Voice Recognition Vote Creation System for Live Streaming
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional vote creation methods in live streaming are inefficient due to the tedious and time-consuming process of text input for question stems and voting options, especially when the content involves a large number of words.
Innovation Solution
A method and system that utilizes voice recognition and semantic analysis to generate question stems and voting options automatically, allowing users to initiate votes through speech input, reducing the need for extensive text input and improving efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the host manually inputs text for question stem and voting options, then the vote can be created with accuracy, but the text input operation becomes tedious and time-consuming
Solution Approach 1:
The patent replaces the mechanical text input system with an acoustic recognition system. The voice input module captures spoken words, the recognition module converts speech to text, and the processing module generates the vote question and options automatically. This substitution eliminates manual typing while maintaining accuracy through speech-to-text conversion and automated semantic processing.
Solution Approach 2:
The system performs self-service by automatically generating the vote question stem and voting options from the recognized voice input. The processing module analyzes the semantic meaning of the spoken input and autonomously constructs the vote structure without requiring manual intervention for text entry, formatting, or option creation, thereby saving time while preserving accuracy.
2Loss of information
If the question stem and voting options contain a large quantity of words, then the vote content becomes comprehensive, but the text input operation becomes more tedious and time-consuming
Solution Approach 1:
The patent replaces manual text input with voice input and automated processing. The host can speak comprehensive vote content naturally without typing, and the system's recognition and processing modules automatically structure the complete content into the required vote format, maintaining information completeness while dramatically improving ease of operation.
Solution Approach 2:
The patent introduces voice input and automated processing as intermediaries between the host's intent and the final vote creation. The voice input module captures the host's comprehensive vote content verbally, the recognition module converts it to text, and the processing module structures it automatically. This intermediary system eliminates the tedious typing process while preserving the completeness of the vote content.
3Manufacturing precision
If the host needs to open a vote creation page and manually enter text, then the vote can be created with proper formatting, but the process becomes complex and time-consuming
Solution Approach 1:
The patent replaces the complex manual text input and formatting process with automated voice recognition and processing. The system captures voice input, converts it to text, and automatically formats it into the required vote structure with proper question stems and voting options, eliminating the need for manual page navigation and text entry while maintaining formatting precision.
Solution Approach 2:
The system performs self-service by automatically handling the formatting and structuring of the vote content. The processing module analyzes the recognized voice input and autonomously generates the properly formatted vote question and options, eliminating the need for manual intervention in formatting tasks and reducing process complexity while maintaining precision.
Data Source
AI summary
Disclosed are a method, an electronic device, and a computer readable storage medium for creating a vote. The method includes: receiving a vote initiation instruction to obtain voice information inputted currently; determining textual information by recognizing the voice information; determining at least two option words based on semantic recognition of the textual information; generating a question stem of the vote based on the textual information; and generating voting options based on the option words for the vote.


