Eye Tracking Voice Input Direction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice input systems in computing devices struggle to accurately direct voice commands to the intended application, especially when multiple applications are running concurrently, leading to inefficiencies and potential misinterpretation of user intentions.
Innovation Solution
An apparatus utilizing eye tracking technology to determine the user's focus on a computing device screen, allowing voice input to be directed to the application currently in view, thereby enhancing command precision and reducing unnecessary button interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the computing device directs voice input to the application that is still viewable when one application is removed from view, then the voice input can be processed, but this limits the user to viewing one application at a time and is cumbersome
Solution Approach 1:
The patent introduces eye tracking technology to add a new dimension (eye gaze direction) for determining application selection, moving beyond traditional single-application-viewing constraints. This allows users to interact with multiple applications simultaneously by directing voice input to different applications based on where their eyes are looking, effectively adding spatial orientation as a new control dimension.
2Productivity
If the computing device receives voice input without eye tracking, then voice commands can be processed, but the device may execute commands that are not meant for it or misinterpret user intentions
Solution Approach 1:
The system uses eye tracking to provide visual feedback about which application is currently selected or being targeted by voice input. This feedback mechanism allows users to verify that their voice commands will be directed to the intended application, and enables the system to adjust its interpretation based on confirmed user intent through gaze direction.
Solution Approach 2:
Eye tracking serves as an intermediary between the user and the voice input system, providing additional contextual information about user intent. The gaze data acts as a mediator that helps disambiguate which application should receive the voice input, reducing misinterpretation of user intentions.
3Adaptability or versatility
If the application provides buttons to start, stop, record, or pause voice input, then voice input control is available, but requiring users to press buttons wastes time and makes the interface complex
Solution Approach 1:
The system automatically determines when voice input should be activated or deactivated based on eye tracking data, without requiring manual button presses. The application monitors gaze direction and autonomously manages voice input states, allowing users to simply look at the desired application to initiate or stop voice recording.
Solution Approach 2:
The patent replaces mechanical button-pressing interactions with optical eye tracking detection. Instead of requiring physical contact with control elements, the system uses non-contact eye gaze detection to control voice input functionality, eliminating the need for physical buttons while maintaining full control capability.
4Adaptability or versatility
If multiple applications are running concurrently, then application functionality is enhanced, but it becomes challenging to direct voice input to the specific intended application
Solution Approach 1:
The system applies different selection criteria to different regions of the display based on where the user is looking. By dividing the display space into different application zones and using eye tracking to determine which zone is being observed, the system can direct voice input to the specific local region (application) that the user intends to interact with, even when multiple applications are running concurrently.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution enables users to efficiently direct voice commands to specific applications without manually switching between them, improving user experience by reducing errors and simplifying the voice interface process.
Implementation Method 1
a location is selected from a group consisting of a computing device and an application being displayed on a screen of the computing device, the location being detected where a user's eyes are directed
Data Source
AI summary
For directing voice input based on eye tracking, a method is disclosed that includes receiving, by use of a processor, an audio signal, the audio signal comprising voice input, selecting a location from the group consisting of a computing device and an application being displayed on a screen of the computing device, the location being detected where a user's eyes are directed, and directing the voice input to the selected location.