| CPC G06F 11/0793 (2013.01) [G06F 11/0787 (2013.01); G06F 16/288 (2019.01); G06F 18/22 (2023.01); G06N 20/00 (2019.01)] | 20 Claims |
|
1. A method comprising:
compiling, by a first computing device, historical incident data maintained in a database, the historical incident data representative of data of assets of an entity previously involved in one or more incidents, into:
a first incident dataset representative of the one or more incidents that were assigned at least one remediation action, wherein each remediation action was assigned to mitigate reoccurrence of a corresponding incident, and
a second incident dataset representative of the one or more incidents that were not assigned at least one remediation action;
inputting the first incident dataset into a first machine learning model trained to classify each remediation action of the first incident dataset to one of a plurality of categories;
inputting the second incident dataset into a second machine learning model trained to:
semantically match one or more first descriptions of the one or more incidents in the first incident dataset with a second description of a first incident in the second incident dataset, and
for each of the one or more first descriptions, output a score representative of a similarity of the one or more first descriptions and the second description;
mapping, based on the scores, one of the at least one remediation action to the first incident;
providing the mapped one of the at least one remediation action; and
performing the mapped one of the at least one remediation action to mitigate the first incident.
|