Automated ticket resolution

Patent metadata

Field	Value
Publication number	US-10380520-B2
Application number	US-201715645440-A
Country	US
Kind code	B2
Filing date	Jul 10, 2017
Priority date	Mar 13, 2017
Publication date	Aug 13, 2019
Grant date	Aug 13, 2019

Abstract

A device may communicate with a server to obtain historical ticket data. The device may generate a data model, based on the historical ticket data. The device may communicate with a client device to obtain ticket data relating to an issue associated with a project. The device may classify, using the data model, the ticket data into a ticket type. The device may generate, using the data model and based on the ticket type, a set of recommended resolutions for resolving the issue associated with the project. The device may select, from the set of recommended resolutions, a particular resolution based on a set of selection criteria. The device may automatically perform one or more actions to implement the particular resolution to resolve the issue associated with the project.

First claim

What is claimed is:

1. A device, comprising:
a memory storing instructions; and
one or more processors to execute the instructions to:
communicate with a server to obtain historical ticket data;
generate a plurality of data models based on processing the historical ticket data, a different data model, of the plurality of data models, being generated for a different ticket type in the historical ticket data;
communicate with a client device to obtain ticket data relating to an issue associated with a project;
classify, using a particular data model of the plurality of data models to apply a natural language processing technique, the ticket data into a first ticket type;
train the particular data model by receiving an indication as to whether to modify a classification of the ticket data from the first ticket type to a second ticket type;
modify, based on receiving the indication, the classification of the ticket data from the first ticket type to the second ticket type;
process, using the particular data model based on training the particular data model and based on modifying the classification of the ticket data, a subset of the historical ticket data;
generate, using the particular data model and based on processing the subset of the historical ticket data, a set of recommended resolutions for resolving the issue;
select, from the set of recommended resolutions, a particular resolution based on one or more values that indicate an effectiveness level of the particular resolution for one or more issues associated with the historical ticket data;
perform one or more actions to implement the particular resolution to resolve the issue,
the one or more actions being based on the issue being internal to the device and including at least one of:
an automatic generation of additional code directed to resolving the issue,
an automatic alteration of existing code of the project to produce altered code directed to resolving the issue, or
an automatic removal of existing code of the project to resolve the issue;

apply a machine learning technique to one or more of the ticket data or the historical ticket data,
the machine learning technique being applied to predict another issue;

generate additional ticket data based on predicting the other issue,
the additional ticket data being different than the ticket data or the historical ticket data; and

generate, using the particular data model, another set of recommended resolutions for resolving the other issue.

2. The device of claim 1 , where the one or more processors, when communicating with the client device to obtain the ticket data, are to:
provide, for display on the client device, a user interface that includes one or more fields associated with the ticket data, and
automatically populate at least a portion of the one or more fields associated with the ticket data by applying the natural language processing technique.

3. The device of claim 1 , where the one or more processors are further to:
parse information included in the ticket data using the natural language processing technique, and
compare the information included in the ticket data and information included in the historical ticket data, and
where the one or more processors, when classifying the ticket data into the first ticket type, are to:
automatically classify the ticket data into the first ticket type based on comparing the ticket data and the historical ticket data.

4. The device of claim 1 , where the set of recommended resolutions is a first set of recommended resolutions;
where the other set of recommended resolutions is a second set of recommended resolutions; and
where the one or more processors are further to:
determine that the particular resolution did not succeed;
obtain additional historical ticket data based on determining that the particular resolution did not succeed;
process at least a portion of the additional historical ticket data; and
generate a third set of recommended resolutions based on the portion of the additional historical ticket data.

5. The device of claim 1 , where the one or more actions include:
a determination of a developer to resolve the issue; and
a communication with the client device to provide information associated with the particular resolution and the issue to the developer to cause the issue to be resolved.

6. The device of claim 1 , where the particular resolution is a first resolution; and
where the one or more processors are to:
provide, for display via a user interface, information identifying a second resolution of the set of recommended resolutions;
detect, via the user interface, a user interaction associated with whether to implement the second resolution or another resolution of the set of recommended resolutions; and
store information associated with whether the user interface indicated to implement the second resolution or the other resolution.

7. A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the one or more processors to:
communicate with a server to obtain historical ticket data;
generate a plurality of data models based on processing the historical ticket data, a different data model, of the plurality of data models, being generated for a different ticket type in the historical ticket data;
communicate with a client device to obtain ticket data relating to an issue associated with a project;
classify, using a particular data model of the plurality of data models to apply a natural language processing technique, the ticket data into a first ticket type;
train the particular data model by receiving an indication as to whether to modify a classification of the ticket data from the first ticket type to a second ticket type;
modify, based on receiving the indication, the classification of the ticket data from the first ticket type to the second ticket type;
process, using the particular data model based on training the data model and based on modifying the classification of the ticket data, a subset of the historical ticket data;
generate, using the particular data model and based on processing the subset of the historical ticket data, a set of recommended resolutions for resolving the issue;
select, from the set of recommended resolutions, a particular resolution based on one or more values that indicate an effectiveness level of the particular resolution for one or more issues associated with the ticket data;
perform one or more actions to implement the particular resolution to resolve the issue,
the one or more actions being based on the issue being internal to the device and including at least one of:
an automatic generation of additional code directed to resolving the issue,
an automatic alteration of existing code of the project to produce altered code directed to resolving the issue, or
an automatic removal of existing code of the project to resolve the issue;

apply a machine learning technique to one or more of the ticket data or the historical ticket data,
the machine learning technique being applied to predict another issue;

generate additional ticket data based on predicting the other issue,
the additional ticket data being different than the ticket data or the historical ticket data; and

generate, using the particular data model, another set of recommended resolutions for resolving the other issue.

8. The non-transitory computer-readable medium of claim 7 , where the particular resolution is a first particular resolution; and
where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
rec

Assignees

• Accenture Global Solutions Ltd

Inventors

• Srivastava Krupa
• Koushik Vijayaraghavan
• Prasad Rajendra T
• Natesan Vijaychandar
• Pappu Rajesh
• Baikady Chetan Kumar
• Golding David
• Higgins Luke
• Whine Leon
• Zion Raanan
• Sankararaman Sunder
• Rangarajan Krishnakumar Dorai
• Selvaraj Radhu
• Paramasivam Lakshmi
• Nagarajan Udayakumar
• Narayanan Parvatha
• Athinarayanan Chandrasekhar
• Venugopal Senthil Kumar
• Rangaswamy Srinivasan

Classifications

• H04L41/5074

  Handling of user complaints or trouble tickets · CPC title

• H04L41/16

  using machine learning or artificial intelligence · CPC title

• G06Q10/06313

  Resource planning in a project environment · CPC title

• H04L41/5096

  wherein the managed service relates to distributed or central networked applications · CPC title

• G06N5/04

  Inference or reasoning models · CPC title