System and method for a cognitive it change request evaluator

Patent metadata

Field	Value
Publication number	US-11093882-B2
Application number	US-201715823968-A
Country	US
Kind code	B2
Filing date	Nov 28, 2017
Priority date	Nov 28, 2017
Publication date	Aug 17, 2021
Grant date	Aug 17, 2021

Abstract

The present invention is a system and method for evaluating an IT change request system based on cognitive and machine learning technologies. The system includes a computing device having a change request evaluator based on a machine learning trained model and in digital communication with a server. A historical database stores change records and a definitions database stores a definition for words appearing in the change records. A change request is received at the change request evaluator, which finds a model change record by comparing the change request to the change records in the historical database and identifying definitions common to both the change request and the change record. A business mapping tool interfaces with the change request evaluator and determines a business impact of the model change record and associates the business impact with the change request. The change request evaluator approves or rejects the change request.

First claim

What is claimed is:

1. A computer system for evaluating an IT change request, comprising:
one or more computer processors;
one or more computer readable storage media;
computer program instructions, the computer program instructions being stored on the one or more computer readable storage media for execution by the one or more computer processors, and the computer program instructions including instructions to:
receive a change request associated with a computing device at a cognitive change request system based on a machine learning model having one or more learned change approval policies, wherein the change request includes at least a date, and a time period at which a change to the computing device will occur, and a change recipe;
generate a change request record for the change request;
determine whether the change recipe included in the change request can be performed at the date and time period specified in the change request based, at least in part, on instructions to:
determine whether the change request has any technical impact on any change records already created for the computing device, based on natural language processing of the change request and any change records already created for the computing device;
responsive to determining the change request does not have any technical impact on any change records already created for the computing device, determine whether a same type of change request as the generated change request was previously successfully executed, based on comparing one or more previous change records from historical data;
generating a new change recipe for the change request based, at least in part on a determination that the same type of change request was not successfully executed;

approve the change request with the new change recipe; and
retraining the one or more learned change approval policies for the machine learning model of the cognitive change request system with the change request record including the new change recipe within a change records database.

2. The computer system of claim 1 , further comprising instructions to:
execute the approved change request associated with the computing device during the time period and on the date specified in the change request.

3. The computer system of claim 1 , wherein the change request presents a technical impact on a change record already created for the computing device based, at least in part, on identifying a sub-component of the computing device included in both the change request and the change record already created for the computing device.

4. The computer system of claim 1 , wherein the program instructions to approve the change request is further based on instructions to:
determine that the time period and the date at which the change to the computing device will occur do not conflict with a predetermined change freeze period associated with the computing device.

5. The computer system of claim 1 , wherein the program instructions to approve the change request is further based on instructions to:
determine that the time period and the date at which the change to the computing device will occur do not conflict with a service level agreement (SLA) associated with the computing device.

6. The computer system of claim 1 , wherein the program instructions to approve the change request is further based on instructions to:
identify a business impact associated with the change request; and
determine that the business impact associated with the change request is below a predetermined threshold.

7. A computer program product for evaluating an IT change request, the computer program product comprising one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions including instructions to:
receive a change request associated with a computing device at a cognitive change request system, based on a machine learning model having one or more learned change approval policies, wherein the change request includes at least a date, and a time period at which a change to the computing device will occur, and a change recipe;
generate a change request record for the change request;
determine whether the change recipe included in the change request can be performed at the date and time period specified in the change request based, at least in part, on instructions to:
determine whether the change request has any technical impact on any change records already created for the computing device, based on natural language processing of the change request and any change records already created for the computing device;
responsive to determining the change request does not have any technical impact on any change records already created for the computing device, determine whether a same type of change request as the generated change request was previously successfully executed, based comparing on one or more previous change records from historical data;
generating a new change recipe for the change request based, at least in part on a determination that the same type of change request was not successfully executed;

approve the change request with the new change recipe; and
retraining the one or more learned change approval policies for the machine learning model of the cognitive change request system with the change request record including the new change recipe within a change records database.

8. The computer program product of claim 7 , further comprising instructions to:
execute the approved change request associated with the computing device during the time period and on the date specified in the change request.

9. The computer program product of claim 7 , wherein the change request presents a technical impact on a change record already created for the computing device based, at least in part, on identifying a sub-component of the computing device included in both the change request and the change record already created for the computing device.

10. The computer program product of claim 7 , wherein the program instructions to approve the change request is further based on instructions to:
determine that the time period and the date at which the change to the computing device will occur do not conflict with a predetermined change freeze period associated with the computing device.

11. The computer program product of claim 7 , wherein the program instructions to approve the change request is further based on instructions to:
determine that the time period and the date at which the change to the computing device will occur do not conflict with a service level agreement (SLA) associated with the computing device.

12. The computer program product of claim 7 , wherein the program instructions to approve the change request is further based on instructions to:
identify a business impact associated with the change request; and
determine that the business impact associated with the change request is below a predetermined threshold.

13. A computer-implemented method for evaluating an IT change request, comprising:
receiving a change request associated with a computing device at a cognitive change request system, based on a machine learning model having one or more learned change approval policies, wherein the change request includes at least a date, and a time period at which a change to the computing device will occur, and a change recipe;
generating a change request record for the change request;
determining whether the change recipe included in the change request can be performed at the date and time period specified in the change request based, at least in part, on

Assignees

• IBM

Inventors

• Rotta Thiago Cesar
• Sant Ana Monteiro Torres Antonio Manuel
• Varga Sergio

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F16/2358

  Change logging, detection, and notification (replication G06F16/27) · CPC title

• G06Q10/067

  Enterprise or organisation modelling · CPC title

• G06Q10/06375 Primary

  Prediction of business process outcome or impact based on a proposed change · CPC title