Harvesting labels for significant locations based on candidate points of interest and contextual data

• US 10,506,373 B2
• Filed: 09/22/2017
• Issued: 12/10/2019
• Est. Priority Date: 06/10/2016
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Warren, Richard B., Zvyagintsev, Danil Yuryevich, Dal Santo, Michael P., Popescu, Liviu T., Kazemi, Pejman Lotfali, Shin, Hyo Jeong, Zhou, Zehua
• Primary Examiner(s): Osifade, Idowu O
• Application Number:
  US15/713,541
• Publication Number:
  US 20180014161A1
• Time in Patent Office: 809 Days
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
• CPC Class Codes: H04W 4/025 using location based information parameters

Abstract

In an example method, a computer system receives a query from a mobile device, including an indication of a location of the mobile device, and an environmental measurement obtained by the mobile device at the location. A set of candidate points of interest in geographical proximity to the location is determined. For each of one or more candidate points of interest of the set, a location fingerprint of the candidate point of interest and contextual data regarding the candidate point of interest are obtained. A similarity between the environmental measurement and each location fingerprint is determined. A particular candidate point of interest is selected from among the set based on the similarity, and based on an assessment of the contextual data. A label of the selected point of interest is associated with the location and transmitted to the mobile device.

Claims

1. A method comprising:

receiving, at a computer system, a query from a mobile device remote from the computer system, the query comprising an indication of a location of the mobile device, and an environmental measurement obtained by the mobile device at the location;

determining, at the computer system, a set of candidate points of interest in geographical proximity to the location;

obtaining, at the computer system for each of one or more candidate points of interest of the set, a location fingerprint of the candidate point of interest and contextual data regarding the candidate point of interest;

determining, at the computer system, a similarity between the environmental measurement and each location fingerprint;

selecting, at the computer system, a particular candidate point of interest from among the set, wherein the particular candidate point of interest is selected based on the similarity between the environmental measurement and each location fingerprint, and based on an assessment of the contextual data;

associating, at the computer system, a label of the selected point of interest with the location; and

transmitting, from the computer system to the mobile device, the label of the selected point of interest.

2. The method of claim 1, wherein determining the set of candidate points of interest in geographical proximity to the location comprises determining one or more points of interest within a radius r of the location.

3. The method of claim 2, wherein the radius r is determined based on an accuracy or a reliability of the location provided by the mobile device.

4. The method of claim 1, wherein the contextual data regarding the candidate point of interest comprises at least one of an hours of operation of the candidate point of interest, a days of operation of the candidate point of interest, a popularity of the candidate point of interest, or a favorability of the candidate point of interest.

5. The method of claim 1, wherein selecting the particular candidate point of interest from among the set comprises:

determining, for each candidate point of interest of the set, a respective likelihood score, each likelihood score representing a likelihood that the location corresponds to the candidate point of interest.

6. The method of claim 5, wherein determining, for each candidate point of interest, the respective likelihood score comprises:

calculating an initial likelihood score based on a similarity between the environmental measurement and the location fingerprint of the candidate point of interest; and

subsequent to calculating the initial likelihood score, modifying the initial likelihood score based on the contextual data of the candidate point of interest.

7. The method of claim 6, wherein determining, for each candidate point of interest, the respective likelihood score further comprises:

determining a particular candidate point of interest of the set not associated with a location fingerprint;

calculating an initial likelihood score for that candidate point of interest based on an interpolation of one or more likelihood scores for one or more other candidate points of interest of the set.

8. The method of claim 5, further comprising identifying one or more additional candidate points of interest based on the likelihood scores, wherein identifying one or more additional candidate points of interest comprises:

determining an additional point of interest not associated with a location fingerprint and in geographical proximity to the location;

determining that the additional point of interest is within a threshold distance of a candidate point of interest of the set having a likelihood score greater than a threshold likelihood value; and

including the additional point of interest in the set.

9. The method of claim 1, wherein the location corresponds to a cluster of ordered locations of the mobile device.

10. The method of claim 1, further comprising:

modifying the location fingerprint of the selected point of interest based on the environmental measurement.

11. The method of claim 1, further comprising:

modifying a boundary of the selected point of interest based on the similarity between the environmental measurement and the location fingerprint of the selected point of interest and the contextual data of the selected point of interest.

12. The method of claim 1, wherein each locational fingerprint comprises measurement data regarding one or more wireless signals measured at a respective candidate point of interest.

13. The method of claim 12, wherein the measurement data comprises indications of one or more wireless access points previously detected at the respective candidate point of interest, and an indication of a signal strength associated with each wireless access point.

14. The method of claim 1, further comprising determining, at the mobile device, a device-specific label of the location based on a plurality of labeling criteria, the labeling criteria comprising the label transmitted by the computer system.

