Voice Input Parameter Formatting for Multi-App Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current speech recognition services incorrectly determine user intent and enter incorrect parameters into application input fields, often due to mismatched formats, leading to errors in processing user inputs across multiple applications.
Innovation Solution
An electronic apparatus with a processor, touchscreen display, microphone, and wireless communication circuit that receives user inputs, transmits data to an external server, and processes responses to match parameters with the attributes of input fields, ensuring accurate parameter entry and preventing errors by converting text formats as needed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech recognition service displays only the result according to user input, then the service is simple to operate, but it cannot process user inputs to request execution of multiple applications
Solution Approach 1:
The user input is segmented into multiple distinct utterances (first utterance and second utterance), where each utterance corresponds to a different application or function. The system processes each segmented utterance separately to execute multiple applications sequentially, enabling complex multi-application control while maintaining simple voice-based operation.
Solution Approach 2:
The system transitions from processing a single-dimensional user input to handling multi-dimensional inputs by introducing temporal sequencing. Multiple utterances are processed in a specific order (first utterance triggering first application, second utterance triggering second application), adding a time-based dimension to the speech recognition process that enables multi-application control.
2Speed
If speech recognition service directly enters parameters from user voice, then the processing speed is fast, but it incorrectly determines user intent and enters wrong parameters with mismatched formats
Solution Approach 1:
An intermediary processing step is introduced between voice input and parameter entry. The system receives the first text from speech recognition, validates it against the expected format of the target input field, and performs format conversion if necessary. This intermediary validation and conversion process ensures parameter accuracy while maintaining relatively fast processing speed.
Solution Approach 2:
The system performs preliminary format validation and conversion before entering the parameter into the input field. By checking whether the first text matches the required format in advance and converting it if needed, the system prevents incorrect parameter entry while maintaining efficient processing through automated preliminary checks.
3Productivity
If speech recognition service enters parameters without format validation, then the processing is simple and fast, but parameters with different formats are incorrectly entered into input fields
Solution Approach 1:
The system performs self-service format validation and conversion by automatically comparing the first text against the required input field format and converting it if necessary. This self-service approach maintains high productivity through automated processing while ensuring manufacturing precision by correcting format mismatches without requiring manual intervention.
Solution Approach 2:
The system implements feedback by comparing the first text against the expected format of the input field and using this comparison result to determine whether conversion is needed. This feedback mechanism ensures that parameters are entered with correct formatting while maintaining efficient automated processing through conditional conversion based on format mismatch detection.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic apparatus is provided. The electronic apparatus includes a housing, a touchscreen display positioned inside the housing and exposed through a first area of the housing, a microphone positioned inside the housing and exposed through a second area of the housing, at least one speaker positioned inside the housing and exposed through a third area of the housing, a wireless communication circuit positioned inside the housing, a processor positioned inside the housing and electrically connected to the touchscreen display, the microphone, the at least one speaker, and the wireless communication circuit, and a memory positioned in the housing and electrically connected with the processor.