IP Library Granted Patent US 11,604,827
Granted Patent B2
US 11,604,827 · App. 16/844,511 · Granted Mar 14, 2023

Systems and methods for generating improved content based on matching mappings

Inventors: Sahir Nasir (San Jose, CA); Alan Waterman (Merced, CA)
Assignee: ROVI GUIDES, INC.
G06F16/783G06F16/71G06F16/73G06F16/738G06F16/7867G06K9/6256G06K9/6267G06N3/04G06N3/08G06V40/1365
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 11,604,827
App. No.
16/844,511
Granted
Mar 14, 2023
Kind
B2
Abstract

Systems and methods are disclosed herein for generating content based on matching mappings by implementing deconstruction and reconstruction techniques. The system may retrieve a first content structure that includes a first object with a first mapping that includes a first list of attribute values. The system may then search content structures for a matching content structure having a second object with a second list of attributes and a second mapping including second attribute values corresponding to the second list of attributes. Upon finding a match, the system may generate a new content structure having the first object from the first content structure with the second mapping from the matching content structure. The system may then generate for output a new content segment based on the newly generated content structure.

Claims (55)

1. A method for generating content based on matching mappings, the method comprising:

retrieving a first content structure comprising a first object with a first list of attributes and a first mapping including first attribute values corresponding to the first list of attributes;

searching a plurality of content structures for a matching content structure that comprises a second object with a second list of attributes and a second mapping including second attribute values corresponding to the second list of attributes, wherein the second mapping matches the first mapping;

generating a new content structure, wherein the new content structure comprises (i) the first object from the first content structure with the second mapping from the matching content structure and (ii) a temporal mapping that indicates times when each attribute of the second list of attributes is mapped to a respective attribute value in the second mapping; and

generating for output a new content segment based on the new content structure, wherein the new content segment presents the first object mapped to the second attribute values at the times indicated by the temporal mapping.

2. The method of claim 1 , wherein determining that the second mapping matches the first mapping comprises:

generating a first mapping fingerprint based on the first list of attributes and the first mapping;

generating a second mapping fingerprint based on the second list of attributes and the second mapping, wherein the second mapping fingerprint matches the first mapping fingerprint; and

comparing the first mapping fingerprint and the second mapping fingerprint.

3. The method of claim 2 , wherein generating the first mapping fingerprint comprises:

providing, via control circuitry, a training dataset to train a neural network, wherein the training dataset comprises a set of mappings and respective action keywords;

modifying the parameters of the training dataset based on a match between the output generated by the neural network when a particular mapping from the training dataset is inputted into the neural network and the action keyword of the inputted particular mapping; and

using the trained neural network to generate an action keyword based on the first mapping being inputted.

4. The method of claim 3 , wherein searching the plurality of content structures for the matching content structure comprises searching a database of content structures for a mapping associated with the generated action keyword.

5. The method of claim 4 , wherein searching the database of content structures for a mapping associated with the generated action keyword comprises searching for a mapping that generated the same generated action keyword when inputted into the trained neural network.

6. The method of claim 1 , wherein determining that the second mapping matches the first mapping comprises:

generating a first mapping fingerprint by inputting the first mapping into a generative neural network;

generating a second mapping fingerprint by inputting the second mapping into the generative neural network; and

comparing the first mapping fingerprint and the second mapping fingerprint.

7. The method of claim 1 , wherein determining that the second mapping matches the first mapping comprises:

inputting the second mapping and the first mapping into a neural network that was trained to compare mappings using a training set comprising a plurality of known matching mappings.

8. The method of claim 1 , wherein searching a plurality of content structures for a matching content structure further comprises:

generating for display a graphical user interface comprising a visual representation of the second mapping fingerprint; and

receiving a selection from the graphical user interface of the visual representation of the second mapping fingerprint.

9. The method of claim 8 , wherein generating for display the visual representation of the second mapping fingerprint comprises generating a visual representation of the second object with the second list of attributes and the second mapping including the second attribute values.

10. The method of claim 1 , wherein each of the plurality of objects comprises a plurality of attributes and wherein one attribute of the plurality of attributes is a vectorized representation of the object.

