Automatically adjusting screen brightness based on screen content

• US 10,665,204 B1
• Filed: 10/08/2019
• Issued: 05/26/2020
• Est. Priority Date: 10/08/2019
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Inventors: Goodsitt, Jeremy Edward, Pham, Vincent, Walters, Austin Grant, Truong, Anh, Rafferty, Galen, Farivar, Reza
• Primary Examiner(s): Gupta, Parul H
• Application Number:
  US16/596,376
• Time in Patent Office: 231 Days
• Field of Search: None
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G09G 2320/00 Control of display operating conditions
• CPC Class Codes: G09G 2320/0606 Manual adjustment
• CPC Class Codes: G09G 2320/062 Adjustment of illumination source parameters
• CPC Class Codes: G09G 2320/0646 Modulation of illumination source brightness and image signal correlated to each other
• CPC Class Codes: G09G 2320/08 Arrangements within a display terminal for setting, manually or automatically, display parameters of the display terminal
• CPC Class Codes: G09G 2320/103 Detection of image changes, e.g. determination of an index representative of the image change
• CPC Class Codes: G09G 2354/00 Aspects of interface with display user
• CPC Class Codes: G09G 2360/144 the light being ambient light
• CPC Class Codes: G09G 2360/145 the light originating from the display screen
• CPC Class Codes: G09G 2370/16 Use of wireless transmission of display information
• CPC Class Codes: G09G 5/10 Intensity circuits

Abstract

Disclosed are examples for adjusting screen brightness based on screen content being presented on a display screen of a mobile device. The described examples may determine a time at which the screen content is to be evaluated. The screen content is categorized based on the evaluation. A category of the screen content may be input into a machine learning algorithm that may be used to determine whether a screen brightness adjustment is appropriate. If a screen brightness adjustment is appropriate, a degree of the screen brightness adjustment may be determined.

Claims

1. A method, comprising:

detecting an occurrence of a set event related to presenting screen content on a mobile device display, wherein the set event is one of a plurality of set events;

in response to the detected occurrence of the set event, accessing a look-up table having a plurality of times;

based on an identification of the set event, determining from the look-up table a time to evaluate the screen content being presented;

at the determined time, evaluating screen content by;

obtaining pixel luminance intensity values of the screen content presented on the mobile device display at a predetermined sampling rate over a predetermined period of time;

generating a histogram using the obtained pixel luminance intensity values; and

inputting values from the histogram into a neural network, wherein the neural network is operable to determine features of the screen content that are to be included in a model useable to categorize the screen content presented on the mobile device display;

based on an output of the neural network, categorizing the screen content being presented on the mobile device display;

based on a category of the screen content, determining that a screen brightness adjustment is appropriate;

in response to determining that the screen brightness adjustment is appropriate, determining a degree of the screen brightness adjustment; and

adjusting the screen brightness according to the determined degree of the screen brightness adjustment.

2. The method of claim 1, further comprising:

receiving a measurement of ambient light intensity; and

utilizing the measurement of ambient light intensity in evaluating the screen content.

3. The method of claim 1, wherein the determined degree of screen brightness adjustment is based on inputs to a machine learning algorithm, and the inputs are selected from:

a user preference setting, an identity of an application presenting the screen content on the mobile device display, an identity of an application selected to present content on the mobile device display, a measurement of ambient light intensity, or a user history.

4. The method of claim 1, wherein the set event is at least one of:

a passage of a predetermined amount of time, a change from a first application presenting screen content on the mobile device display to a second application presenting different screen content on the mobile device display, a selection of a different application from an application currently presenting the screen content on the mobile device display, a detection of an input to a user interface of the mobile device to change a current screen brightness setting, a determination that the mobile device is at a predetermined location related to a brightness change history, a calendar setting, a time of day, or a time of year.

5. The method of claim 1, wherein determining a degree of screen brightness adjustment, comprises:

selecting a rule from a plurality of rules, wherein selection of the rule is based on a categorized screen content resulting from evaluating the screen content.

6. The method of claim 5, wherein determining a degree of screen brightness adjustment, further comprises:

generating thresholds for use in the plurality of rules by applying a further machine learning algorithm to a history of brightness adjustments, wherein the further machine learning algorithm is a supervised machine learning algorithm.

7. The method of claim 6, wherein generating thresholds, further comprises:

inputting ambient light readings included in the history of brightness adjustments into the further machine learning algorithm.

8. A mobile device, comprising:

a screen brightness adjustment application stored in a memory of the mobile device and executable by a processor of the mobile device,

wherein execution of the screen brightness adjustment application enables the mobile device to perform functions, including functions to;

detect an occurrence of a set event related to presenting the screen content on a mobile device display, wherein the set event is one of a plurality of set events;

in response to the detected occurrence of the set event, access a look-up table having a plurality of times;

based on an identification of the set event, determine from the look-up table a time to evaluate the screen content being presented;

at the determined time, evaluate screen content by performing functions to;

obtain pixel luminance intensity values of the screen content presented on the mobile device display at a predetermined sampling rate over a predetermined period of time;

generate a histogram using the obtained pixel luminance intensity values; and

input values from the histogram into a neural network, wherein the neural network is operable to determine features of the screen content that are to be included in a model useable to categorize the screen content presented on the mobile device display;

based on an output of the neural network, categorize the screen content being presented on the mobile device display;

based on a category of the screen content, determine that a screen brightness adjustment is appropriate;

in response to determining that the screen brightness adjustment is appropriate, determine a degree of the screen brightness adjustment; and

adjust the screen brightness according to the determined degree of the screen brightness adjustment.

