Method and apparatus for traffic management

• US 9,424,744 B2
• Filed: 10/18/2010
• Issued: 08/23/2016
• Est. Priority Date: 10/30/2009
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Shang, Wei Xiong, Wang, Hua Yong, Xiang, Zhe, Ying, Chun, Zhou, Jin Z., Zhu, Yan Feng
• Primary Examiner(s): Kan, Yuri
• Application Number:
  US13/505,165
• Publication Number:
  US 20120221232A1
• Time in Patent Office: 2,136 Days
• Field of Search: 701/117, 701/119, 701/118, 701/411, 701/423, 701/424, 701/533, 455/435.1, 455/440, 455/456.1
• US Class Current: 1/1
• CPC Class Codes: G08G 1/0104 Measuring and analyzing of parameters relative to traffic conditions
• CPC Class Codes: G08G 1/012 from other sources than vehicle or roadside beacons, e.g. mobile networks
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: H04W 4/026 using orientation information, e.g. compass
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

A method for determining travel time of a vehicle on a road, wherein the vehicle is operable within a mobile communication network, comprising: collecting historical communication events of a mobile user in order to obtain travel samples, wherein the historical communication events indicate when the mobile user travelled along a monitored road; determining a cell handover sequence from the historical communication events; determining from the cell handover sequence, one of more road segments of the monitored road; determining the travel time of the one or more road segments according to the travel time samples; selecting, for an undetermined road segment of the monitored road for which the real-time travel time is not determined from the collected historical communication events, a candidate mobile user that is most likely to appear on the undetermined road segment; actively positioning the candidate mobile user to obtain positioning information; and returning to the step of collecting communication events of a mobile user currently on a monitored road with the active positioning as one communication event for the candidate mobile user, to determine the real-time travel time of the undetermined road segment.

Claims

1. A method for determining travel time of a vehicle on a road, wherein the vehicle is operable within a mobile communication network, comprising:

collecting historical communication events of a mobile user in order to obtain travel samples, wherein the historical communication events indicate when the mobile user travelled along a monitored road;

determining a cell handover sequence from the historical communication events;

determining from the cell handover sequence, one of more road segments of the monitored road;

determining the travel time of the one or more road segments according to the travel time samples;

selecting, for an undetermined road segment of the monitored road for which the real-time travel time is not determined from the collected historical communication events, a candidate mobile user that is most likely to appear on the undetermined road segment;

calculating a travel probability of each mobile user to pass the undetermined road segment at a specified time, said candidate mobile user being selected based on said calculated travel probability, the travel probability of a mobile user being calculated as a function of an estimated speed and a speed vector of the mobile user on the monitored road, said estimated speed calculated by;

computing a minimum travel speed and a maximum travel speed of the each mobile user, the minimum and maximum travel speed of the each mobile user computed as a function of;

a distance from a position of a cell to which the each mobile user belongs at a current time to a start point of the undetermined road segment, a coverage radius of the cell, a length of the undetermined road segment, and the current time;

actively positioning the candidate mobile user to obtain positioning information; and

returning to the step of collecting communication events of a mobile user currently on a monitored road with the active positioning as one communication event for the candidate mobile user, to determine the real-time travel time of the undetermined road segment.

2. The method of claim 1, wherein the step of collecting historical communication related to a mobile user currently on a monitored road to obtain travel time samples further comprises:

collecting two continuous communication events related to the same mobile user within a predetermined time period; and

recording positions of cells in which the two communication events took place and a time difference between the two communication events as the travel time sample.

3. The method of claim 2, wherein the step of determining the real-time travel time of a road segment in the monitored road according to the travel time samples further comprises:

determining, for each of the travel time samples, whether the positions of two cells in the travel time sample are the same, and determining that the travel time sample is a valid travel time sample when the positions of these two cells are different;

selecting, from the valid travel time samples, an unambiguous sample that can uniquely determine the real-time travel time of a certain road segment;

identifying the certain road segment with the unambiguous sample;

comparing, for an ambiguous sample in the valid travel time samples, the time difference in the ambiguous sample with a sum of the real-time travel time of the respective constituent road segments of each of the possible road segments corresponding to the ambiguous sample to select the possible road segment that is nearest in time, wherein for the constituent road segment for which the real-time travel time is not determined, a baseline travel time of the constituent road segment is used to replace its real-time travel time; and

identifying the possible road segment that is nearest in time with the ambiguous sample.

