Search

US-12621667-B2 - Method of camera capturing signal controlled by security gateway

US12621667B2US 12621667 B2US12621667 B2US 12621667B2US-12621667-B2

Abstract

Techniques for improving alarm event detection for security systems are described herein. For example, a security system can receive a first set of data associated with an event in an environment from a first detection device. The security system can instruct a second detection device to detect a second set of data for the environment based on the first set of data. The security system can determine an alarm status for the event based at least in part on a condition of the event output by an artificial intelligence model. The artificial intelligence model can output the condition responsive to receiving an input including the first set of data and the second set of data. The alarm status can include a false alarm event or an alarm event. The security system can output an alarm indicating the event based on determining that the alarm status is an alarm event.

Inventors

  • Lap Tak Tang
  • Barrett Morgan

Assignees

  • Syber Sense IP Holdings, LLC

Dates

Publication Date
20260505
Application Date
20230306

Claims (20)

  1. 1 . A computer-implemented method, comprising: receiving, from a first detection device, a first set of data associated with an event detected by the first detection device in an environment; in response to receiving the first set of data: instructing a camera to detect data for the environment based at least in part on the first set of data; subsequent to instructing the camera to detect data, receiving, from the camera, a second set of data associated with the event; determining an alarm status for the event based at least in part on a condition of the event output by an artificial intelligence model, the artificial intelligence model configured to output the condition responsive to receiving an input comprising the first set of data and the second set of data, the alarm status comprising a false alarm event or an alarm event; and outputting an alarm indicating the event based on determining that the alarm status is the alarm event.
  2. 2 . The computer-implemented method of claim 1 , further comprising: determining that the alarm status for the event is the false alarm event based at least in part on the condition; and based on determining that the alarm status for the event is the false alarm event, forgoing outputting the alarm indicating the event.
  3. 3 . The computer-implemented method of claim 1 , further comprising: determining a recipient of the alarm based on a type of the event indicated by the condition; and outputting the alarm indicating the event to the recipient.
  4. 4 . The computer-implemented method of claim 1 , wherein the artificial intelligence model comprises a model of user behavior for a user associated with the environment, the user behavior detected by the first detection device and the camera, and wherein the artificial intelligence model is configured to generate the condition by comparing the first set of data and the second set of data to the model of user behavior.
  5. 5 . The computer-implemented method of claim 1 , further comprising: updating the artificial intelligence model using the first set of data and the second set of data in association with the condition.
  6. 6 . The computer-implemented method of claim 1 , wherein the artificial intelligence model is configured to output a probability that the event has occurred to the first detection device in response to the first detection device inputting the first set of data into the artificial intelligence model, and wherein the first set of data is received from the first detection device responsive to the first detection device detecting the event based at least in part on the probability.
  7. 7 . The computer-implemented method of claim 1 , wherein instructing the camera to detect data occurs responsive to: inputting the first set of data into the artificial intelligence model; and determining, based on the condition output by the artificial intelligence model responsive to inputting the first set of data, that further data is needed to determine the alarm status.
  8. 8 . A system, comprising: a first detection device configured to detect data in an environment; a camera configured to detect data in the environment; and a security gateway comprising a processor and a memory configured to store computer-executable instructions, the processor configured to access the memory and execute the computer-executable instructions to at least: receive, from the first detection device, a first set of data associated with an event detected by the first detection device in the environment; in response to receiving the first set of data: instruct the camera to detect data for the environment based at least in part on the first set of data; subsequent to instructing the camera to detect data, receive, from the camera, a second set of data associated with the event; determine an alarm status for the event based at least in part on a condition of the event output by an artificial intelligence model, the artificial intelligence model configured to output the condition responsive to receiving an input comprising the first set of data and the second set of data, the alarm status comprising a false alarm event or an alarm event; and output an alarm indicating the event based on determining that the alarm status is the alarm event.
  9. 9 . The system of claim 8 , wherein the memory is configured to store additional computer-executable instructions, and the processor is configured to execute the additional computer-executable instructions to: determine that the alarm status for the event is the false alarm event based at least in part on the condition; and based on determining that the alarm status for the event is the false alarm event, forgo generating the alarm indicating the event.
  10. 10 . The system of claim 8 , wherein the instructions are further executable by the processor for causing the processor to: determine a recipient of the alarm based on a type of the event indicated by the condition; and output the alarm indicating the event to the recipient.
  11. 11 . The system of claim 8 , wherein the artificial intelligence model comprises a model of user behavior for the environment, the user behavior detected by the first detection device and the camera, and wherein the artificial intelligence model is configured to generate the condition by comparing the first set of data and the second set of data to the model of user behavior.
  12. 12 . The system of claim 8 , wherein the memory is configured to store additional computer-executable instructions, and the processor is configured to execute the additional computer-executable instructions to: update the artificial intelligence model using the first set of data and the second set of data in association with the condition.
  13. 13 . The system of claim 8 , wherein the memory is configured to store additional computer-executable instructions, and the processor is configured to execute the additional computer-executable instructions to instruct the camera to detect data responsive to: inputting the first set of data into the artificial intelligence model; and determining, based on the condition output by the artificial intelligence model responsive to inputting the first set of data, that further data is needed to determine the alarm status.
  14. 14 . The system of claim 8 , wherein the first detection device comprises at least one of a position sensor, a motion sensor, a light sensor, or a liquid detection sensor.
  15. 15 . The system of claim 8 , wherein in response receiving the first set of data, the security gateway changes a gateway operating state corresponding to a device operating state of the first detection device, the gateway operating state and the device operating state comprising at least one of an arm state, an arm away, or a disarm state.
  16. 16 . One or more non-transitory computer-readable storage media comprising computer-executable instructions that, when executed by one or more processors of a computer system, cause the computer system to perform operations comprising: receiving, from a first detection device, a first set of data associated with an event detected by the first detection device in an environment; in response to receiving the first set of data: instructing a camera to detect data for the environment based at least in part on the first set of data; subsequent to instructing the camera to detect data, receiving, from the camera, a second set of data associated with the event; determining an alarm status for the event based at least in part on a condition of the event output by an artificial intelligence model, the artificial intelligence model configured to output the condition responsive to receiving an input comprising the first set of data and the second set of data, the alarm status comprising a false alarm event or an alarm event; and outputting an alarm indicating the event based on determining that the alarm status is the alarm event.
  17. 17 . The one or more non-transitory computer-readable storage media of claim 16 , further comprising computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to: determine that the alarm status for the event is the false alarm event based at least in part on the condition; and based on determining that the alarm status for the event is the false alarm event, forgo outputting the alarm indicating the event.
  18. 18 . The one or more non-transitory computer-readable storage media of claim 16 , wherein the artificial intelligence model comprises a model of user behavior for a user associated with the environment, the user behavior detected by the first detection device and the camera, and wherein the artificial intelligence model is configured to generate the condition by comparing the first set of data and the second set of data to the model of user behavior.
  19. 19 . The one or more non-transitory computer-readable storage media of claim 16 , further comprising computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to: update the artificial intelligence model using the first set of data and the second set of data in association with the condition.
  20. 20 . The one or more non-transitory computer-readable storage media of claim 16 , wherein the artificial intelligence model is configured to output a probability that the event has occurred to the first detection device in response to the first detection device inputting the first set of data into the artificial intelligence model, and wherein the first set of data is received from the first detection device responsive to the first detection device detecting the event based at least in part on the probability.

