including: if the ray and The number of intersections of the target area is an odd number, and the target vehicle t time or t-1 time is determined to be inside the target area; if the number of intersections of the ray and the target area is an even number, the target vehicle is determined The time or time t-1 is outside the target area.
  • the determining, according to the driving data, whether the target vehicle t time and the time t-1 are within the target area further comprising: determining the target vehicle based on the driving data.
  • the time t and the time t-1 are inside the smallest outsourcing area of the target area, and the minimum outsourcing area is a rectangle.
  • the server first determines whether the target vehicle is inside the minimum outsourcing area, and if inside the minimum outsourcing area, determines whether it is inside the target area; if the target vehicle is not inside the minimum outsourcing area, it can directly determine that the target vehicle is outside the target area. Since it is judged whether the target vehicle is faster in the minimum outsourcing area, it is possible to quickly judge whether the target vehicle is inside the target area, so that it is possible to determine in real time whether the target vehicle is to enter the toll booth or leave the toll booth.
  • the determining, according to the driving data, that the target vehicle t time and the t-1 time are within a minimum outsourcing area of the target area including: acquiring two pairs of the minimum outsourcing area The coordinates of the angle; determining a range of the minimum outsourcing area based on the coordinates; obtaining coordinates of the target vehicle at time t and time t-1 based on the driving data; based on the target vehicle at time t and t The coordinates of the -1 time and the range of the minimum outsourced area are determined to be within the minimum outsourced area at time t and time t-1.
  • the method further includes: establishing a spatial index based on the target area and the minimum outsourced area; the coordinates based on the target vehicle at time t and time t-1 and the Determining a range of the minimum outsourcing area, determining that the target vehicle is inside the minimum outsourcing area at time t and time t-1, including: based on coordinates of the target vehicle at time t and time t-1, the minimum outsourcing area The range and the spatial index determine that the target vehicle is inside the minimum outsourced area at time t and time t-1.
  • the server can quickly determine whether the target vehicle is inside the minimum outsourcing area.
  • the method before the determining, by the driving data and the target area, the time when the target vehicle exits the target area, the method further includes: identifying noise data in the driving data; Correcting the noise data to obtain corrected travel data; determining, according to the travel data and the target area, a time at which the target vehicle exits the target area, comprising: based on the corrected second travel data And a target area at which the target vehicle exits the target area.
  • the server since it is determined that the target vehicle leaves the toll booth based on the driving data of the target vehicle, the server recognizes and corrects the noise data in the driving data, thereby increasing the accuracy of the driving data, so that the server determines the target according to the driving data. Whether the vehicle enters the toll booth or leaves the toll booth is more accurate.
  • the identifying the noise data in the travel data includes: calculating a mean and a variance of the travel data in a time period before and after the time t; and performing the travel data at the time t and the multiple of the variance Comparing, if the travel data at the time t is greater than a multiple of the variance, determining that the travel data at the time t is noise data; and the correcting the noise data includes correcting the noise data based on the average value.
  • the correcting the noise data based on the average value includes: replacing the noise data with the average value to obtain initial correction data; and correcting the initial correction data according to a road in the map .
  • the initial correction data is corrected again in combination with the actual road distribution in the map, and part of the travel data that is not traveling on the road can be corrected to the road.
  • the identifying the noise data in the driving data comprises: identifying noise data in the driving data based on a model, wherein the model is by displacement of the target vehicle and The acceleration is obtained by Kalman filtering; the correcting the noise data includes: correcting the noise data based on the model.
  • the Kalman filter is built on the dynamic equation. Due to the non-mutable nature of the displacement and velocity in the driving data, the state of the current moment can be estimated by the state of the target vehicle at a moment, so that the driving data can be identified. Noise data in.
  • the correcting the noise data based on the model includes: initializing the noise data based on the model, and obtaining initial correction data; and correcting the initial in combination with a road in the map Correct the data.
  • the correcting the initial correction data by combining the roads in the map includes: determining a circle centered on the positioning point of the initial correction data and having a radius of a maximum positioning error; determining the The projection distance from the anchor point to the road intersecting the circle; the projection point on the road with the shortest projection distance is determined as the anchor point of the corrected travel data.
  • a vehicle information processing apparatus comprising means for performing the method of any of the above-described first aspect or any of the possible implementations of the first aspect.
  • a vehicle information processing apparatus comprising means for performing the method of any of the above-described second aspect or any of the possible implementations of the second aspect.
  • a fifth aspect provides a vehicle information processing apparatus including a processor and a memory, the memory for storing computer instructions, the processor for executing computer instructions stored in the memory, when the computer instructions are executed
  • the processor is operative to perform the method of any of the first aspect or the first aspect of the first aspect.
  • a sixth aspect provides a vehicle information processing apparatus including a processor and a memory, the memory for storing computer instructions, the processor for executing computer instructions stored in the memory, when the computer instructions are executed
  • the processor is operative to perform the method of any of the second aspect or the second aspect of the second aspect.
  • an electronic non-stop charging ETC system comprising the vehicle information processing apparatus of the fifth aspect.
  • an electronic non-stop charging ETC system comprising the vehicle information processing apparatus of the sixth aspect.
  • a ninth aspect a computer readable storage medium comprising computer instructions that, when executed on a computer, cause the computer to perform any of the possible implementations of the first aspect or the first aspect described above Said method.
  • a tenth aspect a computer readable storage medium comprising computer instructions that, when executed on a computer, cause the computer to perform any of the possible implementations of the second or second aspect described above Said method.
  • a computer program product comprising instructions for causing the computer to execute in any of the possible implementations of the first aspect or the first aspect described above when the computer program product is run on a computer The method described.
  • a twelfth aspect a computer program product comprising instructions for causing a computer to perform any of the possible implementations of the second aspect or the second aspect described above when the computer program product is run on a computer The method described.
  • FIG. 1 is a schematic diagram of a network architecture provided by an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of an information processing method provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of comparison before and after correction of driving data of a target vehicle according to an embodiment of the present application
  • FIG. 4 is a schematic flow chart of a possible implementation of 220 in FIG. 2;
  • FIG. 5 is a schematic diagram of a waveform characteristic of a target vehicle according to an embodiment of the present application.
  • FIG. 6 is a schematic diagram of a stay point of a target vehicle according to an embodiment of the present application.
  • FIG. 7 is a schematic flow chart of a possible implementation of 220 in FIG. 2;
  • FIG. 8 is a schematic diagram of a target area and a minimum outsourcing area provided by an embodiment of the present application.
  • FIG. 9 is a schematic diagram of a manner of determining a target vehicle within a target area according to an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application.
  • FIG. 1 is a schematic diagram of a network architecture of an ETC system to which an embodiment of the present application can be applied.
  • the ETC system 100 can include an in-vehicle device 110, a roadside device 120, and a server 130.
  • the in-vehicle device 110 can be used to collect, transmit, and store data of vehicle travel, such as speed, direction, displacement, and daily travel time of the vehicle.
  • the in-vehicle device 110 may include an OBU, a positioning device (such as a global positioning system (GPS)), a three-axis accelerometer, a driving recorder, and any on-board sensor.
  • GPS can be used to collect the longitude, latitude, altitude, direction, speed, etc. of the vehicle.
  • the three-axis accelerometer can be used to collect the linear acceleration of the vehicle in the X, Y and Z directions during driving. It can be used to record images and sounds while the vehicle is in motion.
  • the roadside device 120 can be used to read and write data stored in the in-vehicle device 110, collect external information of the vehicle, or control vehicle traffic. It can also calculate the toll fee of the vehicle and automatically deduct the toll from the dedicated account of the vehicle user.
  • the roadside device 120 may include an RSU, a phased array antenna, a lane camera, an induction coil, an automatic railing machine, and the like.
  • the server 130 can be configured to receive, store, and process requests sent by the client, wherein the server 130 can be a physical cluster or a virtual cloud or the like.
  • the client may be the in-vehicle device 110 or the roadside device 120 or the like.
  • the road test device 120 can establish a microwave communication link with the in-vehicle device 110 by using DSRC technology, thereby implementing communication between the roadside device 120 and the in-vehicle device 110.
  • the in-vehicle device 110 can transmit the collected data of the vehicle travel to the server 130, and the server 130 stores the received data of the vehicle travel in chronological order.
  • the server 130 may transmit indication information to the in-vehicle device 110, which may instruct the in-vehicle device 110 to turn on trajectory tracking or the like.
  • the roadside device 120 may transmit the calculated vehicle toll fee to the server 130, and after receiving the vehicle toll fee transmitted by the roadside device 120, the server 130 may check whether the vehicle toll is abnormal.
  • FIG. 2 is a schematic flowchart of an information processing method according to an embodiment of the present application.
  • the method of FIG. 2 may be performed by a server, which may be server 130 of FIG.
  • server 130 of FIG. the method of FIG. 2 can also be performed by other devices, which is not limited in this embodiment of the present application.
  • the method of FIG. 2 may include 210-220, and 210-220 are described in detail below.
  • the travel data of the target vehicle is acquired.
  • the driving data of the target vehicle may include at least one of: longitude, latitude, altitude, direction, speed, displacement, linear acceleration in the X direction, linear acceleration in the Y direction, and linearity in the Z direction of the target vehicle. Acceleration, etc.
  • X, Y, and Z represent the X axis, the Y axis, and the Z axis in the space rectangular coordinate system.
  • the server may acquire the driving data of the target vehicle by collecting signals transmitted by the in-vehicle device installed on the target vehicle.
  • the server may collect signals transmitted by the in-vehicle device at a fixed frequency.
  • the frequency of the sensor signal collected by the server may be 1 s or 0.1 s, etc., which is not limited in this embodiment.
  • the signal sent by the onboard device may be a sensor signal.
  • the sensor signal may include, but is not limited to, an in-vehicle device receiving positioning information of the in-vehicle device transmitted by the satellite navigation system, and spatial acceleration information read from a three-axis accelerometer built in the in-vehicle device.
  • a series of driving data such as longitude, latitude, altitude, direction, speed and displacement of the target vehicle can constitute the positioning information of the target vehicle
  • the driving data such as linear acceleration in the three directions of X, Y and Z can constitute the acceleration of the target vehicle. information.
  • the in-vehicle device installed on the target vehicle may transmit the driving data of the target vehicle for a certain period of time to the server.
  • the driving data in the certain period of time may be the driving data of one day, or the driving data of two days or one week, which is not limited in this application.
  • the in-vehicle device may also transmit the driving data of the current time of the target vehicle to the server in real time.
  • the strength of the signal collected by the server may be weakened, or may be caused by the interference source, or even at a certain moment, just in the satellite positioning blind zone, etc., may cause the GPS receiver to calculate Deviation, which may cause noise data to appear in the driving data of the target vehicle.
  • the server can recognize the noise data in the travel data and correct the noise data to obtain the corrected travel data.
  • this process There are many implementations of this process, which are not specifically limited in this embodiment of the present application.
  • the noise data may represent data in which deviations occur in the travel data received by the server.
  • the target vehicle t when the target vehicle t is at a position of 103 degrees east longitude and 34 degrees north latitude, and the position of the target vehicle t acquired by the server is 115 degrees east longitude and 41 degrees north latitude, it can be determined that the travel data of the target vehicle t time acquired by the server is Noise data.
  • the server may calculate the mean and variance of the driving data in the time period before and after the time t, and then compare the driving data at time t with the multiple of the variance. If the driving data at time t is greater than a multiple of the variance, it may be determined that t The driving data at the moment is noise data.
  • the server can also calculate the mean and standard deviation of the driving data in the time period before and after t. After obtaining the variance by the standard deviation, the driving data at time t is compared with the multiple of the variance, and if the driving data at time t is greater than the variance In multiples, it can be determined that the travel data at time t is noise data.
  • the in-vehicle device may obtain driving data of the target vehicle, such as the longitude and latitude of the target vehicle, by using a GPS at a certain update rate, and then transmit the driving data to the server.
  • the update rate of the GPS may be 1 s or 0.1 s.
  • the server wants to detect whether the driving data at the time t of the target vehicle is noise data
  • the time periods tk, t-(k-1), t-(k-2), ..., t-1 and t+1 may be calculated first.
  • ..., t+(k-2), t+(k-1), t+k corresponds to the mean and standard deviation of the longitude and latitude, and then determines whether the value of the longitude and latitude of the target vehicle t is in the range of three times the variance Inside. If it is out of range, it can be determined that the travel data at time t is noise data.
  • the server After identifying the noise data in the travel data, the server can correct the noise data based on the average mentioned above.
  • the server may replace the noise data with the mean value, obtain the initial correction data, and combine the roads in the map to correct the initial correction data.
  • the server may roughly determine which road the target vehicle is traveling on based on the travel trajectory of the target vehicle. Specifically, the server may determine a circle whose center is the center of the initial correction data and whose radius is the maximum positioning error. The road intersecting the circle may constitute a road set that includes the best matching road.
  • the server can then determine the location of the best match road and the corrected travel data. Specifically, the server may determine the projection distance of the positioning point to the road intersecting the circle, determine the road with the shortest projection distance as the best matching road, and the projection point on the best matching road is the positioning of the corrected driving data. point.
  • the travel trajectory of the target vehicle mentioned above may be obtained by chronologically arranging a series of travel data of the target vehicle.
  • the maximum positioning error mentioned above can be read from the GPS. Under normal circumstances, GPS positioning error is within 10-20 meters.
  • the road matching result at time t may be based on the road matching result at time t-1. If the road matching result at time t-1 is located in the matching road set at time t, the server may time t-1 The road is determined as the best matching road at time t; if the road matching result at time t-1 is not in the road set matched at time t, the server can determine the road with the shortest projection distance as the best matching road at time t.
  • the server can then determine the circle with the radius of 20 meters as the center of the initial correction data at time t, and the roads intersecting the circle have L1, L2, and L3.
  • the server can determine the projection distance from the positioning point of the correction data at the beginning of time t to L1, L2 and L3, respectively, and determine the road with the shortest projection distance as the best matching road, for example, the projection distance of the initial correction data to the L1 at time t is 5 meters, the initial correction data at time t to L2 has a projection distance of 3 meters, and the initial correction data at time t to L3 has a projection distance of 2 meters. It can be determined that L3 is the best matching road, and the projection point on L3 is corrected.
  • the server may identify noise data in the travel data based on the model.
  • the server can obtain the optimal estimation model by Kalman filtering of the displacement and acceleration in the target vehicle driving data, and identify the noise data in the driving data based on the obtained optimal estimation model.
  • the subscript t represents the traveling state at the time of the target vehicle t
  • the subscript t-1 represents the traveling state at the time of the target vehicle t-1
  • p represents the displacement of the target vehicle
  • v represents the speed of the target vehicle
  • u represents the acceleration of the target vehicle.
  • Control matrix For the state transition matrix, Control matrix
  • x t contains the observed targets, such as displacement and velocity;
  • w t is the process noise, which is consistent with the Gaussian distribution.
  • the Kalman filter is built on the dynamic process. Due to the non-mutation characteristic of the target vehicle displacement and speed, the state of the time t can be predicted by the state of the target vehicle t-1, thereby identifying the noise data. For example, the acceleration of the target vehicle t-1 is zero, and the speed at time t has changed. It can be determined that there is an observation error at time t, and the travel data at time t is noise data.
  • the in-vehicle device may obtain the positioning information of the target vehicle at a certain update rate through GPS and acceleration integration, and then transmit the driving data to the server.
  • the update rate of the acceleration integral includes, but is not limited to, 0.1 s or 0.01 s, and the like.
  • the server may correct the identified noise data based on the optimal estimation model. Specifically, the server may first correct the noise data based on the optimal estimation model to obtain the initial correction data. Combined with the road in the map, the initial correction data is corrected.
  • the left picture shows the trajectory of the target vehicle after the initial correction
  • the right picture shows the trajectory of the target vehicle after correction.
  • the server combines the roads in the map, and after correcting the initial correction data again, the target vehicles are located on the road.
  • the server since it is determined that the actual vehicle model of the target vehicle is based on the driving data of the target vehicle, the server recognizes and corrects the noise data in the driving data, thereby increasing the accuracy of the driving data, so that the server determines the driving data according to the driving data.
  • the actual vehicle model of the target vehicle is more accurate.
  • an actual vehicle type of the target vehicle is determined based on the first travel data in the travel data.
  • the model may be expressed as a vehicle model corresponding to the toll of the vehicle, such as a passenger car of less than seven seats, a passenger car of more than 40 seats, a truck of 5 to 10 tons of load, and the like.
  • the first travel data may represent travel data for a target vehicle for a certain period of time.
  • the certain period of time may be one day, or one week.
  • the target vehicle may include one vehicle, and may also include multiple vehicles, which is not limited in this application.
  • the server may determine the actual vehicle type of the target vehicle in real time according to the driving data of the target vehicle.
  • the server may determine the actual vehicle models of the plurality of vehicles offline at a certain time according to the first driving data of the plurality of vehicles in the acquired preset time period.
  • the preset time period can be one day.
  • the server may determine the actual vehicle models of the plurality of vehicles offline at 12 o'clock every night based on the first driving data of the plurality of vehicles acquired on the same day.
  • the server may also determine an actual vehicle type of the target vehicle according to the first driving data in the corrected driving data.
  • FIG. 4 is a schematic flow chart of one possible implementation of 220 in FIG. 2.
  • the method of Figure 4 can include 410-420.