4. The method of claim 3, wherein the step of determining the real-time travel time of corresponding road segment in the monitored road according to the travel time samples further comprises:

determining whether these two cells are neighbouring cells when the positions of these two cells are different; and

determining that the travel time sample is valid when these two cells are not the neighbouring cells.

5. The method of claim 3, wherein the step of determining the real-time travel time of corresponding road segment on the monitored road according to the travel time samples further comprises:

calculating arithmetic average value of unambiguous samples when a plurality of unambiguous samples exists for the same road segment; and

identifying the road segment with the arithmetic average value.

6. The method of claim 1, wherein the step of selecting, for an undetermined road segment on the monitored road for which the real-time travel time is not determined, a candidate mobile user that is most likely to appear on the undetermined road segment comprises:

analyzing moving modes and speed vectors of the corresponding mobile users on the monitored road according to the valid travel time samples;

estimating, the travel speed of each corresponding mobile user passing the undetermined road segment from the current time to said specified time; and

selecting a certain number of mobile users with a large calculated travel probability as the candidate mobile user.

7. The method of claim 6, wherein the step of estimating, for each of the corresponding mobile users, the travel speed at which the mobile user passes the undetermined road segment from current time to specified time comprises:

estimating the minimum travel speed of the mobile user according to

8. The method of claim 6, wherein the step of selecting a mobile user that is most likely to appear on the undetermined road segment further comprises:

selecting a mobile user to whom only one communication event happened in a previous road segment of the undetermined road segment as a candidate mobile user.

9. The method of claim 1, further comprising:

before the step of collecting communication events happened to a mobile user currently on a monitored road,

dividing the monitored road into a plurality of road segments according to cells related to the monitored road; and

baselining historical travel time for the road segments to obtain baseline travel time of the respective road segments.

10. The method of claim 9, wherein the step of dividing the monitored road into a plurality of road segments according to cells related to the monitored road comprises:

obtaining all cells within a certain range along the monitored road and their position information;

querying historical handover records related to the cells to find a cell handover sequence corresponding to the monitored road; and

segmenting the monitored road into a plurality of road segments according to the cell handover sequence, wherein middle points between two neighbouring cells are regarded as borders of the respective road segments.

11. The method of claim 9, wherein the step of baselining historical travel time for the road segments to obtain baseline travel time of the respective road segments comprising:

counting the historical travel time for the road segment according to historical handover records in the cell handover sequence; and

filtering interference time out from the historical travel time to generate the baseline travel time of the road segment.

12. The method of claim 1, wherein the communication event is any one of location update service, call/short message service and cell handover.

25. The method of claim 4, wherein the step of determining the real-time travel time of corresponding road segment on the monitored road according to the travel time samples further comprises:

calculating arithmetic average value of unambiguous samples when a plurality of unambiguous samples exists for the same road segment; and

identifying the road segment with the arithmetic average value.

13. An apparatus for determining travel time of a vehicle on a road, wherein the vehicle is operable within a mobile communication network, comprising:

a hardware processor coupled to a memory storage device, said storage device storing instructions for configuring said hardware processor to perform a method, said method comprising;

collecting historical communication events of a mobile user in order to obtain travel samples, wherein the historical communication events indicate when the mobile user travelled along a monitored road;

determining a cell handover sequence from the historical communication events;

determining from the cell handover sequence, one of more road segments of the monitored road;

determining the travel time of the one or more road segments according to the travel time samples;

selecting, for an undetermined road segment of the monitored road for which the real-time travel time is not determined from the collected historical communication events, a candidate mobile user that is most likely to appear on the undetermined road segment;

calculating a travel probability of each mobile user to pass the undetermined road segment at a specified time, said candidate mobile user being selected based on said calculated travel probability, the travel probability of a mobile user being calculated as a function of an estimated speed and a speed vector of the mobile user on the monitored road, said estimated speed calculated by;

computing a minimum travel speed and a maximum travel speed of the each mobile user, the minimum and maximum travel speed of the each mobile user computed as a function of;

a distance from a position of a cell to which the each mobile user belongs at a current time to a start point of the undetermined road segment, a coverage radius of the cell, a length of the undetermined road segment, and the current time;

actively positioning the candidate mobile user to obtain positioning information; and

returning to collecting communication events of a mobile user currently on a monitored road with the active positioning as one communication event for the candidate mobile user, to determine the real-time travel time of the undetermined road segment.

14. The apparatus of claim 13, wherein the hardware processor is further configured to:

collect two continuous communication events happened to the same mobile user within a predetermined time period; and

record the positions of the cells in which these two communication events happened and a time difference between these two communication events as the travel time sample.

