Adaptive notification system based on contextual information

Patent metadata

Field	Value
Publication number	US-12183184-B2
Application number	US-201917309566-A
Country	US
Kind code	B2
Filing date	Nov 25, 2019
Priority date	Dec 7, 2018
Publication date	Dec 31, 2024
Grant date	Dec 31, 2024

Abstract

Adaptive systems and methods for managing and delivering notifications to workers in a work environment are provided. The adaptive notification system receives and assesses contextual information to adjust notification configurations or to propose options or alternatives of adjustments to guide a user to adjust the notification configurations.

First claim

What is claimed is:

1. A method of managing and delivering notifications to a user, the method comprising:
providing a current notification configuration to a notification system;
receiving, via the notification system, contextual information including a combination of first real-time information collected from one or more environmental sensors and second real-time information collected from one or more user sensors, wherein the first real-time information includes one or more of air temperature, humidity, air velocity, or heat radiation in a work environment at which the user is located, and wherein the second real-time information includes one or more biological measurements associated with the user;
implementing, by the notification system, a machine learning (ML) model trained according to a reinforcement learning algorithm to assess the contextual information to determine one or more adjustments to the current notification configuration; and
adjusting, using the notification system, the current notification configuration in response to determining that the contextual information is of a sufficient quantity based on a predetermined level of certainty and based on the one or more determined adjustments to form an adjusted notification configuration.

2. The method of claim 1 , wherein the adjusted notification configuration is configured to defer, redirect, broadcast, advance, amplify, reduce, maintain, or cancel one or more notifications associated with the current notification configuration.

3. The method of claim 1 , further comprising adjusting the current notification configuration to be within the bounds of one or more pre-set policies.

4. The method of claim 1 , further comprising outputting, via a user interface (UI), one or more adjustment recommendations that are associated with the adjusted notification configuration.

5. The method of claim 4 , further comprising receiving, via the UI, one or more inputs indicating one or more adjustments to the current notification configuration.

6. The method of claim 5 , further comprising:
generating one or more safety notifications based on the one or more adjustments; and
delivering the one or more generated safety notifications to the user.

7. The method of claim 1 , further comprising assessing user history data including first history data representing safety notifications sent to the user, and second history data representing one or more responses of the user to the safety notifications.

8. The method of claim 1 , further comprising providing a user interface (UI) to present a result of the assessment to the user.

9. The method of claim 8 , wherein the UI includes one or more default settings reflecting the current notification configuration.

10. The method of claim 8 , wherein the UI includes a dashboard to present the contextual information.

11. The method of claim 8 , wherein the UI includes automatically generated adjustment recommendations.

12. The method of claim 1 , further comprising communicating, by the notification system, with a notification and response device one or more buttons that enable the user to send feedback to the notification system.

13. The method of claim 12 , wherein the one or more buttons of the notification and response device include an alarm button.

14. The method of claim 12 , wherein the one or more buttons of the notification and response device include a first button to accept a notification and a second button to request adjustment of the notification.

15. The method of claim 1 , further comprising directing, by the notification system, via a message initiation component (MIC), a notification to the user, the notification overriding the one or more adjustments to the current notification configuration.

16. The method of claim 1 , further comprising:
receiving, by the notification system, an alarm notification initiated by the user; and
broadcasting, via the notification system, the alarm notification to a selected group of receivers based on respective states associated with each respective receiver of the selected group.

17. A safety notification system comprising:
a data interface component to receive first contextual information from one or more environmental sensors and user sensors and second contextual information from one or more wearable notification and response devices, wherein the first real-time information includes one or more of air temperature, humidity, air velocity, or heat radiation in a work environment at which the user is located, and wherein the second real-time information includes one or more biological measurements associated with the user;
an assessing component to implement a machine learning (ML) model trained according to a reinforcement learning algorithm to assess the first and second contextual information to determine whether to adjust current safety notification configurations;
an adjusting component to adjust at least some of the current safety notification configurations in response to a determination that the contextual information is of a sufficient quantity based on a predetermined level of certainty and based on the contextual information to generate one or more adjustment recommendations;

a user interface (UI) configured to:
present the one or more adjustment recommendations to a user;
receive instructions from the user; and
send the instructions to the assessing component and the adjusting component to generate a notification; and
a delivery component to deliver the notification to the wearable notification and response devices.

18. The method of claim 1 , wherein the one or more biological measurements include one or more of a body temperature or a galvanic skin response associated with the user.

19. The method of claim 1 , wherein the reinforcement learning algorithm is configured to control a learning rate of the ML model according to which the ML adapts the current safety notification system.

Assignees

• 3M Innovative Properties Company

Inventors

• Kruse John M
• Sjolund Lori A
• Shuman Vera

Classifications

• G08B21/18

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

• G08B21/10

  responsive to calamitous events, e.g. tornados or earthquakes · CPC title

• G08B9/00

  Order telegraph apparatus, i.e. means for transmitting one of a finite number of different orders at the discretion of the user, e.g. bridge to engine room orders in ships · CPC title

• G06N20/00

  Machine learning · CPC title

• G08B21/04

  responsive to non-activity, e.g. of elderly persons (G08B21/06 takes precedence) · CPC title