Illuminated Keyboard Feedback Using ML-Based Sentiment Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Prolonged device usage can lead to negative behaviors and sentiments in users, such as distraction or frustration, which hinder productivity and efficiency.
Innovation Solution
A system using machine learning models to analyze user sentiment and behavior through various input devices and sensors, providing subtle visual and haptic feedback via an illuminated keyboard to improve user mood and behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning models and illuminated keyboard are used to detect and provide feedback on user sentiment, then user productivity and task completion effectiveness are improved, but device complexity increases
Solution Approach 1:
The keyboard serves multiple functions: it acts as both a standard input device and a sentiment detection system with illumination capabilities. The same keyboard structure is used for typing while incorporating sensors to detect typing patterns and LEDs to provide visual feedback, eliminating the need for separate devices and reducing overall system complexity despite the advanced functionality.
Solution Approach 2:
The system uses the user's own typing behavior on the keyboard as the data source for sentiment analysis, without requiring external sensors or additional input devices. The keyboard detects typing patterns, pressure, and rhythm inherent in the user's natural interaction, and provides illumination feedback that the user can perceive directly during use, making the system self-contained and reducing external dependencies.
2Productivity
If illumination and haptic feedback are provided to improve user sentiment, then user behavior and mood are improved, but energy consumption increases
Solution Approach 1:
The illumination and haptic feedback are provided periodically or intermittently based on detected sentiment changes rather than continuously. The system monitors typing patterns continuously but only activates the illumination LEDs and haptic actuators when specific sentiment states are detected, such as frustration or distraction, thereby reducing overall energy consumption while maintaining effectiveness in improving user behavior at critical moments.
3Loss of time
If real-time sentiment analysis is performed using machine learning models, then timely feedback is provided to improve user behavior, but processing time and computational resources are consumed
Solution Approach 1:
The machine learning models are trained and configured in advance during a preprocessing phase, where typing pattern data is collected and used to train the sentiment analysis algorithms. During actual keyboard use, the pre-trained models perform rapid inference on incoming typing data, enabling real-time sentiment detection and feedback without consuming excessive processing resources during the critical feedback moment. This separates the computationally intensive training phase from the low-latency inference phase.
Data Source
AI summary
The technology provides a system for controlling illumination of a luminous keyboard. A non-transitory storage medium stores a trained machine learning model for identifying a user sentiment. A processor receives at least one keyboard input entered by the user. The processor processes the keyboard input using the trained machine learning model to identify a sentiment or behavior of the user. The processor determines an illumination profile for the keyboard based on the identified user sentiment or behavior. The keyboard illuminates according to the illumination profile.