Automated system for predicting software application framework deployment changes for incident mitigation
Automated system for predicting software application framework deployment changes for incident mitigation is provided. An incident indication for an incident may be received. One or more incident features associated with the incident may be extracted. One or more data objects associated with the incident may be identified based on the one or more incident features. Candidate incident mitigation dataset comprising a plurality of incident mitigating predictions may be generated based on relation data and a topology graph structure associated with the one or more data objects. A ranked candidate incident mitigation dataset may be generated using one or more ranking models. One or more incident mitigating predictions from the ranked candidate incident mitigation dataset may be selected based on a rank value associated with each of the one or more incident mitigating predictions.
1 . An apparatus for generating incident mitigating predictions, the apparatus comprising at least one processor and at least one memory including program code, the at least one memory and the program code configured to, with the at least one processor, cause the apparatus to at least:
receive an incident indication for an incident;
extract one or more incident features associated with the incident;
identify, based on the one or more incident features, one or more data objects associated with the incident;
generate, based on relation data and a topology graph structure associated with the one or more data objects, candidate incident mitigation dataset comprising a plurality of incident mitigating predictions;
generate, using one or more ranking models, a ranked candidate incident mitigation dataset;
select one or more incident mitigating predictions from the ranked candidate incident mitigation dataset based on a rank value associated with each of the one or more incident mitigating predictions; and
cause rendering of an incident mitigation interface to a user device display, wherein the incident mitigation interface comprises at least a portion of the one or more incident mitigating predictions, and the one or more incident mitigating predictions comprises one or more code deployment modification recommendations.
2 . The apparatus of claim 1 , wherein the one or more data objects comprise an affected service data object and one or more connected data objects.
3 . The apparatus of claim 2 , wherein the at least one memory and the program code are configured to, with the at least one processor, to cause the apparatus to identify the one or more data objects by:
identifying, based on the one or more incident features, the affected service data object; and
identifying, using a one or more machine learning models and based on the affected service data object, at least a portion of the one or more connected data objects.
4 . The apparatus of claim 2 , wherein the at least one memory and the program code are configured to, with the at least one processor, to cause the apparatus to identify the one or more data objects by:
identifying, based on the one or more incident features, the affected service data object; and
identifying, using a service dependency graph structure and based on the affected service data object, at least a portion of the one or more connected data objects.
5 . The apparatus of claim 2 , wherein the at least one memory and the program code are further configured to, with the at least one processor, cause the apparatus to:
generate, using one or more machine learning models and based on the affected service data object and the one or more connected data objects, the relation data.
6 . The apparatus of claim 1 , wherein the one or more ranking models comprise a learning-to-rank model.
7 . The apparatus of claim 6 , wherein the at least one memory and the program code are configured to, with the at least one processor, cause the apparatus to generate the ranked candidate incident mitigation dataset based on user-generated content associated with the one or more data objects and using the learning-to-rank model.
8 . The apparatus of claim 1 , wherein the at least one memory and the program code are configured to, with the at least one processor, cause the apparatus to further generate the ranked candidate incident mitigation dataset based on incident feedback received from a client computing device.
9 . The apparatus of claim 1 , wherein the at least one memory and the program code are configured to, with the at least one processor, to cause the apparatus to extract the one or more incident features using a feature extraction model and based on an incident data object associated with the incident.
10 . A computer-implemented method for generating incident mitigating predictions, the computer-implemented method comprising:
receiving an incident mitigation request for an incident;
extracting one or more incident features associated with the incident;
identifying, based on the one or more incident features, one or more data objects associated with the incident;
generating, based on relation data, topology graph structure, and historical service-related modifications associated with the one or more data objects, candidate incident mitigation dataset comprising a plurality of incident mitigating predictions;
generating, using one or more ranking models, a ranked candidate incident mitigation dataset;
selecting one or more incident mitigating predictions from the ranked candidate incident mitigation dataset based on a rank value associated with each of the one or more incident mitigating predictions; and
causing rendering of an incident mitigation interface to a user device display, wherein the incident mitigation interface comprises at least a portion of the one or more incident mitigating predictions, and the one or more incident mitigating predictions comprises one or more code deployment modification recommendations.
11 . The computer-implemented method of claim 10 , wherein the one or more data objects comprise an affected service data object and one or more connected data objects.
12 . The computer-implemented method of claim 11 , wherein identifying the one or more data objects comprises:
identifying, based on the one or more incident features, the affected service data object; and
identifying, using a one or more machine learning models and based on the affected service data object, at least a portion of the one or more connected data objects.
13 . The computer-implemented method of claim 11 , wherein identifying the one or more data objects comprises:
identifying, based on the one or more incident features, the affected service data object; and
identifying, using a service dependency graph structure and based on the affected service data object, at least a portion of the one or more connected data objects.
14 . The computer-implemented method of claim 11 , further comprising:
generating, using one or more machine learning models and based on the affected service data object and the one or more connected data objects, the relation data.
15 . The computer-implemented method of claim 10 , wherein the one or more ranking models comprise a learning-to-rank model.
16 . The computer-implemented method of claim 15 , wherein generating the ranked candidate incident mitigation dataset further comprises generated the ranked candidate incident mitigation dataset based on user-generated content associated with the one or more data objects and using the learning-to-rank model.
17 . The computer-implemented method of claim 10 , wherein generating the ranked candidate incident mitigation dataset further comprises generating the ranked candidate incident mitigation dataset based on incident feedback received from a client computing device.
18 . At least one non-transitory computer-readable storage medium for generating incident mitigating predictions, the at least one non-transitory computer-readable storage medium having computer coded instructions configured to, when executed by at least one processor:
receive an incident indication for an incident;
identify, based on one or more incident features of the incident, one or more data objects associated with the incident;
generate, based on topology graph structure and historical service-related modifications associated with the one or more data objects, candidate incident mitigation dataset comprising a plurality of incident mitigating predictions;
generate, using a learning-to-rank-model, a ranked candidate incident mitigation dataset;
select one or more incident mitigating predictions from the ranked candidate incident mitigation dataset based on a rank value associated with each of the one or more incident mitigating predictions; and
cause rendering of an incident mitigation interface to a user device display, wherein the incident mitigation interface comprises at least a portion of the one or more incident mitigating predictions, and the one or more incident mitigating predictions comprises one or more code deployment modification recommendations.