Artificial intelligence (AI)-based security systems for monitoring and securing physical locations
AssigneeBank of America Corporation
InventorsGeorge Anthony Albero, Nathalie Elizabeth Conley, Elizabeth Jordan Knight, Lauren Thanh Nguyen-Lo, Robert Jon Armstrong
Life of this patent
Estimating the term…
Abstract
Various aspects of the disclosure relate to monitoring a physical location to determine and/or predict anomalous activities. One or more machine learning algorithms may be used to analyze inputs from one or more sensors, cameras, audio recording equipment, and/or any other types of sensors to detect anomalous measurements/patterns. Notifications may be sent one or more devices in a network based on the detection.
Claims19
An artificial intelligence (AI)-based system for monitoring and securing a retail banking physical location based on measurements of gas concentrations, the retail banking physical location having an entrance, a vault, and a teller window, the system comprising:
- one or more gas sensors installed near an entrance of the retail banking physical location for measuring gas concentrations of a plurality of target gases at the retail banking physical location at a plurality of times;
- and
- an electronic monitoring platform communicatively coupled to the one or more gas sensors, the electronic monitoring platform comprising:
- at least one processor;
- a communication interface communicatively coupled to the at least one processor;
- and
- memory storing computer-readable instructions that, when executed by the at least one processor, cause the electronic monitoring platform to:
- receive, via the communication interface and from the one or more gas sensors, measurements of gas concentrations of the plurality of target gases at the plurality of times at the entrance of the retail banking physical location;
- train, based on the gas concentrations at the plurality of times, an AI model of gas concentrations of the plurality of target gases;
- predict, based on the AI model, gas concentrations of the plurality of target gases for a time T1;
- receive, from the one or more gas sensors and for the time T1, a second measurement of gas concentrations of the plurality of target gases at the entrance of the retail banking physical location;
- determine, based on the predicted gas concentrations and the second measurement, that a gas concentration of a target gas for the time T1 is anomalous;
- and
- based on the determining, send, via the communication interface;
- a first notification to a locking mechanism of the vault at the retail banking physical location, wherein sending the first notification to the locking mechanism causes the vault to lock based on receiving the first notification;
- and
- a second notification a controller of a heating, ventilating and air conditioning (HVAC) system, wherein sending the second notification causes the controller to change a rotational speed of a fan of the HVAC system.
A method for monitoring and securing a retail banking physical location based on gas concentration measurements, the retail banking physical location having an entrance, a vault, and a teller window, the method comprising:
- receiving, from one or more gas sensors installed near an entrance of the retail banking physical location, measurements of gas concentrations of a plurality of target gases at a plurality of times at the entrance of the retail banking physical location;
- training, based on the gas concentrations at the plurality of times, an AI model of gas concentrations of the plurality of target gases;
- predicting, based on the AI model, gas concentrations of the plurality of target gases for a time T1;
- receiving, from the one or more gas sensors and for the time T1, a second measurement of gas concentrations of the plurality of target gases at the entrance of the retail banking physical location;
- determining, based on the predicted gas concentrations and the second measurement, that a gas concentration of a target gas for the time T1 is anomalous;
- and
- based on the determining, sending:
- a first notification to a locking mechanism of the vault at the retail banking physical location, wherein sending the first notification to the locking mechanism causes the vault to lock based on receiving the first notification;
- and
- a second notification a controller of a heating, ventilating and air conditioning (HVAC) system, wherein sending the second notification causes the controller to change a rotational speed of a fan of the HVAC system.
A non-transitory computer-readable medium storing computer-executable instructions that, when executed by a computer processor, causes a computing platform to:
- receive, from one or more gas sensors installed near an entrance of a retail banking physical location, measurements of gas concentrations of a plurality of target gases at a plurality of times, wherein the retail banking physical location incudes the entrance, a vault, and a teller window;
- train, based on the gas concentrations at the plurality of times, an artificial intelligence (AI) model of gas concentrations of the plurality of target gases;
- predict, based on the AI model, gas concentrations of the plurality of target gases for a time T1;
- receive, from the one or more gas sensors and for the time T1, a second measurement of gas concentrations of the plurality of target gases at the entrance of the retail banking physical location;
- determine, based on the predicted gas concentrations and the second measurement, that a gas concentration of a target gas for the time T1 is anomalous;
- and
- based on the determining, send:
- a first notification to a locking mechanism of the vault at the retail banking physical location, wherein sending the first notification to the locking mechanism causes the vault to lock based on receiving the first notification;
- and
- a second notification a controller of a heating, ventilating and air conditioning (HVAC) system, wherein sending the second notification causes the controller to change a rotational speed of a fan of the HVAC system.
Dependencies are inferred from the claim text.