  • a travel time distribution and/or a travel trajectory distribution of the target vehicle is determined based on the first travel data.
  • the waveform mode can be used to characterize the travel time distribution of the target vehicle.
  • the trajectory mode can be used to characterize the trajectory distribution of the target vehicle.
  • the server may determine the waveform mode and/or the trajectory mode of the target vehicle based on the first travel data.
  • the server may determine the waveform mode of the target vehicle according to the first driving data of the target vehicle within the preset time period.
  • the preset time period may be one hour, one day, or one week, which is not limited in this application.
  • the server may determine the waveform characteristics of the target vehicle according to the hourly travel time of the target vehicle during the day and the distribution of the travel time of the day of the week, and then use the clustering algorithm to identify the waveform pattern of the target vehicle.
  • the waveform features may include the total driving duration of the target vehicle per day, the total driving duration of the week, the continuous driving time, the two driving time intervals, and the like.
  • the clustering algorithm may be a k-means algorithm, a clarans algorithm, a birch algorithm, or the like.
  • Figure 5 is a distribution of travel time of a big car and a car during the day.
  • the dotted line indicates the waveform characteristics of the cart
  • the solid line indicates the waveform characteristics of the cart
  • the horizontal axis is 24 hours in the day
  • the vertical axis represents how long the cart and the car have traveled in the time period corresponding to the horizontal axis (0-1 hour).
  • the waveform characteristics of the big car and the small car are different: the car is mainly used in commuting time, while the driving time of the big car is evenly distributed, and the total driving time of one day is much larger than that of the car.
  • the server may determine a trajectory pattern of the target vehicle based on the first travel data of the target vehicle.
  • the server may identify a stop point of the target vehicle according to the first travel data of the target vehicle, and determine a resident point of the target vehicle according to the frequency of occurrence of the identified stop point.
  • the server can combine the map information to determine the geographic location of the target vehicle's resident point.
  • the location of the resident point can be a gas station, a school, an office building, a community, a building materials market, and the like. Based on the geographic location of the resident point, the frequent itemsets in the resident point are combined and connected, so that the trajectory mode of the target vehicle can be obtained.
  • the stop point may be made up of a set of actual anchor points of the target vehicle, which does not refer to the point at which the target vehicle speed is zero.
  • the positioning points P3, P4, P5, and P6 of the target vehicle may constitute a stay point s.
  • the resident point may indicate that a higher frequency of the stay point occurs within a certain time.
  • the stay point 1 appears twice in a day
  • the stay point 2 appears once in a day
  • the stay point 3 appears five times in a day, then it can be determined that the stay point 3 is a resident point.
  • the frequent item set may represent a plurality of resident points that often occur simultaneously.
  • the three resident points of the warehouse 1, the gas station 1 and the gas station 2 often appear together, and the warehouse 1, the gas station 1 and the gas station 2 can be represented as a frequent item set.
  • frequent itemsets that are closer in time may be combined and connected in chronological order.
  • warehouse 1, gas station 1 and gas station 2 are frequent itemsets 1, warehouse 2, gas station 2, gas station 1 and warehouse 1 are frequent itemsets 2, frequent items 1 and frequent items 2 are adjacent.
  • frequent item set 1 often appears first, and frequent item set 2 often appears later. Therefore, after frequent item set 1 and frequent item set 2 are combined and connected, "Warehouse 1-gas station 1-gas station 2- Warehouse 2 - Gas station 2 - Gas station 1 - Warehouse 1" track mode.
  • the server may detect each of the target vehicle travel trajectories in the process of identifying the target vehicle stay point, and then sequentially determine the target vehicle's different locating points as the center of the target vehicle, and determine the radius by the distance threshold. Circles, points within each circle can be grouped into a collection. Within each circle, determine the earliest and latest point of time, and calculate the time difference, that is, the maximum time difference between the anchor points, and then the server can compare the maximum time difference with the time threshold, if If the maximum time difference is greater than the time threshold, it can be determined that the center of the circle where the maximum time difference is located is the candidate stay point. Then calculate the center point of all candidate stay points, which is the stop point of the target vehicle.
  • the server may use an association analysis algorithm to mine a frequent item set from the resident point of the target vehicle.
  • the association analysis algorithm may include, but is not limited to, an FP-growth algorithm, an apriori algorithm, and the like.
  • P1, P2, P3, ..., P8 are the anchor points of the target vehicle, and the distance threshold is Y, and the time threshold is H.
  • the server sequentially determines the circle with P1, P2, P3, ..., P8 as the center and Y as the radius.
  • P2, P3, P4, P5, and P6 are five positioning points. These five positioning points can form a set. The earliest point in the set is P2, and the latest point is P6, calculating the time difference between P2 and P6, and comparing the calculated time difference with H. If the time difference is greater than H, it can be determined that P3 is a candidate stay point, and the remaining seven can be determined by the same method. Whether the anchor points are candidate stay points.
  • the actual vehicle type of the target vehicle is determined based on the waveform mode and/or the trajectory mode of the target vehicle.
  • the server may determine the actual vehicle type of the target vehicle according to the correspondence between the at least one waveform mode and/or the trajectory mode and the at least one vehicle type, and the waveform mode and/or the trajectory mode of the target vehicle.
  • one waveform mode and/or track mode may correspond to one vehicle type.
  • multiple waveform modes and/or track modes may also correspond to one vehicle type.
  • the server may use the travel data of the sample vehicle to obtain a correspondence.
  • the server may obtain a probability that each vehicle is assigned to each of a plurality of vehicle types according to the driving data of each vehicle in the sample vehicle, and a waveform mode and/or a trajectory mode of each vehicle;
  • the vehicle type in which the vehicle corresponding vehicle probability is greater than the first threshold is determined as the actual vehicle model of the first vehicle, and the corresponding relationship can be obtained based on the determined actual vehicle model of the first vehicle and the waveform pattern and/or the trajectory pattern of the first vehicle.
  • the waveform mode of the vehicle A can be obtained as the waveform mode 1, and the probability that the vehicle A is assigned to the trolley is 0.97, and the probability of being assigned to the cart is 0.03, it can be determined that the actual model of the vehicle A is the trolley, and the trolley corresponds to the waveform mode 1.
  • the waveform mode of the target vehicle determined by the server is the waveform mode 1, and the server can determine the actual vehicle model of the target vehicle as the trolley according to the correspondence between the waveform mode 1 and the trolley and the waveform mode of the target vehicle.
  • the server may directly find the travel time distribution of the target vehicle according to the predetermined travel time distribution and/or the corresponding relationship between the travel track distribution and the vehicle type. And the vehicle with the corresponding trajectory distribution, so that the actual vehicle model of the target vehicle can be quickly determined.
  • the server may obtain a probability that each vehicle is assigned to each of the plurality of types of vehicles according to the first driving data of each of the plurality of vehicles. And a waveform mode and/or a trajectory mode of each vehicle, and determining a vehicle model whose vehicle probability corresponding to the first vehicle is greater than the first threshold is determined as an actual vehicle model of the first vehicle.
  • the server may obtain a probability that each vehicle is assigned to each of the plurality of types of vehicles according to the first driving data and the classification model of each of the plurality of vehicles, and the specific implementation manner is illustrated in FIG. 7 . I will not repeat them here.
  • the server may obtain the probability that each vehicle is assigned to the big car and the small car according to the first driving data of the plurality of vehicles, for example, the probability that the target vehicle 1 is assigned to the big car is 0.4, and is assigned to the small car.
  • the probability is 0.6; the probability of the target vehicle 2 to the big car is 0.2, the probability of the minute car is 0.8; the probability of the target vehicle 3 to the big car is 0.99, the probability of the minute car is 0.01, due to the target vehicle 3 points
  • the probability of the cart is greater than the first threshold of 0.9, and therefore, it can be determined that the actual model of the target vehicle 3 is the cart, the target vehicle 3 is marked, and the target vehicle 3 is determined as the representative sample of the cart.
  • the server can determine that the actual number of vehicles in the vehicle is small. For example, if there are 100 vehicles in the target vehicle, the server can determine that the actual vehicle may have only 30 vehicles. Therefore, it is necessary to further determine the remaining vehicles.
  • the actual model For example, if there are 100 vehicles in the target vehicle, the server can determine that the actual vehicle may have only 30 vehicles. Therefore, it is necessary to further determine the remaining vehicles. The actual model.
  • the server may form the same waveform mode and/or the trajectory mode in the waveform mode and/or the trajectory mode of the plurality of vehicles into one type of waveform mode and/or trajectory mode, thereby obtaining multiple types of waveform modes and / or track mode.
  • the server may determine, for each type of waveform mode and/or a vehicle corresponding to the trajectory mode, a proportion of the first vehicle in the vehicle of each vehicle type, and a target vehicle in which the proportion of the first vehicle is greater than a second threshold.
  • the target vehicle type may be determined as the vehicle type of the second vehicle for the second vehicle in the vehicle corresponding to each type of waveform mode and/or trajectory mode.
  • the second vehicle is a vehicle other than the first vehicle among the plurality of vehicles.
  • the first vehicle may also be referred to as a marked vehicle
  • the second vehicle may also be referred to as an unmarked vehicle, which is not limited herein.
  • the multi-class waveform modes determined by the server are: waveform mode 1, waveform mode 2, waveform mode 3, ..., multi-class trajectory mode has trajectory mode 1, trajectory mode 2, trajectory mode 3... .
  • the multi-class waveform modes determined by the server are: waveform mode 1, waveform mode 2, waveform mode 3, ..., multi-class trajectory mode has trajectory mode 1, trajectory mode 2, trajectory mode 3... .
  • the term “and/or” is merely an association relationship describing an associated object, indicating that there may be three relationships, for example, A and/or B, which may indicate that A exists separately, and A and B exist simultaneously. There are three cases of B alone.
  • the server when certain conditions are met, the server can determine the model of the unmarked vehicle as the model of the marked vehicle, so that the number of vehicles of the actual model that the server can determine can be significantly increased.
  • FIG. 7 is a schematic flow chart of a possible implementation of 220 in FIG.
  • the method of Figure 7 can include 710-720.
  • the server can determine the actual vehicle type of the target vehicle in real time based on the first driving data of the target vehicle.
  • the probability that the target vehicle is assigned to different vehicle models is obtained.
  • the model can be trained from the registered vehicle model vehicle in the OBU and the driving data of the sample vehicle.
  • the travel data of the sample vehicle may be a statistical feature of the three-axis acceleration.
  • the statistical characteristics of the three-axis acceleration may be various, which is not specifically limited in the embodiment of the present application.
  • the statistical characteristics of the acceleration may include at least one of the following: maximum acceleration/deceleration, percentage of acceleration/deceleration greater than 1 m/s, and standard deviation of acceleration/deceleration.
  • the model can be a classification model.
  • the classification model may be a random forest, a gradient boosting decision tree (GBDT), a logistic regression (LR), a support vector machine (SVM), or a deep neural network (deep neural network). DNN) and so on.
  • the number of models in the sample vehicle is such that the probability of getting the target vehicle is so many models. If the sample vehicle has five types of vehicles, the server can obtain the probability that the target vehicle is divided into five types of vehicles according to the driving data of the target vehicle and the classification model.
  • an actual vehicle type of the target vehicle is determined based on the obtained probability.
  • the probability that the server can divide the target vehicle into different vehicle models is compared with a first threshold. If the probability that the target vehicle is assigned to a certain type of vehicle is greater than the first threshold, the vehicle model may be determined as the actual vehicle model of the target vehicle.
  • the first threshold is 0.9, according to the driving data of the target vehicle and the classification model, the probability that the target vehicle is assigned to the cart is 0.95, and the probability of being assigned to the cart is 0.05, the server can determine the actual model of the target vehicle. For the big car.
  • the server identifies the actual vehicle model of the target vehicle based on the analysis of the driving data of the target vehicle. Because the driving data of different models is different, for example, the family car is mainly used in commuting time, the driving time of the truck is relatively uniform, that is, the target. The driving data of the vehicle corresponds to the actual vehicle type, so that the actual vehicle type of the target vehicle can be identified with higher accuracy by the driving data.
  • the method may further include: verifying the business behavior information of the target vehicle based on the actual vehicle type, or outputting the business behavior information of the target vehicle.
  • the business behavior information may include non-contributory information and payment information.
  • the non-payment information may include indication information sent by the server to the roadside device, and may also include an elapsed time of the target vehicle, or a picture of the target vehicle, and the like.
  • the server may compare the actual vehicle model of the target vehicle with the registered vehicle model and transmit indication information to the roadside device for indicating a comparison result of the actual vehicle model and the registered vehicle model of the target vehicle.
  • the automatic fence machine of the roadside device is lifted, and the target vehicle passes; if the indication information indicates that the actual vehicle model and the registered vehicle model of the target vehicle are different, the road side The device prohibits the passage of the target vehicle.
  • the roadside device may have a display screen, and if the indication information indicates that the actual vehicle model and the registered vehicle model of the target vehicle are different, the display screen blinks continuously.
  • the alarm device may alarm, such as a beep; if the indication information indicates the actual vehicle type and registration of the target vehicle. If the models are the same, the alarm device will not alarm.
  • the server may store the elapsed time of the target vehicle, a picture of the target vehicle, and the like in a database.
  • the payment information may include information on whether the target vehicle pays, the paid information, and the to-be-paid information.
  • the paid information may include a registered model issued by the OBU when the target vehicle pays, and the to-be-paid information may include the actual model of the target vehicle.
  • the server can verify the paid information of the target vehicle or output the to-be-paid information of the target vehicle.
  • the server may output the actual vehicle model of the target vehicle to the roadside device based on the actual vehicle model of the target vehicle, and the roadside device may charge the target vehicle according to the actual vehicle model.
  • the server may report the relevant case to the system for further review.
  • the server may increase the sample weight of the target vehicle, and correct the registered vehicle type information of the target vehicle that is inconsistent with the feedback result to the actual vehicle type information determined by the server.
  • the server can check whether the actual model of the target vehicle is consistent with the registered model. If the actual model of the target vehicle is inconsistent with the registered model, for example, the registered model of the vehicle C is a small car, but the model identified by the server is a large vehicle, the server can make all the inconsistencies The case is reported to the system for review. For example, there are vehicles C and vehicles D that are suspected of having a small car. After the server reports the inconsistent case to the system, it can feedback to the actual vehicle model of the target vehicle in the system inconsistency case, such as the vehicle C-large car and the vehicle D-large car.
  • the server may change the vehicle type in the registration information of the vehicle C and the vehicle D to a large vehicle, and when training the classification model in the next round, increase the weight of the sample vehicle corresponding to the vehicle C and the vehicle D, and directly drive the vehicle C and the vehicle D.
  • Adding a representative sample set that is, adding a vehicle C and a vehicle D to the representative sample of the cart.
  • the server may verify the paid information of the target vehicle based on the actual vehicle type. If the payment information determined by the server is inconsistent with the actual payment information of the target vehicle, the server may lower the credit value of the target vehicle, or may remotely prohibit the target vehicle from using the OBU. If the owner of the target vehicle does not clarify and pay the amount of the payment, the stop is blocked. The target vehicle enters the high speed next time.
  • the server may verify the paid information of the target vehicle based on the actual vehicle type, or output the to-be-paid information of the target vehicle to the roadside device, and the roadside device charges the target vehicle according to the to-be-paid information, thereby reducing The loss of the target vehicle's small vehicle behavior to the operator.
  • the server may determine the time when the target vehicle exits the target area based on the second travel data and the target area in the travel data.
  • the target area is an area of a toll booth.
  • the target area may be a polygon. As shown in FIG. 8, the area indicated by the solid line is the target area.
  • the server may determine the range of the target area according to the range size of the toll booth.
  • the second travel data may represent travel data of the target vehicle t-1 time and time t.
  • the second driving data may be the longitude and latitude of the target vehicle at time t-1 and time t.
  • the target vehicle t-1 is within the target area and the time t is outside the target area, it may be determined that the time t is the time when the target vehicle exits the target area. .
  • the server may determine whether the target vehicle t time and the t-1 time are inside the target area based on the second travel data of the target vehicle.
  • the server may directly determine whether the target vehicle t time and the t-1 time are inside the target area based on the second travel data of the target vehicle.
  • the server may determine, in a horizontal direction or a vertical direction, a ray whose end point is the target point at the time t and the time t-1, and determine the target vehicle t time and t-1 according to the number of intersections of the ray and the target area. Whether the moment is inside the target area.
  • the target vehicle t time or t-1 time is inside the target area; if the number of intersections of the ray and the target area is an even number, it can be determined that the target vehicle t time or t-1 time is not Inside the target area.
  • the point O1 is an anchor point at the time of the target vehicle t-1
  • O2 is an anchor point at the time of the target vehicle t.
  • Rays with endpoints O1 and O2 as endpoints are determined in the horizontal direction. It can be seen that the ray with O1 as the end point has an intersection with the target area, and the ray with the end point of O2 has two intersections with the target area. Therefore, it can be determined that the target vehicle t-1 is inside the target area, and the time t is at the target. Outside the area, the time t is determined as the time when the target vehicle leaves the target area.
  • the server may further determine, in the horizontal direction and the vertical direction, the ray whose end point is the target point at the time t and the time t-1, thereby determining two rays, respectively, according to the two rays and the target area. The number of intersections is determined whether the target vehicle t time and the time t-1 are inside the target area.
  • the server may determine, based on the second driving data, that the target vehicle t time and the t-1 time are within the minimum outsourcing area, and then determine whether the target vehicle t time and the t-1 time are inside the target area.
  • the minimum outsourcing area may represent an approximate range of the target area, and the minimum outsourcing rectangle may be a rectangle, as shown in FIG. 8, and the area indicated by the broken line is the smallest outsourcing area.
