US 12,244,612 B2
Automated incident response process and automated actions
Apurva Mohan, Sugar Land, TX (US); Himali Saxena, Sugar Land, TX (US); and Gian-Marcio Gey, Houston, TX (US)
Assigned to SCHLUMBERGER TECHNOLOGY CORPORATION, Sugar Land, TX (US)
Filed by SCHLUMBERGER TECHNOLOGY CORPORATION, Sugar Land, TX (US)
Filed on Mar. 27, 2020, as Appl. No. 16/833,257.
Claims priority of provisional application 62/824,749, filed on Mar. 27, 2019.
Prior Publication US 2020/0344249 A1, Oct. 29, 2020
Int. Cl. H04L 29/06 (2006.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); H04L 9/40 (2022.01)
CPC H04L 63/1416 (2013.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method of performing a computer network action, comprising:
receiving data from at least one industrial internet of things (IIOT) device located in a field;
performing at least one artificial intelligence analysis of the data received from the at least one IIOT device;
determining presence of a fault condition or event on a network with the data based on the at least one artificial intelligence analysis of the data received from the at least one IIOT device;
prioritizing a risk of the fault condition or event over a plurality of additional risks associated with a plurality of additional fault conditions or events;
when the fault condition or event is present, performing an automated action in response to the fault condition or event through the artificial intelligence analysis, wherein the automated action involves changing at least one parameter of the network and at least one parameter of the at least one IIOT device, wherein the automated action is specified and triggered by running a playbook of a plurality of playbooks on a computer-based system that includes a neural network, wherein the neural network is configured to predict the automated action for the fault condition or event with learning capability developed over time, wherein the neural network is configured to assign different weights to a plurality of different fault conditions or events on the network, wherein the neural network is configured to modify the different weights over time based on threat levels of security threats, wherein the plurality of playbooks is set in a hierarchy based on the threat levels of the security threats; and
continuing to receive further data from the at least one Internet connected IIOT device located in the field, when the fault condition or event is not present.