US 12,483,485 B1
System performance degradation detection and remediation utilizing discrete inter-message timing calculation and modeling inter-message-timing
Yijin Ouyang, Alpharetta, GA (US); and Jared Mroz, New York, NY (US)
Assigned to Morgan Stanley Services Group Inc., New York, NY (US)
Filed by Morgan Stanley Services Group Inc., New York, NY (US)
Filed on May 20, 2025, as Appl. No. 19/213,522.
Application 19/213,522 is a continuation of application No. 19/020,119, filed on Jan. 14, 2025, granted, now 12,348,383.
Int. Cl. H04L 41/147 (2022.01); H04L 41/14 (2022.01); H04L 41/16 (2022.01)
CPC H04L 41/147 (2013.01) [H04L 41/145 (2013.01); H04L 41/16 (2013.01)] 4 Claims
OG exemplary drawing
 
1. A computer-implemented system for reducing latency in communication over a network comprising:
a dynamic session manager executed by one or more processors and configured to access a data communication network that supports message traffic, wherein a plurality of senders and receivers send messages on a hop-by-hop basis via the data communication network; and
a database coupled to the data communication network configured to record and store the messages occurring in the data communication network and message metadata associated with the messages: in the message traffic,
wherein the dynamic session manager is further configured to:
obtain message hop data from the messages in the message traffic, the message hop data concerning current communications for a respective message communicated in the data communication network, including a time stamp, volume, and a number of active sessions;
generate simulation data, including by using network hop data from the message traffic;
initiate a simulation using the simulation data, via a machine learning algorithm trained using historical data communication data, to forecast respective latency in connection with a plurality of network communication sessions in the data communication network;
determine whether a respective forecasted latency is optimal, as a function of inter-message-timing intervals being within a predetermined range; and
adjust parameters including a number of current communication sessions to improve latency when the respective forecasted latency is determined to be not optimal.