US 12,615,191 B1Granted

Network communication routing with clustering

AssigneeIntuit Inc.

InventorsShon Mendelson, Natalie Bar Eliyahu, Hadassah Gila Dekelboim, Guy Elad, Amnon Mor, Shahar Glatman

Life of this patent

Estimating the term…

Loading patent…

Abstract

A clustering model clusters multiple network communications through a clustering model to generate multiple clusters. Multiple judge models classify the network communications to obtain multiple predictions for each network communication of the network communications. Multiple sample network communications in a cluster are selected based on a discrepancy amongst the predictions of each sample network communication in the sample network communications. A lead model evaluates the sample network communications to select a judge model of the judge models for the cluster. The selected judge model is assigned to the cluster.

Claims20

Dependent claims

A method comprising:

clustering, by a clustering model, a plurality of network communications through the clustering model to generate a plurality of clusters, each cluster comprising a subset of the plurality of network communications;
classifying, by a plurality of judge models, the plurality of network communications to obtain a plurality of predictions for each network communication of the plurality of network communications, wherein the plurality of judge models are separate from the clustering model, and wherein the plurality of predictions are separate from the clustering of the plurality of network communications;
detecting, within a cluster of the plurality of clusters, a discrepancy among a subset of the plurality of predictions for the subset of the plurality of network communications;
selecting a plurality of sample network communications in the cluster of the plurality of clusters based on the discrepancy;
evaluating, by a lead model, the plurality of sample network communications to select a judge model of the plurality of judge models for the cluster;
and
assigning the selected judge model to the cluster, wherein the selected judge model performs a prediction for new network communications assigned to the cluster, and wherein the selected judge model causes a routing of the new network communications by the prediction.

4 more elements

A system comprising:

at least one computer processor;
a clustering model executing on the at least one computer processor for causing a computer system to:
cluster a plurality of network communications through the clustering model to generate a plurality of clusters, each cluster comprising a subset of the plurality of network communications;
a plurality of judge models executing on the at least one computer processor for causing the computer system to:
classify the plurality of network communications to obtain a plurality of predictions for each network communication of the plurality of network communications, wherein the plurality of judge models are separate from the clustering model, and wherein the plurality of predictions are separate from the clustering of the plurality of network communications;
a discrepancy detector executing on the at least one computer processor and configured to:
detect, within a cluster of the plurality of clusters, a discrepancy among a subset of the plurality of predictions for the subset of the plurality of network communications, and
select a plurality of sample network communications in the cluster of the plurality of clusters based on the discrepancy;
a lead model executing on the at least one computer processor and configured to:
evaluate the plurality of sample network communications to select a judge model of the plurality of judge models for the cluster;
and
a training program executing on the at least one computer processor configured to assign the selected judge model to the cluster, wherein the selected judge model performs a prediction for new network communications assigned to the cluster, and wherein the selected judge model causes a routing of the new network communications by the prediction.

9 more elements

Dependencies are inferred from the claim text.