IP Library Patent Application 19633195
Patent Application
App. No. 19/633,195

CROSS-RELEVANT REFINEMENT OF GENERATIVE ARTIFICIAL INTELLIGENCE MODELS FOR CREATIVE CONTENT ACROSS MULTIPLE PLATFORMS

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 None
App. No.
19/633,195
Abstract

Methods and systems provide for cross-relevant refinement of generative artificial intelligence models for creative content across multiple platforms. In one embodiment, the system receives creative content related to a first product listing for a product within a first platform, user engagement data for a user of a second platform, and one or more pieces of contextual information; trains a refinement of a second generative AI model for dynamic creative content generation for a modified version of the first product listing for the second platform; generates and displays one or more pieces of creative content for a second product listing to be published on the second platform; receives feedback regarding user engagement with the pieces of creative content in terms of whether an engagement objective has been achieved; and refines the first generative AI model and the second generative AI model via a network of cross-refinement.

Claims (40)

1 . (canceled)

2 . A computer-implemented method comprising:

receiving a file comprising source content;

determining a plurality of sharing contexts associated with destination platforms or interfaces for the file;

generating, using one or more generative models and based on the plurality of sharing contexts, a plurality of representations derived from the source content for presentation in accordance with the plurality of sharing contexts, the plurality of representations differing from one another based on the respective sharing contexts;

causing the plurality of representations to be presented within the destination platforms or interfaces;

receiving engagement data corresponding to interactions with the plurality of representations; and

refining the one or more generative models based on the engagement data, including using engagement data associated with presentation of a first representation in a first sharing context to refine generation of a second representation for presentation in a second sharing context different from the first sharing context.

3 . The computer-implemented method of claim 2 , further comprising generating the plurality of representations to include at least two of a summary, a preview, a thumbnail, an excerpt, or a content card.

4 . The computer-implemented method of claim 2 , further comprising determining the plurality of sharing contexts to include at least two of a messaging platform context, an email context, a shared-link context, a mobile-interface context, or a web-interface context.

5 . The computer-implemented method of claim 2 , further comprising generating the plurality of representations such that the plurality of representations differ from one another in at least one of length, included content, formatting, metadata, or visual layout.

6 . The computer-implemented method of claim 2 , further comprising receiving the engagement data to include at least one of a view, a click, a dwell time, a save action, a share action, or a selection of the file.

7 . The computer-implemented method of claim 2 , further comprising receiving the engagement data to include a downstream interaction with the file after presentation of at least one of the plurality of representations, wherein the downstream interaction comprises opening, downloading, editing, commenting on, or resharing the file.

8 . The computer-implemented method of claim 2 , further comprising generating the plurality of representations by using a first generative model to generate the first representation for the first sharing context and using a second generative model to generate the second representation for the second sharing context.

9 . A system comprising:

at least one processor; and

a non-transitory computer readable medium storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:

determining a plurality of sharing contexts associated with destination platforms or interfaces for a file comprising source content;

generating, using one or more generative models and based on the plurality of sharing contexts, a plurality of representations derived from the source content for presentation in accordance with the plurality of sharing contexts, the plurality of representations differing from one another based on the respective sharing contexts;

causing the plurality of representations to be presented within the destination platforms or interfaces;

receiving engagement data corresponding to interactions with the plurality of representations; and

refining the one or more generative models based on the engagement data, including using engagement data associated with presentation of a first representation in a first sharing context to refine generation of a second representation for presentation in a second sharing context different from the first sharing context.

10 . The system of claim 9 , further storing instructions that, when executed by the at least one processor, cause the system to generate the plurality of representations to include at least two of a summary, a preview, a thumbnail, an excerpt, or a content card.

11 . The system of claim 9 , further storing instructions that, when executed by the at least one processor, cause the system to determine the plurality of sharing contexts to include at least two of a messaging platform context, an email context, a shared-link context, a mobile-interface context, or a web-interface context.

12 . The system of claim 9 , further storing instructions that, when executed by the at least one processor, cause the system to generate the plurality of representations such that the plurality of representations differ from one another in at least one of length, included content, formatting, metadata, or visual layout.

13 . The system of claim 9 , further storing instructions that, when executed by the at least one processor, cause the system to receive the engagement data to include at least one of a view, a click, a dwell time, a save action, a share action, or a selection of the file.

14 . The system of claim 9 , further storing instructions that, when executed by the at least one processor, cause the system to receive the engagement data to include a downstream interaction with the file after presentation of at least one of the plurality of representations, wherein the downstream interaction comprises opening, downloading, editing, commenting on, or resharing the file.

15 . The system of claim 9 , further storing instructions that, when executed by the at least one processor, cause the system to generate the plurality of representations by using a first generative model to generate the first representation for the first sharing context and using a second generative model to generate the second representation for the second sharing context.

16 . A non-transitory computer readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

receiving a file comprising source content;

determining a plurality of sharing contexts associated with destination platforms or interfaces for the file;

generating, using one or more generative models and based on the plurality of sharing contexts, a plurality of representations derived from the source content for presentation in accordance with the plurality of sharing contexts, the plurality of representations differing from one another based on the respective sharing contexts;

causing the plurality of representations to be presented within the destination platforms or interfaces;

receiving engagement data corresponding to interactions with the plurality of representations, the engagement data including a downstream interaction with the file following presentation of at least one of the plurality of representations; and

refining the one or more generative models based on the engagement data, including using engagement data associated with presentation of a first representation in a first sharing context to refine generation of a second representation for presentation in a second sharing context different from the first sharing context.

17 . The non-transitory computer readable medium of claim 16 , further storing instructions that, when executed by the at least one processor, cause the at least one processor to generate the plurality of representations to include at least two of a summary, a preview, a thumbnail, an excerpt, or a content card.

18 . The non-transitory computer readable medium of claim 16 , further storing instructions that, when executed by the at least one processor, cause the at least one processor to determine the plurality of sharing contexts to include at least two of a messaging platform context, an email context, a shared-link context, a mobile-interface context, or a web-interface context.

19 . The non-transitory computer readable medium of claim 16 , further storing instructions that, when executed by the at least one processor, cause the at least one processor to generate the plurality of representations such that the plurality of representations differ from one another in at least one of length, included content, formatting, metadata, or visual layout.

20 . The non-transitory computer readable medium of claim 16 , further storing instructions that, when executed by the at least one processor, cause the at least one processor to receive the engagement data to include at least one of a view, a click, a dwell time, a save action, a share action, or a selection of the file.

21 . The non-transitory computer readable medium of claim 16 , further storing instructions that, when executed by the at least one processor, cause the at least one processor to generate the plurality of representations by using a first generative model to generate the first representation for the first sharing context and using a second generative model to generate the second representation for the second sharing context.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 31, 2026
From: YATES, ANDREW DONALD
To: PROMOTED.AI, INC.
Reel/Frame 074235/0418 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 31, 2026
From: PROMOTED.AI, INC.
To: DROPBOX, INC.
Reel/Frame 074235/0664 →