Platform to provide supplemental media content based on content of a media stream and a user accessing the media stream

Patent metadata

Field	Value
Publication number	US-10893339-B2
Application number	US-201916286233-A
Country	US
Kind code	B2
Filing date	Feb 26, 2019
Priority date	Feb 26, 2019
Publication date	Jan 12, 2021
Grant date	Jan 12, 2021

Abstract

A device detects that a user device is accessing a media stream that enables the user device to display, via a user interface, media content associated with a subject. The device receives a search query associated with the user device and the media stream, and determines, based on the search query, that a user associated with the user device has a threshold level of interest in a feature of the subject. The device receives feature information associated with the feature based on determining that the user has the threshold level of interest, and receives feature content data that is associated with feature content that includes the feature information. The device causes the feature content to be embedded into the media stream to cause the user device to display the feature content in relation to the feature when the feature is displayed in the media content via the user interface.

First claim

What is claimed is:

1. A method, comprising:
detecting, by a device, that a user device is receiving a media stream associated with a vehicle,
wherein the user device is associated with a user account of a user;

receiving, by the device, activity data associated with the user account, and
wherein the activity data relates to online activity involving the vehicle;

determining, by the device, a characteristic of the user based on the activity data;
identifying, by the device, media content of the media stream,
wherein the media content includes media that is being provided, via a user interface of the user device, and that is associated with the vehicle;

performing, by the device and based on detecting that the user device is receiving the media stream, a search of a database that stores feature information for the vehicle,
the search being based on the characteristic of the user;

receiving, by the device and based on the search, at least one search result specifying a feature of the vehicle that corresponds to the characteristic of the user;
determining, by the device, that the feature is in the media content,
obtaining, by the device, feature content associated with the feature based on feature information associated with the feature,
wherein the feature information is stored in a data structure that includes information associated with the vehicle; and

determining, by the device and for the feature content, a location within a field of view of the media stream,
the field of view of the media stream providing a view of the feature; and

inserting, by the device, within the media stream, and while the feature is within the field of view of the media stream, the feature content at the location within the field of view of the media stream.

2. The method of claim 1 , further comprising:
determining, based on the characteristic of the user and based on a machine learning model, that the user has a threshold level of interest in the feature of the vehicle,
wherein the machine learning model has been trained based on at least one of:
historical data associated with past online activity of the user; or
historical data associated with past online activity of one or more other users.

3. The method of claim 1 , wherein determining that the feature is in the media content comprises:
performing an image processing technique on the media content using a feature recognition model,
wherein the feature recognition model comprises a machine learning model that has been trained based on at least one of:
historical data associated with recognizing the feature in other media content that is associated with the vehicle,
historical data associated with recognizing the feature in other media content that is associated with other vehicles, or
historical data associated with recognizing, in other media content that is associated with other vehicles, other features that are related to the feature.

4. The method of claim 1 , wherein the media stream comprises a multi-view image stream and determining that the feature is in the media content comprises:
obtaining, from the user device, a user input associated with displaying an image of the feature within the media content,
wherein the user input indicates a view of the vehicle,
wherein the view is one of a plurality of views of the vehicle that are capable of being selected from the multi-view image stream; and

determining, from the information associated with the vehicle and the view of the vehicle, that the media content includes the image of the feature.

5. The method of claim 1 , wherein obtaining the feature content comprises:
obtaining the feature information from the data structure;
determining a type of the feature; and
generating the feature content based on the type of the feature,
wherein the generated feature content is configured to be displayed within the media content in relation to the feature.

6. The method of claim 1 , further comprising:
requesting the user to authorize monitoring of the online activity;
receiving a user input that authorizes the monitoring of the online activity; and
receiving the activity data based on the user input.

7. The method of claim 1 , wherein inserting the feature content comprises:
embedding the feature content into the media content,
wherein the embedded feature content is configured to be displayed in a fixed position within the media content in relation to the feature when the user device displays, via the user interface, the feature within the media content.

8. A device, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, configured to:
detect that a user device is receiving a media stream associated with a vehicle,
wherein the user device is associated with a user account of a user;

receive activity data associated with the user account, and
wherein the activity data relates to online activity involving the vehicle;

determine a characteristic of the user based on the activity data;
identify media content of the media stream,
wherein the media content includes media that is being provided, via a user interface of the user device, and that is associated with the vehicle;

perform, based on detecting that the user device is receiving the media stream, a search of a database that stores feature information for the vehicle,
the search being based on the characteristic of the user;

receive, based on the search, at least one search result specifying a feature of the vehicle that corresponds to the characteristic of the user;
determine that the feature is in the media content;
obtain feature content associated with the feature based on feature information associated with the feature,
wherein the feature information is stored in a data structure that includes information associated with the vehicle; and

determine, for the feature content, a location within a field of view of the media stream,
the field of view of the media stream providing a view of the feature; and
insert, within the media stream and while the feature is within the field of view of the media stream, the feature content at the location within the field of view of the media stream.

9. The device of claim 8 , wherein the one or more processors are further configured to:
determine, based on the characteristic of the user and based on a machine learning model, that the user has a threshold level of interest in the feature of the vehicle,
wherein the machine learning model has been trained based on at least one of:
historical data associated with past online activity of the user; or
historical data associated with past online activity of one or more other users.

10. The device of claim 8 , wherein the one or more processors, when determining that the feature is in the media content, are configured to:
perform an image processing technique on the media content using a feature recognition model,
wherein the feature recognition model comprises a machine learning model that has been trained based on at least one of:
historical data associated with recognizing the feature in other media content that is associated with the vehicle,
historical data associated with recognizing the feature in other media content that is associated with other vehicles, or
historical data associated with recognizing, in other media content that is associated with other vehicles, other features that are related to the feature.

11. The device of claim 8 , wherein the media stream comprises a multi-view image stream and the one or more processors, when determining that the feature is in the media content, are c

Assignees

• Capital One Services Llc

Inventors

• Hoover Jason
• Tang Qiaochu
• Dagley Geoffrey
• Price Micah

Classifications

• H04N21/44222

  Analytics of user selections, e.g. selection of programmes or purchase activity (monitoring of user selections in data processing systems G06F11/34; arrangements for monitoring the user's behaviour or opinions in broadcast systems H04H60/33) · CPC title

• H04N21/4828

  for searching programme descriptors (retrieval of video data G06F16/739) · CPC title

• H04N21/25891

  being end-user preferences (retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18) · CPC title

• H04N21/41422

  located in transportation means, e.g. personal vehicle (arrangements specially adapted for transportation systems in broadcast systems H04H20/62) · CPC title

• H04N21/8133 Primary

  specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video programme · CPC title