Granted Patent B2

US 12,443,670 · App. 18/535,988 · Granted Oct 14, 2025

Inventors: Efrat Rotem (Haifa, IL); Ariel Krieger (Tel-Aviv, IL); Emmanuel Merali (Santa Monica, CA)

Assignee: Snap Inc.

G06F16/9536G06F16/285G06F16/951G06F16/9535G06F16/9538G06F16/958G06F40/20G06Q50/01H04L67/02

Abstract

Claims (61)

1. A method, comprising:

receiving, at an enhancement network node from a browser extension of a browser running on a client terminal, a request for content enhancement of a web document currently displayed at the client terminal via the browser after the client terminal accesses the web document from a search result of a search query, the request comprising the search query and the search result, one or more web documents appearing in the search result;

in response to the request:

analyzing one or more search keywords words in the search query and content of one or more web documents to extract a set of features, the one or more web documents appearing in the search result;

using a machine learning process to classify the set of features to generate a set of classified features;

selecting a set of candidate events by matching the set of classified features with one or more features of events described in an event dataset;

generating a ranked set of candidate events by ranking each candidate event, in the set of candidate events, based on relevancy of a set of event features of the candidate event to the search query and the one or more web documents appearing in the search result; and

identifying an individual event from the ranked set of candidate events;

identifying a group of user uploaded media content files, in a plurality of user uploaded media content files, by matching at least one feature of the individual event with at least one event indicating tag associated with an uploaded media content file in the plurality of user uploaded media content files;

forwarding, from the enhancement network node to the browser extension of the browser running on the client terminal, at least one media content file of the group of user uploaded media content files, the browser extension being configured to cause a simultaneous presentation of the at least one media content file on the browser with the web document, the simultaneous presentation of the at least one media content file being separate from presentation of the web document by the browser;

iteratively updating a dataset documenting the plurality of user uploaded media content files with one or more new user uploaded media content files;

updating the group of user uploaded media content files by repeating the identifying of the group of user uploaded media content files with the one or more new user uploaded media content files; and

forwarding at least one media content file of the updated group to cause the at least one media content file of the updated group to be included in the simultaneous presentation.

2. The method of claim 1 , wherein the at least one event indicating tag comprises a tag representing at least one of a capturing location or a capturing time, and wherein the at least one feature of the individual event comprises at least one of an event time value or an area defining value.

3. The method of claim 1 , wherein the plurality of user uploaded media content files comprises a plurality of video files and a plurality of image files both captured by a plurality of different users and uploaded from a plurality of different client terminals.

4. The method of claim 1 , wherein the event dataset is created by an analysis of content from a plurality of web documents.

5. The method of claim 1 , wherein the event dataset is created based on an analysis of information about location and time of at least one of the plurality of user uploaded media content files.

6. The method of claim 1 , wherein the individual event is defined by a first value setting plurality of different locations and a second value defining a common timing.

7. The method of claim 1 , wherein the event dataset is created based on an analysis of a plurality of search queries submitted by a plurality of users.

8. The method of claim 1 , wherein the one or more web documents are webpages.

9. The method of claim 1 , further comprising iteratively updating the event dataset with up-to-date multi participant events.

10. A non-transitory computer readable medium comprising computer executable instructions adapted to perform operations comprising:

receiving, at an enhancement network node from a browser extension of a browser running on a client terminal, a request for content enhancement of a web document currently displayed at the client terminal via the browser after the client terminal accesses the web document from a search result of a search query, the request comprising the search query and the search result, one or more web documents appearing in the search result;

in response to the request:

analyzing one or more search keywords in the search query and content of one or more web documents to extract a set of features, the one or more web documents appearing in the search result;

using a machine learning process to classify the set of features to generate a set of classified features;

selecting a set of candidate events by matching the set of classified features with one or more features of events described in an event dataset, the event dataset is created based on an analysis of a plurality of search queries submitted by a plurality of users;

generating a ranked set of candidate events by ranking each candidate event, in the set of candidate events, based on relevancy of a set of event features of the candidate event to the search query and the one or more web documents appearing in the search result; and

identifying an individual event from the ranked set of candidate events;

