IP Library Granted Patent US 10,235,428
Granted Patent B2
US 10,235,428 · App. 15/195,105 · Granted Mar 19, 2019

Discovery of news-related content

Inventors: Balakrishnan Varadarajan (Mountain View, CA); Sudheendra Vijayanarasimhan (Mountain View, CA); Sanketh Shetty (Sunnyvale, CA); Nisarg Dilipkumar Kothari (Sunnyvale, CA); Nicholas Delmonico Rizzolo (Cupertino, CA)
Assignee: Google LLC
G06F17/30551G06F17/30029G06F17/30554G06F17/30867G10L25/54H04L51/32H04L67/306
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 10,235,428
App. No.
15/195,105
Granted
Mar 19, 2019
Kind
B2
Abstract

Techniques identify time-sensitive content and present the time-sensitive content to communication devices of users interested or potentially interested in the time-sensitive content. A content management component analyzes video or audio content, and extracts information from the content and determines whether the content is time-sensitive content, such as recent news-related content, based on analysis of the content and extracted information. The content management component evaluates user-related information and the extracted information, and determines whether a user(s) is likely to be interested in the time-sensitive content based on the evaluation results. The content management component sends a notification to the communication device(s) of the user(s) in response to determining the user(s) is likely to be interested in the time-sensitive content.

Claims (50)

1. A method, using a hardware processor, for presenting content, the method comprising:

retrieving a model that represents newsworthy content as a vector of binary values, wherein the newsworthy content includes time-sensitive news-related content and wherein each bit of the vector corresponds to an entity, a word, a phase, a search query, or a tag;

receiving a media content item;

in response to receiving the media content item, extracting a plurality of visual objects that are depicted in image portions of the media content item;

determining whether one or more visual objects of the plurality of visual objects match one or more visual objects in a database of stored visual objects associated with previously identified physical entities depicted in other media content items;

in response to determining that an extracted visual object matches a visual object in the database of stored visual objects, determining, based at least on the obtained model, whether the media content item contains newsworthy content by at least performing a search using a search query that includes one or more search terms corresponding to the extracted visual object and analyzing search results responsive to the search query;

in response to determining that the media content item contains the newsworthy content, calculating an interest score based on user-related information contained in a user profile of a user for consuming the newsworthy content;

determining whether the user is likely to have at least a defined interest level in the newsworthy content based on the calculated interest score; and

in response to determining that the user is likely to have at least the defined interest level in the newsworthy content, transmitting a notification to a communication device associated with the user, wherein the notification directs the communication device to the newsworthy content.

2. The method of claim 1 , wherein the one or more visual objects in the database of stored visual objects are associated with entity information, and wherein the media content item is determined to contain newsworthy content based on respective entity information associated with a matching visual object in the database of stored visual objects.

3. The method of claim 1 , further comprising using audio recognition to identify audio information presented in an audio portion of the media content item, wherein the media content item is determined to contain newsworthy content based on the audio information.

4. The method of claim 1 , further comprising analyzing textual information associated with the media content item, wherein the media content item is determined to contain newsworthy content based on the textual information.

5. The method of claim 4 , wherein the textual information includes closed-caption textual information.

6. The method of claim 4 , wherein the textual information includes user comments relating to the media content item provided by other users.

7. The method of claim 1 , further comprising:

applying the model to at least a portion of the media content item to determine whether the media content item contains newsworthy content.

