The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Sep. 29, 2026

Filed:

Mar. 29, 2024
Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Behnoosh Hariri, New York, NY (US);

Gregory George Galante, Little Silver, NJ (US);

Rebecca Wenshu Hsieh, Sunnyvale, CA (US);

Princeton Tirin Poe, New York, NY (US);

Gonzalo Fiorina, Brooklyn, NY (US);

Barak Ben Noon, Brooklyn, NY (US);

Miles Henrichs, New York, NY (US);

Ahsan Wahab, Tampa, FL (US);

Amer Mograbi, New York, NY (US);

Christopher Gregory Tong, Long Island, NY (US);

Nicholas Joseph Pesce, New York, NY (US);

Andrew James Motika, Birmingham, MI (US);

John Gabriel D'angelo, New York, NY (US);

Tomer Aberbach, Hoboken, NJ (US);

Grace Sytin Shih, Cupertino, CA (US);

Albert Orriols Puig, Los Altos, CA (US);

Jayakumar Hoskere, Bangalore, IN;

Assignee:

GOOGLE LLC, Mountain View, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 40/186 (2020.01); G06F 40/103 (2020.01); G06F 40/20 (2020.01);
U.S. Cl.
CPC ...
G06F 40/186 (2020.01); G06F 40/103 (2020.01); G06F 40/20 (2020.01);
Abstract

Systems and methods for generating personalized and structured content using a collaborative generator provide a user interface to a user computing system and receive a prompt from the user computing system via the user interface. The systems and methods provide the prompt to a generative model, with the generative model being a machine-learned model trained to process language input prompts to generate a language output. The systems and methods receive a generative output generated by the generative model in response to the prompt. Additionally, the systems and methods generate a modified output by modifying the generative output based at least in part on historical user data for a user associated with the prompt, and then provide the modified output via the user interface.


Find Patent Forward Citations

Loading…