  • the server may obtain coordinates of two diagonals of the minimum outsourcing area, and determine the range of the minimum outsourcing area based on the acquired coordinates. Based on the second travel data of the target vehicle, the longitude and latitude data of the target vehicle can be obtained, so that the coordinates of the target vehicle at time t and time t-1 can be determined. Based on the coordinates of the target vehicle at time t and time t-1 and the range of the minimum outsourced area, it can be determined that the target vehicle is inside the minimum outsourced area at time t and time t-1.
  • the server can determine that the target vehicle t is within the minimum outsourcing area, and the t-1 time is not within the minimum outsourcing area.
  • the server After the server determines that the target vehicle t is inside the minimum outsourcing area, it can further determine whether the target vehicle t time is inside the target area.
  • the method of the above description has been described in detail, and details are not described herein again.
  • the server first determines whether the target vehicle is inside the minimum outsourcing area, and if inside the minimum outsourcing area, determines whether it is inside the target area; if the target vehicle is not inside the minimum outsourcing area, the target vehicle can be directly determined to be in the target Outside the area, since it is judged whether or not the target vehicle is faster inside the minimum outsourcing area, it is possible to quickly judge whether or not the target vehicle is inside the target area, so that it is possible to determine in real time whether or not the target vehicle is to leave the toll booth.
  • the server may establish a spatial index based on the target area and the minimum outsourced area, and then determine the target vehicle at time t and t- based on the coordinates of the target vehicle at time t and time t-1, the range of the minimum outsourced area, and the spatial index. 1 moment is inside the smallest outsourcing area.
  • the spatial index may be an R-tree spatial index.
  • the server can determine the minimum outsourcing area corresponding to all toll station areas as the leaf node of the R tree, and the parent node can frame all areas of its child nodes and form a minimum boundary area.
  • C, D, E, F, G, H, I, J represent the minimum outsourcing area corresponding to eight toll stations, C, D, E, F are relatively close, and can form the minimum boundary area A; G, H The distance between I and J is relatively close, and the minimum boundary area B can be formed. Therefore, it can be determined that C, D, E, F, G, H, I, and J are leaf nodes, and A is the parent node of C, D, E, and F. , B is the parent node of G, H, I, J.
  • the server may first determine whether the target vehicle is in the A or B area, and if in the A area, the server continues to determine which of the C, D, E, and F the target vehicle is in, without further determining whether the target vehicle is in the G or H. , I, J area.
  • the server can quickly determine whether the target vehicle is inside the minimum outsourcing area.
  • the server may verify the paid information of the target vehicle based on the determined actual vehicle type when the target vehicle exits the target area.
  • the actual vehicle model may be determined by the server according to the first driving data of the target vehicle mentioned in the foregoing content, or may be determined by the server according to other methods such as a picture of the target vehicle, a laser, or the like. Specifically limited.
  • the server may verify whether the target vehicle pays the fee corresponding to the actual vehicle model when the target vehicle exits the target area, and if the target vehicle does not have a payment operation or the payment fee does not correspond to the actual vehicle type, the server may start. A series of measures.
  • the server can automatically report the anomaly to the system for further review.
  • the server may lower the credit value of the target vehicle, and when the credit value of the target vehicle drops to a certain extent, the server will prohibit the high speed on the target vehicle.
  • the server can remotely prohibit the target vehicle from using the OBU. If the owner does not clarify and pay the amount of the payment, the next time the speed is blocked.
  • the server determines the target area, and the range of the target area may be determined according to the diagonal coordinates of the target area, and based on the driving data of the target vehicle, that is, the longitude and the latitude, the coordinates of the target vehicle may be determined, and the range of the target area is
  • the coordinates of the target vehicle can automatically identify the behavior of the target vehicle entering and leaving the toll booth, and can identify whether the target vehicle pays when the target vehicle leaves the fare station. If the server detects that the target vehicle pays abnormally, it starts a series of prevention target vehicles twice. Measures to evade fees. This can reduce the evasion behavior of the target vehicle.
  • the server may determine, according to the driving data of the target vehicle, the number of miles traveled by the target vehicle on the highway within the preset time period.
  • the to-be-paid information of the target vehicle is output based on the actual vehicle type and the number of miles traveled by the target vehicle.
  • the preset time period may be expressed as the time between the target vehicle entering the highway entrance and leaving the highway exit each time.
  • the server may record the toll station of the target vehicle each time on the high speed, and the server may transmit notification information to the in-vehicle device, the notification information may be used to notify the in-vehicle device to turn on the trajectory tracking of the target vehicle.
  • the in-vehicle device transmits the trace tracking data to the server, and the server can determine, according to the data, the mileage of the target vehicle during the time between entering the highway entrance and leaving the highway exit, and then based on the mileage. Determine the actual vehicle type and mileage of the target vehicle, and output the to-be-paid information of the target vehicle.
  • the in-vehicle device can also turn on the trajectory tracking of the target vehicle throughout the day, and the server can determine the number of miles traveled by the target vehicle on the expressway based on the data of the high-speed toll station and the trajectory tracking on the target vehicle.
  • the server can identify the actual driving mileage of the target vehicle according to the driving data of the target vehicle, for example, by trajectory tracking, so as to avoid the card reversal behavior of the target vehicle, thereby reducing the evasion behavior of the reversed card to the operator. Economic losses.
  • the server may include a hardware structure and/or a software module, and the hardware structure, the software module, or the hardware structure may be added.
  • the software modules are in the form of functions to implement the above functions. One of the above functions is performed in a hardware structure, a software module, or a hardware structure plus a software module, depending on the specific application and design constraints of the technical solution.
  • FIG. 10 is a schematic block diagram of an apparatus of an embodiment of the present application. It should be understood that the information processing apparatus 1000 illustrated in FIG. 10 is only an example, and the information processing apparatus 1000 of the embodiment of the present application may further include other modules or units, or include modules similar to those of the respective modules in FIG. 10, or To include all the modules in Figure 10.
  • the data receiving module 1010 is configured to acquire driving data of the target vehicle.
  • the vehicle identification module 1020 is configured to determine an actual vehicle model of the target vehicle based on the first driving data in the driving data.
  • the vehicle type identification module 1020 is further configured to determine a travel time distribution and/or a travel track distribution of the target vehicle according to the first travel data; and determine the target vehicle according to the travel time distribution and/or the travel track distribution of the target vehicle. Actual model.
  • the vehicle type identification module 1020 is further configured to determine the target vehicle according to the at least one travel time distribution and/or the correspondence relationship between the travel trajectory distribution and the at least one vehicle type, and the travel time distribution and/or the travel trajectory distribution of the target vehicle.
  • the actual model is further configured to determine the target vehicle according to the at least one travel time distribution and/or the correspondence relationship between the travel trajectory distribution and the at least one vehicle type, and the travel time distribution and/or the travel trajectory distribution of the target vehicle.
  • the actual model is further configured to determine the target vehicle according to the at least one travel time distribution and/or the correspondence relationship between the travel trajectory distribution and the at least one vehicle type, and the travel time distribution and/or the travel trajectory distribution of the target vehicle.
  • the vehicle type identification module 1020 is further configured to obtain, according to the driving data of each vehicle in the sample vehicle, a probability that each vehicle is assigned to each of the plurality of types of vehicles, and a travel time distribution of each vehicle and/or Or a driving trajectory distribution; determining a vehicle type in which the vehicle model corresponding to the first vehicle is greater than the first threshold as the actual vehicle model of the first vehicle; based on the actual vehicle type of the first vehicle and the travel time distribution and/or the trajectory distribution of the first vehicle, Get the corresponding relationship.
  • the target vehicle includes a plurality of vehicles
  • the vehicle type identification module 1020 is further configured to obtain, according to the first driving data of each of the plurality of vehicles, a probability that each vehicle is assigned to each of the plurality of types of vehicles. And a travel time distribution and/or a travel time distribution of each vehicle; determining a vehicle type in which the vehicle model probability corresponding to the first vehicle is greater than the first threshold as the actual vehicle model of the first vehicle; and distributing the travel time of the plurality of vehicles and/or driving The same travel time distribution and/or travel trajectory distribution in the trajectory distribution constitutes a type of travel time distribution and/or travel trajectory distribution; for each type of travel time distribution and/or travel time distribution corresponding to the vehicle, the first vehicle is determined for each The proportion of the vehicle in the vehicle type; for each vehicle corresponding to the distribution of the travel time and/or the distribution of the travel time, determining the target vehicle type in which the proportion of the first vehicle is greater than the second threshold; for each type of travel time distribution and/or The second vehicle in the
  • the vehicle type identification module 1020 is further configured to identify a stay point of the target vehicle according to the first travel data; determine a resident point of the target vehicle according to the frequency of occurrence of the stay point; and determine the resident point according to the map information. Geographical location; based on the geographic location of the resident point, the frequent itemsets in the resident point are combined and connected to obtain the trajectory distribution of the vehicle.
  • the vehicle type identification module 1020 is further configured to sequentially determine a circle with a third threshold value as a center of different target points of the target vehicle, and determine a maximum time difference between the positioning points in each circle; The time difference is compared with the fourth threshold. If the maximum time difference is greater than the fourth threshold, the center of the circle where the maximum time difference is located is determined as the candidate stay point; the center point of all candidate stay points is calculated, and the center point is the stop of the target vehicle. point.
  • the vehicle type identification module 1020 is further configured to obtain, according to the first driving data and the first model, a probability that the target vehicle is assigned to different vehicle models, wherein the first model is the registered vehicle model and the driving data of the sample vehicle in the OBU. Based on the probability, the actual vehicle type of the target vehicle is determined.
  • the information processing apparatus 1000 may further include a service information module 1030, where the service information module 1030 may be configured to verify the business behavior information of the target vehicle based on the actual vehicle type, or output the business behavior information of the target vehicle.
  • the service information module 1030 may be configured to verify the business behavior information of the target vehicle based on the actual vehicle type, or output the business behavior information of the target vehicle.
  • the information processing apparatus 1000 may further include a toll booth area detecting module 1040, configured to determine, according to the second driving data and the target area in the driving data, a time when the target vehicle exits the target area.
  • a toll booth area detecting module 1040 configured to determine, according to the second driving data and the target area in the driving data, a time when the target vehicle exits the target area.
  • the service information module 1030 is further configured to verify, at a time when the target vehicle exits the target area, whether the target vehicle pays a fee corresponding to the actual vehicle type.
  • the toll booth area detecting module 1040 is further configured to determine, according to the second driving data, whether the target vehicle t time and the t-1 time are inside the target area; if the target vehicle t-1 is within the target area, t At the moment outside the target area, it is determined that time t is the time at which the target vehicle exits the target area.
  • the toll booth area detecting module 1040 is further configured to determine, in a horizontal direction or a vertical direction, a ray whose end point is the target point at the time t and the time t-1; the number of intersections between the ray and the target area It is judged whether or not the target vehicle t time and the time t-1 are inside the target area.
  • the toll booth area detecting module 1040 is further configured to: if the number of intersections of the ray and the target area is an odd number, determine that the target vehicle t time or the time t-1 is inside the target area; if the intersection of the ray and the target area The number is even, and it is determined that the target vehicle t time or t-1 time is outside the target area.
  • the toll booth area detecting module 1040 is further configured to determine, according to the second driving data, that the target vehicle t time and the t-1 time are within a minimum outsourcing area, and the minimum outsourcing area is a rectangle.
  • the toll booth area detecting module 1040 is further configured to acquire coordinates of two diagonals of the minimum outsourcing area; determine a range of the minimum outsourcing area based on the coordinates; and obtain a target vehicle at time t according to the second driving data.
  • the toll booth area detecting module 1040 is further configured to establish a spatial index based on the target area and the minimum outsourcing area.
  • the toll booth area detecting module 1040 is further configured to determine that the target vehicle is at time t and time t-1 based on coordinates of the target vehicle at time t and time t-1, a range of minimum outsourcing area, and a spatial index.
  • the smallest outsourcing area is inside.
  • the service information module 1030 is further configured to verify the paid information of the target vehicle based on the actual vehicle type, or output the to-be-paid information of the target vehicle.
  • the information processing apparatus 1000 may further include a mileage verification module 1050 module, configured to determine, according to the first travel data, the number of miles traveled by the target vehicle on the highway in the preset time.
  • a mileage verification module 1050 module configured to determine, according to the first travel data, the number of miles traveled by the target vehicle on the highway in the preset time.
  • the service information module 1030 is further configured to output the to-be-paid information of the target vehicle based on the actual vehicle type and the mileage.
  • the information processing apparatus 1000 may further include an abnormality detecting module 1060, which may be used to identify noise data in the travel data.
  • an abnormality detecting module 1060 which may be used to identify noise data in the travel data.
  • the information processing apparatus 1000 may further include a trajectory correction module 1070, which may be used to correct the noise data to obtain the corrected travel data.
  • a trajectory correction module 1070 which may be used to correct the noise data to obtain the corrected travel data.
  • the toll booth area detecting module 1330 is further configured to determine the first moment and the second moment based on the corrected driving data and the target area.
  • the information processing apparatus 1000 may further include an abnormality detecting module 1140, which may be used to identify noise data in the traveling data.
  • an abnormality detecting module 1140 which may be used to identify noise data in the traveling data.
  • the information processing apparatus 1100 may further include a trajectory correction module 1150, which may be used to correct the noise data to obtain the corrected travel data.
  • a trajectory correction module 1150 which may be used to correct the noise data to obtain the corrected travel data.
  • the vehicle type identification module 1020 is further configured to determine an actual vehicle type of the target vehicle according to the first driving data in the corrected driving data.
  • the information processing apparatus 1000 can perform the operations of the server in the method provided by the embodiment of the present application. Here, in order to avoid redundancy, detailed description thereof is omitted.
  • An information processing apparatus 1100 is configured to implement the functions of a server in the method provided by the embodiment of the present application.
  • the device 1100 includes a processor 1120 for implementing the functions of the server in the method provided by the embodiment of the present application.
  • the processor 1120 may be configured to determine an actual vehicle type and the like of the target vehicle according to the first driving data in the driving data. For details, refer to the detailed description in the method example, and details are not described herein.
  • Apparatus 1100 can also include a memory 1130 for storing program instructions and/or data.
  • Memory 1130 is coupled to processor 1120.
  • Processor 1120 may operate in conjunction with memory 1130.
  • the processor 1120 may execute program instructions stored in the memory 1130.
  • the device 1100 can also include a transceiver 1110 for communicating with other devices through a transmission medium such that devices for use in the device 1100 can communicate with other devices.
  • the processor 1120 uses the transceiver 1110 to send and receive information and is used to implement the method performed by the server in the method embodiment of the present application.
  • connection medium between the above transceiver 1110, the processor 1120, and the memory 1130 is not limited in the embodiment of the present application.
  • the memory 1130, the processor 1120, and the transceiver 11210 are connected by a bus 1140 in FIG. 11.
  • the bus is indicated by a thick line in FIG. 11, and the connection manner between other components is only schematically illustrated. , not limited to.
  • the bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in Figure 11, but it does not mean that there is only one bus or one type of bus.
  • the size of the sequence numbers of the above processes does not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not be implemented in the present application.
  • the implementation of the examples constitutes any limitation.
  • the processor may be a central processing unit (CPU), a general-purpose processor network processor (NP), a digital signal processing (DSP), a microprocessor. , a microcontroller, a programmable logic device (PLD), or any combination thereof.
  • CPU central processing unit
  • NP general-purpose processor network processor
  • DSP digital signal processing
  • microprocessor e.g., a microcontroller
  • PLD programmable logic device
  • the memory may be a volatile memory, such as a random-access memory (RAM); the memory may also include a non-volatile memory, such as A flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); the memory may also be a combination of the above types of memories.
  • RAM random-access memory
  • the memory may also include a non-volatile memory, such as A flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); the memory may also be a combination of the above types of memories.
  • the memory may be any other medium that can be used to carry or store desired program code in the form of an instruction or data structure and that can be accessed by a computer, but is not limited thereto.
  • the size of the sequence numbers of the above processes does not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not be taken to the embodiments of the present invention.
  • the implementation process constitutes any limitation.
  • the disclosed systems, devices, and methods may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the method provided by the embodiment of the present application may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software When implemented in software, it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions.
  • the computer program instructions When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with embodiments of the present invention are generated in whole or in part.
  • the computer can be a general purpose computer, a special purpose computer, a computer network, a network device, a user device, or other programmable device.
  • the computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be from a website site, computer, server or data center Transmission to another website site, computer, server or data center via wired (eg coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (eg infrared, wireless, microwave, etc.).
  • the computer readable storage medium can be any available media that can be accessed by a computer or a data storage device such as a server, data center, or the like that includes one or more available media.
  • the usable medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, an SSD) or the like.
  • a magnetic medium eg, a floppy disk, a hard disk, a magnetic tape
  • an optical medium eg, a digital video disc (DVD)
  • a semiconductor medium eg, an SSD

