US 11,928,319 B1
Interactive canvas tool for multimodal personalized content generation
Abhay Parasnis, Los Altos, CA (US); Kang Chen, Los Altos, CA (US); Hari Srinivasan, Los Altos, CA (US); Jonathan Moreira, Los Altos, CA (US); and Vishal Sood, Los Altos, CA (US)
Assigned to Typeface Inc., Los Altos, CA (US)
Filed by Typeface Inc., Los Altos, CA (US)
Filed on May 30, 2023, as Appl. No. 18/203,530.
Claims priority of provisional application 63/444,162, filed on Feb. 8, 2023.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 3/0482 (2013.01); G06F 3/0484 (2022.01); G06F 40/186 (2020.01); G06N 3/0475 (2023.01)
CPC G06F 3/0484 (2013.01) [G06F 40/186 (2020.01); G06N 3/0475 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
providing a user interface (UI) by a canvas tool to generate multimodal content, the canvas tool comprising a prompt panel, a variations panel, and a canvas panel the canvas panel configured to present items from a plurality of item types, the plurality of item types comprising a text type and an image type;
receiving text input in the prompt panel, the text input including a textual description with instruction for generating one or more variations, the canvas tool being configured to generate the one or more variations from each type of the plurality of item types;
providing the text input to a generative artificial intelligence (GAI) tool to generate the one or more variations based on the textual description of the text input, the GAI tool configured to generate new content based on the textual description;
presenting, in the variations panel, the one or more variations generated by the GAI tool;
detecting a selection of a selected variation from the one or more variations in the variations panel; and
adding the selected variation to the canvas panel in the UI.