Sensor-based door lock confidence

Patent metadata

Field	Value
Publication number	US-12488262-B1
Application number	US-202318239643-A
Country	US
Kind code	B1
Filing date	Aug 29, 2023
Priority date	Mar 21, 2018
Publication date	Dec 2, 2025
Grant date	Dec 2, 2025

Abstract

A method of implementing a network-enabled secure door lock, comprising obtaining measurements of an environment associated with a door from a variety of sensor types; generating, based at least in part on the measurements, a set of inputs to a machine-learning model; inputting the set of inputs into the machine learning model to determine a status of the door; generating a message that indicates the status of the door; and transmitting the message to a user device.

First claim

What is claimed is:

1 . A system, comprising:
a first component of a lock mechanism, wherein the first component:
comprises an interface to prevent relative motion with a second component of the lock mechanism; and
uses a cryptographic key to cryptographically secure a message to the second component in order to verify relative motion with the second component is prevented in at least one direction.

2 . The system of claim 1 , wherein the first component comprises one or more sensors to obtain information indicating a status of the lock mechanism.

3 . The system of claim 2 , wherein the information from the one or more sensors are input to a machine learning model to determine a status indicating whether the first component is mechanically engaged with the second component of the lock mechanism, and
wherein the machine learning model is trained using measurements of an environment associated with the lock mechanism obtained from the one or more sensors.

4 . The system of claim 1 , wherein the first component is further configured to operate according to logic to:
receive the message to be cryptographically secured encrypt the message with the cryptographic key to create a second encrypted message; and transmit the second encrypted message to another component of the lock mechanism.

5 . The system of claim 1 , wherein the first component comprises an actuator to extend or retract a deadbolt.

6 . The system of claim 1 , wherein the cryptographic key is used to verify an encrypted message indicating a status of an environment of the system.

7 . The system of claim 6 , wherein the cryptographic key is a private key, and the encrypted message received is encrypted with a public cryptographic key.

8 . A method, comprising:
verifying an encrypted message generated by a first component of a lock mechanism with a cryptographic key using a microprocessor; wirelessly transmitting, as a result of the encrypted message being verified, an indication to a computing device that the first component is in an engaged position; encrypting a message with the cryptographic key to create a second encrypted message; and wirelessly transmitting the second encrypted message to a second component of the lock mechanism.

9 . The method of claim 8 , further comprising:
determining a status indicating whether the first component is mechanically engaged with the second component of the lock mechanism based on a machine learning model using information from one or more sensors associated with the first component, and wherein the machine learning model is trained using measurements of an environment associated with the first component obtained from the one or more sensors.

10 . The method of claim 8 , further comprising:
receiving the message at the first component.

11 . The method of claim 8 , further comprising:
receiving, at the first component, a command to be in an engaged position; and using an actuator to engage the first component in an axial direction to prevent relative motion in at least one direction when mechanically engaged.

12 . The method of claim 8 , further comprising:
using a private cryptographic key to encrypt the encrypted message, and wherein the cryptographic key used to verify the encrypted message is a public cryptographic key.

13 . The method of claim 8 , further comprising:
using a public cryptographic key to encrypt the encrypted message, and wherein the cryptographic key used to verify the encrypted message is a private cryptographic key.

14 . A system, comprising one or more processors to:
use a machine learning model to generate a status of a lock mechanism based, at least in part, sensory data obtained from one or more components of the lock mechanism.

15 . The system of claim 14 , wherein the machine learning model determines the status of the lock mechanism based on a confidence factor associated with the sensory data.

16 . The system of claim 14 , wherein the one or more components of the lock mechanism comprises a first component, a second component, and/or one or more sensors to obtain the sensory data.

17 . The system of claim 14 , wherein the status of the lock mechanism indicates whether a first component is mechanically engaged with another component.

18 . The system of claim 16 , wherein the one or more sensors includes at least a weight sensor, a proximity sensor, an infrared sensor, a temperature sensor, an inertial sensor, a position sensor, and/or an RFID sensor.

19 . The system of claim 14 , wherein the one or more processors are to:
generate an encrypted message indicating the status of the lock mechanism; and verify the encrypted message using a cryptographic key.

20 . The system of claim 14 , wherein the one or more processors are to transmit the status of the lock mechanism to a user device.

21 . The system of claim 1 , wherein the first component cryptographically secures the message through encryption or digital signature.

Assignees

• Amazon Tech Inc

Inventors

• Marappan Priti
• Canavor Darren Ernest
• Hitchcock Daniel Wade
• Bhimanaik Bharath Kumar
• Roths Andrew Jay

Classifications

• G06N20/00 Primary

  Machine learning · CPC title

• E05B2047/0016

  with linearly reciprocating motion · CPC title

• E05B2047/0068

  Door closed · CPC title

• E05B2047/0058

  by batteries · CPC title

• E05B2047/0081

  Same pulse to lock or unlock · CPC title