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Computational Linguistics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种信息处理的方法和装置，其中，该方法包括：获取目标车辆的行驶数据（210）；根据所述行驶数据，确定目标车辆的实际车型（220）。通过该信息处理的方法和装置，能够以较高的准确率识别车辆的实际车型。

Description

信息处理的方法和装置
本申请要求于2018年2月12日提交中国专利局、申请号为201810147439.5，发明名称为“信息处理的方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及智能交通领域，并且更具体地，涉及信息处理的方法和装置。
背景技术
电子不停车收费系统(electronic toll collection，ETC)主要包括路侧单元(road side unit，RSU)和车载单元(on board unit，OBU)，RSU设置于ETC车道上，OBU设置于车辆上。在车辆驶入ETC车道后，RSU将采用专用短程通信(dedicated short range communication，DSRC)技术与OBU进行通讯，获取车辆在OBU中的注册车型，利用注册车型对车辆进行收费，从而实现电子不停车收费。
现有技术中，ETC系统在确定车辆的通行费用时，主要是通过读取OBU中记录的车型信息来进行确定的，即认卡不认车，然而OBU中记录的车型并不一定是车辆的实际车型，例如用户注册时提交的是小型车的信息，但最终将电子标签OBU安装在大型车上使用，以此来减少高速通行费用。
因此如何以较高的准确率识别车辆的实际车型是一个亟待解决的问题。
发明内容
本申请提供一种信息处理的方法和装置，可以以较高的准确率识别车辆的实际车型。
第一方面，提供了一种信息处理方法，包括：获取目标车辆的行驶数据；根据所述行驶数据中的第一行驶数据，确定所述目标车辆的实际车型。
本申请实施例，服务器识别目标车辆的实际车型是基于对目标车辆行驶数据的分析，由于不同车型的行驶数据不同，比如家用车主要集中在上下班时间使用，货车的驾驶时间比较均匀，即目标车辆的行驶数据和实际车型是对应的，因此通过行驶数据可以以较高的准确率识别出目标车辆的实际车型。
在一些可能的实现方式中，所述根据所述第一行驶数据，确定所述目标车辆的实际车型，包括：根据所述行驶数据，确定所述目标车辆的行驶时间分布和/或行驶轨迹分布；根据所述目标车辆的行驶时间分布和/或行驶轨迹分布，确定所述目标车辆的实际车型。
在一些可能的实现方式中，所述根据所述目标车辆的行驶时间分布和/或行驶轨迹分布，确定所述目标车辆的实际车型，包括：根据至少一个行驶时间分布和/或行驶轨迹分布与至少一个车型的对应关系，以及所述目标车辆的行驶时间分布和/或行驶轨迹分布，确定所述目标车辆的实际车型。
上述技术方案，服务器在确定目标车辆的行驶时间分布和/或行驶轨迹分布后，可以根据提前确定好的行驶时间分布和/或行驶轨迹分布与车型的对应关系，直接找到目标车辆的行驶时间分布和/或行驶轨迹分布对应的车型，这样可以快速地确定目标车辆的实际车型。
在一些可能的实现方式中，所述对应关系是利用样本车辆的行驶数据采用以下方式得到的：根据所述样本车辆中每个车辆的行驶数据，得到所述每个车辆分到多种车型中每个车型 的概率，以及所述每个车辆的行驶时间分布和/或行驶轨迹分布；将第一车辆对应的车型概率大于第一阈值的车型确定为所述第一车辆的实际车型；基于所述第一车辆的实际车型与所述第一车辆的行驶时间分布和/或行驶轨迹分布，得到所述对应关系。
在一些可能的实现方式中，所述目标车辆包括多个车辆；所述根据所述目标车辆的行驶时间分布和/或行驶时间分布式，确定所述目标车辆的实际车型，包括：根据所述多个车辆中每个车辆的第一行驶数据，得到所述每个车辆分到多种车型中每个车型的概率，以及所述每个车辆的行驶时间分布和/或行驶时间分布；将第一车辆对应的车型概率大于第一阈值的车型确定为所述第一车辆的实际车型；将所述多个车辆的行驶时间分布和/或行驶轨迹分布中相同的行驶时间分布和/或行驶轨迹分布组成一类行驶时间分布和/或行驶轨迹分布；针对每类行驶时间分布和/或行驶时间分布对应的车辆，确定所述第一车辆在每种车型的车辆中所占的比例；针对所述每类行驶时间分布和/或行驶时间分布对应的车辆，确定所述第一车辆所占的比例大于第二阈值的目标车型；针对所述每类行驶时间分布和/或轨迹模式对应的车辆中的第二车辆，将所述目标车型确定为所述第二车辆的车型，所述第二车辆为所述多个车辆中除所述第一车辆之外的车辆。
上述技术方案，在确定第一车辆的车型后，当满足一定的条件时，服务器可以将第一车辆的车型确定为第二车辆的车型，这样服务器在离线条件下可以确定的实际车型的车辆数量能够明显增加。
在一些可能的实现方式中，所述根据所述第一行驶数据，确定所述目标车辆的行驶时间分布和/或行驶轨迹分布，包括：根据所述第一行驶数据，识别所述目标车辆的停留点；根据所述停留点的出现频率，确定所述目标车辆的常驻点结合地图信息，确定所述常驻点的地理位置；基于所述常驻点的地理位置，将所述常驻点中的频繁项集进行组合与连接，得到所述车辆的行驶轨迹分布。
在一些可能的实现方式中，所述根据所述第一行驶数据，识别所述目标车辆的停留点，包括：依次以所述目标车辆的不同定位点为圆心，以第三阈值为半径确定圆；确定每个圆内定位点之间的最大时间差值；将所述最大时间差值与第四阈值进行比较，若所述最大时间差值大于所述第四阈值，确定所述最大时间差值所在圆的圆心为候选停留点；计算所有候选停留点的中心点，所述中心点为所述目标车辆的停留点。
在一些可能的实现方式中，所述根据所述第一行驶数据，确定所述目标车辆的实际车型，包括：根据所述第一行驶数据以及第一模型，得到所述目标车辆分到不同车型的概率，其中，所述第一模型由样本车辆在车载单元OBU中的注册车型以及行驶数据训练得到的；基于所述概率，确定所述目标车辆的实际车型。
上述技术方案，由于样本车辆的数量很多，因此根据样本车辆的注册车型训练得到的第一模型，整体上符合实际车型分布，这样使得服务器根据第一模型在线确定的目标车辆的实际车型准确度较高。
在一些可能的实现方式中，所述方法还包括：基于所述实际车型，验证所述目标车辆的业务行为信息，或者输出所述目标车辆的业务行为信息。
在一些可能的实现方式中，所述方法还包括：基于所述行驶数据中的第二行驶数据和目标区域，确定所述目标车辆驶出所述目标区域的时刻，所述目标区域为收费站的区域；
所述基于所述实际车型，验证所述目标车辆的业务行为信息，或者输出所述目标车辆的业务行为信息，包括：在所述目标车辆驶出所述目标区域的时刻，验证所述目标车辆是否缴 与所述实际车型相应的费用。
上述技术方案，服务器根据目标区域的对角坐标可以确定目标区域的范围，并且基于目标车辆的行驶数据，即当前时刻所处的经度和纬度，能够确定目标车辆的坐标，通过目标区域的范围和目标车辆的坐标可以自动识别目标车辆离开收费站的行为，并且在目标车辆离开收费站时，可以确定目标车辆是否缴费，若缴费，则可以基于确定的实际车型验证目标车辆已缴费信息是否与实际车型相应，这样可以减少目标车辆的逃费行为。
在一些可能的实现方式中，所述基于所述第二行驶数据和目标区域，确定所述目标车辆驶出所述目标区域的时刻，包括：基于所述第二行驶数据，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部；若所述目标车辆t-1时刻在所述目标区域内部，t时刻在所述目标区域外部，确定所述t时刻是所述目标车辆驶出所述目标区域的时刻。
在一些可能的实现方式中，所述基于所述第二行驶数据，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部，包括：沿水平方向或垂直方向确定以所述目标车辆在t时刻和t-1时刻的定位点为端点的射线；根据所述射线与所述目标区域的交点数量，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部。
在一些可能的实现方式中，所述根据所述射线与所述目标区域的交点数量，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部，包括：若所述射线与所述目标区域的交点数量为奇数，确定所述目标车辆t时刻或t-1时刻在所述目标区域内部；若所述射线与所述目标区域的交点数量为偶数，确定所述目标车辆t时刻或t-1时刻在所述目标区域外部。
在一些可能的实现方式中，所述基于所述第二行驶数据，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部，还包括：基于所述第二行驶数据，确定所述目标车辆t时刻和t-1时刻在所述目标区域的最小外包区域内部，所述最小外包区域为矩形。
上述技术方案，服务器先确定目标车辆是否在最小外包区域内部，若在最小外包区域内部，再判断是否在目标区域内部；若目标车辆不在最小外包区域内部，则可以直接确定目标车辆在目标区域外部，由于判断目标车辆是否在最小外包区域内部的速度较快，因此这样可以快速地判断出目标车辆是否在目标区域内部，从而可以实时地确定目标车辆是否要离开收费站。
在一些可能的实现方式中，所述基于所述第二行驶数据，确定所述目标车辆t时刻和t-1时刻在所述目标区域的最小外包区域内部，包括：获取所述最小外包区域两个对角的坐标；基于所述坐标，确定所述最小外包区域的范围；基于所述第二行驶数据，得到所述目标车辆在t时刻和t-1时刻的坐标；基于所述目标车辆在t时刻和t-1时刻的坐标和所述最小外包区域的范围，确定所述目标车辆在t时刻和t-1时刻在所述最小外包区域内部。
在一些可能的实现方式中，所述方法还包括：基于所述目标区域和所述最小外包区域，建立空间索引；所述基于所述目标车辆在t时刻和t-1时刻的坐标和所述最小外包区域的范围，确定所述目标车辆在t时刻和t-1时刻在所述最小外包区域内部，包括：基于所述目标车辆在t时刻和t-1时刻的坐标、所述最小外包区域的范围以及所述空间索引，确定所述目标车辆在t时刻和t-1时刻在所述最小外包区域内部。
上述技术方案，通过建立空间索引，服务器可以快速地判断目标车辆是否在最小外包区域内部。
在一些可能的实现方式中，所述方法还包括：基于所述实际车型，验证所述目标车辆的业务行为信息，或者输出所述目标车辆的业务行为信息，包括：基于所述实际车型，验证所 述目标车辆的已缴费信息，或者输出所述目标车辆的待缴费信息。
上述技术方案，服务器确定目标车辆的实际车型后，可以向路侧装置输出目标车辆的实际车型，路侧装置可以根据接收到的实际车型对目标车辆进行收费；或者服务器可以验证目标车辆的缴费时的车型信息是否与确定的实际车型一致，若不一致，则可以对目标车辆采取一系列措施，从而可以减少因目标车辆的大车小标行为对运营商造成的损失。
在一些可能的实现方式中，所述方法还包括：根据所述第一行驶数据，确定预设时间内所述目标车辆在高速公路的行驶里程数；所述基于所述实际车型，对所述目标车辆的已缴费信息进行验证，或者输出所述目标车辆的待缴费信息，包括：基于所述实际车型以及所述行驶里程数，输出所述目标车辆的待缴费信息。
上述技术方案，服务器可以根据目标车辆的行驶数据，如通过轨迹追踪识别出目标车辆真实的行驶里程数，这样可以避免目标车辆的倒卡行为，从而减少倒卡的逃费行为对运营商造成的经济损失。
在一些可能的实现方式中，所述已缴费信息包括缴费时OBU发出的注册车型。
在一些可能的实现方式中，所述根据所述行驶数据中的第一行驶数据，确定所述目标车辆的实际车型之前，所述方法还包括：识别所述行驶数据中的噪声数据；修正所述噪声数据，得到修正后的行驶数据；所述根据所述行驶数据中的第一行驶数据，确定所述目标车辆的实际车型，包括：根据所述修正后的行驶数据中的第一行驶数据，确定所述目标车辆的实际车型。
上述技术方案，由于确定目标车辆的实际车型是基于目标车辆的行驶数据的，服务器识别出行驶数据中的噪声数据并对其进行修正，可以增加行驶数据的准确率，从而服务器根据行驶数据确定的目标车辆的实际车型的准确度较高。
在一些可能的实现方式中，所述识别所述行驶数据中的噪声数据，包括：计算t时刻前后时间段内的行驶数据的均值和方差；将t时刻的行驶数据与所述方差的倍数进行比较，若所述t时刻的行驶数据大于所述方差的倍数，确定所述t时刻的行驶数据为噪声数据；所述修正所述噪声数据，包括：基于所述均值，修正所述噪声数据。
在一些可能的实现方式中，所述基于所述均值，修正所述噪声数据，包括：用所述均值替换所述噪声数据，得到初修正数据；结合地图中的道路，修正所述初修正数据。
上述技术方案，结合地图中实际的道路分布情况，再次对初修正数据进行修正，可以将部分没有行驶在道路上的行驶数据修正到道路上。
在一些可能的实现方式中，所述识别所述行驶数据中的噪声数据，包括：基于第二模型，识别所述行驶数据中的噪声数据，其中，所述第二模型是通过对所述目标车辆的位移和加速度进行卡尔曼滤波得到的；所述修正所述噪声数据，包括：基于所述第二模型，修正所述噪声数据。
上述技术方案，卡尔曼滤波器是建立在动态方程之上，由于行驶数据中位移和速度的不可突变特性，因此可以通过目标车辆上一时刻的状态估计当前时刻的状态，从而可以识别出行驶数据中的噪声数据。
在一些可能的实现方式中，所述基于所述第二模型，修正所述噪声数据，包括：基于所述第二模型，初修正所述噪声数据，得到初修正数据；结合地图中的道路，修正所述初修正数据。
在一些可能的实现方式中，所述结合地图中的道路，修正所述初修正数据，包括：确定 以所述初修正数据的定位点为圆心，以最大定位误差为半径的圆；确定所述定位点到与所述圆相交的道路的投影距离；将投影距离最短的道路上的投影点确定为修正后的行驶数据的定位点。
第二方面，提供了一种车辆信息处理的方法，其特征在于，包括：接收目标车辆发送的行驶数据；基于所述行驶数据和目标区域，确定所述目标车辆驶出所述目标区域的时刻，所述目标区域为收费站的区域；获取所述目标车辆的实际车型；确定在所述目标车辆驶出所述目标区域的时刻，所述目标车辆是否缴与所述实际车型相应的费用。
本申请实施例，服务器确定目标区域，根据目标区域的对角坐标可以确定目标区域的范围，并且基于目标车辆的行驶数据，即经度和纬度，可以确定目标车辆的坐标，通过目标区域的范围和目标车辆的坐标可以自动识别目标车辆进出离开收费站的行为，并且根据获取到的目标车辆的实际车型，在目标车辆离开车费站时可以识别出目标车辆是否缴与实际车型相应的费用，这样可以减少目标车辆的逃费行为。
在一些可能的实现方式中，所述基于所述行驶数据和目标区域，确定所述目标车辆驶出所述目标区域的时刻，包括：基于所述行驶数据，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部；若所述目标车辆t-1时刻在所述目标区域内部，t时刻在所述目标区域外部，确定所述t时刻是所述目标车辆驶出所述目标区域的时刻。
在一些可能的实现方式中，所述基于所述行驶数据，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部，包括：沿水平方向或垂直方向确定以所述目标车辆在t时刻和t-1时刻的定位点为端点的射线；根据所述射线与所述目标区域的交点数量，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部。
在一些可能的实现方式中，所述根据所述射线与所述目标区域的交点数量，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部，包括：若所述射线与所述目标区域的交点数量为奇数，确定所述目标车辆t时刻或t-1时刻在所述目标区域内部；若所述射线与所述目标区域的交点数量为偶数，确定所述目标车辆t时刻或t-1时刻在所述目标区域外部。
在一些可能的实现方式中，所述基于所述行驶数据，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部，还包括：基于所述行驶数据，确定所述目标车辆t时刻和t-1时刻在所述目标区域的最小外包区域内部，所述最小外包区域为矩形。
上述技术方案，服务器先确定目标车辆是否在最小外包区域内部，若在最小外包区域内部，再判断是否在目标区域内部；若目标车辆不在最小外包区域内部，则可以直接确定目标车辆在目标区域外部，由于判断目标车辆是否在最小外包区域内部的速度较快，因此这样可以快速地判断目标车辆是否在目标区域内部，从而可以实时地确定目标车辆是要进入收费站还是离开收费站。
在一些可能的实现方式中，所述基于所述行驶数据，确定所述目标车辆t时刻和t-1时刻在所述目标区域的最小外包区域内部，包括：获取所述最小外包区域两个对角的坐标；基于所述坐标，确定所述最小外包区域的范围；基于所述行驶数据，得到所述目标车辆在t时刻和t-1时刻的坐标；基于所述目标车辆在t时刻和t-1时刻的坐标和所述最小外包区域的范围，确定所述目标车辆在t时刻和t-1时刻在所述最小外包区域内部。
在一些可能的实现方式中，所述方法还包括：基于所述目标区域和所述最小外包区域，建立空间索引；所述基于所述目标车辆在t时刻和t-1时刻的坐标和所述最小外包区域的范围，确定所述目标车辆在t时刻和t-1时刻在所述最小外包区域内部，包括：基于所述目标 车辆在t时刻和t-1时刻的坐标、所述最小外包区域的范围以及所述空间索引，确定所述目标车辆在t时刻和t-1时刻在所述最小外包区域内部。
上述技术方案，通过建立空间索引，服务器可以快速地判断目标车辆是否在最小外包区域内部。
在一些可能的实现方式中，所述基于所述行驶数据和目标区域，确定所述目标车辆驶出所述目标区域的时刻之前，所述方法还包括：识别所述行驶数据中的噪声数据；修正所述噪声数据，得到修正后的行驶数据；所述基于所述行驶数据和目标区域，确定所述目标车辆驶出所述目标区域的时刻，包括：基于所述修正后的第二行驶数据和目标区域，所述目标车辆驶出所述目标区域的时刻。
上述技术方案，由于确定目标车辆离开收费站是基于目标车辆的行驶数据的，服务器识别出行驶数据中的噪声数据并对其进行修正，可以增加行驶数据的准确率，从而服务器根据行驶数据确定目标车辆是进入收费站还是离开收费站的准确度较高。
在一些可能的实现方式中，所述识别所述行驶数据中的噪声数据，包括：计算t时刻前后时间段内的行驶数据的均值和方差；将t时刻的行驶数据与所述方差的倍数进行比较，若所述t时刻的行驶数据大于所述方差的倍数，确定所述t时刻的行驶数据为噪声数据；所述修正所述噪声数据，包括：基于所述均值，修正所述噪声数据。
在一些可能的实现方式中，所述基于所述均值，修正所述噪声数据，包括：用所述均值替换所述噪声数据，得到初修正数据；结合地图中的道路，修正所述初修正数据。
上述技术方案，结合地图中实际的道路分布情况，再次对初修正数据进行修正，可以将部分没有行驶在道路上的行驶数据修正到道路上。
在一些可能的实现方式中，所述识别所述行驶数据中的噪声数据，包括：基于模型，识别所述行驶数据中的噪声数据，其中，所述模型是通过对所述目标车辆的位移和加速度进行卡尔曼滤波得到的；所述修正所述噪声数据，包括：基于所述模型，修正所述噪声数据。
上述技术方案，卡尔曼滤波器是建立在动态方程之上，由于行驶数据中位移和速度的不可突变特性，因此可以通过目标车辆上一时刻的状态估计当前时刻的状态，从而可以识别出行驶数据中的噪声数据。
在一些可能的实现方式中，所述基于所述模型，修正所述噪声数据，包括：基于所述模型，初修正所述噪声数据，得到初修正数据；结合地图中的道路，修正所述初修正数据。
在一些可能的实现方式中，所述结合地图中的道路，修正所述初修正数据，包括：确定以所述初修正数据的定位点为圆心，以最大定位误差为半径的圆；确定所述定位点到与所述圆相交的道路的投影距离；将投影距离最短的道路上的投影点确定为修正后的行驶数据的定位点。
第三方面，提供了一种车辆信息处理装置，包括用于执行上述第一方面或第一方面的任意可能的实现方式中的方法的模块。
第四方面，提供了一种车辆信息处理装置，包括用于执行上述第二方面或第二方面的任意可能的实现方式中的方法的模块。
第五方面，提供了一种车辆信息处理装置，包括处理器和存储器，所述存储器用于存储计算机指令，所述处理器用于执行所述存储器中存储的计算机指令，当所述计算机指令被执行时，所述处理器用于执行上述第一方面或第一方面的任意可能的实现方式中的方法。
第六方面，提供了一种车辆信息处理装置，包括处理器和存储器，所述存储器用于存储 计算机指令，所述处理器用于执行所述存储器中存储的计算机指令，当所述计算机指令被执行时，所述处理器用于执行上述第二方面或第二方面的任意可能的实现方式中的方法。
第七方面，提供了一种电子不停车收费ETC系统，所述ETC系统包括如第五方面所述的车辆信息处理装置。
第八方面，提供了一种电子不停车收费ETC系统，所述ETC系统包括如第六方面所述的车辆信息处理装置。
第九方面，提供了一种计算机可读存储介质，包括计算机指令，当所述计算机指令在计算机上运行时，使得所述计算机执行如上述第一方面或第一方面的任意可能的实现方式中所述的方法。
第十方面，提供了一种计算机可读存储介质，包括计算机指令，当所述计算机指令在计算机上运行时，使得所述计算机执行如上述第二方面或第二方面的任意可能的实现方式中所述的方法。
第十一方面，提供了一种包含指令的计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机执行如上述第一方面或第一方面的任意可能的实现方式中所述的方法。
第十二方面，提供了一种包含指令的计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机执行如上述第二方面或第二方面的任意可能的实现方式中所述的方法。
