Voiceprint-Mapped Touchscreen Interaction for Multi-User Input
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing human-computer interaction technologies face challenges in touchscreen input efficiency due to difficulties in controlling joined-up handwriting and the confusion of voice content from multiple users, leading to low input efficiency and user experience.
Innovation Solution
A multi-modality human-computer interaction method that establishes a correspondence between a voiceprint and a touchscreen output position, allowing voice content to be accurately displayed at the user's intended location, using touch operations and voice recognition to enhance input efficiency and user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If touchscreen input is implemented by using touch operation for handwriting, then the system can accept user input, but joined-up handwriting and difficulty in controlling handwriting occur, causing difficult input and low input efficiency
Solution Approach 1:
The patent replaces the mechanical touch operation system with an acoustic voice recognition system. Instead of requiring physical touchscreen interaction for handwriting input, the system captures voice signals, converts them to text through recognition, and displays the result, thereby eliminating the control difficulties associated with handwriting while maintaining input functionality
Solution Approach 2:
The patent introduces voice recognition technology as an intermediary between the user and the touchscreen system. The voice signal serves as a mediator that translates spoken language into text output, bridging the gap between user intent and system response without requiring direct touchscreen manipulation
2Adaptability or versatility
If multiple users perform voice input synchronously, then the system can handle concurrent input, but voice content of different users is confused and displayed on the touchscreen
Solution Approach 1:
The patent segments the voice input stream by user identity, creating separate processing channels for each user. Voiceprint recognition divides the mixed audio input into distinct user segments, allowing the system to attribute and display each user's voice content independently at their respective output positions without confusion
Solution Approach 2:
The patent applies local quality by assigning different output positions on the touchscreen to different users based on their voiceprints. Each user's voice content is displayed at a specific location rather than mixing all content together, preserving user identity and content attribution through spatial differentiation
Data Source
AI summary
A human-computer interaction method relates to the field of human-computer interaction technologies. The method includes: establishing a correspondence between a first voiceprint and a first output position on a touchscreen; and receiving first voice, and when it is determined that a voiceprint of the first voice matches the first voiceprint, recognizing content of the voice, and outputting and displaying the content to the first output position.


