Method and apparatus for providing personalized routing based on user routing behaviors

• US 9,778,060 B2
• Filed: 05/22/2015
• Issued: 10/03/2017
• Est. Priority Date: 05/22/2015
• Status: Active Grant

• Current Assignee: HERE Global B.V. (HERE Holding Corporation)
• Original Assignee: HERE Global B.V. (HERE Holding Corporation)
• Inventors: Cheng, Wanli
• Primary Examiner(s): MELTON, TODD M
• Application Number:
  US14/719,891
• Publication Number:
  US 20160341564A1
• Time in Patent Office: 865 Days
• CPC Class Codes: G01C 21/3461 Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types, segments such as motorways, toll roads, ferries
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/3617 using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement
• CPC Class Codes: G01C 21/3641 Personalized guidance, e.g. limited guidance on previously travelled routes

Abstract

An approach is provided for determining one or more previous behaviors made by at least one user traveling at least one calculated route. The one or more previous behaviors include, at least in part, one or more deviations from, one or more matches on, or a combination thereof for the at least one calculated route. The approach involves determining one or more predictor values for one or more predictors associated with the one or more previous behaviors. The approach also involves causing, at least in part, a creation of at least one predictive model based, at least in part, on the one or more predictor values. The at least one predictive model is used to predict one or more potential behaviors by the at least one user while traveling the at least one calculated route, at least one other route, or a combination thereof.

Claims

1. A method comprising:

determining one or more previous behaviors made by at least one user traveling at least one calculated route, wherein the one or more previous behaviors include, at least in part, one or more routing mistakes, one or more behaviors correctly following routing instructions, or a combination thereof for the at least one calculated route;

determining one or more predictor values for one or more predictors associated with the one or more previous behaviors, wherein the one or more predictor values include, at least in part, personalized data for the at least one user;

creating at least one predictive model based, at least in part, on the one or more predictor values;

personalizing the at least one predictive model to the at least one user based, at least in part, on the personalized data; and

determining weighting information for the one or more predictors based, at least in part, on the personalized data,

wherein the at least one predictive model is used to predict one or more potential behaviors by the at least one user while traveling the at least one calculated route, at least one other route, or a combination thereof.

2. The method of claim 1,

wherein the personalization of the at least one predictive model is further based, at least in part, on the weighting information.

3. The method of claim 1, further comprising:

receiving a request by the at least one user to generate at least one subsequent calculated route; and

processing the at least one subsequent calculated route using the at least one predictive model to determine one or more predicted behaviors for the at least one user while traveling the at least one subsequent calculated route.

4. The method of claim 3, further comprising:

personalizing navigation guidance information to present to the at least one user while traveling the at least one subsequent calculated route based, at least in part, on the one or more predicted behaviors.

5. The method of claim 4, wherein the personalization of the navigation guidance information includes, at least part, varying a type of the navigation guidance information, a frequency of the navigation guidance information, a timing for presenting the navigation guidance information, or a combination thereof.

6. The method of claim 1, further comprising:

applying at least one supervised feature selection mechanism to classify the one or more predictors as useful for prediction,

wherein the creation of the at least one predictive model is based, at least in part, on the one or more predictor values associated with the one or more predictors classified as useful for prediction.

7. The method of claim 1, further comprising:

determining predictive accuracy information for the at least one predictive model; and

associating the at least one predictive model with at least one profile of the at least one user if the predictive accuracy information is above at least one threshold value.

8. The method of claim 1, further comprising:

determining the one or more routing mistakes, the one or more behaviors correctly following routing instructions, or a combination thereof by comparing at least one recorded route associated with the at least one user against the at least one calculated route.

9. The method of claim 1, wherein the one or more predictors include, at least in part, a route complexity predictor, a behavior commonality predictor, a route familiarity predictor, a routing sequence predictor, a user behavior predictor, a traffic predictor, a weather predictor, or a combination thereof.

10. The method of claim 1, wherein the one or more routing mistakes includes one or more driving deviations by the user between a recorded route and the calculated route.

11. 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;

determine one or more previous behaviors made by at least one user traveling at least one calculated route, wherein the one or more previous behaviors include, at least in part, one or more routing mistakes, one or more behaviors correctly following routing instructions, or a combination thereof for the at least one calculated route;

determine one or more predictor values for one or more predictors associated with the one or more previous behaviors, wherein the one or more predictor values include, at least in part, personalized data for the at least one user;

create at least one predictive model based, at least in part, on the one or more predictor values;

personalize the at least one predictive model to the at least one user based, at least in part, on the personalized data; and

determine weighting information for the one or more predictors based, at least in part, on the personalized data,

wherein the at least one predictive model is used to predict one or more potential behaviors by the at least one user while traveling the at least one calculated route, at least one other route, or a combination thereof.

12. The apparatus of claim 11,

wherein the personalization of the at least one predictive model is further based, at least in part, on the weighting information.

13. The apparatus of claim 11, further comprising:

receive a request by the at least one user to generate at least one subsequent calculated route; and

process the at least one subsequent calculated route using the at least one predictive model to determine one or more predicted behaviors for the at least one user while traveling the at least one subsequent calculated route.

14. The apparatus of claim 13, further comprising:

personalize navigation guidance information to present to the at least one user while traveling the at least one subsequent calculated route based, at least in part, on the one or more predicted behaviors.

15. The apparatus of claim 11, further comprising:

apply at least one supervised feature selection mechanism to classify the one or more predictors as useful for prediction,

wherein the creation of the at least one predictive model is based, at least in part, on the one or more predictor values associated with the one or more predictors classified as useful for prediction.

16. The apparatus of claim 11, further comprising:

determine predictive accuracy information for the at least one predictive model; and

associate the at least one predictive model with at least one profile of the at least one user if the predictive accuracy information is above at least one threshold value.

17. The apparatus of claim 11, wherein the one or more routing mistakes includes one or more driving deviations by the user between a recorded route and the calculated route.

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 at least perform the following steps:

determining one or more previous behaviors made by at least one user traveling at least one calculated route, wherein the one or more previous behaviors include, at least in part, one or more routing mistakes, one or more behaviors correctly following routing instructions, or a combination thereof for the at least one calculated route;

determining one or more predictor values for one or more predictors associated with the one or more previous behaviors, wherein the one or more predictor values include, at least in part, personalized data for the at least one user;

creating at least one predictive model based, at least in part, on the one or more predictor values;

personalizing the at least one predictive model to the at least one user based, at least in part, on the personalized data; and

determining weighting information for the one or more predictors based, at least in part, on the personalized data,

wherein the at least one predictive model is used to predict one or more potential behaviors by the at least one user while traveling the at least one calculated route, at least one other route, or a combination thereof.

19. The non-transitory computer-readable storage medium of claim 18,

wherein the personalization of the at least one predictive model is further based, at least in part, on the weighting information.

20. The non-transitory computer-readable storage medium of claim 18, wherein the one or more routing mistakes includes one or more driving deviations by the user between a recorded route and the calculated route.