Patent US10482143

Recommending objects to a user of a social networking system based on the location of the user
[+] Show Details

US10482143

1. A method comprising: (4) (5)

obtaining, by a social networking system having one or more computing devices, location information identifying a location of a user of a social networking system;

identifying, by the social networking system, based on the location information, one or more levels of geographical partitions that are associated with the user, each level representing a geographical area encompassing the location of the user identified by the location information, each level of geographic partitions being within a hierarchy of levels of geographic partitions;

accessing, by the social networking system, for each level of geographical partitions associated with the user, relevant objects, each relevant object connected to a number of users of the social networking system, wherein the relevant object has location information identifying a location within the level of geographical partitions;

merging, by the social networking system, the relevant objects accessed at each of the levels of geographical partitions associated with the user, wherein the merging is based on a computed rank of each of the relevant objects, wherein the computed rank of each relevant object that is within a geographical partition is proportional to a number of edges stored in the social networking system that connect the relevant object with user profiles that are within the geographical partition, the user profiles stored in the social networking system, and wherein each of the levels of geographic partitions have location information identifying a location of the user within that level of geographical partitions; and

selecting, by the social networking system, one or more of the merged relevant objects for presentation to the user.

2. The method of claim 1, wherein obtaining location information identifying the location of a user comprises retrieving the location information from a user device used by the user. (0)

3. The method of claim 1, further comprising: (3) (2)

identifying a term frequency-inverse document frequency value associated with each of the accessed relevant objects, the term frequency-inverse document frequency value determined based on the number of users connected to each relevant object and a number of locations within the levels of geographical partitions including a user of the social networking system who is connected to the object; and

merging the relevant objects accessed at each level based on the term frequency-inverse document frequency associated with each relevant object.

4. The method of claim 3 further comprising: (0) (2)

5. The method of claim 3 further comprising: (1) (2)

7. The method of claim 3 further comprising: (0) (2)

8. The method of claim 1 further comprising: (0) (2)

9. The method of claim 1, wherein the computed rank of each relevant object is further based on an a probability of the user interacting with the relevant objects for each of the levels of geographic partitions, as computed by a machine learning algorithm, wherein the machine learning algorithm is trained using ranked relevant objects for users located in different locations, and wherein the machine learning algorithm determines the probability based on at least one of demographic information associated with the relevant object and the user, engagement information associated with the relevant object, and demographic information associated with one or more levels of geographic partitions associated with the relevant object. (0)

10. A non-transitory computer program product comprising a computer-readable storage medium containing computer program code for: (3) (5)

obtaining, by a social networking system having one or more computing devices, location information identifying a location of a user of a social networking system;

selecting, by the social networking system, one or more of the merged relevant objects for presentation to the user.

11. The computer program product of claim 10, wherein obtaining location information identifying the location of a user comprises retrieving the location information from a user device used by the user. (0)

12. The computer program product of claim 10, further comprising: (3) (2)

merging the relevant objects accessed at each level based on the term frequency-inverse document frequency associated with each relevant object.

13. The computer program product of claim 12, further comprising: (0) (2)

14. The computer program product of claim 12, further comprising: (1) (2)

16. The computer program product of claim 12, further comprising: (0) (2)

17. The computer program product of claim 10, further comprising: (0) (2)

18. A system comprising: (2) (7)

a processor;

a non-transitory computer readable storage medium, comprising instructions, that when executed by the processor, cause the processor to:

obtain, by a social networking system having one or more computing devices, location information identifying a location of a user of a social networking system;

identify, by the social networking system, based on the location information, one or more levels of geographical partitions that are associated with the user, each level representing a geographical area encompassing the location of the user identified by the location information, each level of geographical partitions being within a hierarchy of levels of geographical partitions;

access, by the social networking system, for each level of geographical partitions associated with the user, relevant objects, each relevant object connected to a number of users of the social networking system, wherein the relevant object has location information identifying a location within the level of geographical partitions;

merge, by the social networking system, the relevant objects accessed at each of the levels of geographical partitions associated with the user, wherein the merging is based on a computed rank of each of the relevant objects, wherein the computed rank of each relevant object that is within a geographical partition is proportional to a number of edges stored in the social networking system that connect the relevant object with user profiles that are within the geographical partition, the user profiles stored in the social networking system, and wherein each of the levels of geographic partitions have location information identifying a location of the user within that level of geographical partitions; and

select, by the social networking system, one or more of the merged relevant objects for presentation to the user.

19. The system of claim 18, the non-transitory computer readable storage medium comprising further instructions, that when executed by the processor, cause the processor to: (0) (3)

identify a term frequency-inverse document frequency value associated with each of the accessed relevant objects, the term frequency-inverse document frequency value determined based on the number of users connected to each relevant object and a number of locations within the levels of geographical partitions including a user of the social networking system who is connected to the object;

rank, for each level, the accessed relevant objects based on the term frequency-inverse document frequency value associated with each of the accessed relevant objects; and

merge the relevant objects based on the rank associated with each relevant object.

20. The system of claim 18, the non-transitory computer readable storage medium comprising further instructions, that when executed by the processor, cause the processor to: (0) (3)

rank, for each level, the accessed relevant objects based on a weight associated with a location within the level of geographical locations, the location having been identified from the location information of users connected to the relevant object, the weight associated with a location based on the term frequency-inverse document frequency value associated with the accessed relevant objects; and

merge the relevant objects based on the rank associated with each relevant object.

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Patent US10482143

Recommending objects to a user of a social networking system based on the location of the user

Patent Matrix® Search