Vehicle type identification method and device based on mobile phone data

Patent metadata

Field	Value
Publication number	US-10573173-B2
Application number	US-201816322095-A
Country	US
Kind code	B2
Filing date	Mar 28, 2018
Priority date	Jun 29, 2017
Publication date	Feb 25, 2020
Grant date	Feb 25, 2020

Abstract

A vehicle type identification method and device based on mobile phone data for solving the problem of providing a convenient and low-cost vehicle type identification method. The method includes: obtaining trajectory data recorded by a mobile phone of a user within a period of time; judging mobile phone users who are on the same vehicle according to the data, and obtaining a vehicle trajectory and the number of passengers corresponding to the vehicle trajectory; obtaining a vehicle origin and destination according to the vehicle trajectory, and obtaining an origin-destination type of the vehicle trajectory in combination with geographic data; obtaining vehicle driving data according to the vehicle trajectory; and obtaining service area data of vehicle staying according to the vehicle trajectory. The cost of obtaining data by using mobile phone big data and by using mobile phone signaling data collected and provided by an operator is low.

First claim

The invention claimed is:

1. A vehicle type identification method for use with mobile phone data, the vehicle type identification method comprising:
obtaining, by a processor, trajectory data recorded by a mobile phone of a user within a period of time;
judging, by the processor, mobile phone users who are on a same vehicle according to the trajectory data, and obtaining a vehicle trajectory and a number of passengers corresponding to the vehicle trajectory;
obtaining, by the processor, a vehicle origin and destination according to the vehicle trajectory, and obtaining an origin-destination type of the vehicle trajectory in combination with geographic data;
obtaining, by the processor, vehicle driving data according to the vehicle trajectory;
obtaining, by the processor, service area data of vehicle staying according to the vehicle trajectory;
constructing, by the processor, a feature vector including: (i) the number of passengers corresponding to the vehicle trajectory, (ii) the origin-destination type, (iii) the vehicle driving data, and (iv) and the service area data of vehicle staying; and
processing, by the processor, the feature vector with a vehicle classifier to obtain a vehicle type identification result; wherein
the vehicle classifier is a vehicle classifier obtained by training via a machine learning method and the feature vector of a sample.

2. The method according to claim 1 , wherein judging mobile phone users who are on the same vehicle according to the trajectory data, and obtaining a vehicle trajectory and the number of passengers corresponding to the vehicle trajectory comprises:
if a time coincidence degree of the trajectory of passing by a first geographic location and a second geographic location is greater than a first time coincidence degree, indicating that the first geographic location and the second geographic location have an intersection;
dividing the trajectory data into sets one by one according to different geographic locations to produce a plurality of trajectories;
calculating matching degrees between the plurality of trajectories in the sets one by one; and
if one trajectory is matched based on the calculated matching degrees out of the plurality of trajectories, indicating that the one trajectory belongs to the passenger on the same vehicle, and then determining the trajectory and the number of passengers corresponding to the one vehicle trajectory.

3. The method according to claim 1 , wherein the origin-destination type comprises a residential area, an industrial area, a commercial area, a scenic spot, an entertainment area and a bus station.

4. The method according to claim 1 , wherein the obtaining vehicle driving data according to the vehicle trajectory comprises:
calculating a set of time intervals (t s un , t e un ) in which the speed is less than a first speed V un according to a plurality of vehicle trajectories;
calculating a number of vehicle trajectories that are overlapped at a third geographic location within a certain time interval (t s un , t e un );
when the number of vehicle trajectories overlapped at the third geographic location is greater than a traffic jam threshold, determining the occurrence of a traffic jam within the period of time, and obtaining a traffic jam sub-trajectory, wherein the third geographic location does not include the service area; and
calculating a service area sub-trajectory, which is located in the service area and the vehicle speed is less than a second speed V sa in the vehicle trajectory according to the geographic location information of the service area, and calculating one or more driving data including an average speed, the maximum speed, a speed standard deviation and speed distribution of the vehicle according to the vehicle trajectory after the service area sub-trajectory and the traffic jam sub-trajectory are deducted.

5. The method according to claim 1 , wherein the service area data comprises: a service area staying count, a total service area staying time and an average staying time in each service area.

6. The method according to claim 1 , wherein the machine learning method is a random forest method.

7. A non-transitory computer readable storage medium, storing a computer program thereon, wherein the computer program implements the steps of the method according to claim 1 when being executed by a processor.

8. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to claim 1 when executing the program.

9. A non-transitory computer readable storage medium, storing a computer program thereon, wherein the computer program implements the steps of the method according to claim 2 when being executed by a processor.

10. A non-transitory computer readable storage medium, storing a computer program thereon, wherein the computer program implements the steps of the method according to claim 3 when being executed by a processor.

11. A non-transitory computer readable storage medium, storing a computer program thereon, wherein the computer program implements the steps of the method according to claim 4 when being executed by a processor.

12. A non-transitory computer readable storage medium, storing a computer program thereon, wherein the computer program implements the steps of the method according to claim 5 when being executed by a processor.

13. A non-transitory computer readable storage medium, storing a computer program thereon, wherein the computer program implements the steps of the method according to claim 6 when being executed by a processor.

14. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to claim 2 when executing the program.

15. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to claim 3 when executing the program.

16. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to claim 4 when executing the program.

17. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to claim 5 when executing the program.

18. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to claim 6 when executing the program.

Assignees

• Shandong Provincial Communications Planning And Design Inst
• Univ Tsinghua

Inventors

• Liu Wei
• Wu Weiling
• Zhao Kai
• Li Yong
• Jin Depeng
• Mu Tao
• Li Yiwu
• Bi Yufeng
• Zheng Jianhui
• Chang Ying
• Xu Xiaobin
• Shao Xiaoming

Classifications

• H04W4/029 Primary

  Location-based management or tracking services · CPC title

• G08G1/012 Primary

  from other sources than vehicle or roadside beacons, e.g. mobile networks · CPC title

• G08G1/0112

  from the vehicle, e.g. floating car data [FCD] · CPC title

• G06N20/20

  Ensemble learning · CPC title

• H04W4/027

  using movement velocity, acceleration information · CPC title