DBL and ALS Brightness Control via Semi-Supervised Machine Learning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current information handling systems face issues with dynamic backlight (DBL) and ambient light sensor (ALS) brightness control systems often working cumulatively or against each other, leading to deleterious effects on the user's front-of-screen experience, such as washout or dimming, due to simultaneous operation without proper coordination.

Innovation Solution

A DBL and ALS brightness control management system that employs semi-supervised machine learning to learn user behavior and preferences, adjusting brightness levels gradually or stepping them to minimize disruption, and weights the operation of both systems based on location and ambient light levels to optimize the viewing experience.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Use of energy by moving object

If both DBL and ALS control systems operate simultaneously to adjust brightness, then power consumption is reduced and viewing experience is optimized, but conflicts arise causing washout or dimming effects that degrade the front-of-screen experience

Engineering Contradiction:
Improvepower consumptionVSAvoidwashout or dimming effects
Core Design Contradiction:
Use of energy by moving objectVSObject-affected harmful factors

Solution Approach 1:

A machine learning model is introduced as an intermediary between the DBL and ALS control systems. The model predicts whether ALS should be engaged based on current context (location, ambient light, user behavior) and outputs a confidence score that determines the degree of ALS engagement. This intermediary prevents direct conflict between the two control systems by intelligently mediating their interaction.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically changes the engagement parameter of ALS based on predicted confidence scores. When confidence is high, ALS is fully engaged; when confidence is low, ALS engagement is reduced or disabled. This parameter adjustment resolves the contradiction by adapting the ALS contribution to current conditions, preventing washout or dimming while maintaining power savings.

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If ALS control system operates to adjust brightness based on ambient light levels, then viewing experience is improved, but conflicts with DBL control system cause deleterious effects on front-of-screen experience

Engineering Contradiction:
Improveviewing experienceVSAvoidconflicts causing washout or dimming
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The system incorporates feedback loops where the machine learning model continuously learns from user interactions and system performance. User behavior data, location information, and ambient light conditions are fed back into the model to refine predictions about when ALS should be engaged. This feedback mechanism ensures ALS operates effectively without causing conflicts with DBL.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The ALS engagement level is made dynamic rather than static. The system adjusts the degree of ALS engagement in real-time based on predicted confidence scores, location context, and ambient light conditions. This dynamic approach allows ALS to provide viewing experience improvements while adapting to prevent conflicts with DBL control.

Inventive Principle:
Principle #15Dynamics

3Loss of energy

If DBL control system adjusts brightness dynamically, then power is conserved, but simultaneous operation with ALS control system without coordination creates conflicts

Engineering Contradiction:
Improvepower conservationVSAvoidcontrol system coordination
Core Design Contradiction:
Loss of energyVSReliability

Solution Approach 1:

The machine learning model performs preliminary action by predicting whether ALS should be engaged before the actual brightness adjustment occurs. By analyzing location, ambient light, and user behavior in advance, the model determines the optimal engagement level for ALS, preventing conflicts before they arise and ensuring reliable coordinated operation between DBL and ALS.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11107440B2System and method for dynamic backlight and ambient light sensor control management with semi-supervised machine learning for digital display operation
Publication Date: 2021.08.31 DELL PROD LP
  • US11107440B2 patent drawing
  • US11107440B2 patent drawing
  • US11107440B2 patent drawing

AI summary

A method of operating or an information handling system operating a dynamic backlight and ambient light sensor (DBL and ALS) brightness control management system comprising a digital display having a selectable brightness level, a processor operatively connected to the digital display for executing code instructions of a dynamic backlight (DBL) control system for modifying brightness levels of some or all portions of the display screen in response to inputs relating to display content type and associated optimal contrast levels for the display content and the processor executing code instructions of an ambient light sensor (ALS) control system to modify brightness levels of some or all portions of the display screen in response to detected ambient light levels of the information handling system where the processor executing code instructions of the DBL and ALS brightness control management system adjusts operation of either the DBL control system or the ALS control system based on location or detected ambient light levels and wherein the adjustment to the DBL control system or the ALS control system prevents interfering impact by both systems.