US 11,336,539 B2Granted

Support ticket summarizer, similarity classifier, and resolution forecaster

AssigneeSupportLogic, Inc.

InventorPoonam Rath

Life of this patent

Estimating the term…

Loading patent…

Abstract

A support ticket summarizer, similarity classifier, and resolution forecaster are described. A system trains a machine learning model to identify topic sequences for support ticket communications, identify topic sequences that are classified as similar, and predict subsequent topics for multiple support ticket communications, in response to receiving the support ticket communications. The machine learning model receives a communication for a support ticket, and then identifies a sequence of topics for the communication for the support ticket. The machine-learning model identifies historical sequences of topics, for historical support tickets, which are classified as similar to the sequence of topics. The machine-learning model uses the historical sequences of topics to predict at least one subsequent topic for the sequence of topics. The system outputs the at least one subsequent topic.

Claims17

Dependent claims

A system for a support ticket summarizer, similarity classifier, and resolution forecaster, the system comprising:

one or more processors;
and
a non-transitory computer readable medium storing a plurality of instructions, which when executed, cause the one or more processors to:
train a machine learning model to identify topic sequences for support ticket communications, identify topic sequences that are classified as similar, and predict subsequent topics for multiple support ticket communications, in response to receiving the support ticket communications;
identify, by the machine learning model, a sequence of topics for a communication for a support ticket and an age of the support ticket, in response to receiving the communication;
identify, by the machine-learning model, historical sequences of topics, for historical support tickets, which are classified as similar to the sequence of topics, comprising determining historical ages of the historical support tickets are classified as similar to the age of the support ticket;
predict, by the machine-learning model, based on the historical sequences of topics, at least one subsequent topic for the sequence of topics;
and
output the at least one subsequent topic.

6 more elements

A computer-implemented method for a support ticket summarizer, similarity classifier, and resolution forecaster, the computer-implemented method comprising:

training a machine learning model to identify topic sequences for support ticket communications, identify topic sequences that are classified as similar, and predict subsequent topics for multiple support ticket communications, in response to receiving the support ticket communications;
identifying, by the machine learning model, a sequence of topics for a communication for a support ticket and an age of the support ticket, in response to receiving the communication;
identifying, by the machine-learning model, historical sequences of topics, for historical support tickets, which are classified as similar to the sequence of topics, comprising determining historical ages of the historical support tickets are classified as similar to the age of the support ticket;
predicting, by the machine-learning model, based on the historical sequences of topics, at least one subsequent topic for the sequence of topics;
and
outputting the at least one subsequent topic.

3 more elements

A computer program product, comprising a non-transitory computer-readable medium having a computer-readable program code embodied therein to be executed by one or more processors, the program code including instructions to:

train a machine learning model to identify topic sequences for support ticket communications, identify topic sequences that are classified as similar, and predict subsequent topics for multiple support ticket communications, in response to receiving the support ticket communications;
identify, by the machine learning model, a sequence of topics for a communication for a support ticket and an age of the support ticket, in response to receiving the communication;
identify, by the machine-learning model, historical sequences of topics, for historical support tickets, which are classified as similar to the sequence of topics, comprising determining historical ages of the historical support tickets are classified as similar to the age of the support ticket;
predict, by the machine-learning model, based on the historical sequences of topics, at least one subsequent topic for the sequence of topics;
and
output the at least one subsequent topic.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/208,115Filed 22 Mar 2021 · us provisional application
Priority: 20 Apr 2020
Published: US 2021/0328888 A121 Oct 2021
Granted: 17 May 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification16 codes

G06Q 30/016
Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk: after-sales
G06F 18/22
Analysing: matching criteria, e.g. proximity measures
G06N 3/045
Architecture, e.g. interconnection topology: combinations of networks
G06N 3/08
Neural networks: learning methods