Voice-Driven Expression Curve Generation for Instant Messaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing instant messaging systems require complex and inflexible expression input methods, relying heavily on user identification and selection, which are inefficient and uninteresting, especially when expressing nuanced emotions like pleasure, anger, or joy, as they often rely on single expression inputs and linear displays.
Innovation Solution
An expression curve generating method based on voice input that divides an audio file into time periods, calculates sound volume levels, and maps these to expression icons, creating a fluctuating curve that represents emotions more vividly and accurately, allowing multiple emotions to be expressed simultaneously.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional expression selection interface is used, then users can select expressions, but the operation becomes complex and time-consuming when many expressions are available
Solution Approach 1:
The patent replaces the mechanical manual selection process with automatic recognition technology. Voice recognition and facial expression recognition systems automatically identify user intent and select appropriate expressions, eliminating the need for manual page turning and selection operations.
Solution Approach 2:
The system enables self-service by automatically selecting expressions based on user's voice input or facial expressions. The computer itself performs the selection task without requiring user intervention in the selection process, making the system serve itself in completing the expression selection.
2Measurement precision
If user manually differentiates and selects expressions, then specific expressions can be chosen, but accuracy is insufficient when expressions have similar meanings
Solution Approach 1:
The patent introduces intermediary technologies (voice recognition and facial expression recognition) that mediate between the user and the expression selection system. These intermediaries translate user's natural voice or facial expressions into accurate expression selections, avoiding the complexity of manual differentiation of similar expressions.
Solution Approach 2:
The system changes the parameters used for expression selection from manual text-based differentiation to automated recognition parameters such as voice patterns,语调 (intonation), and facial muscle movements. This parameter change enables more accurate differentiation of expressions with similar meanings.
3Adaptability or versatility
If single expression input is used, then simple expressions can be input, but complex emotions like pleasure, anger, sorrow, and joy cannot be completely expressed
Solution Approach 1:
The patent implements dynamic expression curves that can represent multiple expressions simultaneously and show their temporal evolution. Instead of static single expression selection, the system dynamically generates curves showing how expressions change over time, enabling versatile emotional expression while maintaining ease of operation through automated generation.
Solution Approach 2:
The system adds the time dimension to expression representation by generating expression curves. This transforms single-point expression selection into continuous temporal expression sequences, allowing complex emotions to be expressed through combinations of multiple expressions over time without increasing operational complexity.
4Adaptability or versatility
If multiple expressions need to be output simultaneously, then complete emotions can be expressed, but user needs to repeat page turning actions multiple times
Solution Approach 1:
The system performs preliminary actions by pre-processing user input (voice or facial expression) to automatically determine the sequence and combination of multiple expressions needed. This preliminary analysis eliminates the need for repeated page turning, as the system proactively prepares and presents the complete expression sequence in one operation.
Data Source
AI summary
Disclosed are an expression curve generating method based on voice input, and an device using the same. The method comprises the following steps: (1) inputting voice, and generating an audio file; (2) selecting expression graph buttons corresponding to a type of expressions from multiple expression graph buttons; (3) dividing the audio file into multiple equal time sections according to a time length, and respectively calculating a corresponding volume of each time section; (4) quantifying the corresponding volumes of the different time sections in the audio file into different volume levels; (5) obtaining expression icons corresponding to the volume level of each time section from a same group of expression icons, generating an expression curve using time as a horizontal axis and the volume level as a vertical axis; and (6) displaying the expression curve formed in step (5).