15. The method of claim 14, wherein the plurality of labeling criteria further comprises at least one of contact information associated with a user of the mobile device, a search history associated with the user, a location history associated with the user, geocoded information, a transaction history associated with the user, and messages transmitted to the user by one or more other users and/or received by the user from one or other users.

16. The method of claim 14, wherein determining the device-specific label of the location comprises assigning a respective weight to each criterion of the labeling criteria.

17. The method of claim 16, wherein determining the device-specific label of the location at the mobile device comprises:

determining one or more additional labels based on the plurality of labeling criteria, and

determining a score for the label transmitted by the computer system and each additional label based on the weights.

18. A non-transitory computer-readable medium including one or more sequences of instructions which, when executed by one or more processors, causes:

receiving, at a computer system, a query from a mobile device remote from the computer system, the query comprising an indication of a location of the mobile device, and an environmental measurement obtained by the mobile device at the location;

determining, at the computer system, a set of candidate points of interest in geographical proximity to the location;

obtaining, at the computer system for each of one or more candidate points of interest of the set, a location fingerprint of the candidate point of interest and contextual data regarding the candidate point of interest;

determining, at the computer system, a similarity between the environmental measurement and each location fingerprint;

selecting, at the computer system, a particular candidate point of interest from among the set, wherein the particular candidate point of interest is selected based on the similarity between the environmental measurement and each location fingerprint, and based on an assessment of the contextual data;

associating, at the computer system, a label of the selected point of interest with the location; and

transmitting, from the computer system to the mobile device, the label of the selected point of interest.

19. The non-transitory computer-readable medium of claim 18, wherein determining the set of candidate points of interest in geographical proximity to the location comprises determining one or more points of interest within a radius of the location.

20. The non-transitory computer-readable medium of claim 19, wherein the radius r is determined based on an accuracy or a reliability of the location provided by the mobile device.

21. The non-transitory computer-readable medium of claim 18, wherein the contextual data regarding the candidate point of interest comprises at least one of an hours of operation of the candidate point of interest, a days of operation of the candidate point of interest, a popularity of the candidate point of interest, or a favorability of the candidate point of interest.

22. The non-transitory computer-readable medium of claim 18, wherein selecting the particular candidate point of interest from among the set comprises:

determining, for each candidate point of interest of the set, a respective likelihood score, each likelihood score representing a likelihood that the location corresponds to the candidate point of interest.

23. The non-transitory computer-readable medium of claim 22, wherein determining, for each candidate point of interest, the respective likelihood score comprises:

calculating an initial likelihood score based on a similarity between the environmental measurement and the location fingerprint of the candidate point of interest; and

subsequent to calculating the initial likelihood score, modifying the initial likelihood score based on the contextual data of the candidate point of interest.

24. The non-transitory computer-readable medium of claim 23, wherein determining, for each candidate point of interest, the respective likelihood score further comprises:

determining a particular candidate point of interest of the set not associated with a location fingerprint;

calculating an initial likelihood score for that candidate point of interest based on an interpolation of one or more likelihood scores for one or more other candidate points of interest of the set.

25. The non-transitory computer-readable medium of claim 22, wherein executing the one or more sequences of instructions further causes:

identifying one or more additional candidate points of interest based on the likelihood scores, wherein identifying one or more additional candidate points of interest comprises;

determining an additional point of interest not associated with a location fingerprint and in geographical proximity to the location;

determining that the additional point of interest is within a threshold distance of a candidate point of interest of the set having a likelihood score greater than a threshold likelihood value; and

including the additional point of interest in the set.

26. The non-transitory computer-readable medium of claim 18, wherein the location corresponds to a cluster of ordered locations of the mobile device.

27. The non-transitory computer-readable medium of claim 18, wherein executing the one or more sequences of instructions further causes:

modifying the location fingerprint of the selected point of interest based on the environmental measurement.

28. The non-transitory computer-readable medium of claim 18, wherein executing the one or more sequences of instructions further causes:

modifying a boundary of the selected point of interest based on the similarity between the environmental measurement and the location fingerprint of the selected point of interest and the contextual data of the selected point of interest.

29. The non-transitory computer-readable medium of claim 18, wherein each locational fingerprint comprises measurement data regarding one or more wireless signals measured at a respective candidate point of interest.

30. The non-transitory computer-readable medium of claim 29, wherein the measurement data comprises indications of one or more wireless access points previously detected at the respective candidate point of interest, and an indication of a signal strength associated with each wireless access point.

31. The non-transitory computer-readable medium of claim 18, wherein executing the one or more sequences of instructions further causes:

determining, at the mobile device, a device-specific label of the location based on a plurality of labeling criteria, the labeling criteria comprising the label transmitted by the computer system.

32. The non-transitory computer-readable medium of claim 31, wherein the plurality of labeling criteria further comprises at least one of contact information associated with a user of the mobile device, a search history associated with the user, a location history associated with the user, geocoded information, a transaction history associated with the user, and messages transmitted to the user by one or more other users and/or received by the user from one or other users.