附图说明
图1是本申请实施例提供的一种网络架构示意图；
图2是本申请实施例提供的信息处理方法的示意性流程图；
图3是本申请实施例提供的目标车辆的行驶数据修正前后对比示意图；
图4是图2中的220的一种可能的实现方式的示意性流程图；
图5是本申请实施例提供的目标车辆波形特征的示意图；
图6是本申请实施例提供的目标车辆的停留点示意图；
图7是图2中的220的一种可能的实现方式的示意性流程图；
图8是本申请实施例提供的目标区域和最小外包区域的示意图；
图9是本申请实施例提供的目标车辆在目标区域内部的判断方式的示意图；
图10是本申请实施例提供的信息处理装置的示意性结构图；
图11是本申请实施例提供的信息处理装置的示意性结构图；
具体实施方式
下面将结合附图，对本申请中的技术方案进行描述。
图1是可以应用本申请实施例的ETC系统的一种网络架构示意图。如图1所示，该ETC系统100可以包括车载装置110、路侧装置120和服务器130。
其中，车载装置110可以用于收集、发送、存储车辆行驶的数据，如车辆行驶的速度、方向、位移以及每天的行驶时间等等。车载装置110可以包括OBU、定位设备(如全球定位系统(global positioning system，GPS))、三轴加速度计、行车记录仪，以及任何车载传感器等。其中，GPS可以用来收集车辆行驶的经度、纬度、高度、方向、速度等，三轴加速度 计可以用来收集车辆在行驶过程中的X、Y、Z三个方向的线性加速度，行车记录仪可以用来记录车辆行驶过程中的影像和声音。
路侧装置120可以用于读写车载装置110中存储的数据、收集车辆的外部信息，或控制车辆通行，它还可以计算车辆的通行费用，并自动从车辆用户的专用账户中扣除通行费等。其中，路侧装置120可以包括RSU、相控阵天线、车道摄像头、感应线圈和自动栏杆机等。
服务器130可以用于接收、存储以及处理客户端发送的请求，其中，服务器130可以是物理集群或者虚拟云等。
可选地，客户端可以是车载装置110，也可以是路侧装置120等。
路测装置120可以采用DSRC技术，建立与车载装置110之间的微波通讯链路，从而实现路侧装置120和车载装置110之间的通讯。车载装置110可以将收集到的车辆行驶的数据发送给服务器130，服务器130将接收到的车辆行驶的数据按时间顺序进行存储。服务器130可以向车载装置110发送指示信息，该指示信息可以指示车载装置110开启轨迹追踪等。路侧装置120可以将计算的车辆通行费用发送给服务器130，服务器130在接收到路侧装置120发送的车辆通行费用后，可以检验车辆通行费用是否异常。
图2是根据本申请实施例的信息处理方法的示意性流程图。图2的方法可以由服务器执行，其中，可以是图1中的服务器130。当然，图2的方法也可以由其他设备执行，本申请实施例对此不作限定。
图2的方法可以包括210-220，下面分别对210-220进行详细描述。
在210中，获取目标车辆的行驶数据。
可选地，目标车辆的行驶数据可以包括以下中的至少一种：目标车辆所在的经度、纬度、高度、方向、速度、位移、X方向的线性加速度、Y方向的线性加速度、Z方向的线性加速度等。其中，X、Y、Z表示空间直角坐标系中的X轴、Y轴和Z轴。
可选地，服务器通过采集目标车辆上安装的车载装置发送的信号，可以获取到目标车辆的行驶数据。
可选地，服务器可以按照固定频率采集车载装置发送的信号。其中，服务器采集传感器信号的频率可以为1s或者0.1s等，本申请实施例对此不作限定。
可选地，车载装置发送的信号可以为传感器信号。
其中，传感器信号可以包括但不限于车载装置接收卫星导航系统发送的该车载装置的定位信息，以及从车载装置内置的三轴加速度计中读取的空间加速度信息。其中，目标车辆所在的经度、纬度、高度、方向、速度、位移等一系列行驶数据可以组成目标车辆的定位信息，X、Y、Z三个方向的线性加速度等行驶数据可以组成目标车辆的加速度信息。
可选地，目标车辆上安装的车载装置可以将目标车辆一定时间段内的行驶数据发送给服务器。其中，该一定时间段内的行驶数据可以是一天的行驶数据，也可以是两天或一周的行驶数据等，本申请对此并不限定。
可选地，车载装置也可以将目标车辆当前时刻的行驶数据实时地发送给服务器。
应理解，由于地形遮挡、天气状况等情况可能会导致服务器采集的信号的强度减弱，或者因受到干扰源的影响，甚至是某时刻刚好处于卫星定位盲区等原因，可能会导致GPS接收器计算出现偏差，从而可能使目标车辆的行驶数据中出现噪声数据。
因此，服务器可以识别行驶数据中的噪声数据，并且修正噪声数据，以得到修正后的行驶数据。此过程的实现方式可以有很多种，本申请实施例对此不作具体限定。
可选地，噪声数据可以表示服务器接收的行驶数据中出现偏差的数据。
例如，目标车辆t时刻处于东经103度、北纬34度的位置，服务器获取到的目标车辆t时刻位置为东经115度、北纬41度，则可以确定服务器获取到的目标车辆t时刻的行驶数据为噪声数据。
可选地，服务器可以计算t时刻前后时间段内的行驶数据的均值和方差，然后将t时刻的行驶数据与方差的倍数进行比较，若t时刻的行驶数据大于方差的倍数，则可以确定t时刻的行驶数据为噪声数据。
当然，服务器也可以计算t时刻前后时间段内的行驶数据的均值和标准差，通过标准差得到方差后，将t时刻的行驶数据与方差的倍数进行比较，若t时刻的行驶数据大于方差的倍数，则可以确定t时刻的行驶数据为噪声数据。
可选地，车载装置可以通过GPS，以一定的更新率得到目标车辆的行驶数据，如目标车辆的经度和纬度，然后将该行驶数据发送给服务器。示例性地，GPS的更新率可以为1s，也可以为0.1s。
例如，若服务器要检测目标车辆t时刻的行驶数据是否为噪声数据，可以先计算时段t-k,t-(k-1),t-(k-2),…,t-1与t+1,…,t+(k-2),t+(k-1),t+k所对应的经度和纬度的均值与标准差，然后判断目标车辆t时刻的经度和纬度的值是否在三倍方差的范围内。若超出范围，则可以确定t时刻的行驶数据为噪声数据。
应理解，本申请实施例中的具体的例子只是为了帮助本领域技术人员更好地理解本申请实施例，而非限制本申请实施例的范围。
在识别出行驶数据中的噪声数据后，服务器可以基于上述提到的均值来来修正噪声数据。
可选地，服务器可以用该均值替换噪声数据，得到初修正数据，再结合地图中的道路，修正该初修正数据。
作为一种示例，服务器可以根据目标车辆的行驶轨迹，大致确定目标车辆行驶在哪条道路上。具体地，服务器可以确定以初修正数据的定位点为圆心，以最大定位误差为半径的圆。与该圆相交的道路可以组成道路集合，该道路集合中包括最佳匹配道路。
然后服务器可以确定最佳匹配道路和修正后的行驶数据的定位点。具体地，服务器可以确定该定位点到与该圆相交的道路的投影距离，将投影距离最短的道路确定为最佳匹配道路，最佳匹配道路上的投影点则为修正后的行驶数据的定位点。
可选地，上述提到的目标车辆的行驶轨迹可以由目标车辆的一系列行驶数据按时间顺序排列得到。
可选地，上述提到的最大定位误差可以从GPS中读取到。正常情况下，GPS的定位误差在10-20米以内。
可选地，t时刻的道路匹配结果可以以t-1时刻的道路匹配结果为基础，若t-1时刻的道路匹配结果位于t时刻匹配的道路集合中，则服务器可以将t-1时刻的道路确定为t时刻的最佳匹配道路；若t-1时刻的道路匹配结果没有在t时刻匹配的道路集合中，则服务器可以将投影距离最短的道路确定为t时刻的最佳匹配道路。
例如，假定t时刻的行驶数据为噪声数据，GPS读到的最大定位误差为20米，服务器用t时刻前后时间段内的行驶数据的均值替换该噪声数据后，可以得到t时刻的初修正数据。然后服务器可以确定以t时刻的初修正数据的定位点为圆心、以20米为半径的圆，与该圆相 交的道路有L1、L2和L3。
然后服务器可以分别确定从t时刻初修正数据的定位点到L1、L2和L3的投影距离，将投影距离最短的道路确定为最佳匹配道路，如t时刻的初修正数据到L1的投影距离为5米，t时刻的初修正数据到L2的投影距离为3米，t时刻的初修正数据到L3的投影距离为2米，则可以确定L3为最佳匹配道路，L3上的投影点为修正后的t时刻行驶数据的定位点。
可选地，服务器可以基于模型识别行驶数据中的噪声数据。其中，服务器可以通过目标车辆行驶数据中的位移和加速度进行卡尔曼滤波得到最优估计模型，基于得到的最优估计模型，识别行驶数据中的噪声数据。
示例性地，假设已知t-1时刻目标车辆的行驶数据，则有：
Figure PCTCN2018105889-appb-000001
v t＝v t-1+u t×Δt                  (2)
其中，下标t表示目标车辆t时刻的行驶状态，下标t-1表示目标车辆t-1时刻的行驶状态，p表示目标车辆的位移，v表示目标车辆的速度，u表示目标车辆的加速度。
则可以得到目标车辆t时刻的状态预测公式：
Figure PCTCN2018105889-appb-000002
其中，
Figure PCTCN2018105889-appb-000003
为状态转移矩阵，
Figure PCTCN2018105889-appb-000004
为控制矩阵
也可以将目标车辆的状态空间模型写为：
x t＝Fx t-1+Bu t+w t              (4)
其中x t包含了观测的目标，如位移、速度；w t是过程噪声，符合高斯分布。
上述技术方案，卡尔曼滤波器建立在动态过程之上，由于目标车辆位移、速度的不可突变特性，这样就可以通过目标车辆t-1时刻的状态预测t时刻的状态，从而识别出噪声数据。比如目标车辆t-1时刻加速度为零，t时刻速度却发生了变化，可以确定t时刻有观测误差，t时刻的行驶数据为噪声数据。
可选地，车载装置可以通过GPS和加速度积分，以一定的更新率得到目标车辆的定位信息，然后将该行驶数据发送给服务器。示例性地，加速度积分的更新率包括但不限于0.1s或0.01s等。
可选地，服务器可以基于最优估计模型，修正识别出来的噪声数据。具体地，服务器可以基于该最优估计模型，初修正噪声数据，得到初修正数据。再结合地图中的道路，修正初修正数据。
服务器结合地图中的道路修正初修正数据的具体实现过程上述内容已经详细描述过了，为了内容的简洁，此处不再赘述。
如图3所示，左图为初修正后目标车辆的行驶轨迹，右图为修正后目标车辆的行驶轨迹，从图3中可以看到，初修正后，目标车辆的部分定位点并非行驶在道路上，服务器结合地图中的道路，再次对初修正数据进行修正后，目标车辆的定位点都在道路上。
上述技术方案，由于确定目标车辆的实际车型是基于目标车辆的行驶数据的，服务器识 别出行驶数据中的噪声数据并对其进行修正，可以增加行驶数据的准确率，从而服务器根据行驶数据确定的目标车辆的实际车型的准确度较高。
在220中，根据行驶数据中的第一行驶数据，确定目标车辆的实际车型。
可选地，车型可以表示为与车辆的通行费对应的车辆型号，如7座以内客车、超过40座的客车、载重5至10吨的货车等。
可选地，第一行驶数据可以表示目标车辆一定时间段内的行驶数据。其中，该一定时间段可以为一天，或者一周等。
在本申请实施例中，目标车辆可以包括一个车辆，也可以包括多个车辆，本申请对此不作限定。
可选地，当目标车辆包括一个车辆时，服务器可以根据目标车辆的行驶数据，实时地确定目标车辆的实际车型。
可选地，当目标车辆包括多个车辆时，服务器可以根据获取到的预设时间段内的多个车辆的第一行驶数据，在一定的时间离线确定该多个车辆的实际车型。示例性地，该预设时间段可以为一天。
例如，服务器可以在每天晚上12点，根据当天获取到的多个车辆的第一行驶数据，离线确定该多个车辆的实际车型。
可选地，服务器也可以根据修正后的行驶数据中的第一行驶数据，确定目标车辆的实际车型。
220的实现方式可以有很多种，下面结合图4-图7，对220的具体实现方式进行详细的举例说明。
图4是图2中220的一种可能的实现方式的示意性流程图。图4的方法可以包括410-420。
在410中，根据第一行驶数据，确定目标车辆的行驶时间分布和/或行驶轨迹分布。
可选地，波形模式可以用于表征目标车辆的行驶时间分布。
可选地，轨迹模式可以用于表征目标车辆的行驶轨迹分布。
也就是说，服务器可以根据第一行驶数据，确定目标车辆的波形模式和/或轨迹模式。
服务器可以根据预设时间段内目标车辆的第一行驶数据，确定目标车辆的波形模式。可选地，该预设时间段可以是一个小时，也可以是一天，还可以是一周，本申请对此不作限定。
示例性地，服务器可以根据目标车辆一天中每小时的行驶时间，以及一周中每天的行驶时间分布情况，确定目标车辆的波形特征，然后使用聚类算法可以识别出目标车辆的波形模式。
可选地，波形特征可以包括目标车辆每天的驾驶总时长、每周的驾驶总时长、连续驾驶时间、两次驾驶时间间隔等。
可选地，聚类算法可以为k-means算法、clarans算法、birch算法等。
图5为大车和小车在一天中的行驶时间分布图。其中，虚线表示大车的波形特征，实线表示小车的波形特征，横轴是一天中的24个小时，纵轴代表横轴对应的时段内大车和小车一共行驶了多久(0-1小时)。从图5中可以看到，大车和小车的波形特征不同：小车主要集中在上下班时间使用，而大车的驾驶时间分布比较均匀，并且一天的驾驶总时长也远大于小车。
服务器可以根据目标车辆的第一行驶数据，确定目标车辆的轨迹模式。
在一种实现方式中，服务器可以根据目标车辆的第一行驶数据，识别出目标车辆的停留 点，并根据识别出的停留点的出现频率，确定目标车辆的常驻点。服务器可以结合地图信息，确定目标车辆常驻点的地理位置，如常驻点的地理位置可以为加油站、学校、写字楼、小区、建材市场等。基于常驻点的地理位置，将常驻点中的频繁项集进行组合与连接，从而可以得到目标车辆的轨迹模式。
可选地，停留点可以由目标车辆的一组实际的定位点构成，它并不是指目标车辆速度为零的点。如图6所示，目标车辆的定位点P3、P4、P5和P6可以构成停留点s。
与其它定位点相比，停留点可以具有更重要的信息。例如，货车大多出现在加油站，家用车经常往返于小区、公司等区域。
可选地，常驻点可以表示在一定的时间内出现频率较高的停留点。
例如，停留点1在一天时间内出现了两次，停留点2在一天时间内出现了一次，停留点3在一天时间内出现了五次，则可以确定停留点3为常驻点。
可选地，频繁项集可以表示经常同时出现的多个常驻点。例如，仓库1、加油站1以及加油站2这三个常驻点常常一起出现，则可以将仓库1、加油站1以及加油站2表示为频繁项集。
可选地，可以将时间相邻较近的频繁项集组合在一起，并按时间先后顺序将它们进行连接。
例如，仓库1、加油站1和加油站2为频繁项集1，仓库2、加油站2、加油站1和仓库1为频繁项集2，频繁项集1和频繁项集2时间相邻较近，并且频繁项集1经常先出现，频繁项集2经常后出现，因此，将频繁项集1和频繁项集2进行组合与连接后可以得到“仓库1-加油站1-加油站2-仓库2-加油站2-加油站1-仓库1”的轨迹模式。
在一种实现方式中，服务器在识别目标车辆停留点的过程中，可以检测目标车辆行驶轨迹中的每个定位点，然后可以依次以目标车辆的不同定位点为圆心，以距离阈值为半径确定圆，在每个圆范围内的点可以组成给一个集合。在每个圆内，确定时间最早与最晚的点，并计算出时间差值，即定位点之间的最大时间差值，然后服务器可以将该最大时间差值与时间阈值进行比较，若该最大时间差值大于时间阈值，则可以确定该最大时间差值所在圆的圆心为候选停留点。然后计算所有候选停留点的中心点，该中心点即为目标车辆的停留点。
可选地，服务器可以用关联分析算法从目标车辆的常驻点中挖掘出频繁项集。
可选地，关联分析算法可以包括但不限于FP-growth算法和apriori算法等。
例如，如图6所示，P1,P2,P3,…,P8为目标车辆的定位点，令距离阈值为Y，时间阈值为H。服务器依次以P1,P2,P3,…,P8为圆心、以Y为半径确定圆。比如以P3为圆心的圆内，有P2,P3,P4,P5,P6五个定位点，这五个定位点可以组成一个集合，该集合中时间最早的点为P2，时间最晚的点为P6，计算P2与P6之间的时间差值，将计算得到的时间差值与H进行比较，若时间差值大于H，则可以确定P3为一个候选停留点，以相同的方法可以确定其余七个定位点是否为候选停留点。
若最终确定P3,P4,P5,P6为候选停留点，确定包围P3,P4,P5,P6的最小的圆，如图6所示，虚线表示的圆为包围P3,P4,P5,P6的最小的圆，然后计算出该圆的圆心，该圆心即为目标车辆的停留点。
在420中，根据目标车辆的波形模式和/或轨迹模式，确定目标车辆的实际车型。
在一种可能的实施例中，服务器可以根据至少一个波形模式和/或轨迹模式与至少一个车型的对应关系，以及目标车辆的波形模式和/或轨迹模式，确定目标车辆的实际车型。
可选地，一个波形模式和/或轨迹模式可以对应一个车型。
可选地，多个波形模式和/或轨迹模式也可以对应一个车型。
可选地，服务器可以利用样本车辆的行驶数据得到对应关系。
示例性地，服务器可以根据样本车辆中每个车辆的行驶数据，得到每个车辆分到多种车型中每个车型的概率，以及每个车辆的波形模式和/或轨迹模式；然后可以将第一车辆对应的车型概率大于第一阈值的车型确定为第一车辆的实际车型，再基于确定的第一车辆的实际车型与第一车辆的波形模式和/或轨迹模式，可以得到该对应关系。
例如，令第一阈值为0.9，若根据样本车辆中车辆A的行驶数据，可以得到车辆A的波形模式为波形模式1，并且车辆A分到小车的概率为0.97，分到大车的概率为0.03，则可以确定车辆A的实际车型为小车，以及小车对应波形模式1。服务器确定的目标车辆的波形模式为波形模式1，则服务器可以根据波形模式1与小车的对应关系，以及目标车辆的波形模式，确定目标车辆的实际车型为小车。
上述技术方案，服务器在确定目标车辆的行驶时间分布和/或行驶轨迹分布后，可以根据提前确定好的行驶时间分布和/或行驶轨迹分布与车型的对应关系，直接找到目标车辆的行驶时间分布和/或行驶轨迹分布对应的车型，这样可以快速地确定目标车辆的实际车型。
在一种可能的实施例中，当目标车辆包括多个车辆时，服务器可以根据多个车辆中每个车辆的第一行驶数据，得到每个车辆分到多种车型中每个车型的概率，以及每个车辆的波形模式和/或轨迹模式，将第一车辆对应的车型概率大于第一阈值的车型确定为第一车辆的实际车型。
可选地，服务器可以根据多个车辆中每个车辆的第一行驶数据以及分类模型，得到每个车辆分到多种车型中每个车型的概率，具体实现方式将在图7中进行阐述，此处不再赘述。
例如，令第一阈值为0.9，服务器可以根据多个车辆的第一行驶数据得到每个车辆分到大车和小车的概率，如目标车辆1分到大车的概率为0.4，分到小车的概率为0.6；目标车辆2分到大车的概率为0.2，分到小车的概率为0.8；目标车辆3分到大车的概率为0.99，分到小车的概率为0.01，由于目标车辆3分到大车的概率大于第一阈值0.9，因此，可以确定目标车辆3的实际车型为大车，标记目标车辆3，并且将目标车辆3确定为大车的代表样本。
应理解，在这种方式下，服务器可以确定实际车型的车辆数量较少，如目标车辆中有100辆车，服务器可以确定的实际车型的车辆可能只有30辆，因此，还需要进一步确定剩余车辆的实际车型。
在一种实现方式中，服务器可以将多个车辆的波形模式和/或轨迹模式中相同的波形模式和/或轨迹模式组成一类波形模式和/或轨迹模式，则可以得到多类波形模式和/或轨迹模式。服务器可以针对每类波形模式和/或轨迹模式对应的车辆，确定第一车辆在每种车型的车辆中所占的比例，以及第一车辆所占的比例大于第二阈值的目标车型。针对所述每类波形模式和/或轨迹模式对应的车辆中的第二车辆，可以将所述目标车型确定为所述第二车辆的车型。
其中，第二车辆为多个车辆中除第一车辆之外的车辆。
可选地，第一车辆也可以称为标记车辆，第二车辆也可以称为未标记车辆，本申请不作限定。
例如，令第二阈值为0.9，服务器确定的多类波形模式有：波形模式1、波形模式2、波形模式3……，多类轨迹模式有轨迹模式1、轨迹模式2、轨迹模式3……。假定波形模式1中有50个车辆，标记车辆有30个，未标记车辆有20个，其中，在标记车辆中，有17个大 车，13个小车，大车的比例为0.57，小车的比例为0.43；轨迹模式1中有30个目标车辆，标记车辆有15个，未标记车辆有15个，标记车辆中有14个小车，1个大车，小车的比例为0.93。由于轨迹模式1中标记车辆在两种车型的车辆中所占的比例大于0.9，因此可以将轨迹模式1中的未标记车辆的车型确定为小车。
本申请实施例中，术语“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。
上述技术方案，当满足一定的条件时，服务器可以将未标记车辆的车型确定为标记车辆的车型，这样服务器可以确定的实际车型的车辆数量能够明显增加。
图7是图2中220的一种可能的实现方式的示意性流程图。图7的方法可以包括710-720。
服务器可以根据目标车辆的第一行驶数据，实时地确定目标车辆的实际车型。
在710中，根据目标车辆的第一行驶数据以及模型，得到目标车辆分到不同车型的概率。
可选地，该模型可以由样本车辆在OBU中的注册车型以及样本车辆的行驶数据训练得到。
可选地，样本车辆的行驶数据可以为三轴加速度的统计特征。其中，三轴加速度的统计特征可以有很多种，本申请实施例对此不作具体限定。例如，加速度的统计特征可以包括以下中的至少一种：最大加/减速度、大于1m/s的加/减速度所占的百分比、加/减速度的标准差。
可选地，该模型可以为分类模型。其中，分类模型可以是随机森林、梯度提升决策树(gradient boosting decision tree，GBDT)、逻辑回归(logistic regression，LR)、支持向量机(support vector machine，SVM)、深度神经网络(deep neural network，DNN)等。
