IP Library › Granted Patent US 12705885
Granted Patent B2
US 12705885 · App. 18/745,351 · Granted Aug 11, 2026

Augmented reality devices for safety alerting

Inventor: Alyssa N. Scarbrough (Boise, ID)
Assignee: Micron Technology, Inc.
G06V20/20G06V20/41G06V40/172G08B21/02G08B25/00G06F40/35
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 12705885
App. No.
18/745,351
Granted
Aug 11, 2026
Kind
B2
Abstract

Disclosed in some examples are methods, systems, and machine-readable mediums which utilize augmented reality devices to detect and warn vulnerable individuals about real-life situations that could pose a hazard to their safety. One or more signals identified from data captured by sensors of one or more devices of the user may be analyzed to determine whether elements such as persons, objects, or the like pose a danger to the user. The system, upon detection of an unsafe event, situation, or person may then warn the user through the augmented reality glasses of the unsafe events, situations, or persons. In addition, a caregiver or other individual and/or the police may also be notified.

Claims (48)

1 . A method for alerting a user to a dangerous situation, the method comprising:

monitoring, via a sensor of a device of the user, audio and video of an environment of the user;

analyzing audio of the environment of the user to determine one or more spoken words or phrases of a person in the environment of the user;

analyzing video of the environment of the user to identify an identity of a speaker of the one or more spoken words or phrases;

determining, based upon both the one or more spoken words or phrases and the identity of the speaker, whether the person in the environment of the user is exhibiting indicators that the person poses a threat to the user; and

responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, causing display to the user, in augmented reality glasses, an indicator that the person poses the threat to the user.

2 . The method of claim 1 , further comprising, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, causing delivery of a message to a second user.

3 . The method of claim 1 , further comprising, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, contacting police.

4 . The method of claim 1 , wherein analyzing audio of the environment of the user to determine one or more spoken words or phrases comprises:

transcribing audio spoken by the person to create a transcript; and

wherein determining, based upon both the one or more spoken words or phrases and the identity of the speaker whether the person in the environment of the user is exhibiting indicators that the person poses a threat to the user comprises identifying words or phrases in the transcript corresponding to a list of threatening words or phrases.

5 . The method of claim 1 ,

wherein determining, based upon both the one or more spoken words or phrases and the identity of the speaker whether the person in the environment of the user is exhibiting indicators that the person poses a threat to the user comprises:

determining that the identity of the person is on a list of persons that pose a threat.

6 . The method of claim 1 , further comprising, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, causing the audio and video to be saved to a storage device in a network-based storage device.

7 . The method of claim 1 , further comprising, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user: causing geolocation data of the augmented reality glasses to be streamed to a network-based service.

8 . The method of claim 1 , wherein the audio and video are captured by sensors on the augmented reality glasses.

9 . A computing device for alerting a user to a dangerous situation, the computing device comprising:

a processor;

a memory, the memory storing instructions, which when executed by the processor, cause the computing device to perform operations comprising:

monitoring, via a sensor of a device of the user, audio and video of an environment of the user;

analyzing audio of the environment of the user to determine one or more spoken words or phrases of a person in the environment of the user;

analyzing video of the environment of the user to identify an identity of a speaker of the one or more spoken words or phrases;

determining, based upon both the one or more spoken words or phrases and the identity of the speaker, whether the person in the environment of the user is exhibiting indicators that the person poses a threat to the user; and

responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, causing display to the user, in augmented reality glasses, an indicator that the person poses the threat to the user.

10 . The computing device of claim 9 , wherein the operations further comprise, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, causing delivery of a message to a second user.

11 . The computing device of claim 9 , wherein the operations further comprise, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, contacting police.

12 . The computing device of claim 9 , wherein the operations of analyzing audio of the environment of the user to determine one or more spoken words or phrases comprises

transcribing audio spoken by the person to create a transcript; and

wherein the operations of determining, based upon both the one or more spoken words or phrases and the identity of the speaker whether the person in the environment of the user is exhibiting indicators that the person poses a threat to the user comprises identifying words or phrases in the transcript corresponding to a list of threatening words or phrases.

13 . The computing device of claim 9 ,

wherein the operations of determining, based upon both the one or more spoken words or phrases and the identity of the speaker whether the person in the environment of the user is exhibiting indicators that the person poses a threat to the user comprises:

determining that the identity of the person is on a list of persons that pose a threat.

14 . The computing device of claim 9 , wherein the operations further comprise, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, causing the audio and video to be saved to a storage device in a network-based storage device.

15 . The computing device of claim 9 , wherein the operations further comprise, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user:

causing geolocation data of the augmented reality glasses to be streamed to a network-based service.

16 . The computing device of claim 9 , wherein the audio and video are captured by sensors on the augmented reality glasses.

17 . A non-transitory machine-readable medium, storing instructions, which when executed by a computing device, cause the computing device to perform operations comprising:

monitoring, via a sensor of a device of the user, audio and video of an environment of the user;

analyzing audio of the environment of the user to determine one or more spoken words or phrases of a person in the environment of the user;

analyzing video of the environment of the user to identify an identity of a speaker of the one or more spoken words or phrases;

determining, based upon both the one or more spoken words or phrases and the identity of the speaker, whether the person in the environment of the user is exhibiting indicators that the person poses a threat to the user; and

responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, causing display to the user, in augmented reality glasses, an indicator that the person poses the threat to the user.

18 . The non-transitory machine-readable medium of claim 17 , wherein the operations further comprise, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, causing delivery of a message to a second user.

19 . The non-transitory machine-readable medium of claim 17 , wherein the operations further comprise, responsive to detecting the person in the environment of the user is exhibiting indicators that the person poses the threat to the user, contacting police.

20 . The non-transitory machine-readable medium of claim 17 , wherein the operations of analyzing audio of the environment of the user to determine one or more spoken words or phrases comprises:

transcribing audio spoken by the person to create a transcript; and

wherein the operations of determining, based upon both the one or more spoken words or phrases and the identity of the speaker whether the person in the environment of the user is exhibiting indicators that the person poses a threat to the user comprises identifying words or phrases in the transcript corresponding to a list of threatening words or phrases.