Speech Logic Boundary Detection Using Feedback Input
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current speech input methods in electronic devices often misinterpret sentence boundaries due to incomplete consideration of user pauses, leading to errors in semantics recognition and misunderstanding of the original intention.
Innovation Solution
An information processing method that determines a logic boundary position for speech information using additional input information, allowing for accurate conversion and display of speech input, preventing division of sentences and improving semantics recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the electronic device uses halt time to determine sentence boundaries in speech input, then the device can automatically identify sentence intersections, but the device may incorrectly divide sentences when the user halts midway due to incomplete consideration
Solution Approach 1:
The patent introduces a feedback mechanism where the electronic device waits for additional input information after detecting a halt time, then uses this feedback to confirm whether a sentence boundary actually exists. This prevents incorrect division of sentences when users halt midway due to incomplete consideration.
Solution Approach 2:
The patent performs preliminary action by collecting additional input information before finalizing sentence boundary determination. The device does not immediately conclude sentence boundaries based solely on halt time, but rather gathers more data first to ensure accurate identification.
2Productivity
If the electronic device immediately processes speech information based on halt time, then the processing speed is fast, but the semantics recognition may be erroneous due to incomplete sentence detection
Solution Approach 1:
The patent performs preliminary data collection by gathering additional input information before finalizing speech recognition. This preliminary action ensures that the device has complete sentence boundaries before processing, preventing erroneous semantics recognition while maintaining efficient processing workflow.
Solution Approach 2:
The patent implements feedback by waiting for additional input confirmation before initiating final speech processing. This feedback loop ensures reliability of semantics recognition by confirming complete sentence boundaries, while the overall process remains efficient through automated decision-making.
3Productivity
If the electronic device divides speech content into multiple sentences based on halt time, then the device can process speech segments, but the original connotation may be misunderstood due to incorrect sentence division
Solution Approach 1:
The patent uses feedback to verify sentence boundaries before finalizing segmentation. By waiting for additional input information and confirming whether a halt indicates a true sentence boundary, the device prevents loss of original connotation accuracy while maintaining productive speech segmentation capability.
Solution Approach 2:
The patent performs preliminary verification by collecting additional input data before confirming sentence boundaries for segmentation. This ensures that the segmentation process does not lose original connotation, as each segment is validated against the complete input context before being finalized.
Data Source
AI summary
An information processing method and an electronic device are provided. The method includes an electronic device obtaining an input information through a second collection manner when the electronic device is in a speech collection state for obtaining speech information through a first collection manner, and determining a logic boundary position in relation to a first speech information in accordance with the input information, the first speech information is obtained by the electronic device through the first collection manner which is different from the second collection manner. An electronic device corresponding thereto is also disclosed.