Granted Patent B2

US 12,524,076 · App. 17/879,195 · Granted Jan 13, 2026

Inventors: Katherine Blair Huffman (Menlo Park, CA); Forrest Robert Smith (Buffalo, NY)

Assignee: Google LLC

G06F3/016G06F2203/011

Abstract

Claims (85)

1 . A system for controlling illumination of a user input device, comprising:

a non-transitory computer-readable storage medium configured to store at least one trained machine learning model configured to identify a sentiment of a user and one or more predefined illumination profiles configured to affect the sentiment of the user; and

at least one processor configured to:

receive, from the user input device, content entered by the user;

use the at least one trained machine learning model to identify a first sentiment of the user;

identify a target change in sentiment of the user;

select a first illumination profile of the one or more predefined illumination profiles for the user input device based on the identified first sentiment and the identified target change in sentiment; and

instruct the user input device to illuminate according to the first illumination profile;

wherein the first illumination profile includes a repeated illumination pattern; and

wherein the at least one processor is further configured to determine a haptic profile for the user input device based on the identified first sentiment, and instruct the user input device to generate haptic feedback to the user according to the haptic profile.

2 . The system of claim 1 , wherein the first illumination profile includes a value for at least one adjustable parameter associated with light emitted from the user input device.

3 . The system of claim 2 , wherein the at least one adjustable parameter includes one or more of the following:

illumination brightness;

illumination intensity;

illumination color;

illumination color temperature;

illumination graphical pattern;

illumination time sequence;

illumination power on; or

illumination power off.

4 . The system of claim 1 , wherein the content includes one or more of:

one or more certain words;

typing mistakes;

deleted words; or

modified text.

5 . The system of claim 1 , wherein the at least one processor is configured to:

receive, from the user input device, additional content entered by the user;

process the additional content using the at least one trained machine learning model to identify a second sentiment of the user;

compare the identified second sentiment of the user with the identified first sentiment of the user;

select a second illumination profile different from the first illumination profile based on the comparison; and

instruct the user input device to illuminate according to the second illumination profile.

6 . The system of claim 1 , wherein the at least one trained machine learning model identifies the sentiment of the user based on at least one of a typing speed or typing intensity of the user.

7 . The system of claim 1 , wherein the at least one trained machine learning model is configured to process imagery received from a camera to identify one or more types of contextual information of the user.

8 . The system of claim 1 , wherein a plurality of models are used in combination to collect data from multiple sources to analyze the first sentiment.

9 . The system of claim 1 , wherein a plurality of models are employed to identify the first sentiment, each model of the plurality of models corresponding to a different source of contextual information.

10 . A system for controlling illumination of a user input device, comprising:

a non-transitory computer-readable storage medium configured to store at least one trained machine learning model to identify a behavior of a user and one or more predefined illumination profiles configured to affect the behavior of the user; and

a processor configured to:

receive, from the user input device, content entered by the user;

use the at least one trained machine learning model to identify a first behavior of the user;

identify a target change in behavior of the user;

select a first illumination profile of the one or more predefined illumination profiles for the user input device based on the identified first behavior of the user and the identified target change in behavior; and

instruct the user input device to illuminate according to the first illumination profile;

wherein the first illumination profile includes a repeated illumination pattern; and

wherein the at least one processor is further configured to determine a haptic profile for the user input device based on the identified first behavior, and instruct the user input device to generate haptic feedback to the user according to the haptic profile.

11 . The system of claim 10 , wherein the identified first behavior of the user indicates a workflow condition.

12 . The system of claim 11 , wherein the first illumination profile is configured to instruct the user input device to generate a visual signal to the user based on the workflow condition.

13 . The system of claim 10 , wherein the identified first behavior of the user indicates a concentration condition.

14 . The system of claim 13 , wherein the first illumination profile is configured to instruct the user input device to generate a visual signal to the user based on the concentration condition.

15 . The system of claim 10 , wherein the processor is further configured to:

receive, from the user input device, additional content entered by the user;

process the additional content using the at least one trained machine learning model to identify a second behavior of the user;

compare the identified second behavior of the user with the identified first behavior of the user;

select a second illumination profile different from the first illumination profile based on the comparison; and

instruct the user input device to illuminate according to the second illumination profile.

16 . A computer-implemented method for controlling illumination of a user input device, comprising:

storing, by a non-transitory computer-readable storage medium, at least one trained machine learning model configured to identify a sentiment of a user and one or more predefined illumination profiles configured to affect the sentiment of the user;

receiving, from the user input device, content entered by the user;

using the at least one trained machine learning model to identify a first sentiment of the user;

identifying a target change in sentiment of the user;

selecting, by at least one processor, a first illumination profile of the one or more predefined illumination profiles for the user input device based on the identified first sentiment and the identified target change in sentiment; and

instructing, by the at least one processor, the user input device to illuminate according to the first illumination profile;

wherein the first illumination profile includes a repeated illumination pattern; and

wherein the at least one processor is further configured to determine a haptic profile for the user input device based on the identified first sentiment, and instruct the user input device to generate haptic feedback to the user according to the haptic profile.

17 . The method of claim 16 , further comprising:

receiving, from the user input device, additional content entered by the user;

processing the additional content using the at least one trained machine learning model to identify a second sentiment of the user;

comparing the identified second sentiment of the user with the identified first sentiment of the user;

selecting a second illumination profile different from the first illumination profile based on the comparison; and

instructing the user input device to illuminate according to the second illumination profile.

18 . A computer-implemented method for controlling illumination of a user input device, comprising:

storing, by a non-transitory computer-readable storage medium, at least one trained machine learning model configured to identify a behavior of a user and one or more predefined illumination profiles configured to affect the behavior of the user;

receiving, from the user input device, content entered by the user;

using the at least one trained machine learning model to identify a first behavior of the user;

identifying a target change in behavior of the user;

selecting, by at least one processor, a first illumination profile of the one or more predefined illumination profiles for the user input device based on the identified first behavior and the identified target change in behavior; and

instructing, by the at least one processor, the user input device to illuminate according tothe first illumination profile;

wherein the first illumination profile includes a repeated illumination pattern; and

wherein the at least one processor is further configured to determine a haptic profile for the user input device based on the identified first behavior, and instruct the user input device to generate haptic feedback to the user according to the haptic profile.

19 . The method of claim 18 , further comprising:

receiving, from the user input device, additional content entered by the user;

processing the additional content using the at least one trained machine learning model to identify a second behavior of the user;

comparing the identified second behavior of the user with the identified first behavior of the user;

selecting a second illumination profile different from the first illumination profile based on the comparison; and

instructing the user input device to illuminate according to the second illumination profile.

Assignments (1)

Continuity (1)

References Cited (10)