Predictive incident aggregation

• US 9,613,529 B2
• Filed: 02/03/2014
• Issued: 04/04/2017
• Est. Priority Date: 02/03/2014
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Downs, Oliver, Tennent, Toby, Arcot, Praveen
• Primary Examiner(s): Tran, Khoi
• Assistant Examiner(s): RINK, RYAN J
• Application Number:
  US14/171,049
• Publication Number:
  US 20150221218A1
• Time in Patent Office: 1,156 Days
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• 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

In one embodiment, an incident report including a path segment identifier and an incident identifier is received at a computing device. The incident identifier is sent to a traffic prediction model. The traffic prediction model returns a traffic distribution value. The traffic distribution value identifies a portion of a traffic prediction distribution derived from historical data. The computing device accesses a lookup table according to traffic distribution value and the path segment identifier to receive a speed prediction.

Claims

1. A method comprising:

receiving an incident identifier for a category of incident from an incident reporting device;

sending at least the incident identifier to a traffic prediction model;

receiving a traffic distribution value from the traffic prediction model, wherein the traffic distribution value is a statistical placeholder for a distribution of predicted traffic for the incident identifier and independent of path segment data applicable to multiple path segments;

accessing a lookup table according to the traffic distribution value and a first path segment identifier to receive a first speed prediction for the combination of the category of incident and the first path segment identifier;

accessing the lookup table according to the traffic distribution value and a second path segment identifier to receive a second speed prediction for the combination of the category of the incident and the second path segment identifier; and

providing map data including the first speed prediction and the second speed prediction.

2. The method of claim 1, wherein the traffic distribution value is a single digit.

3. The method of claim 1, wherein the lookup table matches speed ranges for path segments according to a plurality of traffic distribution values including the traffic distribution value received from the traffic prediction model.

4. The method of claim 1, wherein the traffic distribution value is a quintile number is defined according to a path segment.

5. The method of claim 4, wherein the quintile number corresponds to a graphical representation of the road.

6. The method of claim 1, further comprising:

modifying the traffic distribution value from the traffic prediction model as a function of distance between a road location along a path identified by the path segment identifier and an incident location identified by the incident identifier.

7. The method of claim 1, further comprising:

modifying the traffic distribution value from the traffic prediction model as a function of an elapsed period of time relative to a timestamp from the incident identifier.

8. The method of claim 1, wherein the traffic prediction model associates traffic distribution values with incidents including at least one of an accident event, a hazard event, a weather event, or a flow improving event.

9. The method of claim 8, wherein the traffic prediction model associates traffic distribution values with attributes of the incidents, wherein the attributes include at least one of shoulder location, left lane location, center lane location, right lane location, median location, emergency vehicles present, or multiple vehicles.

17. The method of claim 1, wherein the path segment identifier includes a road classification value.

10. 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;

receive a path segment identifier for a category of path segment;

receive a category of a path segment;

identify a first numerical representation for a traffic distribution value of expected traffic for the path segment, wherein the traffic distribution value is a statistical division of the expected traffic for the path segment;

identify a traffic incident type reported by a police scanner, a camera, a telephone, a text message, a social networking service, or a mobile application;

perform a traffic prediction algorithm based on the traffic incident type;

receive an adjustment for the traffic distribution value from the traffic prediction algorithm, wherein the adjustment for the traffic distribution value is a second numerical representation and independent of path segment data;

combine the traffic distribution value and the adjustment for the traffic distribution value as an adjusted traffic distribution value that is applicable to multiple categories of path segments;

determine a predicted traffic speed according to adjusted traffic distribution value; and

,

send a message including an indication of the predicted traffic speed to a mobile device.

11. The apparatus of claim 10, wherein the predicted traffic speed is calculated as a function of a path segment.

12. The apparatus of claim 10, wherein the statistical division corresponds to a graphical representation of the road.

13. The apparatus of claim 10, wherein the traffic distribution value varies as a function of distance between a road location along a path identified by the path segment identifier and an incident location identified by the incident identifier.

14. The apparatus of claim 10, wherein the traffic prediction algorithm associates traffic distribution values with incidents including at least one of an accident event, a hazard event, a weather event, or a flow improving event.

15. The apparatus of claim 10, wherein the traffic prediction algorithm associates traffic distribution values with attributes of the incidents, wherein the attributes include at least one of shoulder location, left lane location, center lane location, right lane location, median location, emergency vehicles present, or multiple vehicles.

18. The apparatus of claim 10, wherein the statistical division is a tertile, a quartile, a quintile, a decile, or a centile.

19. The apparatus of claim 10, wherein the statistical division is defined according to one or more standard deviations.

16. A method comprising:

detecting historic traffic flow data;

receiving historic incident data, wherein the historic incident data describes types of incidents including at least one of an accident event, a hazard event, a weather event, or a flow improving event, wherein the historic incident data describes attributes of incidents including at least one of shoulder location, left lane location, center lane location, right lane location, median location, emergency vehicles present, or multiple vehicles;

generating a traffic prediction model based on the historic traffic flow data and the historic incident data, wherein the traffic prediction model outputs a traffic distribution value based on an input incident type and input incident attribute, wherein the traffic distribution value is a numerical representation of a traffic prediction distribution based on the input incident type and input incident attribute,

wherein the numerical representation of the traffic prediction distribution is a statistical placeholder for a statistical division of the traffic distribution and independent of path segment data applicable to multiple categories of road type;

receiving a path identifier after the traffic distribution value is generated; and

accessing a lookup table according to the numerical representation of the traffic distribution value and the path identifier to determine a speed prediction.

20. The method of claim 16, wherein the statistical division is a tertile, a quartile, a quintile, a decile, or a centile.