Artificial intelligence with cyber security
AssigneeNautilus TRUE, LLC
InventorArnold Castillo Magcale
Life of this patent
Estimating the term…
Abstract
A cyber security system that uses artificial intelligence, such neural networks, to monitor the security of a computer network and take automated remedial action based on the monitoring. The security system autonomically learns behavior profiles, attack profiles and circumvention techniques used to target the network. The remedial action taken by the system includes isolating any misuse that has been identified, surveilling the misuse in the isolated environment, analyzing its behavior profile and reconfiguring the network to enhance security.
Claims16
A computer implemented method comprising:
- aggregating data from a plurality of physical sensors coupled to a cooling system comprising a controller and connected to a computer automated system over a network, wherein aggregating data comprises collecting data over the network from a plurality of appliances and application layers;
- based on the aggregated data, estimating an energy efficiency of the cooling system with reference to a plurality of pre-defined parameters;
- based on the estimated energy efficiency with reference to the plurality of pre-defined parameters, initiating a single or plurality of calibrations to the cooling system via the controller such that the energy efficiency matches the plurality of pre-defined parameters, wherein the plurality of pre-defined parameters are based on an optimal energy efficiency range;
- estimating based on the collected data and on pre-determined criteria, a single or plurality of remedial actions for the corresponding plurality of appliances, wherein the estimation of the single or plurality of remedial actions is derived from an artificial neural network implementation;
- sending the estimated single or plurality of remedial actions to the corresponding plurality of application layers over the network;
- based on a verification by the plurality of application layers against a plurality of pre-defined local parameters, triggering the estimated single or plurality of remedial actions to the corresponding appliances;
- autonomically learning a behavior profile of the plurality of appliances via the corresponding plurality of application layers based on the triggered estimated single or plurality of remedial actions;
- and
- based on the learned behavior profile, predicting a future energy efficiency of the plurality of appliances.
A computer automated system comprising a hardware processor coupled to a memory element having encoded instructions thereon, which encoded instructions implemented by the hardware processor cause the computer automated system to:
- aggregate data from a plurality of physical sensors coupled to a cooling system comprising a controller and connected to the computer automated system over a network, wherein aggregating data comprises collecting data over the network from a plurality of appliances and application layers;
- based on the aggregated data, estimate an energy efficiency of the cooling system with reference to a plurality of pre-defined parameters;
- based on the estimated energy efficiency with reference to the plurality of pre-defined parameters, initiate a single or plurality of calibrations to the cooling system via the controller such that the energy efficiency matches the plurality of pre-defined parameters, wherein the plurality of pre-defined parameters are based on an optimal energy efficiency range;
- in initiating the single or plurality of calibrations for the cooling system, estimate based on the collected data and on pre-determined criteria, a single or plurality of remedial actions for the corresponding plurality of appliances, wherein the estimation of the single or plurality of remedial actions is derived from an artificial neural network implementation;
- and
- send the estimated single or plurality of remedial actions to the corresponding plurality of application layers over the network;
- based on a verification by the plurality of application layers against a plurality of pre-defined local parameters, trigger the estimated single or plurality of remedial actions to the corresponding appliances;
- autonomically learn a behavior profile of the plurality of appliances via the corresponding plurality of application layers based on the triggered estimated single or plurality of remedial actions;
- and
- based on the learned behavior profile, predict a future energy efficiency of the plurality of appliances.
Dependencies are inferred from the claim text.