Location-based place determination using online social networks
View Patent ↗In one embodiment, a method includes sending information associated with multiple candidate place-entities to a user, receiving a selection of one candidate place-entity by the user, and updating the rating of the selected candidate place-entity on an online social network. In particular, the sending is based on calculated probabilities the candidate place-entities are associated with a particular geographic location.
1. A method comprising, by one or more computing devices:
sending, to a mobile-client system of a first user, information associated with a plurality of candidate place-entities based on calculated probabilities the candidate place-entities are associated with a particular geographic location, wherein the information associated with each place-entity comprises a rating of the candidate place-entity;
receiving, from the mobile-client system, a selection by the first user of one of the plurality of candidate place-entities; and
updating, by the one or more computing devices, the rating of the selected candidate place-entity on an online social network responsive to the selection by the first user of the selected candidate place-entity.
2. The method of claim 1 , wherein the particular geographic location is associated with a latitude-longitude pair determined based on one or more signals received by the mobile-client system.
3. The method of claim 2 , wherein the one or more signals comprise one or more of a Global Positioning System (GPS) signal, a Wi-Fi signal, a BLUETOOTH signal, a cellular signal, or a near field communication (NFC) signal.
4. The method of claim 3 , wherein each of the one or more signals is associated with one or more of:
a signal strength; or
an identifier of a device that sent the signal.
5. The method of claim 1 , further comprising:
accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each of the edges between two of the nodes representing a single degree of separation between them, wherein the first user corresponds to a first node in the social graph and the plurality of candidate place-entities correspond to a plurality of second nodes in the social graph, respectively.
6. The method of claim 1 , wherein each of the calculated probabilities further represents a probability that the mobile-client system is located at a corresponding candidate place-entity.
7. The method of claim 1 , wherein each of the calculated probabilities is further based on social-graph information associated with the corresponding candidate place-entity of the online social network, the candidate place-entity being within a threshold degree of separation from the first user.
8. The method of claim 1 , wherein each of the calculated probabilities is further based on a location-probability distribution associated with the candidate place-entity.
9. The method of claim 8 , wherein:
the location-probability distribution associated with the candidate place-entity comprises a point, the point corresponding to a geographic location of the candidate place-entity; and
the calculated probability is further based on a distance between the point and the particular geographic location.
10. The method of claim 8 , wherein:
the location-probability distribution associated with the candidate place-entity comprises a power-law distribution centered at a point, the point corresponding to a geographic location of the candidate place-entity; and
the calculated probability is further based on a value of the power-law distribution at the particular geographic location.
11. The method of claim 8 , wherein:
the location-probability distribution associated with the candidate place-entity comprises a kernel density estimate corresponding to a probability density associated with the candidate place-entity; and
the calculated probability is further based on a value of the kernel density estimate at the particular geographic location.
12. The method of claim 8 , wherein:
the location-probability distribution associated with the candidate place-entity comprises a polygon representing a shape of the candidate place-entity; and
the calculated probability is further based on the particular geographic location with respect to the polygon.
13. The method of claim 8 , further comprising:
recalculating, based on the received selection, the location-probability distribution associated with one or more of the plurality of candidate place-entities sent to the mobile-client system.
14. The method of claim 1 , further comprising:
receiving a plurality of new information associated with a new place-entity, the new information sent by a respective plurality of other mobile-client systems associated with a respective plurality of other users of the online social network;
generating, in a social graph, a new social-graph node corresponding to the new place-entity, the social graph comprising a plurality of nodes and a plurality of edges connecting the nodes; and
creating an edge between the new social-graph node and each node associated with each of the plurality of other users.
15. The method of claim 1 , wherein the information sent to the mobile-client system comprises an advertisement associated with one of the candidate place-entities based on its respective calculated probability.
16. The method of claim 1 , wherein the information sent to the mobile-client system comprises a suggestion to the first user to perform an action associated with one of the one or more candidate place-entities.
17. The method of claim 16 , wherein the action comprises one or more of:
a check-in to the candidate place-entity; or
a request for additional information of the candidate place-entity.
18. The method of claim 1 , wherein each candidate place-entity represents a particular physical place associated with a particular feature.
19. The method of claim 18 , wherein the particular feature comprises one or more of:
an attribute associated with the candidate place-entity;
a type associated with the candidate place-entity;
a descriptor associated with the candidate place-entity; or
a characteristic associated with the candidate place-entity.
20. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
send, to a mobile-client system of a first user, information associated with a plurality of candidate place-entities based on calculated probabilities the candidate place-entities are associated with a particular geographic location, wherein the information associated with each place-entity comprises a rating of the candidate place-entity;
receive, from the mobile-client system, a selection by the first user of one of the plurality of candidate place-entities; and
update, by the one or more computing devices, the rating of the selected candidate place-entity on an online social network responsive to the selection by the first user of the selected candidate place-entity.
21. A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
send, to a mobile-client system of a first user, information associated with a plurality of candidate place-entities based on calculated probabilities the candidate place-entities are associated with a particular geographic location, wherein the information associated with each place-entity comprises a rating of the candidate place-entity;
receive, from the mobile-client system, a selection by the first user of one of the plurality of candidate place-entities; and
update, by the one or more computing devices, the rating of the selected candidate place-entity on an online social network responsive to the selection by the first user of the selected candidate place-entity.