应理解，样本车辆有多少车型，得到的概率就为目标车辆分到这么多车型的概率。如样本车辆有5种车型，则服务器可以根据目标车辆的行驶数据以及分类模型，得到目标车辆分到5种车型的概率。
在720中，基于得到的概率，确定目标车辆的实际车型。
可选地，服务器可以将目标车辆分到不同车型的概率与第一阈值进行比较，若目标车辆分到某种车型的概率大于第一阈值，则可以将该车型确定为目标车辆的实际车型。
示例性地，令第一阈值为0.9，根据目标车辆的行驶数据以及分类模型，得到目标车辆分到大车的概率为0.95，分到小车的概率为0.05，则服务器可以确定目标车辆的实际车型为大车。
应理解，本申请实施例的各种实施方式既可以单独实施，也可以结合实施，本申请实施例对此并不限定。
本申请实施例，服务器识别目标车辆的实际车型是基于对目标车辆行驶数据的分析，由于不同车型的行驶数据不同，比如家用车主要集中在上下班时间使用，货车的驾驶时间比较均匀，即目标车辆的行驶数据和实际车型是对应的，因此通过行驶数据可以以较高的准确率识别出目标车辆的实际车型。
可选地，该方法还可以包括：基于实际车型，验证目标车辆的业务行为信息，或者输出目标车辆的业务行为信息。
可选地，业务行为信息可以包括非缴费信息和缴费信息。
可选地，非缴费信息可以包括服务器向路侧装置发送的指示信息，还可以包括目标车辆的经过时间，或者目标车辆的图片等。
作为一种示例，服务器可以将目标车辆的实际车型和注册车型进行比较，并向路侧装置发送指示信息，该指示信息用于指示目标车辆的实际车型和注册车型的比较结果。
可选地，若指示信息指示目标车辆的实际车型和注册车型相同，则路侧装置的自动栅栏机抬起，目标车辆通行；若指示信息指示目标车辆的实际车型和注册车型不同，则路侧装置禁止目标车辆通行。
可选地，路侧装置中可以有显示屏，若指示信息指示目标车辆的实际车型和注册车型不同，则显示屏不停地闪烁。
可选地，路侧装置中可以有报警装置，若指示信息指示目标车辆的实际车型和注册车型不同，则报警装置会报警，比如发出蜂鸣声；若指示信息指示目标车辆的实际车型和注册车型相同，则报警装置不报警。
作为一种示例，若目标车辆的注册车型和实际车型不一致，则服务器可以将目标车辆的经过时间、目标车辆的图片等存储到数据库中。
可选地，缴费信息可以包括目标车辆是否缴费的信息、已缴费信息和待缴费信息。
可选地，已缴费信息可以包括目标车辆缴费时OBU发出的注册车型，待缴费信息可以包括目标车辆的实际车型。
也就是说，基于实际车型，服务器可以对目标车辆的已缴费信息进行验证，或者输出目标车辆的待缴费信息。
可选地，服务器可以基于目标车辆的实际车型，向路侧装置输出目标车辆的实际车型，路侧装置可以根据该实际车型对目标车辆进行收费。
可选地，若目标车辆的注册车型和实际车型不同，则服务器可以将相关案例上报给系统进一步审查。对于系统反馈的结果，在下一轮训练分类模型时，服务器可以增加目标车辆的样本权重，并将与反馈结果不一致的目标车辆的注册车型信息更正为服务器确定的实际车型信息。
服务器可以检验目标车辆的实际车型与注册车型是否一致，若目标车辆的实际车型与注册车型不一致，比如车辆C的注册车型是小车，但服务器识别出的车型为大车，则服务器可以将所有不一致的案例上报给系统进行审核，比如疑似大车小标的有车辆C、车辆D等。服务器将不一致的案例上报给系统之后，可以再反馈给系统不一致案例中目标车辆的实际车型，比如车辆C-大车、车辆D-大车。服务器可以将车辆C与车辆D的注册信息中的车型改为大车，在下一轮中训练分类模型时，增大车辆C和车辆D所对应样本车辆的权重，且直接将车辆C和车辆D加入代表样本集合，即大车的代表样本中增加车辆C和车辆D。可选地，服务器可以基于实际车型，对目标车辆的已缴费信息进行验证。若服务器确定的缴费信息和目标车辆实际的缴费信息不一致，则服务器可以降低目标车辆的信用值，或者可以远程禁止目标车辆使用OBU，若目标车辆的车主没有做澄清处理且补请缴费金额，阻止目标车辆下一次进入高速。
上述技术方案，服务器基于实际车型，可以对目标车辆的已缴费信息进行验证，或者向路侧装置输出目标车辆的待缴费信息，路侧装置根据该待缴费信息对目标车辆进行收费，这样可以减少目标车辆大车小标的行为对运营商造成的损失。
可选地，服务器可以基于行驶数据中的第二行驶数据和目标区域，确定目标车辆驶出目标区域的时刻。
其中，该目标区域为收费站的区域。可选地，该目标区域可以为多边形。如图8所示， 实线表示的区域为目标区域。
可选地，服务器可以根据收费站的范围大小确定目标区域的范围。
可选地，第二行驶数据可以表示目标车辆t-1时刻和t时刻的行驶数据。
可选地，第二行驶数据可以为t-1时刻和t时刻目标车辆所在的经度和纬度。
可选地，若目标车辆t-1时刻在目标区域内部，t时刻在目标区域外部，则可以确定t时刻是目标车辆驶出目标区域的时刻。。
可选地，服务器可以基于目标车辆的第二行驶数据，判断目标车辆t时刻和t-1时刻是否在目标区域内部。
在一种实现方式下，服务器可以基于目标车辆的第二行驶数据，直接判断目标车辆t时刻和t-1时刻是否在目标区域内部。
可选地，服务器可以沿水平方向或垂直方向确定以目标车辆在t时刻和t-1时刻的定位点为端点的射线，根据射线与目标区域的交点数量，判断目标车辆t时刻和t-1时刻是否在目标区域内部。
若射线与目标区域的交点数量为奇数，可以确定目标车辆t时刻或t-1时刻在目标区域内部；若射线与目标区域的交点数量为偶数，可以确定目标车辆t时刻或t-1时刻未在目标区域内部。
如图9所示，点O1为目标车辆t-1时刻的定位点，O2为目标车辆t时刻的定位点。沿水平方向分别确定以点O1和O2为端点的射线。可以看到，以O1为端点的射线与目标区域有一个交点，以O2为端点的射线与目标区域有两个交点，因此，可以确定目标车辆t-1时刻在目标区域内部，t时刻在目标区域外部，确定t时刻为目标车辆驶出目标区域的时刻。
可选地，服务器还可以分别沿水平方向和垂直方向确定以目标车辆在t时刻和t-1时刻的定位点为端点的射线，即可以确定两条射线，根据这两条射线分别与目标区域的交点数量，判断目标车辆t时刻和t-1时刻是否在目标区域内部。
在一种实现方式下，服务器可以基于第二行驶数据，确定目标车辆t时刻和t-1时刻在最小外包区域内部，然后再判断目标车辆t时刻和t-1时刻是否在目标区域内部。
可选地，最小外包区域可以表示目标区域的近似范围，该最小外包矩形可以为矩形，如图8所示，虚线表示的区域为最小外包区域。
可选地，服务器可以获取最小外包区域两个对角的坐标，基于获取到的坐标可以确定最小外包区域的范围。基于目标车辆的第二行驶数据，可以得到目标车辆的经度和纬度数据，从而可以确定目标车辆在t时刻和t-1时刻的坐标。再基于目标车辆在t时刻和t-1时刻的坐标以及最小外包区域的范围，从而可以确定目标车辆在t时刻和t-1时刻在最小外包区域内部。
示例性地，若最小外包区域的两个对角的坐标分别为(3,1)和(6,4)，目标车辆t时刻的坐标为(4,2)，t-1时刻的坐标为(2,5)，则服务器可以确定目标车辆t时刻在最小外包区域内部，t-1时刻没有在最小外包区域内部。
服务器确定目标车辆t时刻在最小外包区域内部后，可以进一步判断目标车辆t时刻是否在目标区域内部，判断的方法上述内容已经进行了详细地描述，此处不再赘述。
本申请实施例中，服务器先确定目标车辆是否在最小外包区域内部，若在最小外包区域内部，再判断是否在目标区域内部；若目标车辆不在最小外包区域内部，则可以直接确定目标车辆在目标区域外部，由于判断目标车辆是否在最小外包区域内部的速度较快，因此这样 可以快速地判断目标车辆是否在目标区域内部，从而可以实时地确定目标车辆是否要离开收费站。
可选地，服务器可以基于目标区域和最小外包区域建立空间索引，然后基于目标车辆在t时刻和t-1时刻的坐标、最小外包区域的范围以及空间索引，确定目标车辆在t时刻和t-1时刻在最小外包区域内部。
可选地，空间索引可以为R树空间索引。
服务器可以将所有收费站区域对应的最小外包区域确定为R树的叶子节点，父节点可以框住其子节点的所有区域，并形成一个最小边界区域。
例如，C、D、E、F、G、H、I、J表示八个收费站对应的最小外包区域，C、D、E、F离得较近，可以形成最小边界区域A；G、H、I、J距离较近，可以形成最小边界区域B，因此，可以确定C、D、E、F、G、H、I、J为叶子节点，A为C、D、E、F的父节点，B为G、H、I、J的父节点。服务器可以先判断目标车辆是否在A或B区域内，若在A区域内，则服务器继续判断目标车辆在C、D、E和F中的哪个区域，而不用再判断目标车辆是否在G、H、I、J区域。
上述技术方案，通过建立空间索引，服务器可以快速地判断目标车辆是否在最小外包区域内部。
服务器可以在目标车辆驶出目标区域的时刻，基于确定的实际车型，对目标车辆的已缴费信息进行验证。
可选地，该实际车型可以是服务器根据上述内容提到的目标车辆的第一行驶数据确定的，也可以是服务器根据目标车辆的图片、激光等其他方式确定的，本申请实施例对此不作具体限定。
可选地，服务器可以在目标车辆驶出目标区域的时刻，验证目标车辆是否缴与实际车型相应的费用，若目标车辆没有发生过缴费操作或缴的费与实际车型不对应，则服务器可以启动一系列措施。
作为一种示例，服务器可以将异常现象自动上报给系统，系统进行进一步审核。
作为一种示例，服务器可以降低目标车辆的信用值，当目标车辆的信用值降到一定程度时，服务器将禁止目标车辆上高速。
作为一种示例，服务器可以远程禁止目标车辆使用OBU，若车主没有做澄清处理且补请缴费金额，阻止下一次进入高速。
本申请实施例，服务器确定目标区域，根据目标区域的对角坐标可以确定目标区域的范围，并且基于目标车辆的行驶数据，即经度和纬度，可以确定目标车辆的坐标，通过目标区域的范围和目标车辆的坐标可以自动识别目标车辆进出收费站的行为，并且在目标车辆离开车费站时可以识别出目标车辆是否缴费，若服务器检测出来目标车辆缴费异常，则启动一系列防止目标车辆二次逃费的措施。这样可以减少目标车辆的逃费行为。
可选地，服务器可以根据目标车辆的行驶数据，确定预设时间段内目标车辆在高速公路的行驶里程数。基于目标车辆的实际车型和行驶里程数，输出目标车辆的待缴费信息。
可选地，预设时间段可以表示为目标车辆每次进入高速公路入口和离开高速公路出口之间的时间。
示例性地，服务器可以记录目标车辆每次上高速的收费站点，并且服务器可以向车载装置发送通知信息，该通知信息可以用于通知车载装置开启目标车辆的轨迹追踪。车载装置将 轨迹追踪的数据发送给服务器，服务器可以根据该数据确定目标车辆在每次进入高速公路入口和离开高速公路出口之间的这段时间内，在高速公路的行驶里程数，然后可以基于确定的目标车辆的实际车型和行驶里程数，输出目标车辆的待缴费信息。
当然，车载装置也可以全天都开启目标车辆的轨迹追踪，服务器可以根据目标车辆上高速的收费站点和轨迹追踪的数据，确定目标车辆在高速公路的行驶里程数。
上述技术方案，服务器可以根据目标车辆的行驶数据，如通过轨迹追踪识别出目标车辆真实的行驶里程数，这样可以避免目标车辆的倒卡行为，从而减少倒卡的逃费行为对运营商造成的经济损失。
以上对本申请实施例提供的方法进行了详细描述，为了实现上述本申请实施例提供的方法中的各功能，服务器可以包括硬件结构和/或软件模块，以硬件结构、软件模块、或硬件结构加软件模块的形式来实现上述各功能。上述各功能中的某个功能以硬件结构、软件模块、还是硬件结构加软件模块的方式来执行，取决于技术方案的特定应用和设计约束条件。
基于与上述方法实施例同样的发明构思，本申请实施例提供了一种信息处理装置，用于实现上述方法中服务器的功能。图10是本申请实施例装置的示意性框图。应理解，图10示出的信息处理装置1000仅是示例，本申请实施例的信息处理装置1000还可以包括其他模块或单元，或者包括与图10中的各个模块的功能相似的模块，或者并非要包括图10中所有模块。
数据接收模块1010，用于获取目标车辆的行驶数据。
车型识别模块1020，用于根据行驶数据中的第一行驶数据，确定目标车辆的实际车型。
可选地，该车型识别模块1020还可以用于根据第一行驶数据，确定目标车辆的行驶时间分布和/行驶轨迹分布；根据目标车辆的行驶时间分布和/或行驶轨迹分布，确定目标车辆的实际车型。
可选地，该车型识别模块1020还可以用于根据至少一个行驶时间分布和/或行驶轨迹分布与至少一个车型的对应关系，以及目标车辆的行驶时间分布和/或行驶轨迹分布，确定目标车辆的实际车型。
可选地，该车型识别模块1020还可以用于根据样本车辆中每个车辆的行驶数据，得到每个车辆分到多种车型中每个车型的概率，以及每个车辆的行驶时间分布和/或行驶轨迹分布；将第一车辆对应的车型概率大于第一阈值的车型确定为第一车辆的实际车型；基于第一车辆的实际车型与第一车辆的行驶时间分布和/或行驶轨迹分布，得到对应关系。
可选地，目标车辆包括多个车辆，该车型识别模块1020还可以用于根据多个车辆中每个车辆的第一行驶数据，得到每个车辆分到多种车型中每个车型的概率，以及每个车辆的行驶时间分布和/或行驶时间分布；将第一车辆对应的车型概率大于第一阈值的车型确定为第一车辆的实际车型；将多个车辆的行驶时间分布和/或行驶轨迹分布中相同的行驶时间分布和/或行驶轨迹分布组成一类行驶时间分布和/或行驶轨迹分布；针对每类行驶时间分布和/或行驶时间分布对应的车辆，确定第一车辆在每种车型的车辆中所占的比例；针对每类行驶时间分布和/或行驶时间分布对应的车辆，确定第一车辆所占的比例大于第二阈值的目标车型；针对每类行驶时间分布和/或行驶时间分布对应的车辆中的第二车辆，将目标车型确定为第二车辆的车型，第二车辆为多个车辆中除第一车辆之外的车辆。
可选地，该车型识别模块1020还可以用于根据第一行驶数据，识别目标车辆的停留点；根据停留点的出现频率，确定目标车辆的常驻点；结合地图信息，确定常驻点的地理位置； 基于常驻点的地理位置，将常驻点中的频繁项集进行组合与连接，得到车辆的行驶轨迹分布。
可选地，该车型识别模块1020还可以用于依次以目标车辆的不同定位点为圆心，以第三阈值为半径确定圆；确定每个圆内定位点之间的最大时间差值；将最大时间差值与第四阈值进行比较，若最大时间差值大于第四阈值，确定最大时间差值所在圆的圆心为候选停留点；计算所有候选停留点的中心点，中心点为目标车辆的停留点。
可选地，该车型识别模块1020还可以用于根据第一行驶数据以及第一模型，得到目标车辆分到不同车型的概率，其中，第一模型由样本车辆在OBU中的注册车型以及行驶数据训练得到的；基于该概率，确定目标车辆的实际车型。
可选地，该信息处理装置1000还可以包括业务信息模块1030，该业务信息模块1030可以用于基于实际车型，验证目标车辆的业务行为信息，或者输出目标车辆的业务行为信息。
可选地，该信息处理装置1000还可以包括收费站区域检测模块1040，用于基于行驶数据中的第二行驶数据和目标区域，确定所述目标车辆驶出目标区域的时刻。
可选地，该业务信息模块1030还可以用于在目标车辆驶出目标区域的时刻，验证目标车辆是否缴与实际车型相应的费用。
可选地，该收费站区域检测模块1040还可以用于基于第二行驶数据，判断目标车辆t时刻和t-1时刻是否在目标区域内部；若目标车辆t-1时刻在目标区域内部，t时刻在目标区域外部，确定t时刻是目标车辆驶出目标区域的时刻。
可选地，该收费站区域检测模块1040还可以用于沿水平方向或垂直方向确定以目标车辆在t时刻和t-1时刻的定位点为端点的射线；根据该射线与目标区域的交点数量，判断目标车辆t时刻和t-1时刻是否在目标区域内部。
可选地，该收费站区域检测模块1040还可以用于若该射线与目标区域的交点数量为奇数，确定目标车辆t时刻或t-1时刻在目标区域内部；若该射线与目标区域的交点数量为偶数，确定目标车辆t时刻或t-1时刻在目标区域外部。
可选地，该收费站区域检测模块1040还可以用于基于第二行驶数据，确定目标车辆t时刻和t-1时刻在最小外包区域内部，最小外包区域为矩形。
可选地，该收费站区域检测模块1040还可以用于获取最小外包区域两个对角的坐标；基于该坐标，确定最小外包区域的范围；基于第二行驶数据，得到目标车辆在t时刻和t-1时刻的坐标；基于目标车辆在t时刻和t-1时刻的坐标和最小外包区域的范围，确定目标车辆在t时刻和t-1时刻在最小外包区域内部。
可选地，该收费站区域检测模块1040还可以用于基于目标区域和最小外包区域，建立空间索引。
可选地，该收费站区域检测模块1040还可以用于基于目标车辆在t时刻和t-1时刻的坐标、最小外包区域的范围以及空间索引，确定目标车辆在t时刻和t-1时刻在最小外包区域内部。
可选地，该业务信息模块1030还可以用于基于实际车型，验证目标车辆的已缴费信息，或者输出目标车辆的待缴费信息。
可选地，该信息处理装置1000还可以包括行驶里程验证模块1050模块，用于根据第一行驶数据，确定预设时间内目标车辆在高速公路的行驶里程数。
可选地，该业务信息模块1030还可以用于基于实际车型以及行驶里程数，输出目标车辆的待缴费信息。
可选地，该信息处理装置1000还可以包括异常检测模块1060，该异常检测模块1060可以用于识别所述行驶数据中的噪声数据。
可选地，该信息处理装置1000还可以包括轨迹修正模块1070，该轨迹修正模块1070可以用于修正噪声数据，得到修正后的行驶数据。
可选地，该收费站区域检测模块1330还可以用于基于修正后的行驶数据和目标区域，确定第一时刻和第二时刻。
可选地，该信息处理装置1000还可以包括异常检测模块1140，该异常检测模块1140可以用于识别所述行驶数据中的噪声数据。
可选地，该信息处理装置1100还可以包括轨迹修正模块1150，该轨迹修正模块1150可以用于修正噪声数据，得到修正后的行驶数据。
可选地，该车型识别模块1020还可以用于根据修正后的行驶数据中的第一行驶数据，确定目标车辆的实际车型。
应理解，该信息处理装置1000可以执行本申请实施例提供的方法中服务器的动作，这里，为了避免赘述，省略其详细说明。
如图11所示为本申请实施例提供的信息处理装置1100，用于实现本申请实施例提供的方法中服务器的功能。装置1100包括处理器1120，用于实现本申请实施例提供的方法中服务器的功能。示例性地，处理器1120可以用于根据行驶数据中的第一行驶数据，确定目标车辆的实际车型等，具体参见方法示例中的详细描述，此处不做赘述。
装置1100还可以包括存储器1130，用于存储程序指令和/或数据。存储器1130和处理器1120耦合。处理器1120可能和存储器1130协同操作。处理器1120可能执行存储器1130中存储的程序指令。
装置1100还可以包括收发器1110，用于通过传输介质和其它设备进行通信，从而用于装置1100中的装置可以和其它设备进行通信。处理器1120利用收发器1110收发信息，并用于实现本申请方法实施例中服务器所执行的方法。
本申请实施例中不限定上述收发器1110、处理器1120以及存储器1130之间的具体连接介质。本申请实施例在图11中以存储器1130、处理器1120以及收发器11210之间通过总线1140连接，总线在图11中以粗线表示，其它部件之间的连接方式，仅是进行示意性说明，并不引以为限。所述总线可以分为地址总线、数据总线、控制总线等。为便于表示，图11中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
应理解，在本申请实施例中，“第一”和“第二”仅仅为了区分不同的对象，但并不对本发明实施例的范围构成限制。
还应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
在本申请实施例中，处理器可以是中央处理器(central processing unit，CPU)，通用处理器网络处理器(network processor，NP)、数字信号处理器(digital signal processing，DSP)、微处理器、微控制器、可编程逻辑器件(programmable logic device，PLD)或它们的任意组合。
在本申请实施例中，存储器可以是易失性存储器(volatile memory)，例如随机存取存储器(random-access memory，RAM)；存储器也可以包括非易失性存储器(non-volatile  memory)，例如快闪存储器(flash memory)，硬盘(hard disk drive，HDD)或固态硬盘(solid-state drive，SSD)；存储器还可以是上述种类的存储器的组合。存储器可以是能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此。
应理解，在本发明的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本发明实施例的实施过程构成任何限定。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
本申请实施例提供的方法中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本发明实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、网络设备、用户设备或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机可以存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，数字视频光盘(digital video disc，DVD))、或者半导体介质(例如,SSD)等。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (23)

