Personalized content creation using neural networks

Patent metadata

Field	Value
Publication number	US-11501079-B1
Application number	US-201916704752-A
Country	US
Kind code	B1
Filing date	Dec 5, 2019
Priority date	Dec 5, 2019
Publication date	Nov 15, 2022
Grant date	Nov 15, 2022

Abstract

A technique for dynamic generation of a derivative story includes obtaining content preferences from a content consumer. The content preferences indicate preferences for characteristics of the derivative story. A content data structure is identified based at least in part on the content preferences. The content data structure specifies story elements of a preexisting story. The story elements are defined at one or more different levels of story abstraction and associated with metadata constraints that constrain modification or use of the story elements within the derivative story. At least some of the metadata constraints indicate whether associated ones of the story elements are mutable story elements. One or more of the mutable story elements are adapted to the content preferences of the content consumer as constrained by the metadata constraints to generate the derivative story. The derivative story is then rendered via a user interface.

First claim

What is claimed is:

1. At least one non-transitory machine-readable storage medium that provides instructions that, when executed by one or more machines, will cause the one or more machines to perform operations comprising:
obtaining content preferences from a content consumer, the content preferences indicating preferences for characteristics of a derivative story;
identifying a content data structure based at least in part on the content preferences, the content data structure specifying story elements of a preexisting story, the story elements defined at one or more different levels of story abstraction and associated with metadata constraints that constrain a modification or a use of the story elements within the derivative story, wherein at least some of the metadata constraints indicate whether associated ones of the story elements are mutable story elements that are permitted to be modified or immutable story elements that are not permitted to be modified;
comparing the content preferences against the metadata constraints to identify a conflict between the preferences for characteristics in the derivative story and constraints on the modification or the use of the story elements specified by the content data structure;
requesting the content consumer to revise the content preferences when the conflict is irreconcilable;
adapting one or more of the mutable story elements to the content preferences of the content consumer as constrained by the metadata constraints to generate the derivative story; and
rendering the derivative story for consumption by the content consumer via a user interface.

2. The at least one non-transitory machine-readable storage medium of claim 1 , wherein the story elements comprise one or more of objects within the preexisting story, environments within the preexisting story, characters within the preexisting story, frame sequences, a narrative structure of the preexisting story, a narrative arc of the preexisting story, or a high-level concept of the preexisting story.

3. The at least one non-transitory machine-readable storage medium of claim 1 , wherein the content preferences include identification of at least one of a format type for the derivative story, a time constraint for consuming the derivative story, a genre of the derivative story, a theme of the derivative story, a character for inclusion in the derivative story, a cultural adaptation for the derivative story, a subject matter maturity rating for the derivative story, or a subject matter for the derivative story.

4. The at least one non-transitory machine-readable storage medium of claim 1 , wherein identifying the content data structure comprises identifying the content data structure with an artificial neural network trained to select the content data structure from a library of content data structures based upon the content preferences.

5. The at least one non-transitory machine-readable storage medium of claim 1 , wherein the comparing and the requesting are performed prior to the rendering of the derivative story.

6. The at least one non-transitory machine-readable storage medium of claim 1 , wherein adapting the one or more of the mutable story elements comprises:
populating a given mutable story element with another story element defined by another content data structure.

7. The at least one non-transitory machine-readable storage medium of claim 6 , wherein the other story element comprises a copyrighted story element, and wherein the operations further comprise:
accessing the copyrighted story element from a content marketplace that tracks royalty fees for incorporating the copyrighted story element into the derivative story.

8. The at least one non-transitory machine-readable storage medium of claim 1 , wherein adapting the one or more mutable story elements comprises:
feeding the content data structure along with at least a portion of the content preferences into a trained artificial neural network; and
modifying the one or more mutable story elements with the trained artificial neural network based upon the content data structure and the content preferences.

9. The at least one non-transitory machine-readable storage medium of claim 8 , wherein the trained artificial neural network comprises one of a generative adversarial network (GAN) or a variational autoencoder trained to create derivative stories using a dataset of preexisting stories.

10. The at least one non-transitory machine-readable storage medium of claim 8 , wherein modifying comprises populating or replacing the mutable story element with another story element defined in another content data structure as selected by the trained artificial neural network based upon the content preferences.

11. A computer implemented method for dynamic generation of a derivative story, the method comprising:
obtaining content preferences from a content consumer, the content preferences indicating preferences for characteristics of the derivative story;
identifying a content data structure based at least in part on the content preferences, the content data structure specifying story elements of a preexisting story, the story elements defined at one or more different levels of story abstraction and associated with metadata constraints that constrain a modification or a use of the story elements within the derivative story, wherein at least some of the metadata constraints indicate whether associated ones of the story elements are mutable story elements that are permitted to be modified or immutable story elements that are not permitted to be modified;
comparing the content preferences against the metadata constraints to identify a conflict between the preferences for characteristics in the derivative story and constraints on the modification or the use of the story elements specified by the content data structure;
requesting the content consumer to revise the content preferences when the conflict is irreconcilable;
adapting one or more of the mutable story elements to the content preferences of the content consumer as constrained by the metadata constraints to generate the derivative story; and
rendering the derivative story for consumption by the content consumer via a user interface.

12. The computer implemented method of claim 11 , wherein the story elements comprise one or more of objects within the preexisting story, environments within the preexisting story, characters within the preexisting story, frame sequences, a narrative structure of the preexisting story, a narrative arc of the preexisting story, or a high-level concept of the preexisting story.

13. The computer implemented method of claim 11 , wherein the content preferences include identification of at least one of a format type for the derivative story, a time constraint for consuming the derivative story, a genre of the derivative story, a theme of the derivative story, a character for inclusion in the derivative story, a cultural adaptation for the derivative story, a subject matter maturity rating for the derivative story, or a subject matter for the derivative story.

14. The computer implemented method of claim 11 , wherein identifying the content data structure comprises identifying the content data structure with an artificial neural network trained to select the content data structure from a library of content data structures based upon the content preferences.

15. The computer implemented method of claim 11 , wherein adapting the one or more of the mutable story elements comprises:
populating a given mutable story element with another story element defined by another content data structu

Assignees

• X Dev Llc

Inventors

• Watson Philip E
• Ervin Christian

Classifications

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title

• G06N3/088

  Non-supervised learning, e.g. competitive learning · CPC title

• G06N3/0454

  Physics · mapped topic

• G06N3/094

  Adversarial learning · CPC title