Method and apparatus for providing context-related point-of-interest recommendations

• US 9,648,463 B2
• Filed: 12/19/2014
• Issued: 05/09/2017
• Est. Priority Date: 12/19/2014
• Status: Active Grant

• Current Assignee: HERE Global B.V. (HERE Holding Corporation)
• Original Assignee: HERE Global B.V. (HERE Holding Corporation)
• Inventors: Dousse, Olivier, Gaebler, Frank, Seyde, Daniel Cornelius Manuel
• Primary Examiner(s): Gonzalez, Amancio
• Application Number:
  US14/576,922
• Publication Number:
  US 20160183060A1
• Time in Patent Office: 872 Days
• Field of Search: 4554563
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 30/0261 based on user location
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

An approach is provided for providing context-related destination location recommendations. The destination recommendation platform determines at least one context associated with at least one user. The platform processes and/or facilitates a processing of mobility pattern information associated with the at least one user to determine one or more predicted destination locations and associated probability information based, at least in part, on the at least one context. The probability information represents respective one or more probabilities that the at least one user will travel to the one or more predicted destination locations under the at least one context. The platform further determines entropy information based, at least in part, on the probability information. The platform determines whether to cause, at least in part, a presentation of one or more recommended destination locations to the at least one user based, at least in part, on the entropy information.

Claims

1. A method comprising:

determining, by an apparatus, at least one context associated with at least one user;

processing, by the apparatus, mobility pattern information associated with the at least one user to determine one or more predicted destination locations and associated probability information based, at least in part, on the at least one context, wherein the probability information represents respective one or more probabilities that the at least one user will travel to the one or more predicted destination locations under the at least one context;

determining, by the apparatus, entropy information based, at least in part, on the probability information under the at least one context;

determining, by the apparatus, one or more travel costs for the at least one user to travel to the one or more predicted destination locations; and

determining, by the apparatus, whether to initiate a presentation of one or more recommended destination locations among the one or more predicted destination locations to the at least one user based, at least in part, on the entropy information and the one or more travel costs.

2. A method of claim 1, further comprising:

processing the probability information to determine a probability distribution, a sum of probabilities, or a combination thereof;

factoring the one or more travel costs in the sum of the probabilities to obtain a score;

determining to not initiate the presentation of the one or more recommended destination locations if the score is below a threshold value; and

initiating the presentation of the one or more recommended destination locations if the score is above a threshold value.

3. A method of claim 1, further comprising:

processing the mobility pattern information to determine familiarity information for the at least one user with respect to the at least one context,

wherein a determination of the one or more recommended destination locations, the presentation of one or more recommended destination locations, or a combination is further based, at least in part, on the familiarity information.

4. A method of claim 3, wherein the familiarity information includes, at least in part, place familiarity information, place type familiarity information, link familiarity information, area familiarity information, or a combination thereof.

5. A method of claim 3, further comprising:

processing metadata associated with the one or more predicted destination locations to determine one or more features, wherein the one or more features include user preference on locations that the user has not yet visited and is willing to visit, wherein the one or more recommended destination locations are further determined based, at least in part, on the one or more features.

6. A method of claim 5, further comprising:

processing the mobility pattern information to determine feature probability distribution information with respect to the one or more features;

determining feature entropy information for the one or more features based, at least in part, the feature probability distribution information; and

determining the one or more recommended destination locations based, at least in part, on the feature entropy information.

7. A method of claim 1, further comprising:

processing the mobility pattern information to determine at least one familiar zone for the at least one context; and

determining at least one exploration zone based, at least in part, on the at least one familiar zone,

wherein the one or more recommended destination locations is determined from the at least one exploration zone, and

wherein the one or more travel costs are calculated based on one or more prices associated with travelling to the one or more predicted destination locations, a travel time of day, a predicted available time of the at least one user, a deviation from a known route required to travel to the one or more predicted destination locations, or a combination thereof.

8. A method of claim 7, further comprising:

processing the mobility pattern information to determine information regarding a distance threshold that the at least one user travels in response to at least one recommendation,

wherein the at least one exploration zone represents at least one area beyond the at least one familiar zone and within the distance threshold.

9. A method of claim 7, further comprising:

determining familiarity information, relevance information, or a combination thereof for one or more candidate destination locations in the at least one exploration zone; and

selecting the one or more recommended destination locations from the one or more candidate destination locations based, at least in part, on the familiarity information, the relevance information, or a combination thereof.

