IP Library Granted Patent US 11,741,148
Granted Patent B2
US 11,741,148 · App. 17/458,994 · Granted Aug 29, 2023

Methods and systems for personalized screen content optimization

Inventor: Kyle Miller (Durham, NC)
Assignee: Rovi Guides, Inc.
G06F16/435G06F16/24578G06F16/41G06F16/438
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 11,741,148
App. No.
17/458,994
Granted
Aug 29, 2023
Kind
B2
Abstract

Systems and associated methods are described for providing content recommendations. The system selects, using a multi-armed bandit solution model, a first plurality of content categories based on a reward score of each content category. The categories are displayed. When a user selects an item from the displayed categories, the system finds all categories that include the selected item, but rewards only the category with the highest score. The system selects, using the multi-armed bandit solution model, the second plurality of content categories based on the updated reward score of each content category. The categories are then displayed. The system may also repeat the steps to refine the multi-armed bandit solution model.

Claims (44)

1. A method comprising:

selecting, based on demographical data of a user, a first plurality of content items from a first plurality of content categories for recommendation on a device, wherein each content category of the first plurality of content categories has an associated reward score;

receiving from the device a request to access a content item from the first plurality of content items;

identifying multiple content categories of the first plurality of content categories that include the requested content item;

only increasing reward score of the content category of the multiple identified content categories that has the highest reward score, wherein reward scores of other content categories of the multiple identified content categories are not increased;

selecting, based on a multi-armed bandit solution model, a second plurality of content categories based on the reward score of each content category;

selecting, based on demographical data of the user, a second plurality of content items from the second plurality of content categories; and

causing the user device to generate for display, identifiers of the second plurality of content items.

2. The method of claim 1 , wherein, only increasing reward score of the content category of the multiple identified content categories further comprises:

selecting an identifier of a category;

identifying a plurality of categories that include the identifier;

determining a score of each identified category, from the plurality of categories, that include the identifier, to identify a category having the highest score; and

only increasing the reward score of the category with the highest score.

3. The method of claim 1 , wherein the demographical data of a user is the age of the user.

4. The method of claim 1 , wherein the multiple content categories are identified from genres consisting of kids, educational, mystery, news, comedy, documentary, game show, sci-fi, fantasy, sports, action popularity, sitcom, movie, community, and drama.

5. The method of claim 1 , further comprising, calculating the increase of the reward score of the content category of the multiple identified content categories based on a recall value.

6. The method of claim 5 , wherein the recall value is computed to be proportional to a number of requests for a content item.

7. The method of claim 5 , wherein the recall value is computed to be inversely proportional to a number of times an identifier of that content item was generated for display in a carousel.

8. The method of claim 1 , wherein the request to access a content item is specific to a single user.

9. The method of claim 1 , further comprising, tracking reward scores to provide a confidence level.

10. The method of claim 1 , further comprising generating a graphical user interface to display the content categories as carousels on a display screen.

11. A system comprising:

communications circuitry configured to access a database containing content items; and

control circuitry configured to:

select, based on demographical data of a user, a first plurality of content items, from the database, from a first plurality of content categories for recommendation on a device, wherein each content category of the first plurality of content categories has an associated reward score;

receive from the device a request to access a content item from the first plurality of content items;

identify multiple content categories of the first plurality of content categories that include the requested content item;

only increase reward score of the content category of the multiple identified content categories that has the highest reward score, wherein reward scores of other content categories of the multiple identified content categories are not increased;

select, based on a multi-armed bandit solution model, a second plurality of content categories based on the reward score of each content category;

select, based on demographical data of the user, a second plurality of content items from the second plurality of content categories; and

cause, using the communications circuitry, to generate for display on the device, identifiers of the second plurality of content items.

12. The system of claim 11 , wherein, only increasing reward score of the content category of the multiple identified content categories further comprises, the control circuitry configured to:

select an identifier of a category;

identify a plurality of categories that include the identifier;

determine a score of each identified category, from the plurality of categories, that include the identifier, to identify a category having the highest score; and

only increase the reward score of the category with the highest score.

13. The system of claim 11 , wherein the demographical data of a user is the age of the user.

14. The system of claim 11 , wherein the multiple content categories are identified by the control circuitry from genres consisting of kids, educational, mystery, news, comedy, documentary, game show, sci-fi, fantasy, sports, action popularity, sitcom, movie, community, and drama.

15. The system of claim 11 , further comprising, the control circuitry configured to calculate the increase of the reward score of the content category of the multiple identified content categories based on a recall value.

16. The system of claim 15 , wherein the recall value is computed by the control circuitry to be proportional to a number of requests for a content item.

17. The system of claim 15 , wherein the recall value is computed by the control circuitry configured to be inversely proportional to a number of times an identifier of that content item was generated for display in a carousel.

18. The system of claim 11 , wherein the request to access a content item is specific to a single user.

19. The system of claim 11 , further comprising, the control circuitry configured to track the reward scores and provide a confidence value related to the reward score.

20. The system of claim 11 , further comprising, the control circuitry configured to generate a graphical user interface to display the content categories as carousels on a display screen.

Assignments (3)
CHANGE OF NAME Recorded Oct 3, 2024
From: ROVI GUIDES, INC.
To: ADEIA GUIDES INC.
Reel/Frame 069106/0231 →
SECURITY INTEREST Recorded May 19, 2023
From: ADEIA GUIDES INC.; ADEIA MEDIA HOLDINGS LLC; ADEIA MEDIA SOLUTIONS INC.; ADEIA SEMICONDUCTOR BONDING TECHNOLOGIES INC.; ADEIA SEMICONDUCTOR SOLUTIONS LLC; ADEIA SEMICONDUCTOR TECHNOLOGIES LLC
To: BANK OF AMERICA, N.A., AS COLLATERAL AGENT
Reel/Frame 063707/0884 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 27, 2021
From: MILLER, KYLE
To: ROVI GUIDES, INC.
Reel/Frame 057313/0150 →
Continuity (2)
Continuation 16454834 · Jun 27, 2019
Related Publication 20210390129A1 · Dec 16, 2021