11. A system for generating content based on matching mappings, comprising:

control circuitry configured to:

retrieve a first content structure comprising a first object with a first list of attributes and a first mapping including first attribute values corresponding to the first list of attributes;

search a plurality of content structures for a matching content structure that comprises a second object with a second list of attributes and a second mapping including second attribute values corresponding to the second list of attributes, wherein the second mapping matches the first mapping;

generate a new content structure, wherein the new content structure comprises (i) the first object from the first content structure with the second mapping from the matching content structure and (ii) a temporal mapping that indicates times when each attribute of the second list of attributes is mapped to a respective attribute value in the second mapping; and

generate for output a new content segment based on the new content structure, wherein the new content segment presents the first object mapped to the second attribute values at the times indicated by the temporal mapping.

12. The system of claim 11 , wherein the control circuitry is further configured to determining that the second mapping matches the first mapping by:

generating a first mapping fingerprint based on the first list of attributes and the first mapping;

generating a second mapping fingerprint based on the second list of attributes and the second mapping, wherein the second mapping fingerprint matches the first mapping fingerprint; and

comparing the first mapping fingerprint and the second mapping fingerprint.

13. The system of claim 12 , wherein the control circuitry is further configured to generate the first mapping fingerprint by:

providing, via control circuitry, a training dataset to train a neural network, wherein the training dataset comprises a set of mappings and respective action keywords;

modifying the parameters of the training dataset based on a match between the output generated by the neural network when a particular mapping from the training dataset is inputted into the neural network and the action keyword of the inputted particular mapping; and

using the trained neural network to generate an action keyword based on the first mapping being inputted.

14. The system of claim 13 , wherein the control circuitry is further configured to search the plurality of content structures for the matching content structure by searching a database of content structures for a mapping associated with the generated action keyword.

15. The system of claim 14 , wherein the control circuitry is further configured to search the database of content structures for a mapping associated with the generated action keyword comprises searching for a mapping that generated the same generated action keyword when inputted into the trained neural network.

16. The system of claim 11 , wherein the control circuitry is further configured to determining that the second mapping matches the first mapping by:

generating a first mapping fingerprint by inputting the first mapping into a generative neural network;

generating a second mapping fingerprint by inputting the second mapping into the generative neural network; and

comparing the first mapping fingerprint and the second mapping fingerprint.

17. The system of claim 11 , wherein the control circuitry is further configured to determining that the second mapping matches the first mapping by:

inputting the second mapping and the first mapping into a neural network that was trained to compare mappings using a training set comprising a plurality of known matching mappings.

18. The system of claim 11 , wherein the control circuitry is further configured to search for a plurality of content structures for a matching content structure further comprises:

generating for display a graphical user interface comprising a visual representation of the second mapping fingerprint; and

receiving a selection from the graphical user interface of the visual representation of the second mapping fingerprint.

19. The system of claim 18 , wherein the control circuitry is further configured to generate for display the visual representation of the second mapping fingerprint by generating a visual representation of the second object with the second list of attributes and the second mapping including the second attribute values.

20. The system of claim 11 , wherein each of the plurality of objects comprises a plurality of attributes and wherein one attribute of the plurality of attributes is a vectorized representation of the object.

21. The method of claim 1 , wherein an attribute of the second list of attributes is an action attribute representing a series of actions, and wherein the new content segment comprises video content displaying the first object performing the series of actions.

22. The system of claim 11 , wherein an attribute of the second list of attributes is an action attribute representing a series of actions, and wherein the new content segment comprises video content displaying the first object performing the series of actions.

Assignments (3)
CHANGE OF NAME Recorded Oct 3, 2024
From: ROVI GUIDES, INC.
To: ADEIA GUIDES INC.
Reel/Frame 069106/0207 →
SECURITY INTEREST Recorded May 3, 2023
From: ADEIA GUIDES INC.; ADEIA IMAGING LLC; ADEIA MEDIA HOLDINGS LLC; ADEIA MEDIA SOLUTIONS INC.; ADEIA SEMICONDUCTOR ADVANCED TECHNOLOGIES INC.; ADEIA SEMICONDUCTOR BONDING TECHNOLOGIES INC.; ADEIA SEMICONDUCTOR INC.; ADEIA SEMICONDUCTOR SOLUTIONS LLC; ADEIA SEMICONDUCTOR TECHNOLOGIES LLC; ADEIA SOLUTIONS LLC
To: BANK OF AMERICA, N.A., AS COLLATERAL AGENT
Reel/Frame 063529/0272 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 9, 2020
From: NASIR, SAHIR; WATERMAN, ALAN
To: ROVI GUIDES, INC.
Reel/Frame 052358/0517 →
Continuity (2)
Provisional Application 62979732 · Feb 21, 2020
Related Publication 20210263964A1 · Aug 26, 2021
Cited By (3)
US 12,335,583 US 12,386,892 US 12,711,805