US 12,321,696 B2
Artificial intelligence enterprise application framework
Dmitry Gutzeit, New York, NY (US); and Rina Feifan Charles, New York, NY (US)
Assigned to LeapXpert Limited, Causeway Bay (HK)
Filed by LeapXpert Limited, Causeway Bay (HK)
Filed on Jan. 30, 2024, as Appl. No. 18/427,041.
Application 18/427,041 is a continuation of application No. 18/482,787, filed on Oct. 6, 2023, granted, now 11,928,426.
Claims priority of provisional application 63/587,381, filed on Oct. 2, 2023.
Prior Publication US 2025/0111144 A1, Apr. 3, 2025
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/00 (2020.01); G06F 16/34 (2019.01); G06F 40/20 (2020.01); H04L 51/02 (2022.01)
CPC G06F 40/20 (2020.01) [G06F 16/345 (2019.01); H04L 51/02 (2013.01)] 28 Claims
OG exemplary drawing
 
1. A method for providing machine-learning-based analysis of communications in a central communication platform, comprising:
receiving a plurality of messages for a plurality of internal users of an organization from a plurality of external users;
constructing a plurality of embedding representations based on the plurality of messages;
identifying an analysis task for an internal user of the organization, wherein:
the analysis task is obtained based on a query of the internal user of the organization,
the organization comprises a plurality of internal user groups, and
the internal user of the organization is associated with an internal user group of the plurality of internal user groups;
retrieving, based on the internal user group, a subset of embeddings from the plurality of embeddings representations;
executing the analysis task by providing the retrieved subset of embeddings to a trained machine-learning model; and
displaying a graphical user interface comprising one or more outputs based on the execution of the analysis task.