Voice Input Ambiguity Resolution via User Selection Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Information processing devices, such as smart speakers and smartphones, face challenges in executing user requests accurately when the voice commands are ambiguous, leading to unclear processing details.
Innovation Solution
An information processing device with an input unit, extracting unit, output unit, and specifying unit that receives voice operations, extracts processing details, and outputs response information to allow users to select the appropriate processing detail when ambiguity occurs, enabling the device to specify the intended action.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the information processing device analyzes ambiguous voice utterances, then it can process user inputs, but it cannot execute processing as expected because the utterance is ambiguous
Solution Approach 1:
The system outputs response information presenting multiple possible processing details to the user, then receives user input to select the correct one. This feedback loop allows the system to resolve ambiguity by letting the user clarify their intent, thereby maintaining both versatility in accepting various voice inputs and reliability in executing the correct action.
Solution Approach 2:
The system performs preliminary analysis of the ambiguous voice utterance to identify multiple possible processing details before executing any action. By pre-identifying potential interpretations and presenting them to the user for selection, the system avoids premature execution of incorrect actions while maintaining the ability to process diverse inputs.
2Adaptability or versatility
If the device extracts multiple processing details from ambiguous voice operations, then it can cover all possible interpretations, but it increases the complexity of specifying the correct processing detail
Solution Approach 1:
Instead of attempting to automatically resolve the complexity of selecting among multiple processing details, the system uses feedback by presenting the extracted processing details to the user and receiving their selection. This transfers the specification task to the user, maintaining completeness of extraction while avoiding the complexity burden on the system's automatic specification mechanisms.
3Reliability
If the device outputs response information for user selection, then it can clarify ambiguous processing details, but it increases the interaction time between user and device
Solution Approach 1:
The system performs preliminary extraction of multiple processing details and prepares the response information in advance, presenting all possible options to the user simultaneously. This allows the user to select the correct interpretation in a single interaction step rather than requiring multiple iterative clarifications, thereby reducing the total interaction time while maintaining accurate specification.
Data Source
AI summary
An information processing device includes an input unit, an extracting unit, an output unit, and a specifying unit. The input unit receives a voice operation. The extracting unit extracts a processing detail corresponding to the voice operation received by the input unit. When the processing detail corresponding to the voice operation received by the input unit cannot be specified, the output unit outputs response information for the user to make a selection of at least one processing detail from a plurality of processing details extracted by the extracting unit. The specifying unit specifies the processing detail selected from among the plurality of processing details contained in the response information as the processing detail corresponding to the voice operation received by the input unit.