Discovery of public points of interest

• US 8,566,014 B1
• Filed: 05/17/2012
• Issued: 10/22/2013
• Est. Priority Date: 05/17/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Canavor, Darren E., Kozolchyk, Jonathan, Hess, Blake P., Fielding, Jeffrey J.
• Primary Examiner(s): Black, Thomas
• Assistant Examiner(s): PAYNE, ROBERT T
• Application Number:
  US13/474,047
• Time in Patent Office: 523 Days
• Field of Search: 701/426, 701/300, 701/521, 701/438, 701/425, 701/9, 345/419, 118/708, 427/136, 427/137, 340/686.1, 340/540, 702/2, 702/130, 700/283, 705/1.1, 704/8
• US Class Current: 701/300
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G01C 21/3679 Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities G01C21/3611 takes precedence
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/024 Guidance services
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

Disclosed are various embodiments for discovery of public points of interest. Data identifying points of interest is obtained. Each point of interest is associated with a respective user and specifies a respective name and a respective geographic location. A public point of interest is determined based at least in part on a similarity of the respective names of a subset of the points of interest, a proximity of the respective geographic locations of the subset of the points of interest, and a number of different users associated with the subset of the points of interest.

Claims

1. A non-transitory computer-readable medium embodying a program executable in a computing device, comprising:

code that obtains check-in data identifying a plurality of personal points of interest each associated with a respective one of a plurality of users, each of the personal points of interest specifying a respective name, a respective geographic location, and a respective time associated with a visit to the respective geographic location, at least one of the personal points of interest being generated by a check-in application executed in a mobile computing device;

code that determines a plurality of different public points of interest, each of the different public points of interest being determined based at least in part on external data, a measure of similarity of the respective names of a respective subset of the personal points of interest meeting a similarity threshold, a measure of proximity of the respective geographic locations of the respective subset of the personal points of interest meeting a first proximity threshold, and a number of different users associated with the respective subset of the personal points of interest meeting a quantity threshold; and

code that infers a composite public point of interest from the different public points of interest based at least in part on a measure of proximity of corresponding representative geographic locations for the different public points of interest meeting a second proximity threshold.

2. The non-transitory computer-readable medium of claim 1, wherein the code that determines the different public points of interest is further configured to submit at least one of the different public points of interest as a potential public point of interest to a manual review system based at least in part on a manual review threshold;

wherein the manual review system is configured to provide at least one image of a representative geographic location for the potential public point of interest for a manual review; and

wherein the manual review system is configured to direct an agent to capture the at least one image at the representative geographic location.

3. The non-transitory computer-readable medium of claim 1, wherein the external data indicates a name validity or a geographic location validity.

4. A system, comprising:

at least one computing device; and

at least one application executable in the at least one computing device, the at least one application comprising;

logic that obtains data identifying a plurality of points of interest, each of at least some of the points of interest being associated with a respective user, and each of the points of interest specifying a respective name and a respective geographic location; and

logic that determines a public point of interest based at least in part on a similarity of the respective names of a subset of the points of interest, a proximity of the respective geographic locations of the subset of the points of interest, and a number of different users associated with the subset of the points of interest.

5. The system of claim 4, wherein each of the points of interest further specify a respective time associated with a visit to the respective geographic location, and the public point of interest is determined based at least in part on a time window encompassing the respective times for the subset of the points of interest.

6. The system of claim 5, wherein the at least one application further comprises logic that infers a periodic time window of operation for the public point of interest based at least in part on the respective times for the subset of the points of interest.

7. The system of claim 5, wherein the at least one application further comprises logic that determines a busy period of operation for the public point of interest based at least in part on the respective times for the subset of the points of interest.

8. The system of claim 5, wherein the at least one application further comprises logic that determines a corresponding representative geographic location for the public point of interest for each of a plurality of time periods.

9. The system of claim 4, wherein the logic that determines the public point of interest is further configured to submit the public point of interest as a potential public point of interest to a manual review system based at least in part on a manual review threshold.

10. The system of claim 9, wherein the manual review system is configured to provide at least one image of a representative geographic location for the potential public point of interest for a manual review.

11. The system of claim 10, wherein the manual review system is configured to direct an agent to capture the at least one image at the representative geographic location.

12. The system of claim 4, wherein the at least one application further comprises logic that infers a composite public point of interest from a plurality of different public points of interest determined by the logic that determines the public point of interest.

13. The system of claim 4, wherein the at least one application further comprises logic that infers a composite public point of interest from the data identifying the points of interest.

14. The system of claim 4, wherein the at least one application further comprises logic that updates an existing public point of interest based at least in part on the data identifying the points of interest.

15. The system of claim 4, wherein the at least one application further comprises logic that removes an existing public point of interest based at least in part on the data identifying the points of interest.

16. The system of claim 4, wherein the logic that determines the public point of interest is further configured to determine the public point of interest based at least in part on external name data and the respective names of the subset of the points of interest.

17. The system of claim 4, wherein the at least one application further comprises logic that stores the public point of interest in a data store for public points of interest.

18. The system of claim 4, wherein the logic that obtains is configured to obtain data identifying one of the points of interest by way of a check-in application executed in a mobile computing device, wherein the respective geographic location for the one of the points of interest is determined by way of a location-finding device in the mobile computing device.

19. The system of claim 4, wherein the logic that obtains is configured to obtain data identifying one of the points of interest by way of at least one network page served up by a network site, wherein the respective geographic location for the one of the points of interest is indicated by a user relative to a map included in the at least one network page.

20. A method, comprising:

obtaining, in at least one computing device, data identifying a plurality of points of interest each associated with a respective user, each of the points of interest specifying a respective name and a respective geographic location;

determining, in the at least one computing device, a plurality of different public points of interest, each of the different public points of interest being determined based at least in part on a similarity of the respective names of a respective subset of the points of interest, a proximity of the respective geographic locations of the respective subset of the points of interest, and a number of different users associated with the respective subset of the points of interest; and

inferring, in the at least one computing device, a composite public point of interest from the different public points of interest based at least in part on a proximity of corresponding representative geographic locations for the different public points of interest.

21. The method of claim 20, wherein the composite public point of interest is inferred based at least in part on behavior data associated with a subset of the users who are associated with the subsets of the points of interest corresponding to the different public points of interest.

22. The method of claim 20, wherein the composite public point of interest is inferred based at least in part on transaction data associated with the different public points of interest.

23. The method of claim 20, further comprising inferring, in the at least one computing device, another composite public point of interest directly from the points of interest based at least in part on a proximity of corresponding representative geographic locations for the points of interest.

24. The method of claim 20, wherein each of the points of interest specify a respective time associated with a visit of the respective user to the respective geographic location, and the composite public point of interest is inferred based at least in part on the respective times associated with the subsets of the points of interest.

25. The method of claim 24, wherein inferring the composite public point of interest further comprises inferring, in the at least one computing device, the composite public point of interest to be an ephemeral public point of interest based at least in part on the respective times associated with the subsets of the points of interest.

26. The method of claim 24, wherein inferring the composite public point of interest further comprises inferring, in the at least one computing device, the composite public point of interest to be a periodic public point of interest based at least in part on the respective times associated with the subsets of the points of interest.

27. The method of claim 20, further comprising determining, in the at least one computing device, a representative name for the composite public point of interest.

28. The method of claim 20, further comprising determining, in the at least one computing device, a representative geographic location for the composite public point of interest.

29. The method of claim 20, further comprising submitting, in the at least one computing device, the composite public point of interest as a potential composite public point of interest to a manual review system based at least in part on a manual review threshold.