IP Library Granted Patent US 10,565,838
Granted Patent B2
US 10,565,838 · App. 16/269,472 · Granted Feb 18, 2020

Building access control system with complex event processing

Inventors: Donagh S Horgan (Cork, IE); Jan R Holliday (Maryville, IL); Eamonn O'Toole (Cork, IE)
Assignee: Johnson Controls Technology Company
G08B13/08G06N20/00G07C9/00103G08B13/04G08B25/001G08B29/16G08B29/185
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,565,838
App. No.
16/269,472
Granted
Feb 18, 2020
Kind
B2
Abstract

A method for controlling access to at least a portion of a building includes providing a temporal model identifying relationships between a first set of access control events based on times at which the first set of access control events occurred, providing a spatial model identifying relationships between a second set of access control events based on locations associated with the second set of access control events, providing a user model identifying patterns of user behavior based on a third set of access control events, receiving a fourth set of access control events comprising time data, and location data, and user data associated with the access control events, and determining whether to generate alarms responsive to receiving the fourth set of access control events using the temporal model, the spatial model, and the user model.

Claims (42)

1. A method for controlling access to at least a portion of a building, the method comprising:

providing a temporal model identifying relationships between a first set of access control events based on times at which the first set of access control events occurred;

providing a spatial model identifying relationships between a second set of access control events based on locations associated with the second set of access control events;

providing a user model identifying patterns of user behavior based on a third set of access control events;

receiving a fourth set of access control events comprising time data, and location data, and user data associated with the access control events; and

determining whether to generate alarms responsive to receiving the fourth set of access control events using the temporal model, the spatial model, and the user model.

2. The method of claim 1 , wherein the plurality of access control events is received from a plurality of access control devices comprising at least one of a card reader, a keypad reader, a biometric reader, a motion detector, or a camera.

3. The method of claim 2 , wherein the first, second, and third sets of access control events are received from the plurality of access control devices, such that the temporal model, the spatial model, and the user model are trained on data from the same access control devices from which the access control events are received.

4. The method of claim 1 , wherein at least one of the first, second, or third set of access control events comprises a same access control event as at least another of the first, second, or third set of access control events.

5. The method of claim 1 , wherein determining whether to generate alarms comprises generating an alarm for a first access control event of the plurality of access control events responsive to any of the temporal model, the spatial model, and the user model indicating an alarm should be raised.

6. The method of claim 1 , wherein the temporal model comprises an occupancy model estimating an occupancy level of the at least a portion of the building, and wherein determining whether to generate alarms comprises generating an alarm based on a first access control event of the fourth set of access control events responsive to the temporal model indicating the at least a portion of the building is unoccupied.

7. The method of claim 1 , wherein the temporal model comprises an event rate model indicating a time relationship between alert events for one or more access control devices, and wherein determining whether to generate alarms comprises suppressing an alarm based on a first access control event responsive to:

the first access control event being associated with a first access control device of the one or more access control devices; and

the event rate model indicating a fault with the first access control device based on a time relationship between alert events for a plurality of access control events of the first set of access control events associated with the first access control device.

8. The method of claim 1 , wherein the spatial model comprises a connectivity model indicative of spatial relationships between a plurality of access control devices in the building determined based on time data and location data of the second set of access control events, and wherein determining whether to generate alarms comprises, for a first subset of access control events of the fourth set of access control events, generating an alarm responsive to the connectivity model determining the time data and location data of the first subset of access control events indicates an abnormal pattern of movement.

9. The method of claim 8 , wherein the spatial model further comprises floorplan information used to supplement data from the connectivity model.

10. The method of claim 1 , wherein the user model comprises an access device type model identifying patterns of behavior in the manner in which access devices of a plurality of access device types are used based on the type of access device, and wherein determining whether to generate alarms comprises, for a first subset of access control events of the fourth set of access control events, generating an alarm responsive to the access device type model indicating a pattern of behavior exhibited by a first access device of a first access device type associated with the first subset of access control events does not match an expected pattern of behavior for the first access device type.

11. The method of claim 10 , wherein the first access device type comprises a temporary access device, and wherein the access device type model indicates that the pattern of behavior exhibited by the first access device does not match an expected pattern of behavior for a temporary access device.

12. The method of claim 1 , wherein the user model is configured to determine a home building associated with a first user based on the third set of access control events, and wherein determining whether to generate alarms comprises determining to generate an alarm based on a first access control event of the fourth set of access control events responsive to determining the building is not the home building, the first access control event associated with the first user.

13. The method of claim 1 , wherein the user model comprises a user-specific model configured to determine a normal pattern of behavior for a particular user based on the third set of access control events, and wherein determining whether to generate alarms comprises determining to generate an alarm based on a first subset of access control events of the fourth set of access control events responsive to the user-specific model indicating a pattern of behavior of the particular user reflected in the first subset of access control events does not match the normal pattern of behavior.