10. A method of claim 1, further comprising:

processing the mobility pattern information to determine one or more known locations of the at least one user; and

excluding the one or more known locations from the one or more recommended destination locations,

wherein the one or more travel costs are factored in by subtracting the one or more travel costs from the sum of the probabilities.

11. A method of claim 1, wherein the at least one context comprises a current time, a current weekday, a current static location or movement along a route of travel, a current vehicle occupancy, or a combination thereof.

12. A method of claim 1, wherein the context comprises driving task intensity, the method further comprising:

determining the driving task intensity information based on a route of travel to the one or more predicted locations, wherein the driving task intensity requires the at least one user'"'"'s full attention, the at least one user'"'"'s regular attention, or the at least one user'"'"'s low attention under the context.

13. 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 at least one context associated with at least one user;

process mobility pattern information associated with the at least one user to determine one or more predicted destination locations and associated probability information based, at least in part, on the at least one context, wherein the probability information represents respective one or more probabilities that the at least one user will travel to the one or more predicted destination locations under the at least one context;

determine entropy information based, at least in part, on the probability information under the at least one context;

determine one or more travel costs for the at least one user to travel to the one or more predicted destination locations; and

determine whether to initiate a presentation of one or more recommended destination locations among the one or more predicted destination locations to the at least one user based, at least in part, on the entropy information and the one or more travel costs.

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

process the probability information to determine a probability distribution, a sum of probabilities, or a combination thereof;

determine to not initiate the presentation of the one or more recommended destination locations if the sum of the probabilities is below a probability sum threshold value; and

initiate the presentation of the one or more recommended destination locations if the sum of the probabilities is above a probability distribution threshold value.

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

process the mobility pattern information to determine familiarity information for the at least one user with respect to the at least one context,

wherein a determination of the one or more recommended destination locations, the presentation of one or more recommended destination locations, or a combination is further based, at least in part, on the familiarity information.

16. An apparatus of claim 15, wherein the familiarity information includes, at least in part, place familiarity information, place type familiarity information, link familiarity information, area familiarity information, or a combination thereof.

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

process metadata associated with the one or more predicted destination locations to determine one or more features; and

determine the one or more recommended destination locations based, at least in part, on the one or more features.

18. An apparatus of claim 17, wherein the apparatus is further caused to:

process the mobility pattern information to determine feature probability distribution information with respect to the one or more features;

determine feature entropy information for the one or more features based, at least in part, the feature probability distribution information; and

determine the one or more recommended destination locations based, at least in part, on the feature entropy information.

19. An apparatus of claim 13, wherein the apparatus is further caused to:

process the mobility pattern information to determine at least one familiar zone for the at least one context; and

determine at least one exploration zone based, at least in part, on the at least one familiar zone,

wherein the one or more recommended destination locations is determined from the at least one exploration zone.

20. 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 the following steps:

determining at least one context associated with at least one user;

processing mobility pattern information associated with the at least one user to determine one or more predicted destination locations and associated probability information based, at least in part, on the at least one context, wherein the probability information represents respective one or more probabilities that the at least one user will travel to the one or more predicted destination locations under the at least one context;

determining entropy information based, at least in part, on the probability information under the at least one context;

determining one or more travel costs for the at least one user to travel to the one or more predicted destination locations; and

determining whether to initiate a presentation of one or more recommended destination locations among the one or more predicted destination locations to the at least one user based, at least in part, on the entropy information and the one or more travel costs.

21. A computer-readable storage medium of claim 20, wherein the apparatus is further caused to perform:

processing the probability information to determine a probability distribution, a sum of probabilities, or a combination thereof;

determining to not initiate the presentation of the one or more recommended destination locations if the sum of the probabilities is below a probability sum threshold value; and

initiating the presentation of the one or more recommended destination locations if the sum of the probabilities is above a probability distribution threshold value.

22. A computer-readable storage medium of claim 20, wherein the apparatus is further caused to perform:

processing the mobility pattern information to determine familiarity information for the at least one user with respect to the at least one context,

wherein a determination of the one or more recommended destination locations, the presentation of one or more recommended destination locations, or a combination is further based, at least in part, on the familiarity information.