	US 12,395,397 B2
	Real-time monitoring ecosystem
Japan Mehta, Dallas, TX (US); Abhishek Seth, Singapore (SG); and Siva Koti Reddy Malapati, Singapore (SG)
Assigned to Citibank, N.A., New York, NY (US)
Filed by CITIBANK, N.A., New York, NY (US)
Filed on Mar. 31, 2023, as Appl. No. 18/129,306.
Prior Publication US 2024/0333578 A1, Oct. 3, 2024
Int. Cl. H04L 41/0631 (2022.01); G06N 3/02 (2006.01); H04L 41/16 (2022.01)

CPC H04L 41/0631 (2013.01) [G06N 3/02 (2013.01); H04L 41/16 (2013.01)]

16 Claims

1. A computer-implemented method to monitor computer resources from real-time user data and real-time infrastructure data, comprising:

receiving, using one or more computing devices, a plurality of real-time user data and real-time infrastructure data;

transferring, by the one or more computing devices, the real-time user data and the real-time infrastructure data to a deployed machine learning network;

first processing the real-time user data with the deployed machine learning network thereby transforming the plurality of real-time user data into a plurality of transformed real-time user data, wherein transforming the plurality of real-time user data comprises tokenization; stemming; lemmatization; removing stop words; creating multi-grams; or any combination thereof, and processing the plurality of transformed real-time user data and the real-time infrastructure data with the deployed machine learning network, the deployed machine learning network generated and deployed from a training machine learning network;

inputting, into the deployed machine learning network, both the plurality of transformed real-time user data and the real-time infrastructure data to obtain a prediction of one or more recurring user problems related to a computing device, wherein the deployed machine learning network outputs the one or more recurring user problems related to the computing device; and

transmitting, using the one or more computing devices, the one or more recurring user problems to a device associated with a user.