Systems and methods to determine location of media items

Patent metadata

Field	Value
Publication number	US-10360255-B2
Application number	US-201514962575-A
Country	US
Kind code	B2
Filing date	Dec 8, 2015
Priority date	Dec 8, 2015
Publication date	Jul 23, 2019
Grant date	Jul 23, 2019

Abstract

Systems, methods, and non-transitory computer readable media are configured to generate a hash value of an evaluation content item. Hash values of a plurality of content items associated with location information are generated. A pairwise distance value between the hash value of the evaluation content item and a hash value of each content item of the plurality of content items assigned to a group of a plurality of groups is determined. A score for each group of the plurality of groups is generated based on a combination of distance values for the group. At least one location associated with the evaluation content item is determined based on scores for the plurality of groups.

First claim

What is claimed is:

1. A computer-implemented method comprising:
determining, by a computing system, a pairwise distance value between a hash value that has been generated for an evaluation content item and a hash value that has been generated for each content item of a plurality of content items associated with location information and assigned to a group of a plurality of groups, wherein the evaluation content item is associated with a position subject to a range of error;
generating, by the computing system, a score for each group of the plurality of groups based on a combination of distance values for the group; and
determining, by the computing system, at least one location associated with the evaluation content item based on scores for the plurality of groups.

2. The computer-implemented method of claim 1 , further comprising:
assigning each content item of the plurality of content items to a group of the plurality of groups based on the location information, wherein the plurality of groups are associated with a plurality of locations.

3. The computer-implemented method of claim 2 , wherein assignment of the content item to the group satisfies a threshold confidence level.

4. The computer-implemented method of claim 1 , further comprising:
determining an area based on application of a threshold radius value to the position associated with the evaluation content item; and
selecting the plurality of content items from a set of content items based on locations associated with the plurality of content items that fall within the area.

5. The computer-implemented method of claim 1 , further comprising:
applying a weight to each distance value.

6. The computer-implemented method of claim 5 , wherein the weight is based on an exponential decay function.

7. The computer-implemented method of claim 1 , further comprising:
sorting the scores for the plurality of groups;
selecting at least one group based on application of a threshold selection value to the sorted scores; and
providing to a user the at least one location as a candidate location for the evaluation content item, the at least one location associated with the selected at least one group.

8. The computer-implemented method of claim 1 , wherein the location information is at least one of a place, an address, a residence, an establishment, and other type of location.

9. The computer-implemented method of claim 1 , wherein the combination of distance values for the group is a summation of weighted distance values for the group.

10. A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
determining a pairwise distance value between a hash value that has been generated for an evaluation content item and a hash value that has been generated for each content item of a plurality of content items associated with location information and assigned to a group of a plurality of groups, wherein the evaluation content item is associated with a position subject to a range of error;
generating a score for each group of the plurality of groups based on a combination of distance values for the group; and
determining at least one location associated with the evaluation content item based on scores for the plurality of groups.

11. The system of claim 10 , further comprising:
assigning each content item of the plurality of content items to a group of the plurality of groups based on the location information, wherein the plurality of group groups are associated with a plurality of locations.

12. The system of claim 10 , further comprising:
determining an area based on application of a threshold radius value to the position associated with the evaluation content item; and
selecting the plurality of content items from a set of content items based on locations associated with the plurality of content items that fall within the area.

13. The system of claim 10 , further comprising:
applying a weight to each distance value.

14. The system of claim 10 , wherein the combination of distance values for the group is a summation of weighted distance values for the group.

15. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
determining a pairwise distance value between a hash value that has been generated for an evaluation content item and a hash value that has been generated for each content item of a plurality of content items associated with location information and assigned to a group of a plurality of groups, wherein the evaluation content item is associated with a position subject to a range of error;
generating a score for each group of the plurality of groups based on a combination of distance values for the group; and
determining at least one location associated with the evaluation content item based on scores for the plurality of groups.

16. The non-transitory computer-readable storage medium of claim 15 , further comprising:
assigning each content item of the plurality of content items to a group of the plurality of groups based on the location information, wherein the plurality of group groups are associated with a plurality of locations.

17. The non-transitory computer-readable storage medium of claim 15 , further comprising:
determining an area based on application of a threshold radius value to the position associated with the evaluation content item; and
selecting the plurality of content items from a set of content items based on locations associated with the plurality of content items that fall within the area.

18. The non-transitory computer-readable storage medium of claim 15 , further comprising:
applying a weight to each distance value.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the combination of distance values for the group is a summation of weighted distance values for the group.

Assignees

• Facebook Inc

Inventors

• Almas Hassan
• Bourdev Lubomir

Classifications

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06Q10/40

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

• G06F18/241

  relating to the classification model, e.g. parametric or non-parametric approaches · CPC title

• G06K9/00677

  Physics · mapped topic

• G06F16/487 Primary

  using geographical or spatial information, e.g. location · CPC title