33. The non-transitory computer-readable medium of claim 31, wherein determining the device-specific label of the location comprises assigning a respective weight to each criterion of the labeling criteria.

34. The non-transitory computer-readable medium of claim 33, wherein determining the device-specific label of the location at the mobile device comprises:

determining one or more additional labels based on the plurality of labeling criteria, and

determining a score for the label transmitted by the computer system and each additional label based on the weights.

35. A system comprising:

one or more processors; and

a non-transitory computer-readable medium including one or more sequences of instructions which, when executed by the one or more processors, causes;

receiving, at a computer system, a query from a mobile device remote from the computer system, the query comprising an indication of a location of the mobile device, and an environmental measurement obtained by the mobile device at the location;

determining, at the computer system, a set of candidate points of interest in geographical proximity to the location;

obtaining, at the computer system for each of one or more candidate points of interest of the set, a location fingerprint of the candidate point of interest and contextual data regarding the candidate point of interest;

determining, at the computer system, a similarity between the environmental measurement and each location fingerprint;

selecting, at the computer system, a particular candidate point of interest from among the set, wherein the particular candidate point of interest is selected based on the similarity between the environmental measurement and each location fingerprint, and based on an assessment of the contextual data;

associating, at the computer system, a label of the selected point of interest with the location; and

transmitting, from the computer system to the mobile device, the label of the selected point of interest.

36. The system of claim 35, wherein determining the set of candidate points of interest in geographical proximity to the location comprises determining one or more points of interest within a radius r of the location.

37. The system of claim 36, wherein the radius r is determined based on an accuracy or a reliability of the location provided by the mobile device.

38. The system of claim 35, wherein the contextual data regarding the candidate point of interest comprises at least one of an hours of operation of the candidate point of interest, a days of operation of the candidate point of interest, a popularity of the candidate point of interest, or a favorability of the candidate point of interest.

39. The system of claim 35, wherein selecting the particular candidate point of interest from among the set comprises:

determining, for each candidate point of interest of the set, a respective likelihood score, each likelihood score representing a likelihood that the location corresponds to the candidate point of interest.

40. The system of claim 39, wherein determining, for each candidate point of interest, the respective likelihood score comprises:

calculating an initial likelihood score based on a similarity between the environmental measurement and the location fingerprint of the candidate point of interest; and

subsequent to calculating the initial likelihood score, modifying the initial likelihood score based on the contextual data of the candidate point of interest.

41. The system of claim 40, wherein determining, for each candidate point of interest, the respective likelihood score further comprises:

determining a particular candidate point of interest of the set not associated with a location fingerprint;

calculating an initial likelihood score for that candidate point of interest based on an interpolation of one or more likelihood scores for one or more other candidate points of interest of the set.

42. The system of claim 39, wherein executing the one or more sequences of instructions further causes:

identifying one or more additional candidate points of interest based on the likelihood scores, wherein identifying one or more additional candidate points of interest comprises;

determining an additional point of interest not associated with a location fingerprint and in geographical proximity to the location;

determining that the additional point of interest is within a threshold distance of a candidate point of interest of the set having a likelihood score greater than a threshold likelihood value; and

including the additional point of interest in the set.

43. The system of claim 35, wherein the location corresponds to a cluster of ordered locations of the mobile device.

44. The system of claim 35, wherein executing the one or more sequences of instructions further causes:

modifying the location fingerprint of the selected point of interest based on the environmental measurement.

45. The system of claim 35, wherein executing the one or more sequences of instructions further causes:

modifying a boundary of the selected point of interest based on the similarity between the environmental measurement and the location fingerprint of the selected point of interest and the contextual data of the selected point of interest.

46. The system of claim 35, wherein each locational fingerprint comprises measurement data regarding one or more wireless signals measured at a respective candidate point of interest.

47. The system of claim 46, wherein the measurement data comprises indications of one or more wireless access points previously detected at the respective candidate point of interest, and an indication of a signal strength associated with each wireless access point.

48. The system of claim 35, wherein executing the one or more sequences of instructions further causes:

determining, at the mobile device, a device-specific label of the location based on a plurality of labeling criteria, the labeling criteria comprising the label transmitted by the computer system.

49. The system of claim 48, wherein the plurality of labeling criteria further comprises at least one of contact information associated with a user of the mobile device, a search history associated with the user, a location history associated with the user, geocoded information, a transaction history associated with the user, and messages transmitted to the user by one or more other users and/or received by the user from one or other users.

50. The system of claim 48, wherein determining the device-specific label of the location comprises assigning a respective weight to each criterion of the labeling criteria.

51. The system of claim 50, wherein determining the device-specific label of the location at the mobile device comprises:

determining one or more additional labels based on the plurality of labeling criteria, and

determining a score for the label transmitted by the computer system and each additional label based on the weights.