US 12,307,551 B2
Machine learning based on graphical element generator for communication platform
Aaron Maurer, New York, NY (US); Lichen Ni, Vancouver (CA); Kyle Jablon, Long Island City, NY (US); Ryan Slama, Brooklyn, NY (US); and Jake Polacek, San Francisco, CA (US)
Assigned to Salesforce, Inc., San Francisco, CA (US)
Filed by Salesforce, Inc., San Francisco, CA (US)
Filed on Nov. 30, 2022, as Appl. No. 18/060,377.
Prior Publication US 2024/0177358 A1, May 30, 2024
Int. Cl. G06T 11/00 (2006.01); G06F 3/04817 (2022.01); G06F 3/0482 (2013.01); G06F 3/0484 (2022.01); G06F 40/30 (2020.01); G06F 40/40 (2020.01)
CPC G06T 11/00 (2013.01) [G06F 3/04817 (2013.01); G06F 3/0482 (2013.01); G06F 3/0484 (2013.01); G06F 40/30 (2020.01); G06F 40/40 (2020.01); G06T 2200/24 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, implemented at least in part by one or more computing devices associated with a group-based communication platform, comprising:
receiving, from a user associated with the group-based communication platform, an indication of an interaction between the user and the group-based communication platform;
receiving, from the user, a request to generate one or more graphical elements for the group-based communication platform, wherein the request includes at least one natural language statement associated with the one or more graphical elements;
inputting the request to generate the one or more graphical elements for the group-based communication platform into a machine-learning model, wherein the machine-learning model is trained based at least in part on (i) first data including information regarding prior natural language statements associated with prior graphical elements, and (ii) second data including prior confidence levels associated with prior requests to generate prior graphical elements, to learn one or more relationships between the first data and the second data, such that the machine-learning model is configured to use the learned relationships to generate the one or more graphical elements and one or more respective confidence levels associated with the one or more graphical elements upon the inputting of the request;
receiving, from the machine-learning model and based at least in part on inputting the request, the one or more graphical elements, wherein the one or more graphical elements are generated by the machine-learning model;
causing presentation, to the user and via the one or more computing devices, of the one or more graphical elements;
receiving, from the user, an indication of a selection of one of the one or more graphical elements to share to the group-based communication platform; and
sending, based at least in part on the indication, the selected one of the one or more graphical elements to the group-based communication platform.