14. A system for controlling access to at least a portion of a building, the system comprising:

one or more processors; and

one or more computer-readable storage media having instructions stored thereon that, when executed by the one or more processors, cause the one or more processors to implement operations comprising:

providing a temporal model identifying relationships between a first set of access control events based on times at which the first set of access control events occurred;

providing a spatial model identifying relationships between a second set of access control events based on locations associated with the second set of access control events;

providing a user model identifying patterns of user behavior based on a third set of access control events;

receiving a fourth set of access control events comprising time data, and location data, and user data associated with the access control events; and

determining whether to generate alarms responsive to receiving the fourth set of access control events using the temporal model, the spatial model, and the user model.

15. The system of claim 14 , wherein the plurality of access control events are received from a plurality of access control devices comprising at least one of a card reader, a keypad reader, a biometric reader, a motion detector, or a camera.

16. The system of claim 15 , wherein the first, second, and third sets of access control events are received from the plurality of access control devices, such that the temporal model, the spatial model, and the user model are trained on data from the same access control devices from which the access control events are received.

17. The system of claim 14 , wherein at least one of the first, second, or third set of access control events comprises a same access control event as at least another of the first, second, or third set of access control events.

18. The system of claim 14 , wherein determining whether to generate alarms comprises generating an alarm for a first access control event of the plurality of access control events responsive to any of the temporal model, the spatial model, and the user model indicating an alarm should be raised.

19. The system of claim 14 , wherein the temporal model comprises an occupancy model estimating an occupancy level of the at least a portion of the building, and wherein determining whether to generate alarms comprises generating an alarm based on a first access control event of the fourth set of access control events responsive to the temporal model indicating the at least a portion of the building is unoccupied.

20. The system of claim 14 , wherein the temporal model comprises an event rate model indicating a time relationship between alert events for one or more access control devices, and wherein determining whether to generate alarms comprises suppressing an alarm based on a first access control event responsive to:

the first access control event being associated with a first access control device of the one or more access control devices; and

the event rate model indicating a fault with the first access control device based on a time relationship between alert events for a plurality of access control events of the first set of access control events associated with the first access control device.

21. The system of claim 14 , wherein the spatial model comprises a connectivity model indicative of spatial relationships between a plurality of access control devices in the building determined based on time data and location data of the second set of access control events, and wherein determining whether to generate alarms comprises, for a first subset of access control events of the fourth set of access control events, generating an alarm responsive to the connectivity model determining the time data and location data of the first subset of access control events indicates an abnormal pattern of movement.

22. The system of claim 21 , wherein the spatial model further comprises floorplan information used to supplement data from the connectivity model.

23. The system of claim 14 , wherein the user model comprises an access device type model identifying patterns of behavior in the manner in which access devices of a plurality of access device types are used based on the type of access device, and wherein determining whether to generate alarms comprises, for a first subset of access control events of the fourth set of access control events, generating an alarm responsive to the access device type model indicating a pattern of behavior exhibited by a first access device of a first access device type associated with the first subset of access control events does not match an expected pattern of behavior for the first access device type.

24. The system of claim 23 , wherein the first access device type comprises a temporary access device, and wherein the access device type model indicates that the pattern of behavior exhibited by the first access device does not match an expected pattern of behavior for a temporary access device.

25. The system of claim 14 , wherein the user model is configured to determine a home building associated with a first user based on the third set of access control events, and wherein determining whether to generate alarms comprises determining to generate an alarm based on a first access control event of the fourth set of access control events responsive to determining the building is not the home building, the first access control event associated with the first user.

26. The system of claim 14 , wherein the user model comprises a user-specific model configured to determine a normal pattern of behavior for a particular user based on the third set of access control events, and wherein determining whether to generate alarms comprises determining to generate an alarm based on a first subset of access control events of the fourth set of access control events responsive to the user-specific model indicating a pattern of behavior of the particular user reflected in the first subset of access control events does not match the normal pattern of behavior.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 9, 2024
From: JOHNSON CONTROLS TYCO IP HOLDINGS LLP
To: TYCO FIRE & SECURITY GMBH
Reel/Frame 067056/0552 →
NUNC PRO TUNC ASSIGNMENT Recorded Feb 4, 2022
From: JOHNSON CONTROLS TECHNOLOGY COMPANY
To: JOHNSON CONTROLS TYCO IP HOLDINGS LLP
Reel/Frame 058959/0764 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 24, 2019
From: HORGAN, DONAGH S.; HOLLIDAY, JAN R.; O'TOOLE, EAMONN
To: JOHNSON CONTROLS TECHNOLOGY COMPANY
Reel/Frame 050819/0003 →