15. The apparatus of claim 14, wherein the hardware processor is further configured to:

determine, for each of the travel time samples, whether the positions of two cells in the travel time sample are the same, and determining that the travel time sample is a valid travel time sample when the positions of these two cells are different;

select from the valid travel time samples an unambiguous sample that can uniquely determine the real-time travel time of a certain road segment;

identify the certain road segment with the unambiguous sample;

compare, for an ambiguous sample in the valid travel time samples, a time difference in the ambiguous sample with a sum of the real-time travel time of the respective constituent road segments of each of the possible road segments corresponding to the ambiguous sample to select the possible road segment that is nearest in time, wherein for the constituent road segment for which the real-time travel time is not determined, its real-time travel time is replaced with a baseline travel time of the constituent road segment;

wherein the the hardware processor identifies the possible road segment that is nearest in time with the ambiguous sample.

16. The apparatus of claim 15, wherein the hardware processor is further configured to determine whether these two cells are neighbouring cells when the positions of these two cells are different, and to determine that the travel time sample is valid when these two cells are not neighbouring cells.

17. The apparatus of claim 15, wherein the hardware processor is further configured to calculate, when a plurality of unambiguous samples exists for the same road segment, an arithmetic average value of the plurality of unambiguous samples;

wherein the hardware processor identifies the road segment with the arithmetic average value.

18. The apparatus of claim 13, wherein the hardware processor is further configured to:

analyze moving modes and speed vectors of the corresponding mobile users on the monitored road according to the valid travel time samples;

estimate, for each of the corresponding mobile users, the travel speed at which the mobile user passes the undetermined road segment from the current time to said specified time; and

select a certain number of mobile users with a large calculated travel probability as the candidate mobile user.

19. The apparatus of claim 18, wherein the hardware processor is further configured to:

estimate the minimum travel speed of the mobile user according to

20. The apparatus of claim 18, wherein the hardware processor is further configured to select the mobile user to whom only one communication event happened in a previous road segment of the undetermined road segment.

21. The apparatus of claim 13, wherein the hardware processor is further configured to:

divide the monitored road into a plurality of road segments according to cells related to the monitored road; and

baseline historical travel time for the road segments to obtain the baseline travel time of the respective road segments.

22. The apparatus of claim 21, wherein the hardware processor is further configured to:

obtain all the cells within a certain range along the monitored road and their position information;

query historical handover records related to the cells to find a cell handover sequence corresponding to the monitored road; and

segment the monitored road into a plurality of road segments according to the cell handover sequence, wherein middle points between two neighbouring cells are regarded as borders of the respective road segments.

23. The apparatus of claim 21, wherein the hardware processor is further configured to:

count the historical travel time for the road segment according to the historical handover records in the cell handover sequence; and

filter interference time out from the historical travel time to generate the baseline travel time of the road segment.

26. The apparatus of claim 16, wherein the hardware processor is further configured to calculate, when a plurality of unambiguous samples exists for the same road segment, an arithmetic average value of the plurality of unambiguous samples;

wherein the hardware processor identifies the road segment with the arithmetic average value.

24. A computer software program comprising computer program code to, when loaded into a non-transitory computer readable medium and executed, perform all the steps of a method for determining travel time of a vehicle on a road, wherein the vehicle is operable within a mobile communication network, comprising:

collecting historical communication events of a mobile user in order to obtain travel samples, wherein the historical communication events indicate when the mobile user travelled along a monitored road;

determining a cell handover sequence from the historical communication events;

determining from the cell handover sequence, one of more road segments of the monitored road;

determining the travel time of the one or more road segments according to the travel time samples;

selecting, for an undetermined road segment of the monitored road for which the real-time travel time is not determined from the collected historical communication events, a candidate mobile user that is most likely to appear on the undetermined road segment;

calculating a travel probability of each mobile user to pass the undetermined road segment at a specified time, said candidate mobile user being selected based on said calculated travel probability, the travel probability of a mobile user being calculated as a function of an estimated speed and a speed vector of the mobile user on the monitored road, said estimated speed calculated by;

computing a minimum travel speed and a maximum travel speed of the each mobile user, the minimum and maximum travel speed of the each mobile

user computed as a function of;

a distance from a position of a cell to which the each mobile user belongs at a current time to a start point of the undetermined road segment, a coverage radius of the cell, a length of the undetermined road segment, and the current time;

actively positioning the candidate mobile user to obtain positioning information; and

returning to the step of collecting communication events of a mobile user currently on a monitored road with the active positioning as one communication event for the candidate mobile user, to determine the real-time travel time of the undetermined road segment.