Wearable Device Settings Optimization via Machine Learning Feedback

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Wearable devices often have user-configurable settings for environmental stimuli, but users may not know which configuration is optimal, leading to suboptimal experiences, particularly for individuals with sensory processing disorders who are oversensitive or undersensitive to environmental inputs.

Innovation Solution

Implementing a machine learning-based optimization system that uses a training process involving user interactions with the wearable device to collect sensor data and feedback, which is analyzed to generate optimized settings through a cloud-based application, allowing the device to adjust its output modalities such as light, sound, and vibration to better suit the user's preferences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users manually configure wearable device settings for environmental stimuli, then users have control over device outputs, but users may not know which configuration is optimal leading to suboptimal experiences

Engineering Contradiction:

Improveease of configuring optimal settingsVSAvoidloss of information about optimal configuration

Core Design Contradiction:

Ease of operationVSLoss of information

Solution Approach 1:

The system implements feedback loops where sensor data from the wearable device and user responses are continuously collected and used to refine machine learning models. This feedback mechanism enables the system to learn from user interactions and automatically adjust settings to optimize the user experience without requiring manual configuration expertise.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The wearable device performs self-configuration through machine learning algorithms that automatically analyze sensor data and user feedback to determine optimal settings. This self-service capability eliminates the need for users to manually configure complex environmental stimulus parameters, allowing the device to autonomously optimize its performance.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If wearable devices provide multiple configurable settings for environmental stimuli, then device functionality is enhanced, but determining optimal settings becomes complex

Engineering Contradiction:

Improveadaptability of device settingsVSAvoidcomplexity of setting configuration

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent replaces manual mechanical configuration with machine learning-based automatic optimization. Instead of users physically adjusting multiple settings parameters, the system uses computational algorithms to analyze sensor data and automatically determine optimal configurations, substituting complex manual adjustment mechanisms with intelligent software-based solutions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system dynamically changes device parameters based on sensor data and user feedback rather than requiring static manual configuration. Machine learning models continuously adjust environmental stimulus parameters such as light intensity, sound volume, and vibration strength to optimize the user experience, allowing flexible adaptation without user intervention.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If wearable devices collect sensor data and user feedback for optimization, then personalized settings are achieved, but data processing requirements increase

Engineering Contradiction:

Improveprecision of user preference detectionVSAvoidquantity of data to be processed

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The system segments the data processing task by dividing sensor data collection and analysis into distinct modules. Different sensors (accelerometer, gyroscope, microphone, light sensor) are processed independently, and user feedback is separately integrated. This segmentation allows efficient handling of large data volumes by processing different data types through specialized algorithms rather than treating all data uniformly.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS9781243B1Optimizing wearable device settings using machine learning

Publication Date: 2017.10.03 INTEL CORP

AI summary

Techniques for optimizing wearable device settings using machine learning are described. A mobile device may receive, from a wearable device (such as a wristwatch), sensor data corresponding to a reaction of a user wearing the wearable device to an output modality produced by the wearable device. The mobile device may solicit user feedback for the output modality produced by the wearable device. The mobile device may receive, via a sensor set, user feedback data corresponding to a user feedback for the output modality. The mobile device may upload the sensor data and the user feedback data to a cloud-based application. The mobile device may receive a knowledge package, including a classification algorithm trained using the sensor data and the user feedback data, from the cloud-based application. Finally, the mobile device may send the knowledge package to the wearable device.