International Business Machines Corporation

Kyndryl, Inc.

Michael H Roehl

George E Stark

Daniel S Riley

Pawel Jasionowski

Steven J Mazzuca

Howard N Smallowitz

Daniel Grey Yates

David M Northcutt

Randall W Blondeau

A method, computer system, and a computer program product for estimating the probability of invoking information technology (IT) disaster recovery at a location based on an incident risk is provided. The present invention may include receiving a piece of data associated with an incident at the location. The present invention may also include estimating a similarity value associated with the incident based on a plurality of past incidents from a knowledge base. The present invention may then include receiving a plurality of mined data based on the location. The present invention may further include predicting the incident risk to the location based on the received plurality of mined data and the estimated similarity value to the plurality of past incidents.

Predicting the disaster recovery invocation response time

A system to provide end users with recommendations on improving the quality of the incident management process is provided. A computer device identifies a set of historical incident reports, wherein the historical incident reports identify: (i) incident tickets, (ii) one or more skills associated with personnel assigned to the incident tickets, and (iii) whether the incident tickets were resolved within threshold periods of time to resolve. The computing device trains a machine learning model to predict sets of skills associated with resolving incident tickets within the threshold periods of time to resolve based, at least in part, on the identified set of historical incident reports. The computing device assigns a set of personnel to the new incident ticket based, at least in part, on the predicted set of skills associated with resolving the new incident ticket within the threshold period of time to resolve.

Identification of incident required resolution time

A method of identifying an incident root cause probability that includes identifying, using a monitoring system, a first incident/incident class and generating, using a change management application, a first change request and change class. The method also includes generating, from the change management application, a second change request from a second incident, and where the first and second incidents are in a set of incidents, and where the first and second change requests are in a set of changes, mapping, by a cause analysis application, the set of incidents to the set of changes to identify a root cause probability, where the probability is formed by from a Galois linkage chain between the two sets, and developing, from the cause analysis application, a root cause probability value of the first incident, and executing, using a parameter management application, a mitigation process.

Incident root cause analysis using Galois connections

A method includes obtaining, by one or more processor, data related to a service level agreement for a service from a provider, wherein the service includes providing, to a client, network resources from a shared pool of network resources in a computing environment. The one or more processor utilizes the data to generate input parameters and these input parameters include target parameters for the service level agreement, penalty parameters for the service level agreement, and statistical process control parameters. The one or more processor analyzes the input parameters to model risk associated with probability of failure of the service from the provider in a given computing environment and generates and based on the risk model, allocating, by the one or more processor, a portion of the network resources.

Predictive modeling of risk for services in a computing environment

Approaches are provided for determining a risk level for server health check processing. An approach includes creating statistical process control analyzes for each of one or more servers on a network by calculating performance parameters for each of one or more servers based on historical values for one or more key process indicators of server health or vulnerability. The approach further includes collecting new values for each of the one or more key process indicators, detecting significant changes of the mean or variation in each of the one or more key process indicators, and determining a risk level for each of the one or more servers based on a number of the significant changes of the mean or variation. The approach further includes providing a health check recommendation for each of the one or more servers based on the risk level determined for each of the one or more servers.

Growing community of inventors

New Fairfield, CT, United States of America

Michael H Roehl