US 2026/0087499 A1 · LOGFILE RECOMMENDER SERVICE

Abstract

A logfile recommender service incorporates trained machine learning models to predict recommended logfile types for support tickets. The machine learning models are trained using data from past support tickets such as titles, problem descriptions, and communication records. After receiving a request to generate a logfile recommendation for a given support ticket, the logfile recommender service first calls an attachment prediction machine learning model (e.g., a binary classification model) to predict whether logfiles are relevant to the support ticket. If so, the logfile recommender service calls an attachment recommendation machine learning model (e.g., a multi-label classification model) to generate a list of recommended logfile types for the support ticket, which is output by the logfile recommender service as the logfile recommendation. Logfiles of the recommended types can then be attached to the support ticket to facilitate and expedite resolution of the support ticket.

Claims20

Dependent claims

A computer-implemented method comprising:

receiving, by a logfile recommender server, a request for a logfile recommendation for a support ticket via a user interface, the request comprising data attributes of the support ticket;
and
responsive to the request, by the logfile recommender server:
generating a prediction that one or more logfiles are relevant to the support ticket, wherein the prediction is generated by a binary classification machine learning model trained with a dataset comprising observed data attributes of past support tickets and observed data regarding logfile attachments of the past support tickets, wherein the logfile recommender server determines, based on the prediction, whether to call a multi-label classification machine learning model trained with the dataset;
responsive to the prediction that the one or more logfiles are relevant to the support ticket, calling the multi-label classification machine learning model, wherein the multi-label classification machine learning model generates a list of recommended logfile types for the support ticket;
and
displaying the list of recommended logfile types for the support ticket as the logfile recommendation via the user interface.

4 more elements

A computing system comprising:

at least one hardware processor;
at least one memory coupled to the at least one hardware processor;
a logfile recommender service comprising a logfile recommender server;
a binary classification machine learning model trained with a dataset comprising observed data attributes of past support tickets and observed data regarding logfile attachments of the past support tickets;
a multi-label classification machine learning model trained with the dataset;
and
one or more non-transitory computer-readable media having stored therein computer-executable instructions that, when executed by the computing system, cause the computing system to perform:
receiving, via a user interface, an input comprising data attributes of a support ticket;
responsive to receiving the input, sending a request for a logfile recommendation for a support ticket to the logfile recommender server, the request comprising the data attributes of the support ticket;
responsive to sending the request, receiving the logfile recommendation for the support ticket from the logfile recommender server, wherein the logfile recommender server determines the logfile recommendation for the support ticket by generating a prediction using the binary classification machine learning model based on the data attributes of the support ticket and, based on the prediction, calling the multi-label classification machine learning model to generate a list of recommended logfile types for the support ticket based on the data attributes of the support ticket, wherein the prediction indicates that one or more logfiles are relevant to the support ticket;
and
responsive to receiving the logfile recommendation for the support ticket, displaying the list of the recommended logfile types for the support ticket via the user interface.

9 more elements

One or more non-transitory computer-readable media comprising computer-executable instructions that, when executed by a computing system, cause the computing system to perform operations comprising:

training a binary classification machine learning model with a dataset comprising observed data attributes of past support tickets and observed data regarding logfile attachments of the past support tickets;
training a multi-label classification machine learning model with the dataset;
receiving, by a logfile recommender server, a request for a logfile recommendation for a support ticket via a user interface, the request comprising data attributes of the support ticket;
and
responsive to the request, by the logfile recommender server:
generating a prediction that one or more logfiles are relevant to the support ticket, wherein the prediction is generated by the binary classification machine learning model based on the data attributes of the support ticket, wherein the logfile recommender server determines, based on the prediction, whether to call the multi-label classification machine learning model;
responsive to the prediction that the one or more logfiles are relevant to the support ticket, calling the multi-label classification machine learning model, wherein the multi-label classification machine learning model generates a list of recommended logfile types for the support ticket based on the data attributes of the support ticket;
and
displaying the list of recommended logfile types for the support ticket as the logfile recommendation for the support ticket via the user interface.

6 more elements

Dependencies are inferred from the claim text.

Logfile recommender service

Life of this patent

Logfile recommender service

Life of this patent

Abstract

Claims20