US 11,928,426 B1
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 Oct. 6, 2023, as Appl. No. 18/482,787.
Claims priority of provisional application 63/587,381, filed on Oct. 2, 2023.
Int. Cl. G06F 40/20 (2020.01); G06F 16/34 (2019.01); H04L 51/02 (2022.01)
CPC G06F 40/20 (2020.01) [G06F 16/345 (2019.01); H04L 51/02 (2013.01)] 29 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 of the plurality of messages by converting each message of the plurality of messages into one or more embedding representations;
storing the plurality of embeddings in an embedding database, wherein each embedding of the plurality of embeddings is associated with a corresponding sender identity or a corresponding recipient identity;
identifying an analysis task for an internal user of the organization, wherein the organization comprises a plurality of internal user groups in accordance with a plurality of ethical walls, 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 and one or more ethical walls of the plurality of ethical walls, a subset of embeddings from the stored plurality of embeddings;
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.