identifying a group of user uploaded media content files, in a plurality of user uploaded media content files, by matching at least one feature of the individual event with at least one event indicating tag associated with an uploaded media content file in the plurality of user uploaded media content files;

forwarding, from the enhancement network node to the browser extension of the browser running on the client terminal, at least one media content file of the group of user uploaded media content files, the browser extension being configured to cause a simultaneous presentation of the at least one media content file on the browser with the web document, the simultaneous presentation of the at least one media content file being separate from presentation of the web document by the browser;

iteratively updating a dataset documenting the plurality of user uploaded media content files with one or more new user uploaded media content files;

updating the group of user uploaded media content files by repeating the identifying of the group of user uploaded media content files with the one or more new user uploaded media content files; and

forwarding at least one media content file of the updated group to cause the at least one media content file of the updated group to be included in the simultaneous presentation.

11. The non-transitory computer readable medium of claim 10 , wherein the at least one event indicating tag comprises a tag representing at least one of a capturing location or a capturing time, and wherein the at least one feature of the individual event comprises at least one of an event time value or an area defining value.

12. The non-transitory computer readable medium of claim 10 , wherein the plurality of user uploaded media content files comprises a plurality of video files and a plurality of image files both captured by a plurality of different users and uploaded from a plurality of different client terminals.

13. The non-transitory computer readable medium of claim 10 , wherein the event dataset is created by an analysis of content from a plurality of web documents.

14. The non-transitory computer readable medium of claim 10 , wherein the event dataset is created based on an analysis of information about location and time of at least one of the plurality of user uploaded media content files.

15. The non-transitory computer readable medium of claim 10 , wherein the individual event is defined by a first value setting plurality of different locations and a second value defining a common timing.

16. The non-transitory computer readable medium of claim 10 , wherein the event dataset is created based on an analysis of a plurality of search queries submitted by a plurality of users.

17. The non-transitory computer readable medium of claim 10 , wherein the one or more web documents are webpages.

18. The non-transitory computer readable medium of claim 10 , further comprising iteratively updating the event dataset with up-to-date multi participant events.

19. An enhancement network node, comprising:

a database that hosts an event dataset documenting a plurality of multi participant events, each of the plurality of multi participant events being held in a geographical venue that hosts a plurality of participants;

at least one processor;

a web document analyzer that uses the at least one processor to:

access a search query and a search result of the search query, the search query and the search result being received from a browser extension of a browser running on a client terminal;

analyze one or more search keywords in the search query and content of one or more web documents to extract a set of features, the one or more web documents appearing in the search result; and

using a machine learning process to classify the set of features to generate a set of classified features;

a selection module that uses the at least one processor to:

select a set of candidate events by matching the set of classified features with one or more features of events described in an event dataset;

generate a ranked set of candidate events by ranking each candidate event, in the set of candidate events, based on relevancy of a set of event features of the candidate event to the search query and the one or more web documents appearing in the search result;

identify an individual event from the ranked set of candidate events; and

identify a group of user uploaded media content files, in a plurality of user uploaded media content files, by matching at least one feature of the individual event with at least one event indicating tag associated with an uploaded media content file in the plurality of user uploaded media content files; and

a client interface module that uses the at least one processor to:

receive a request for content enhancement of a web document currently displayed at the client terminal via the browser after the client terminal accesses the web document from the search result of the search query, the request comprising the search query and the search result;

forward to the browser extension of the browser running on the client terminal, in response to the request, at least one media content file of the group of user uploaded media content files, the browser extension being configured to cause a simultaneous presentation of the at least one media content file on the browser with the web document, the simultaneous presentation of the at least one media content file being separate from presentation of the web document by the browser;

iteratively update a dataset documenting the plurality of user uploaded media content files with one or more new user uploaded media content files;

update the group of user uploaded media content files by repeating the identifying of the group of user uploaded media content files with the one or more new user uploaded media content files; and

forward at least one media content file of the updated group to cause the at least one media content file of the updated group to be included in the simultaneous presentation.

20. The enhancement network node of claim 19 , wherein the at least one event indicating tag comprises a tag representing at least one of a capturing location or a capturing time, and wherein the at least one feature of the individual event comprises at least one of an event time value or an area defining value.

Assignments (2)

Continuity (5)

References Cited (400)