8. A system for presenting content, comprising:

a memory that stores computer-executable instructions; and

a hardware processor that, when executing the computer-executable instructions stored in the memory, is configured to:

retrieve a model that represents newsworthy content as a vector of binary values, wherein the newsworthy content includes time-sensitive news-related content and wherein each bit of the vector corresponds to an entity, a word, a phase, a search query, or a tag;

receive a media content item;

in response to receiving the media content item, extract a plurality of visual objects that are depicted in image portions of the media content item;

determine whether one or more visual objects of the plurality of visual objects match one or more visual objects in a database of stored visual objects associated with previously identified physical entities depicted in other media content items;

in response to determining that an extracted visual object matches a visual object in the database of stored visual objects, determining, based at least on the obtained model, whether the media content item contains newsworthy content by at least performing a search using a search query that includes one or more search terms corresponding to the extracted visual object and analyzing search results responsive to the search query;

in response to determining that the media content item contains the newsworthy content, calculate an interest score based on user-related information contained in a user profile of a user for consuming the newsworthy content;

determine whether the user is likely to have at least a defined interest level in the newsworthy content based on the calculated interest score; and

in response to determining that the user is likely to have at least the defined interest level in the newsworthy content, transmit a notification to a communication device associated with the user, wherein the notification directs the communication device to the newsworthy content.

9. The system of claim 8 , wherein the one or more visual objects in the database of stored visual objects are associated with entity information, and wherein the media content item is determined to contain newsworthy content based on respective entity information associated with a matching visual object in the database of stored visual objects.

10. The system of claim 8 , wherein the hardware processor is further configured to use audio recognition to identify audio information presented in an audio portion of the media content item, wherein the media content item is determined to contain newsworthy content based on the audio information.

11. The system of claim 8 , wherein the hardware processor is further configured to analyze textual information associated with the media content item, wherein the media content item is determined to contain newsworthy content based on the textual information.

12. The system of claim 11 , wherein the textual information includes closed-caption textual information.

13. The system of claim 11 , wherein the textual information includes user comments relating to the media content item provided by other users.

14. The system of claim 8 , wherein the hardware processor is further configured to:

apply the model to at least a portion of the media content item to determine whether the media content item contains newsworthy content.

15. A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for presenting content, the method comprising:

retrieving a model that represents newsworthy content as a vector of binary values, wherein the newsworthy content includes time-sensitive news-related content and wherein each bit of the vector corresponds to an entity, a word, a phase, a search query, or a tag;

receiving a media content item;

in response to receiving the media content item, extracting a plurality of visual objects that are depicted in image portions of the media content item;

determining whether one or more visual objects of the plurality of visual objects match one or more visual objects in a database of stored visual objects associated with previously identified physical entities depicted in other media content items;

in response to determining that an extracted visual object matches a visual object in the database of stored visual objects, determining, based at least on the obtained model, whether the media content item contains newsworthy content by at least performing a search using a search query that includes one or more search terms corresponding to the extracted visual object and analyzing search results responsive to the search query;

in response to determining that the media content item contains the newsworthy content, calculating an interest score based on user-related information contained in a user profile of a user for consuming the newsworthy content;

determining whether the user is likely to have at least a defined interest level in the newsworthy content based on the calculated interest score; and

in response to determining that the user is likely to have at least the defined interest level in the newsworthy content, transmitting a notification to a communication device associated with the user, wherein the notification directs the communication device to the newsworthy content.

16. The non-transitory computer-readable medium of claim 15 , wherein the one or more visual objects in the database of stored visual objects are associated with entity information, and wherein the media content item is determined to contain newsworthy content based on respective entity information associated with a matching visual object in the database of stored visual objects.

17. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises using audio recognition to identify audio information presented in an audio portion of the media content item, wherein the media content item is determined to contain newsworthy content based on the audio information.

18. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises analyzing textual information associated with the media content item, wherein the media content item is determined to contain newsworthy content based on the textual information.

19. The non-transitory computer-readable medium of claim 18 , wherein the textual information includes closed-caption textual information.

20. The non-transitory computer-readable medium of claim 18 , wherein the textual information includes user comments relating to the media content item provided by other users.

21. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises:

applying the model to at least a portion of the media content item to determine whether the media content item contains newsworthy content.

Assignments (1)
CHANGE OF NAME Recorded Dec 5, 2017
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 044695/0115 →
Continuity (2)
Continuation 13827573 · Mar 14, 2013
Related Publication 20160306804A1 · Oct 20, 2016
Cited By (1)
US 12,501,263