Implicit geolocation of social networking users

Patent metadata

Field	Value
Publication number	US-9762689-B2
Application number	US-201514594895-A
Country	US
Kind code	B2
Filing date	Jan 12, 2015
Priority date	Aug 17, 2012
Publication date	Sep 12, 2017
Grant date	Sep 12, 2017

Abstract

In one embodiment, one or more computing systems receive a request for a location prediction for a user from a service. The computing systems access one or more real-time location signals and one or more aggregated location signals. The aggregated location signals may comprise one or more previous location signals. The computing systems may then generate one or more location predictions from the one or more real-time location signals and the one or more aggregated location signals, and calculate a single location prediction for the user from the one or more location predictions. The computing systems may then send, in response to the request, the single location prediction for the user to the requesting service.

First claim

What is claimed is:

1. A method comprising, by one or more computing systems:
receiving, from a service, a request for a location prediction for a user;
accessing one or more real-time location signals, received within a predetermined time span from a time that the request for the location prediction was received from the service, and one or more aggregated location signals, each comprising one or more previous location signals, received before the predetermined time span;
generating a plurality of current location predictions from the one or more real-time location signals and the one or more aggregated location signals;
calculating a single location prediction for the user from the plurality of current location predictions; and
sending, in response to the request, the single location prediction for the user to the requesting service.

2. The method of claim 1 , wherein the one or more real-time location signals comprise the user's last IP address.

3. The method of claim 1 , wherein the one or more real-time location signals comprise a self-declared user location.

4. The method of claim 1 , wherein the one or more real-time location signals comprise location signals received during a same session as the location prediction request from the service.

5. The method of claim 1 , wherein the one or more aggregated location signals comprise a fast-decay histogram and a slow decay histogram, and wherein the fast-decay histogram comprises received location signals of a first type, and the slow-decay histogram comprises received location signals of a second type.

6. The method of claim 1 , further comprising:
filtering the plurality of location predictions based on a set of rules, wherein the set of rules comprises filtering out location predictions that exceed a predetermined geographic radius from a location associated with the user's IP address.

7. The method of claim 1 , the calculating a single location prediction comprising calculating a weighted average for the plurality of location predictions, wherein a weight of each prediction is based at least in part on a source of signals from which the prediction was generated.

8. The method of claim 7 , wherein the source of the signals comprises real-time signals, a fast-decay histogram, and a slow-decay histogram, and wherein the weight for each source is determined via a machine learning algorithm.

9. One or more computer-readable non-transitory storage media in one or more computing systems, the media embodying logic that is operable when executed to:
receive, from a service, a request for a location prediction for a user;
access one or more real-time location signals, received within a predetermined time span from a time that the request for the location prediction was received from the service, and one or more aggregated location signals, each comprising one or more previous location signals received before the predetermined time span;
generate a plurality of current location predictions from the one or more real-time location signals and the one or more aggregated location signals;
calculate a single location prediction for the user from the plurality of current location predictions; and
send, in response to the request, the single location prediction for the user to the requesting service.

10. The media of claim 9 , wherein the one or more real-time location signals comprise the user's last IP address.

11. The media of claim 9 , wherein the one or more real-time location signals comprise a self-declared user location.

12. The media of claim 9 , wherein the one or more real-time location signals comprise location signals received during a same session as the location prediction request from the service.

13. The media of claim 9 , wherein the one or more aggregated location signals comprise a fast-decay histogram and a slow decay histogram, and wherein the fast-decay histogram comprises received location signals of a first type, and the slow-decay histogram comprises received location signals of a second type.

14. The media of claim 9 , the calculating a single location prediction comprising calculating a weighted average for the plurality of location predictions, wherein a weight of each prediction is based at least in part on a source of signals from which the prediction was generated.

15. The media of claim 9 , wherein the media further embodies logic that is operable to:
filter the plurality of location predictions based on a set of rules, wherein the set of rules comprises filtering out location predictions that exceed a predetermined geographic radius from a location associated with the user's IP address.

16. A system comprising:
one or more processors; and
a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:
receive, from a service, a request for a location prediction for a user;
access one or more real-time location signals, received within a predetermined time span from a time that the request for the location prediction was received from the service, and one or more aggregated location signals, each comprising one or more previous location signals received before the predetermined time span;
generate a plurality of current location predictions from the one or more real-time location signals and the one or more aggregated location signals;
calculate a single location prediction for the user from the plurality of current location predictions; and
send, in response to the request, the single location prediction for the user to the requesting service.

17. The system of claim 16 , wherein the one or more real-time location signals comprise the user's last IP address.

18. The system of claim 16 , wherein the one or more real-time location signals comprise a self-declared user location.

19. The system of claim 16 , wherein the one or more real-time location signals comprise location signals received during a same session as the location prediction request from the service.

20. The system of claim 16 , wherein the one or more aggregated location signals comprise a fast-decay histogram and a slow decay histogram, and wherein the fast-decay histogram comprises received location signals of a first type, and the slow-decay histogram comprises received location signals of a second type.

21. The system of claim 16 , wherein the processors are further operable when executing the instructions to:
filter the plurality of location predictions based on a set of rules, wherein the set of rules comprises filtering out location predictions that exceed a predetermined geographic radius from a location associated with the user's IP address.

22. The system of claim 16 , the calculating a single location prediction comprising calculating a weighted average for the plurality of location predictions, wherein a weight of each prediction is based at least in part on a source of signals from which the prediction was generated.

23. The system of claim 16 , wherein the source of the signals comprises real-time signals, a fast-decay histogram, and a slow-decay histogram, and wherein the weight for each source is determined via a machine learning algorithm.

Assignees

• Facebook Inc

Inventors

• Moreels Pierre
• Narasimhan Mukund

Classifications

• G06Q30/0261

  based on user location · CPC title

• G06Q10/0833

  Tracking · CPC title

• H04W4/029

  Location-based management or tracking services · CPC title

• G06Q10/40 Primary

  Business processes related to social networking or social networking services · CPC title

• G06Q50/01

  Physics · mapped topic