US 2023/0412494 A1 · SYSTEM AND METHOD FOR OPTIMIZING ROUTING OF DATA TRANSFERS OVER A COMPUTER NETWORK

Abstract

A system and a method of optimizing a plurality of data elements including one or more nodes within a first network of nodes may include: receiving a value of one or more data transfer parameters pertaining to one or more data transfers conducted over one or more nodes of a first computer network; perturbating a value of one or more elements; creating a simulated computer network based on the one or more perturbated values; for each network of the first computer network and the simulated computer network, calculating a value of at least one performance parameter; and generating, based on the calculation, a suggestion for optimizing the data elements, wherein the suggestion may include at least one perturbated data element value.

Claims20

Dependent claims

A system for routing data transfers between nodes of a computer network, each node connected to at least one other node via one or more links, the system comprising:

a clustering model;
at least one neural network;
a routing engine;
and
at least one processor,
wherein the at least one processor is configured to:
receive a request to route a data transfer between two nodes of the computer network;
extract from the data transfer request, a feature vector (FV), comprising at least one feature;
and
associate the requested data transfer with a cluster of data transfers in the clustering model based on the extracted FV,
and wherein the neural network is configured to produce a selection of an optimal route for the requested data transfer from a plurality of available routes, based on the FV,
and wherein the routing engine is configured to route the requested data transfer according to the selection.

9 more elements

A method of routing data transfers within a computer network, method comprising:

receiving, by a processor, a request to route a data transfer between two nodes of the computer network, each node connected to at least one other node via one or more links;
extracting, by the processor, from the data transfer request, a feature vector (FV), comprising at least one feature associated with the requested data transfer;
associating the requested data transfer with a cluster of data transfers in a clustering model based on the extracted FV;
selecting an optimal route for the requested data transfer from a plurality of available routes, based on the FV;
and
routing the requested data transfer according to the selection.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application

18/220,124Filed 10 Jul 2023

Priority

2 May 2018

Published

21 Dec 2023

Term ends

Not estimatedThe source records don’t support an estimate.

Classification20 codes

G06Q 20/20
Payment architectures: point-of-sale [POS] network systems
H04L 45/34
Routing or path finding of packets in data switching networks: source routing
G06N 3/0499
Architecture, e.g. interconnection topology: feedforward networks
G06N 3/08
Neural networks: learning methods

Family

Application15/968,771Continuation in part · filed 2 May 2018

Application16/255,871Continuation in part · filed 24 Jan 2019

Application16/274,282Continuation in part · filed 13 Feb 2019

Application16/392,715Continuation in part · filed 24 Apr 2019

Application16/547,133Continuation · filed 21 Aug 2019

Application18/110,975Continuation · filed 17 Feb 2023

Application18/220,124Continuation

Application16/547,133Continuation in part

US 2019/0340583 A1Published application

US 2019/0340589 A1Published application

US 2019/0342203 A1Published application

US 2019/0342205 A1Published application

US 2019/0379595 A1Published application

US 2023/0198886 A1Published application

US 2023/0412494 A1This patent

From the US filing history. Foreign family members aren’t listed.

System and method for optimizing routing of data transfers over a computer network

Life of this patent

System and method for optimizing routing of data transfers over a computer network

Life of this patent

Abstract

Claims20