Learned overrides for home security

Patent metadata

Field	Value
Publication number	US-9916751-B2
Application number	US-201615348126-A
Country	US
Kind code	B2
Filing date	Nov 10, 2016
Priority date	Dec 30, 2014
Publication date	Mar 13, 2018
Grant date	Mar 13, 2018

Abstract

Systems and techniques are provided for learned overrides for home security. A sensor of a security system may be armed. A trip signal may be received indicating a tripping of the sensor. It may be determined that the trip signal can be automatically overridden based on matching an identity of the sensor and a state of the security system with a pattern in a model. The pattern may represent a state of the security system in which automatically overriding the trip signal from the sensor is permitted. The trip signal from the sensor may be automatically overridden without input from a user.

First claim

The invention claimed is:

1. A method for learning overrides of a security system, the method comprising:
receiving a trip signal indicating a tripping of a security system sensor;
sending, when an automatic override of the trip signal is not permitted by a model, an override request to a user device;
receiving a response to the override request, wherein the response indicates the trip signal is to be overridden; and
updating, after receiving at least a set number of override responses indicating a respective trip signal from the security system sensor is to be overridden, the model to automatically override a subsequent trip signal received from the security system sensor.

2. The method of claim 1 , further comprising determining the trip signal cannot be automatically overridden, wherein:
the determining is based on matching both an identity of the security system sensor and a current state of the security system with at least one pattern;
the at least one pattern is incorporated in the model; and
the at least one pattern represents a possible state of the security system.

3. The method of claim 2 , wherein the matching is based on at least one of parameter-based matching, probabilistic matching, statistical matching, or machine learning-based matching.

4. The method of claim 3 , wherein the at least one pattern in the model is one or more of parameter-based, probabilistic, statistical, or machine learning-based.

5. The method of claim 2 , wherein the possible state of the security system comprises one or more parameters selected from the group consisting of:
a state of other sensors coupled to the security system;
a presence of one or more persons within an environment monitored by the security system;
a time of day;
a day of the week;
a day of the month;
a month of the year;
a climate within the environment monitored by the security system;
a climate outside the environment monitored by the security system; and
a mode of the security system.

6. The method of claim 1 , further comprising:
receiving a second trip signal indicating a tripping of a second security system sensor;
determining that the second trip signal from the second security system sensor cannot be automatically overridden, wherein the determining is based on either:
matching both an identity of the second security system sensor and a current state of the security system with the at least one pattern in the model, wherein the at least one pattern represents a possible state of the security system in which automatically overriding the second trip signal from the security system sensor is not permitted, or
not matching both the identity of the second security system sensor and the current state of the security system with any pattern in the model; and

sending a second override request to the security system speaker.

7. The method of claim 6 , further comprising:
receiving a response to the second override request, wherein the response to the second override request indicates the second trip signal is to be overridden;
overriding the second trip signal; and
updating the model to automatically override a subsequent trip signal received from the second security system sensor, wherein the updating the model comprises either:
adding a new pattern to the model, or
updating the at least one pattern.

8. The method of claim 7 , wherein the response to the second override request is received from the security system speaker.

9. The method of claim 6 , further comprising:
receiving a response to the second override request, wherein the response to the second override request indicates the second trip signal from the second security system sensor is not to be overridden; and
generating at least one of an alarm, an alert, or a notification indicating that the second security system sensor has generated the second trip signal.

10. The method of claim 9 , wherein the response to the second override request is received from the security system speaker.

11. The method of claim 1 , wherein the security system sensor remains armed while the trip signal from the security system sensor is overridden.

12. The method of claim 1 , wherein the response is received from the security system speaker.

13. A system for learning overrides, comprising:
a storage device configured to store data describing a model, wherein the model comprises at least one pattern representing a state of a security system; and
a computing device configured to:
receive a trip signal indicating a tripping of a security system sensor;
send, when an automatic override of the trip signal is not permitted by the model, an override request to a user device;
receive a response to the override request, wherein the response indicates the trip signal is to be overridden; and
update, after receiving at least a set number of override responses indicating a respective trip signal from the security system sensor is to be overridden, the model to automatically override a subsequent trip signal received from the security system sensor.

14. The system of claim 13 , wherein the computing device further comprises the security system speaker.

15. The system of claim 13 , wherein the computing device is further configured to send a notification of a trip signal override to the security system speaker.

16. The system of claim 13 , wherein the computing device is further configured to determine the trip signal cannot be automatically overridden, based on:
a current state of the security system and an identity of the security system sensor having a match the at least one pattern incorporated in the model; and
the at least one pattern does not permit automatically overriding the trip signal from the security system sensor.

17. The system of claim 16 , wherein the match is based on at least one of parameter-based matching, probabilistic matching, statistical matching, or machine learning-based matching.

18. The system of claim 17 , wherein the at least one pattern in the model is one or more of parameter-based, probabilistic, statistical, or machine learning-based.

19. The system of claim 16 , wherein a possible state of the security system comprises one or more parameters selected from the group consisting of:
a state of other sensors coupled to the security system;
a presence of one or more persons within an environment monitored by the security system;
a time of day;
a day of the week;
a day of the month;
a month of the year;
a climate within the environment monitored by the security system;
a climate outside the environment monitored by the security system; and
a mode of the security system.

20. The system of claim 13 , wherein the computing device is further configured to:
receive a second trip signal indicating a tripping of a second security system sensor;
determine that the second trip signal from the second security system sensor cannot be automatically overridden, wherein the a determination is based on either:
matching both an identity of the second security system sensor and a current state of the security system with the at least one pattern in the model, wherein the at least one pattern represents a possible state of the security system in which automatically overriding the second trip signal from the security system sensor is not permitted, or
not matching both the identity of the second security system sensor and the current state of the security system with any pattern in the model; and

send a second override request to the secur

Assignees

• Google Inc
• Google Llc

Inventors

• Malhotra Mark Rajan
• Le Guen Sophie
• Boyd Jeffrey Alan
• Lee Jeffery Theodore
• Hester Todd

Classifications

• G08B21/18

  Status alarms (G08B21/02 takes precedence) · CPC title

• G08B25/008 Primary

  Alarm setting and unsetting, i.e. arming or disarming of the security system · CPC title

• G08B25/009

  Signalling of the alarm condition to a substation whose identity is signalled to a central station, e.g. relaying alarm signals in order to extend communication range · CPC title

• G08B13/2491

  Intrusion detection systems, i.e. where the body of an intruder causes the interference with the electromagnetic field · CPC title