Back to results
US 12,647,332 B2Granted
Apparatuses, methods, and computer program products for predictive determinations of causal change identification for service incidents
AssigneesAtlassian Pty Ltd., Atlassian US, Inc.
InventorChristopher Mann
Life of this patent
Estimating the term…
Abstract
Methods, apparatuses, or computer program products provide for generating a predictive causal probability score data object. A complex federated service network may be monitored to identify a service incident data object associated with a service incident. A predictive causal machine learning model may generate a predictive causal probability score data object based at least in part on a service incident time associated with the service incident data object. The predictive causal probability score data object may be output.
Claims20
An apparatus comprising at least one processor and at least one memory, the at least one memory having computer-coded instructions therein, wherein the computer-coded instructions are configured to, in execution with the at least one processor, cause the apparatus to:
- identify a service incident data object associated with a service incident and a service incident time, the service incident data object comprising an impacted service identifier and one or more upstream service identifiers;
- generate, using a predictive causal machine learning model, a predictive causal probability score data object based at least in part on the service incident time associated with the service incident data object, wherein (i) the predictive causal probability score data object describes at least one predictive causal probability score, (ii) the at least one predictive causal probability score is indicative of a probability at least one corresponding service change or upstream service change is a cause contributor of the service incident described by the service incident data object, and (iii) the at least one predictive causal probability score is based at least in part on a risk assessment value for the at least one corresponding service change or upstream service change, wherein the risk assessment value is determined based at least in part on (i) an incident history of one or more affected services associated with the at least one corresponding service change or upstream service change and (ii) a conflicting change associated with a change time window corresponding to the at least one service change or upstream service change;
- cause generation of a causal change analysis interface based on the predictive causal probability score data object, wherein the causal change analysis interface comprises:
- a service incident element that describes at least one impacted service or upstream service, and
- a user interactable element rendered in association with at least one service change or upstream service change, wherein the at least one service change or upstream service change is identified according to the at least one predictive causal probability score;
- receive a user interaction via the user interactable element of the causal change analysis interface, wherein the user interaction indicates a modification of the at least one impacted service or upstream service;
- and
- update the at least one impacted service or upstream service to reflect the modification as indicated by the user interaction received via the user interactable element.
5 more elements
A computer-implemented method comprising:
- identifying, using one or more processors, a service incident data object associated with a service incident and a service incident time, the service incident data object comprising an impacted service identifier and one or more upstream service identifiers;
- generating, using the one or more processors and a predictive causal machine learning model, a predictive causal probability score data object based at least in part on the service incident time associated with the service incident data object, wherein (i) the predictive causal probability score data object describes at least one predictive causal probability score, (ii) the at least one predictive causal probability score is indicative of a probability a corresponding service change or upstream service change is a cause contributor of the service incident described by the service incident data object, and (iii) the at least one predictive causal probability score is based at least in part on a risk assessment value for the corresponding service change or upstream service change, wherein the risk assessment value is determined based at least in part on (i) an incident history of one or more affected services associated with the at least one corresponding service change or upstream service change and (ii) a conflicting change associated with a change time window corresponding to the at least one service change or upstream service change;
- causing generation of a causal change analysis interface based on the predictive causal probability score data object, wherein the causal change analysis interface comprises:
- a service incident element that describes at least one impacted service or upstream service, and
- a user interactable element rendered in association with at least one service change or upstream service change, wherein the at least one service change or upstream service change is identified according to the at least one predictive causal probability score;
- receiving a user interaction via the user interactable element of the causal change analysis interface, wherein the user interaction indicates a modification of the at least one impacted service or upstream service;
- and
- updating the at least one impacted service or upstream service to reflect the modification as indicated by the user interaction received via the user interactable element.
5 more elements
A computer program product comprising at least one memory, the at least one memory having computer-coded instructions therein, wherein the computer-coded instructions comprise instructions to:
- identify a service incident data object associated with a service incident and a service incident time, the service incident data object comprising an impacted service identifier and one or more upstream service identifiers;
- generate, using a predictive causal machine learning model, a predictive causal probability score data object based at least in part on the service incident time associated with the service incident data object, wherein (i) the predictive causal probability score data object describes at least one predictive causal probability score, (ii) the at least one predictive causal probability score is indicative of a probability a corresponding service change or corresponding upstream service change is a cause contributor of the service incident described by the service incident data object, and (iii) the at least one predictive causal probability score is based at least in part on a risk assessment value for the corresponding service change or upstream service change, wherein the risk assessment value is determined based at least in part on (i) an incident history of one or more affected services associated with the at least one corresponding service change or upstream service change and (ii) a conflicting change associated with a change time window corresponding to the at least one service change or upstream service change;
- cause generation of a causal change analysis interface based on the predictive causal probability score data object, wherein the causal change analysis interface comprises:
- a service incident element that describes at least one impacted service or upstream service, and
- a user interactable element rendered in association with at least one service change or upstream service change, wherein the at least one service change or upstream service change is identified according to the at least one predictive causal probability score;
- receive a user interaction via the user interactable element of the causal change analysis interface, wherein the user interaction indicates a modification of the at least one impacted service or upstream service;
- and
- update the at least one impacted service or upstream service to reflect the modification as indicated by the user interaction received via the user interactable element.
5 more elements
Dependencies are inferred from the claim text.