Trend based predictive traffic

• US 8,892,345 B2
• Filed: 04/06/2012
• Issued: 11/18/2014
• Est. Priority Date: 04/08/2011
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Arcot, Praveen J., Lindsay, Matthew G., McGrath, Timothy A., Devries, Steven P.
• Primary Examiner(s): Marc, McDieunel
• Application Number:
  US14/110,319
• Publication Number:
  US 20140032091A1
• Time in Patent Office: 956 Days
• Field of Search: 701/117, 701/119, 429/143, 429/149, 250/396.ML, 250/396.R
• US Class Current: 701/119
• CPC Class Codes: G08G 1/00 Traffic control systems for road vehicles arrangement of road signs or traffic signals E01F9/00 ; automatic vehicle control B62D
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0141 for traffic information dissemination

Abstract

A method for predicting traffic wherein the method is a trend based extrapolation method that uses real time traffic data and historic traffic data to generate a predictive traffic product. The predictive traffic product provides expected traffic speeds for the short term future, for example, between two to twelve hours into the future.

Claims

1. A method for predicting traffic speeds, comprising:

calculating, by a processor, speed differences between real time data and historic data for a plurality of epochs;

calculating, by the processor, an average difference of the plurality of epochs, weighting the difference in the most recent epoch most and the difference in the oldest epoch least;

calculating, by the processor, a rate of change of the difference between the real time data and the historic data in the last two epochs;

calculating, by the processor, a trend value as a sum of the calculated average difference and the calculated rate of change;

predicting, by the processor, a speed at a next epoch as a sum of the historic speed for the next epoch and the calculated trend value; and

predicting, by the processor, a speed at a future epoch by applying the trend value in a decreasing fashion.

2. The method of claim 1 wherein the plurality of epochs comprises at least four epochs.

3. A computer implemented method comprising:

receiving, by a processor, an expected speed value of at least a portion of a road for each of a successive plurality of previously occurring time periods prior to or including a current time period and an expected speed value for a yet to occur time period subsequent thereto;

receiving, by the processor, an actual speed value for the portion of the road for each of the successive plurality of previously occurring time periods prior to the current time period;

computing, by the processor, a speed value trend based on the received expected speed values for each of the successive plurality of previously occurring time periods prior to the current time period and the received actual speed values; and

adjusting, by a processor, the expected speed value for the portion of the road for at least the yet to occur time period based on the computed speed value trend.

4. The computer implemented method of claim 3 further including:

receiving, by the processor, an expected speed value for the portion of the road for each of a successive plurality of time periods succeeding the yet to occur time period; and

for each of the successive plurality of time periods succeeding the yet to occur time period, adjusting, by the processor, the computed speed value trend and, further, adjusting, based thereon, the expected speed value of the associated time period of the successive plurality of time periods succeeding the yet to occur time period.

5. The computer implemented method of claim 4 wherein the adjusting of the computed speed value trend further includes diminishing the computed speed value trend.

6. The computer implemented method of claim 5 wherein a number of successive time periods over which the speed value trend is diminished until the speed value trend is at or near zero is based on the a magnitude of a difference between the expected speed value for the portion of the road for the yet to occur time period and the adjusted expected speed value of the portion of the road for the yet to occur time period.

7. The computer implemented method of claim 3 wherein the computing further comprises:

calculating, by the processor, a weighted average difference between the expected speed valued and the actual speed values for the successive plurality of previously occurring time periods;

calculating, by the processor, a rate of change of a difference between the expected speed value and the actual speed value of at least a two of the successive plurality of previously occurring time periods closest to the current time period; and

wherein the speed value trend is computed as a function of the calculated average difference and the calculated rate of change.

8. The computer implemented method of claim 3 further comprising repeating, by the processor periodically, the receiving of the expected speed values and actual speed values, the computing and the adjusting as the current time period advances.

9. The computer implemented method of claim 3 further comprising:

determining, by the processor, a known condition of the portion of the road wherein the received expected speed values comprise expected speed values of the portion of the road accounting for the known condition.

10. The computer implemented of claim 9 wherein the known condition comprises one of time of day, day of week, weather condition, sporting event, civic event, entertainment event, road construction, or combinations thereof.

11. The computer implemented method of claim 3 further comprising publishing, by the processor, the adjusted expected speed value for the portion of the road for the yet to occur time period.

12. A system comprising:

a processor and a memory coupled therewith; and

first logic stored in the memory and executable by the processor to cause the processor to receive an expected speed value of at least a portion of a road for each of a successive plurality of previously occurring time periods prior to or including a current time period and an expected speed value for a yet to occur time period subsequent thereto;

second logic stored in the memory and executable by the processor to cause the processor to receive an actual speed value for the portion of the road for each of the successive plurality of previously occurring time periods prior to the current time period;

third logic stored in the memory and executable by the processor to cause the processor to compute a speed value trend based on the received expected speed values for the successive plurality of previously occurring time periods and the received actual speed values; and

fourth logic stored in the memory and executable by the processor to cause the processor to adjust the expected speed value for the portion of the road for at least the yet to occur time period based on the computed speed value trend.

13. The system of claim 12 further including:

fifth logic stored in the memory and executable by the processor to cause the processor to receive an expected speed value for the portion of the road for each of a successive plurality of time periods succeeding the yet to occur time period, and for each of the successive plurality of time periods succeeding the yet to occur time period, adjust the computed speed value trend and, further, adjust, based thereon, the expected speed value of the associated time period of the successive plurality of time periods succeeding the yet to occur time period.

14. The system of claim 13 wherein the adjustment of the computed speed value trend further include a diminishment of the computed speed value trend.

15. The system of claim 14 wherein a number of successive time periods over which the speed value trend is diminished until the speed value trend is at or near zero is based on the a magnitude of a difference between the expected speed value for the portion of the road for the yet to occur time period and the adjusted expected speed value of the portion of the road for the yet to occur time period.

16. The system of claim 12 wherein the third logic is further executable by the processor to cause the processor to:

calculate a weighted average difference between the expected speed valued and the actual speed values for the successive plurality of previously occurring time periods;

calculate a rate of change of a difference between the expected speed value and the actual speed value of at least a two of the successive plurality of previously occurring time periods closest to the current time period; and

wherein the speed value trend is computed as a function of the calculated average difference and the calculated rate of change.

17. The system of claim 12 wherein the first, second, third and fourth logic are repeatedly executable by the processor as the current time period advances.

18. The system of claim 12 further comprising:

sixth logic stored in the memory and executable by the processor to cause the processor to determine a known condition of the portion of the road wherein the received expected speed values comprise expected speed values of the portion of the road accounting for the known condition.

19. The system of claim 18 wherein the known condition comprises one of time of day, day of week, weather condition, sporting event, civic event, entertainment event, road construction, or combinations thereof.

20. The system of claim 12 further comprising seventh logic stored in the memory and executable by the processor to cause the processor to publish the adjusted expected speed value for the portion of the road for the yet to occur time period.