IP Library › Granted Patent US 11,860,888
Granted Patent B2
US 11,860,888 · App. 17/131,444 · Granted Jan 2, 2024

Event detection system

Inventors: Yupeng Gu (Los Angeles, CA); Xiaolin Shi (Santa Monica, CA); Jie Luo (Marina Del Rey, CA)
Assignee: Snap Inc.
G06F16/26G06F16/24578G06F16/29G06F16/438G06F16/45G06F16/487G06F16/489G06T11/206
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,860,888
App. No.
17/131,444
Granted
Jan 2, 2024
Kind
B2
Abstract

An event detection system is configured to access a repository that contains a collection of media content. The media content may for example include images, videos, audio clips, and the like, wherein the media content comprises features that include: tags (e.g., hashtags or other similar mechanisms to label and sort content); captions that comprises one or more words or phrases; continuous numerical values; geolocation data (e.g., geo-hash, check-in data, coordinates); as well as temporal data (e.g., timestamps).

Claims (65)

1. A system comprising:

a memory; and

at least one hardware processor coupled to the memory and comprising instructions that causes the system to perform operations comprising:

accessing a collection of media content that comprises metadata, the collection of content associated with a temporal criteria and a location criteria;

grouping a subset of the collection of media content based on the metadata and a clustering parameter that comprises one or more threshold values, the subset of the collection of media content comprising content feature data, the content feature data including a plurality of hashtags;

determining a total number of occurrences of a hashtag from among the plurality of hashtags, the total number of occurrences of the hashtag representing a most common hashtag among the collection of media content;

selecting the hashtag from among the plurality of hashtags based on the total number of occurrences of the hashtag representing the most common hashtag among the collection of media content;

extracting the hashtag from the content feature data of the subset of the collection of media content;

plotting a representation of the subset of the collection of media content upon a graph based on the metadata, the representation of the subset of the plurality of media content comprising a cluster of data points;

designating the hashtag to the cluster of data points; and

generating a data-table that comprises a display of the metadata and the hashtag associated with the cluster of data points.

2. The system of claim 1 , wherein the metadata includes geolocation data and temporal data.

3. The system of claim 2 , wherein the grouping the subset of the collection of media content is based on one or more of the geolocation data and the temporal data.

4. The system of claim 2 , wherein subset of the collection of media content includes a first media content, the graph comprises a first axis that represents location values, a second axis that represents temporal values, and a third axis that represents feature values, and the plotting the representation of the first media content upon the graph based on the metadata includes:

designating the content feature of the first media content to a position along the third axis; and

plotting a representation of the first media content upon the graph based on the metadata of the first media content and the position of the content feature along the third axis.

5. The system of claim 2 , wherein the grouping the subset of collection of media content based on the metadata includes:

receiving a grouping parameter that comprises a temporal threshold and a geological threshold; and

grouping the subset of the collection of media content based on the grouping parameter.

6. The system of claim 1 , wherein the subset of the collection of media content includes a first media content, the representation of the first media content is a first representation, and the operations further comprise:

plotting a second representation of a second media content upon the graph based on the metadata of the second media content;

determining that the second representation of the second media content and the first representation of the first media content are within a threshold distance on the graph; and

detecting a similarity between the first media content and the second media content based on the determining that the second representation of the second media content and the first representation of the first media content are within the threshold distance on the graph.

7. A method comprising:

accessing a collection of media content that comprises metadata, the collection of content associated with a temporal criteria and a location criteria;

grouping a subset of the collection of media content based on the metadata and a clustering parameter that comprises one or more threshold values, the subset of the collection of media content comprising content feature data, the content feature data including a plurality of hashtags;

determining a total number of occurrences of a hashtag from among the plurality of hashtags, the total number of occurrences of the hashtag representing a most common hashtag among the collection of media content;

selecting the hashtag from among the plurality of hashtags based on the total number of occurrences of the hashtag representing the most common hashtag among the collection of media content;

extracting the hashtag from the content feature data of the subset of the collection of media content;

plotting a representation of the subset of the collection of media content upon a graph based on the metadata, the representation of the subset of the plurality of media content comprising a cluster of data points;

designating the hashtag to the cluster of data points; and

generating a data-table that comprises a display of the metadata and the hashtag associated with the cluster of data points.