  1. 一种信息处理方法，其特征在于，包括：
    获取目标车辆的行驶数据；
    根据所述行驶数据中的第一行驶数据，确定所述目标车辆的实际车型。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述第一行驶数据，确定所述目标车辆的实际车型，包括：
    根据所述第一行驶数据，确定所述目标车辆的行驶时间分布和/或行驶轨迹分布；
    根据所述目标车辆的行驶时间分布和/或行驶轨迹分布，确定所述目标车辆的实际车型。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述目标车辆的行驶时间分布和/或行驶轨迹分布，确定所述目标车辆的实际车型，包括：
    根据至少一个行驶时间分布和/或行驶轨迹分布与至少一个车型的对应关系，以及所述目标车辆的波形模式和/或行驶轨迹分布，确定所述目标车辆的实际车型。
  4. 根据权利要求3所述的方法，其特征在于，所述对应关系是利用样本车辆的行驶数据采用以下方式得到的：
    根据所述样本车辆中每个车辆的行驶数据，得到所述每个车辆分到多种车型中每个车型的概率，以及所述每个车辆的行驶时间分布和/或行驶轨迹分布；
    将第一车辆对应的车型概率大于第一阈值的车型确定为所述第一车辆的实际车型；
    基于所述第一车辆的实际车型与所述第一车辆的行驶时间分布和/或行驶轨迹分布，得到所述对应关系。
  5. 根据权利要求2所述的方法，其特征在于，所述目标车辆包括多个车辆；所述根据所述目标车辆的行驶时间分布和/或行驶时间分布，确定所述目标车辆的实际车型，包括：
    根据所述多个车辆中每个车辆的第一行驶数据，得到所述每个车辆分到多种车型中每个车型的概率，以及所述每个车辆的行驶时间分布和/或行驶轨迹分布；
    将第一车辆对应的车型概率大于第一阈值的车型确定为所述第一车辆的实际车型；
    将所述多个车辆的行驶时间分布和/或行驶轨迹分布中相同的行驶时间分布和/或行驶轨迹分布组成一类行驶时间分布和/或行驶轨迹分布；
    针对每类行驶时间分布和/或行驶轨迹分布对应的车辆，确定所述第一车辆在每种车型的车辆中所占的比例；
    针对所述每类行驶时间分布和/或行驶轨迹分布对应的车辆，确定所述第一车辆所占的比例大于第二阈值的目标车型；
    针对所述每类行驶时间分布和/或行驶轨迹分布对应的车辆中的第二车辆，将所述目标车型确定为所述第二车辆的车型，所述第二车辆为所述多个车辆中除所述第一车辆之外的车辆。
  6. 根据权利要求2至5中任一项所述的方法，其特征在于，所述根据所述第一行驶数据，确定所述目标车辆的行驶时间分布和/或行驶轨迹分布，包括：
    根据所述第一行驶数据，识别所述目标车辆的停留点；
    根据所述停留点的出现频率，确定所述目标车辆的常驻点；
    结合地图信息，确定所述常驻点的地理位置；
    基于所述常驻点的地理位置，将所述常驻点中的频繁项集进行组合与连接，得到所述车辆的行驶轨迹分布。
  7. 根据权利要求6所述的方法，其特征在于，所述根据所述第一行驶数据，识别所述目标车辆的停留点，包括：
    依次以所述目标车辆的不同定位点为圆心，以第三阈值为半径确定圆；
    确定每个圆内定位点之间的最大时间差值；
    将所述最大时间差值与第四阈值进行比较，若所述最大时间差值大于所述第四阈值，确定所述最大时间差值所在圆的圆心为候选停留点；
    计算所有候选停留点的中心点，所述中心点为所述目标车辆的停留点。
  8. 根据权利要求1所述的方法，其特征在于，所述根据所述第一行驶数据，确定所述目标车辆的实际车型，包括：
    根据所述第一行驶数据以及第一模型，得到所述目标车辆分到不同车型的概率，其中，所述第一模型由样本车辆在车载单元OBU中的注册车型以及行驶数据训练得到的；
    基于所述概率，确定所述目标车辆的实际车型。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，所述方法还包括：
    基于所述实际车型，验证所述目标车辆的业务行为信息，或者输出所述目标车辆的业务行为信息。
  10. 根据权利要求9所述的方法，其特征在于，所述方法还包括：
    基于所述行驶数据中的第二行驶数据和目标区域，确定所述目标车辆驶出所述目标区域的时刻，所述目标区域为收费站的区域；
    所述基于所述实际车型，验证所述目标车辆的业务行为信息，或者输出所述目标车辆的业务行为信息，包括：
    在所述目标车辆驶出所述目标区域的时刻，验证所述目标车辆是否缴与所述实际车型相应的费用。
  11. 根据权利要求10所述的方法，其特征在于，所述基于所述第二行驶数据和目标区域，确定所述目标车辆驶出所述目标区域的时刻，包括：
    基于所述第二行驶数据，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部；
    若所述目标车辆t-1时刻在所述目标区域内部，t时刻在所述目标区域外部，确定所述t时刻是所述目标车辆驶出所述目标区域的时刻。
  12. 根据权利要求11所述的方法，其特征在于，所述基于所述第二行驶数据，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部，包括：
    沿水平方向或垂直方向确定以所述目标车辆在t时刻和t-1时刻的定位点为端点的射线；
    根据所述射线与所述目标区域的交点数量，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部。
  13. 根据权利要求12所述的方法，其特征在于，所述根据所述射线与所述目标区域的交点数量，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部，包括：
    若所述射线与所述目标区域的交点数量为奇数，确定所述目标车辆t时刻或t-1时刻在所述目标区域内部；
    若所述射线与所述目标区域的交点数量为偶数，确定所述目标车辆t时刻或t-1时刻在所述目标区域外部。
  14. 根据权利要求11至13中任一项所述的方法，其特征在于，所述基于所述第二行驶数据，判断所述目标车辆t时刻和t-1时刻是否在所述目标区域内部，还包括：
    基于所述第二行驶数据，确定所述目标车辆t时刻和t-1时刻在所述目标区域的最小外包区域内部，所述最小外包区域为矩形。
  15. 根据权利要求14所述的方法，其特征在于，所述基于所述第二行驶数据，确定所述目标车辆t时刻和t-1时刻在所述目标区域的最小外包区域内部，包括：
    获取所述最小外包区域两个对角的坐标；
    基于所述坐标，确定所述最小外包区域的范围；
    基于所述第二行驶数据，得到所述目标车辆在t时刻和t-1时刻的坐标；
    基于所述目标车辆在t时刻和t-1时刻的坐标和所述最小外包区域的范围，确定所述目标车辆在t时刻和t-1时刻在所述最小外包区域内部。
  16. 根据权利要求15所述的方法，其特征在于，所述方法还包括：
    基于所述目标区域和所述最小外包区域，建立空间索引；
    所述基于所述目标车辆在t时刻和t-1时刻的坐标和所述最小外包区域的范围，确定所述目标车辆在t时刻和t-1时刻在所述最小外包区域内部，包括：
    基于所述目标车辆在t时刻和t-1时刻的坐标、所述最小外包区域的范围以及所述空间索引，确定所述目标车辆在t时刻和t-1时刻在所述最小外包区域内部。
  17. 根据权利要求9所述的方法，其特征在于，所述基于所述实际车型，验证所述目标车辆的业务行为信息，或者输出所述目标车辆的业务行为信息，包括：
    基于所述实际车型，验证所述目标车辆的已缴费信息，或者输出所述目标车辆的待缴费信息。
  18. 根据权利要求17所述的方法，其特征在于，所述方法还包括：
    根据所述第一行驶数据，确定预设时间内所述目标车辆在高速公路的行驶里程数；
    所述基于所述实际车型，验证所述目标车辆的已缴费信息，或者输出所述目标车辆的待缴费信息，包括：
    基于所述实际车型以及所述行驶里程数，输出所述目标车辆的待缴费信息。
  19. 根据权利要求17或18所述的方法，其特征在于，所述已缴费信息包括缴费时OBU发出的注册车型。
  20. 根据权利要求1至19中任一项所述的方法，其特征在于，所述根据所述行驶数据中的第一行驶数据，确定所述目标车辆的实际车型之前，所述方法还包括：
    识别所述行驶数据中的噪声数据；
    修正所述噪声数据，得到修正后的行驶数据；
    所述根据所述行驶数据中的第一行驶数据，确定所述目标车辆的实际车型，包括：
    根据所述修正后的行驶数据中的第一行驶数据，确定所述目标车辆的实际车型。
  21. 一种信息处理装置，其特征在于，包括处理器和存储器，其中：
    所述存储器，用于存储程序指令；
    所述处理器，用于调用并执行所述存储器中存储的程序指令，实现如权利要求1至20中任一项所述方法。
  22. 一种电子不停车收费ETC系统，所述ETC系统包括如权利要求21所述的车辆信息处理装置。
  23. 一种计算机可读存储介质，包括指令，当其在计算机上运行时，使得所述计算机执行如权利要求1至20中任一项所述的方法。
PCT/CN2018/105889 2018-02-12 2018-09-15 信息处理的方法和装置 WO2019153745A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP18905774.8A EP3706097A4 (en) 2018-02-12 2018-09-15 INFORMATION PROCESSING METHOD AND DEVICE
US16/927,112 US20200342430A1 (en) 2018-02-12 2020-07-13 Information Processing Method and Apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810147439.5 2018-02-12
CN201810147439.5A CN110164134B (zh) 2018-02-12 2018-02-12 信息处理的方法和装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/927,112 Continuation US20200342430A1 (en) 2018-02-12 2020-07-13 Information Processing Method and Apparatus

