Granted Patent B2

US 12,307,886 · App. 17/562,585 · Granted May 20, 2025

Inventors: Jingwei Xu (Buffalo Grove, IL); Yuxin Guan (Chicago, IL); Bruce Bernhardt (Wauconda, IL); Weimin Huang (Chicago, IL); Ian He (Chicago, IL)

Assignee: HERE Global B.V.

G08G1/0129G01C21/3691G08G1/052

Abstract

Claims (64)

1. A method comprising:

using one or more location sensors of one or more devices, one or more vehicles, or a combination thereof to collect real-time probe data for each road segment within a geographic area, wherein the real-time probe data is provided as real-time traffic information, wherein the one or more location sensors are based on satellite positioning, inertial measurement, wireless signals, or a combination thereof;

retrieving historical traffic information for said each road segment;

in real time, aggregating traffic flow speed data in the real-time traffic information to compute traffic pattern data for each road segment, wherein the traffic pattern data includes static speed data of said each road segment;

in real time, aggregating traffic flow speed data in the historical traffic information to compute a first travel time reliability index metric using a first index methodology and a second travel time reliability index metric using a second index methodology that is different from the first index methodology for said each road segment, wherein the first travel time reliability index metric and the second travel time reliability index metric are computed to indicate a consistency in a plurality of travel times in the historical traffic information from day-to-day, across different times of day, or a combination thereof; and

in real time, determining, based on the first travel time reliability index metric and the second travel time reliability index metric, to use the traffic pattern data, a mean, or a percentile of a road segment travel time distribution in the historical traffic information for traffic prediction associated with said each road segment.

2. The method of claim 1 , wherein the traffic flow speed data in the historical traffic information is aggregated for said each road segment and per one or more predefined time windows in a day, back to a predefined time period to compute the first travel time reliability index metric and the second travel time reliability index metric.

3. The method of claim 2 , further comprising:

calculating the mean, the percentile, or a combination thereof of the road segment travel time distribution for said each road segment per time window,

wherein the first travel time reliability index metric and the second travel time reliability index metric are computed based on the mean, the percentile, or a combination thereof of the road segment travel time distribution.

4. The method of claim 3 , further comprising:

determining a road segment travel time reliability based on the first travel time reliability index metric and the second travel time reliability index metric and

either (1) blending the traffic pattern data or a first percentile of the road segment travel time distribution with the real time traffic information for the traffic prediction, when the road segment travel time reliability is determined as reliable,

or (2) blending the first percentile or a second percentile of the road segment travel time distribution with the real time traffic information for the traffic prediction, when the road segment travel time reliability is determined as unreliable.

5. The method of claim 4 , further comprising:

determining whether a delta between the traffic pattern data and the first percentile exceeds a threshold,

wherein the traffic pattern data is blended for the traffic prediction when delta does not exceed the threshold, and the first percentile is blended for the traffic prediction when the delta exceeds the threshold.

6. The method of claim 4 , further comprising:

determining a root cause of the road segment travel time reliability being determined as unreliable based on a determination that the first travel time reliability index metric and the second travel time reliability index metric exceed one or more thresholds associated with one or more input event resources in the historical traffic information,

wherein the root cause is a work zone, weather, special event, incident, traffic control, demand variability, or lack of base capacity.

7. The method of claim 6 , wherein the second percentile is blended for the traffic prediction when a cause of the unreliable is known, and the first percentile is blended for the traffic prediction when the root cause is unknown.

8. The method of claim 4 , further comprising:

providing the road segment travel time distribution for traffic prediction, when the first percentile or the second percentile is blended for the traffic prediction.

9. The method of claim 1 , further comprising:

providing the first travel time reliability index metric, the second travel time reliability index metric, the traffic prediction, or a combination thereof as an output.

10. The method of claim 1 , further comprising:

training a machine learning model to determine the first travel time reliability index metric and the second travel time reliability index metric for said each road segment.

11. The method of claim 9 , further comprising:

processing the output to perform at least one of:

providing navigation routing data to a vehicle, a user, or a combination thereof,

fleet management, and

vehicle dispatch.

12. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

use one or more location sensors of one or more devices, one or more vehicles, or a combination thereof to collect real-time probe data for each road segment within a geographic area, wherein the real-time probe data is provided as real-time traffic information, wherein the one or more location sensors are based on satellite positioning, inertial measurement, wireless signals, or a combination thereof;

retrieve historical traffic information for each road segment;

in real time, aggregate traffic flow speed data in the real-time traffic information to compute traffic pattern data for each road segment, wherein the traffic pattern data includes static speed data of said each road segment, and wherein the static speed data includes an average speed over a designated interval of time;

in real time, aggregate traffic flow speed data in the historical traffic information to compute one or more travel time reliability index metrics for said each road segment, wherein the one or more travel time reliability index metrics is computed to indicate a consistency in a plurality of travel times in the historical traffic information from day-to-day, across different times of day, or a combination thereof; and

in real time, determine, based on the one or more travel time reliability index metrics, to use the traffic pattern data, a mean, or a percentile of a road segment travel time distribution in the historical traffic information for traffic prediction associated with said each road segment.

13. The apparatus of claim 12 , wherein the traffic flow speed data in the historical traffic information is aggregated for said each road segment and per one or more predefined time windows in a day, back to a predefined time period to compute the first travel time reliability index metric and the second travel time reliability index metric.

14. The apparatus of claim 13 , wherein the apparatus is further caused to:

calculate the mean, the percentile, or a combination thereof of the road segment travel time distribution for said each road segment per time window,

wherein the first travel time reliability index metric and the second travel time reliability index metric are computed based on the mean, percentile, or a combination thereof of the road segment travel time distribution.

15. The apparatus of claim 14 , wherein the apparatus is further caused to:

determine a road segment travel time reliability based on the first travel time reliability index metric and the second travel time reliability index metric, and

either (1) blend the traffic pattern data or a first percentile of the road segment travel time distribution with the real time traffic information for the traffic prediction, when the road segment travel time reliability is determined as reliable,

or (2) blend the first percentile or a second percentile of the road segment travel time distribution with the real time traffic information for the traffic prediction, when the road segment travel time reliability is determined as unreliable.

16. The apparatus of claim 15 , wherein the apparatus is further caused to:

determine whether a delta between the traffic pattern data and the first percentile exceeds a threshold,

wherein the traffic pattern data is blended for the traffic prediction when delta does not exceed the threshold, and the first percentile is blended for the traffic prediction when the delta exceeds the threshold.

17. The apparatus of claim 15 , wherein the apparatus is further caused to:

provide the road segment travel time distribution for traffic prediction, when the first percentile or the second percentile is blended for the traffic prediction.

18. A non-transitory computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to perform:

using one or more location sensors of one or more devices, one or more vehicles, or a combination thereof to collect real-time probe data for each road segment within a geographic area, wherein the real-time probe data is provided as real-time traffic information, wherein the one or more location sensors are based on satellite positioning, inertial measurement, wireless signals, or a combination thereof;

retrieving real-time traffic information, historical traffic information, or a combination thereof for each road segment within a geographic area;

in real time, aggregating traffic flow speed data in the real-time traffic information to compute traffic pattern data for each road segment, wherein the traffic pattern data includes static speed data of each said road segment;

in real time, aggregating traffic flow speed data in the historical traffic information to compute one or more travel time reliability index metrics for each said road segment, wherein the one or more travel time reliability index metrics is computed to indicate a consistency in a plurality of travel times in the historical traffic information from day-to-day, across different times of day, or a combination thereof; and

in real time, determining, based on the one or more travel time reliability index metrics, to use the traffic pattern data, a mean, or a percentile of a road segment travel time distribution in the historical traffic information for traffic prediction associated with each said road segment.

19. The non-transitory computer-readable storage medium of claim 18 , wherein the traffic flow speed data in the historical traffic information is aggregated for said each road segment and per one or more predefined time windows in a day, back to a predefined time period to compute the first travel time reliability index metric and the second travel time reliability index metric.

20. The non-transitory computer-readable storage medium of claim 19 , wherein the apparatus is caused to further perform:

calculating the mean, the percentile, or a combination thereof of the road segment travel time distribution for each said road segment per time window,

wherein the first travel time reliability index metric and the second travel time reliability index metric are computed based on the mean, percentile, or a combination thereof of the road segment travel time distribution.

Assignments (1)

Continuity (1)

References Cited (14)