9. The mobile device of claim 8, wherein execution of the screen brightness adjustment application enables the mobile device to perform further functions, including functions to:

receive a measurement of ambient light intensity; and

utilize the measurement of ambient light intensity in evaluating the screen content.

10. The mobile device of claim 8, wherein the determined degree of screen brightness adjustment is based on inputs to a machine learning algorithm, and the inputs are selected from:

a user preference setting, an identity of an application presenting screen content on the mobile device display, an identity of an application selected to present content on the mobile device display, a measurement of ambient light intensity, or a user history.

11. The mobile device of claim 8, wherein the set event is at least one of:

a passage of a predetermined amount of time, a change from a first application presenting the screen content on the mobile device display to a second application presenting different screen content on the mobile device display, a selection of a different application from an application currently presenting screen content on the mobile device display, a detection of an input to a user interface of the mobile device to change a current screen brightness setting, a determination that the mobile device is at a predetermined location related to a brightness change history, a calendar setting, a time of day, or a time of year.

12. The mobile device of claim 8, wherein execution of the screen brightness adjustment application enables the mobile device, when determining a degree of the screen brightness adjustment, to perform further functions, including functions to:

select a rule from a plurality of rules, wherein selection of the rule is based on a categorized screen content resulting from evaluating the screen content.

13. The mobile device of claim 12, wherein execution of the screen brightness adjustment application enables the mobile device, when further determining a degree of the screen brightness adjustment, to perform further functions, including functions to:

generate thresholds for use in the plurality of rules by applying a further machine learning algorithm to a history of brightness adjustments, wherein the further machine learning algorithm is a supervised machine learning algorithm.

14. The mobile device of claim 13, wherein execution of the screen brightness adjustment application enables the mobile device, when generating the thresholds, including functions to:

input ambient light readings included in the history of brightness adjustments into the further machine learning algorithm.

15. A non-transitory computer readable medium embodied with programming instructions that when executed causes a processor to perform functions, including functions to:

obtain pixel luminance intensity values of screen content presented on a mobile device display at a predetermined sampling rate over a predetermined period of time;

generate a histogram using the obtained pixel luminance intensity values; and

input values from the histogram into a neural network, wherein the neural network is operable to determine features of the screen content that are to be included in a model useable to categorize the screen content presented on the mobile device display;

based on an output of the neural network, categorize the screen content being presented on the mobile device display;

based on a category of the screen content, determine that a screen brightness adjustment is appropriate;

in response to determining that the screen brightness adjustment is appropriate, determine a degree of the screen brightness adjustment; and

adjust the screen brightness according to the determined degree of the screen brightness adjustment.

16. The non-transitory computer readable medium of claim 15, further embodied with programming instructions that when executed causes the processor to perform further functions, including functions to:

receive a measurement of ambient light intensity; and

utilize the measurement of ambient light intensity in evaluating the screen content.

17. The non-transitory computer readable medium of claim 15, further embodied with programming instructions that when executed causes the processor to perform further functions, wherein:

the determined degree of screen brightness adjustment is based on inputs to a machine learning algorithm, and the inputs are selected from;

a user preference setting, an identity of an application presenting the screen content on the mobile device display, an identity of an application selected to present content on the mobile device display, a measurement of ambient light intensity, or a user history.

18. The non-transitory computer readable medium of claim 15, further embodied with programming instructions when executed causes the processor to perform further functions:

prior to obtaining pixel luminance intensity values of screen content, detect an occurrence of a set event related to presenting screen content on a mobile device display, wherein the set event is at least one of;

a passage of a predetermined amount of time, a change from a first application presenting the screen content on the mobile device display to a second application presenting different screen content on the mobile device display, a selection of a different application from an application currently presenting the screen content on the mobile device display, a detection of an input to a user interface of the mobile device to change a current screen brightness setting, a determination that the mobile device is at a predetermined location related to a brightness change history, a calendar setting, a time of day, or a time of year.

19. The non-transitory computer readable medium of claim 15, further embodied with programming instructions to determine a degree of screen brightness adjustment that when executed causes the processor to perform further functions, including functions to:

generate thresholds for use in a plurality of rules by applying a further machine learning algorithm to a history of brightness adjustments, wherein the further machine learning algorithm is a supervised machine learning algorithm.

20. The non-transitory computer readable medium of claim 19, further embodied with programming instructions to generate thresholds that when executed causes the processor to perform further functions, including functions to:

input ambient light readings included in the history of brightness adjustments into the further machine learning algorithm.