Voice Command Response Level Control for Electronic Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice command recognition systems in electronic devices often fail to accurately interpret user intentions, leading to unintended actions when the spoken command does not match a pre-stored command, resulting in undesired services or feedback.
Innovation Solution
An electronic device with a processor and memory that determines a response level for user voice inputs, allowing immediate action if the level is a first response or delaying action until an additional event is detected if it's a second response level, thereby aligning the device's actions with the user's intended commands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the electronic device performs voice command recognition using pre-stored command combinations, then command execution speed is improved, but accuracy in interpreting user intention deteriorates when the spoken command does not match pre-stored commands
Solution Approach 1:
The system performs preliminary voice recognition to convert spoken commands into text, then conducts a first determination to check if the recognized text matches pre-stored command combinations. This preliminary action enables quick execution for standard commands while preparing for further processing if needed.
Solution Approach 2:
The system dynamically adjusts its processing path based on the first determination result. When a match is found, it executes the pre-stored command immediately for speed. When no match is found, it transitions to a second determination process that performs meaning-level analysis to accurately interpret user intention, thus adapting the processing depth to the specific situation.
2Measurement precision
If the electronic device performs meaning level analysis using ontology or semantic parsing, then user intention interpretation accuracy is improved, but processing time increases
Solution Approach 1:
The voice command recognition process is segmented into two distinct determination stages. The first determination checks for exact matches with pre-stored commands, handling simple cases quickly. The second determination performs comprehensive meaning-level analysis only when needed, dividing the processing workload to minimize overall time while maintaining accuracy.
Solution Approach 2:
The system applies partial action by performing only the necessary level of analysis for each command. For standard commands that match pre-stored combinations, no meaning-level analysis is performed. For non-matching commands, the full meaning-level analysis with ontology and semantic parsing is applied, ensuring accuracy without unnecessary processing overhead.
3Speed
If the electronic device performs a command corresponding to user voice immediately, then response speed is improved, but unintended actions occur when the spoken command does not match expected commands
Solution Approach 1:
The system uses feedback from the first determination to control the execution flow. When the recognized text matches a pre-stored command, the system executes immediately with high reliability. When no match is found, the feedback triggers a second determination that performs meaning-level analysis to accurately understand user intention before execution, preventing unintended actions while maintaining fast response for standard commands.
Data Source
AI summary
An electronic device and a method for controlling the electronic device are disclosed. The electronic device includes a memory and a processor electrically connected with the memory. The memory stores instructions to be executed by the processor. The processor is configured to obtain a user voice, determine a response level of the user voice, when the response level of the user voice is a first response level, perform an operation corresponding to the user voice based on a time point of obtaining the user voice, and when the response level of the user voice is a second response level, perform the operation corresponding to the user voice based on a time point of detecting an additional event.