Description

CROSS-REFERENCE TO RELATED APPLICATION This claims the benefit of priority of U.S. Provisional Patent Application No. 63/316,640, titled “A Method Of Camera Capturing Signal Controlled By Security Gateway” and filed Mar. 4, 2022, the entirety of which is incorporated herein by reference. BACKGROUND Home security systems can include various devices for detecting objects and/or people. For example, home security systems can include cameras, motion sensors, and heat sensors. The devices can send a signal to a hub when a disturbance is detected. For example, when a person is detected in a house or a there is heat from a fire, the devices can signal the hub. The hub can trigger an alarm and/or alert authorities based on the signal received from the devices. However, the hub can trigger the alarm and/or alert authorities when there is no actual disturbance or when the disturbance is minor. This can result in users ignoring the alarms and not taking appropriate actions and/or authorities being slow to respond to alarms. BRIEF DESCRIPTION OF THE DRAWINGS Various embodiments in accordance with the present disclosure will be described with reference to the drawings, in which: FIG. 1 illustrates an example home security system, according to embodiments of the present disclosure; FIG. 2 illustrates an example communication diagram for a home security system, according to embodiments of the present disclosure; FIG. 3 shows an example data flow for a home security system, according to embodiments of the present disclosure; FIG. 4 shows another example data flow for the home security system, according to embodiments of the present disclosure; FIG. 5 illustrates an example detection device receiving an event notification from a security gateway, according to embodiments of the present disclosure; FIG. 6 illustrates an example security gateway receiving a signal from a detection device, according to some embodiments of the present disclosure; FIG. 7 illustrates an example detection device, according to embodiments of the present disclosure; FIG. 8 illustrates an example security gateway, according to embodiments of the present disclosure; FIG. 9 illustrates an example process after a detection device receives a signal from a security gateway, according to embodiments of the present disclosure; FIG. 10 is an example flow chart of an alarm process, according to embodiments of the present disclosure; FIG. 11 illustrates a block diagram of an example security system, according to embodiments of the present disclosure; and FIG. 12 is an example flow chart of a process for generating an alarm based on an event, according to embodiments of the present disclosure. DETAILED DESCRIPTION Home security systems can include various devices for detecting objects and/or people. For example, home security systems can include detection devices (e.g., cameras, motion sensors, and/or heat sensors). The detection devices can send a signal to a hub when a disturbance is detected. For example, when a person is detected in a house or a there is heat from a fire, the detection devices can send a detection signal to the hub. In traditional home security systems, the various detection devices work independently to detect events and send detection signals to the hub. In these traditional systems, a detection device can send a detection signal to a hub. The hub can receive the signal and send an alert based on the one signal. However, because the hub sends the alert based off of a signal from one detection device, the hub can send alarms for minor disturbances that may not necessitate an alarm (e.g., false alarms). For example, a single smoke detector may send a detection signal to the hub that smoke has been detected and the hub can send a fire alarm (e.g., an alarm alerting the local authorities, a monitoring station, and/or homeowner that there is a fire). However, this smoke may be from burning food and/or candles and not from an actual fire. These false alarms can impact a user's confidence in their home security system and may cause the user and/or local authorities to ignore alarms and/or respond slowly to alarms, which could impact the user's safety. Additionally, traditional home security systems may fail to fully capture the details of a detected event. For example, the system can include a detection device (e.g., a door sensor and/or a window sensor) that can detect that a window or door has been opened and/or a window has been broken. However, the detection devices that detect the event may not include a camera and would be unable to capture the identity of a potential intruder. Alternatively, the security system may include a camera separate from the door and/or window sensors. However, the activation of the door and/or window sensor may not the camera to activate and record the event. An example home security system can include one or more detection devices that can communicate with a hub. The detection devices can capture (e.g., record)