Publications (1)

Publication Number Publication Date
WO2019153745A1 true WO2019153745A1 (zh) 2019-08-15

Family

ID=67548180

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/105889 WO2019153745A1 (zh) 2018-02-12 2018-09-15 信息处理的方法和装置

Country Status (4)

Country Link
US (1) US20200342430A1 (zh)
EP (1) EP3706097A4 (zh)
CN (1) CN110164134B (zh)
WO (1) WO2019153745A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111859112A (zh) * 2020-06-16 2020-10-30 北京嘀嘀无限科技发展有限公司 消息推送方法、装置及服务器
CN115273259A (zh) * 2022-07-21 2022-11-01 北京物资学院 车辆识别方法、装置、设备及介质
CN117593806A (zh) * 2023-11-21 2024-02-23 北京交科公路勘察设计研究院有限公司 一种行车记录仪的自由流精准计费系统实现方法

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110517364B (zh) * 2019-09-04 2021-08-20 南京亿儒科技有限公司 基于大数据分析的节假日免费打逃系统及方法
CN111050299B (zh) * 2019-11-07 2023-04-18 腾讯科技（深圳）有限公司 智能车辆数据互检方法和装置
CN110969190B (zh) * 2019-11-07 2023-05-12 厦门大学 非法营运车辆检测方法、介质、设备及装置
CN111125510B (zh) * 2019-11-11 2023-12-22 广东联合电子服务股份有限公司 一种精准营销obu用户车辆数据的获取方法及存储介质
CN114694373A (zh) * 2020-12-30 2022-07-01 北京万集科技股份有限公司 车辆资源配置方法、系统、路侧设备和存储介质
CN113420960B (zh) * 2021-05-31 2023-04-07 同济大学 一种高速公路收费站工作人员调度方法、系统及存储介质
CN113421428A (zh) * 2021-08-25 2021-09-21 深圳市城市交通规划设计研究中心股份有限公司 一种基于多源gps数据的出行阻抗模型标定及校核方法
CN116129541B (zh) * 2022-12-28 2024-03-01 广州天长信息技术有限公司 一种基于广义加性模型的逃费稽查方法、装置及设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050278214A1 (en) * 2002-10-25 2005-12-15 Yoshiaki Takida Toll road charge collection system using artificial satellite, charge collecting machine, and charge collecting method
US20090313096A1 (en) * 2006-06-26 2009-12-17 Mitsubishi Heavy Industries, Ltd. Automatic toll collection system without requiring vehicle classification unit
CN102402861A (zh) * 2011-11-25 2012-04-04 金庆江 一种车辆判别控制系统
CN105946796A (zh) * 2016-05-20 2016-09-21 浩宇天地（天津）科技有限公司 一种机动车行驶控制方法及系统
CN107154151A (zh) * 2017-06-19 2017-09-12 北京车薄荷科技有限公司 一种车辆认证方法及装置

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5528234A (en) * 1994-02-01 1996-06-18 Mani; Siva A. Traffic monitoring system for determining vehicle dimensions, speed, and class
JP3552171B2 (ja) * 1994-06-21 2004-08-11 富士通株式会社 料金自動精算システム並びに同システム用無線通信機能付き記憶媒体，同システム用周波数変換装置，同システム用書込装置，同システム用決済装置，同システム用入金装置および同システム用照会装置
KR100243317B1 (ko) * 1997-04-18 2000-03-02 윤종용 차종 판별 장치
US7725348B1 (en) * 2001-10-17 2010-05-25 United Toll Systems, Inc. Multilane vehicle information capture system
AU2011244813B2 (en) * 2010-04-21 2014-10-16 Bae Systems Plc Classification of range profiles
CN102708690A (zh) * 2012-06-20 2012-10-03 中国计量学院 一种基于道路监控视频测量道路噪声的方法
CN203888640U (zh) * 2014-06-05 2014-10-22 展德企业社 抬头显示器
JP6440193B2 (ja) * 2015-02-27 2018-12-19 三菱重工機械システム株式会社 車種判別装置、料金収受設備、車種判別方法及びプログラム
DE102015120659A1 (de) * 2015-11-27 2017-06-14 Ice Gateway Gmbh Klassifizieren eines oder mehrerer Reflektionsobjekte
CN205563728U (zh) * 2016-04-26 2016-09-07 成都市同一源科技有限责任公司 一种高速路收费系统
JP6750967B2 (ja) * 2016-06-09 2020-09-02 株式会社東芝 車種判別装置および車種判別方法
CN106855415B (zh) * 2017-01-09 2020-03-03 北京京东尚科信息技术有限公司 地图匹配方法和系统
CN107463940B (zh) * 2017-06-29 2020-02-21 清华大学 基于手机数据的车辆类型识别方法和设备
CN107369218B (zh) * 2017-07-21 2019-02-22 北京图森未来科技有限公司 实现车辆自动缴费的方法及系统、相关设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050278214A1 (en) * 2002-10-25 2005-12-15 Yoshiaki Takida Toll road charge collection system using artificial satellite, charge collecting machine, and charge collecting method
US20090313096A1 (en) * 2006-06-26 2009-12-17 Mitsubishi Heavy Industries, Ltd. Automatic toll collection system without requiring vehicle classification unit
CN102402861A (zh) * 2011-11-25 2012-04-04 金庆江 一种车辆判别控制系统
CN105946796A (zh) * 2016-05-20 2016-09-21 浩宇天地（天津）科技有限公司 一种机动车行驶控制方法及系统
CN107154151A (zh) * 2017-06-19 2017-09-12 北京车薄荷科技有限公司 一种车辆认证方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3706097A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111859112A (zh) * 2020-06-16 2020-10-30 北京嘀嘀无限科技发展有限公司 消息推送方法、装置及服务器
CN115273259A (zh) * 2022-07-21 2022-11-01 北京物资学院 车辆识别方法、装置、设备及介质
CN117593806A (zh) * 2023-11-21 2024-02-23 北京交科公路勘察设计研究院有限公司 一种行车记录仪的自由流精准计费系统实现方法
CN117593806B (zh) * 2023-11-21 2024-07-02 北京交科公路勘察设计研究院有限公司 一种行车记录仪的自由流精准计费系统实现方法

Also Published As

Publication number Publication date
CN110164134B (zh) 2021-08-13
US20200342430A1 (en) 2020-10-29
CN110164134A (zh) 2019-08-23
EP3706097A4 (en) 2021-01-06
EP3706097A1 (en) 2020-09-09

Similar Documents

Publication Publication Date Title
WO2019153745A1 (zh) 信息处理的方法和装置
CN109690606B (zh) 基于远程信息处理的系统及其相应的方法
US20240232963A1 (en) System and Method for Estimation of Vehicle Accident Damage and Repair
US11216888B2 (en) Electronic system for dynamic, quasi-realtime measuring and identifying driver maneuvers solely based on mobile phone telemetry, and a corresponding method thereof
CN109844793B (zh) 基于智能、远程信息处理的oem线路装配系统及其对应方法
US11067404B2 (en) Vehicle usage-based pricing alerts
US20190122447A1 (en) Methods and systems for payments of services used by vehicles based on time, distance and place
JP2021168193A (ja) テレマティックス接続サーチエンジンを使用する動的なスコアベースの危険性測定及び集約のためのインテリジェントな自己適応型車両用装置及びその対応する方法
US10446022B2 (en) Reversible lane active direction detection based on GNSS probe data
CN107228676A (zh) 来自连接的车辆队列的地图更新
CN106952481A (zh) 用于获取驾驶员行为数据的平台
US20160379486A1 (en) Apparatus and system to manage monitored vehicular flow rate
US20160209219A1 (en) Method of autonomous lane identification for a multilane vehicle roadway
US9934682B2 (en) Systems and methods for monitoring roadways using magnetic signatures
US20220084398A1 (en) Method, apparatus, and system for detecting road incidents
US20200258383A1 (en) Systems and Methods for Monitoring Roadways
US12079778B1 (en) Systems and methods for classifying a vehicular trip as for personal use or for work based upon similarity in operation features
Ferreira et al. A blockchain and gamification approach for smart parking
CN113808414B (zh) 道路荷载确定方法、装置及存储介质
CN109313847A (zh) 用于错路驾驶员识别的方法、设备和系统
Chang et al. Vehicle detection approach adjusting road curves to estimate local traffic density under real driving conditions
Xyntarakis et al. Active transportation and demand management (ATDM) trajectory-level validation state of the practice review.
Foss et al. Geofencing for smart urban mobility. Summarizing the main findings of Work Package 1
US11170647B2 (en) Detection of vacant parking spaces
US11455668B2 (en) Method and system of automatic billing of transportation services

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: 18905774

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2018905774

Country of ref document: EP

Effective date: 20200602

NENP Non-entry into the national phase

Ref country code: DE