8. The method of claim 7 , wherein the metadata includes geolocation data and temporal data.

9. The method of claim 8 , wherein the grouping the subset of the collection of media content is based on one or more of the geolocation data and the temporal data.

10. The method of claim 8 , wherein subset of the collection of media content includes a first media content, the graph comprises a first axis that represents location values, a second axis that represents temporal values, and a third axis that represents feature values, and the plotting the representation of the first media content upon the graph based on the metadata includes:

designating the content feature of the first media content to a position along the third axis; and

plotting a representation of the first media content upon the graph based on the metadata of the first media content and the position of the content feature along the third axis.

11. The method of claim 8 , wherein the grouping the subset of collection of media content based on the metadata includes:

receiving a grouping parameter that comprises a temporal threshold and a geological threshold; and

grouping the subset of the collection of media content based on the grouping parameter.

12. The method of claim 7 , wherein the subset of the collection of media content includes a first media content, the representation of the first media content is a first representation, and the method further comprises:

plotting a second representation of a second media content upon the graph based on the metadata of the second media content;

determining that the second representation of the second media content and the first representation of the first media content are within a threshold distance on the graph; and

detecting a similarity between the first media content and the second media content based on the determining that the second representation of the second media content and the first representation of the first media content are within the threshold distance on the graph.

13. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

accessing a collection of media content that comprises metadata, the collection of content associated with a temporal criteria and a location criteria;

grouping a subset of the collection of media content based on the metadata and a clustering parameter that comprises one or more threshold values, the subset of the collection of media content comprising content feature data, the content feature data including a plurality of hashtags;

determining a total number of occurrences of a hashtag from among the plurality of hashtags, the total number of occurrences of the hashtag representing a most common hashtag among the collection of media content;

selecting the hashtag from among the plurality of hashtags based on the total number of occurrences of the hashtag representing the most common hashtag among the collection of media content;

extracting the hashtag from the content feature data of the subset of the collection of media content;

plotting a representation of the subset of the collection of media content upon a graph based on the metadata, the representation of the subset of the plurality of media content comprising a cluster of data points;

designating the hashtag to the cluster of data points; and

generating a data-table that comprises a display of the metadata and the hashtag associated with the cluster of data points.

14. The non-transitory machine-readable storage medium of claim 13 , wherein the metadata includes geolocation data and temporal data.

15. The non-transitory machine-readable storage medium of claim 14 , wherein the grouping the subset of the collection of media content is based on one or more of the geolocation data and the temporal data.

16. The non-transitory machine-readable storage medium of claim 14 , wherein subset of the collection of media content includes a first media content, the graph comprises a first axis that represents location values, a second axis that represents temporal values, and a third axis that represents feature values, and the plotting the representation of the first media content upon the graph based on the metadata includes:

designating the content feature of the first media content to a position along the third axis; and

plotting a representation of the first media content upon the graph based on the metadata of the first media content and the position of the content feature along the third axis.

17. The non-transitory machine-readable storage medium of claim 14 , wherein the grouping the subset of collection of media content based on the metadata includes:

receiving a grouping parameter that comprises a temporal threshold and a geological threshold; and

grouping the subset of the collection of media content based on the grouping parameter.

18. The non-transitory machine-readable storage medium of claim 13 , wherein the subset of the collection of media content includes a first media content, the representation of the first media content is a first representation, and the operations further comprise:

plotting a second representation of a second media content upon the graph based on the metadata of the second media content;

determining that the second representation of the second media content and the first representation of the first media content are within a threshold distance on the graph; and

detecting a similarity between the first media content and the second media content based on the determining that the second representation of the second media content and the first representation of the first media content are within the threshold distance on the graph.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 3, 2023
From: GU, YUPENG; SHI, XIAOLIN; LUO, JIE
To: SNAP INC.
Reel/Frame 065102/0987 →
Continuity (3)
Continuation 16057565 · Aug 7, 2018
Provisional Application 62674997 · May 22, 2018
Related Publication 20210117439A1 · Apr 22, 2021