Context-Aware Voice Operation Integration for Existing Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face difficulties in adding voice operation functions due to the need for hard-coded programs and lack of consideration for user situations, resulting in numerous predefined voice commands.
Innovation Solution
A voice operation device with a task determination unit to identify processing based on system operation, a conversion unit to convert voice data into text data for command or parameter determination, and an operation unit to execute commands using the text data as parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If default voice commands are used in existing VUI systems, then the system can perform basic voice operations, but it requires hard-coded programs and cannot easily add unique voice operation functions
Solution Approach 1:
The patent introduces a conversion unit that acts as an intermediary between voice data and command determination. This unit converts voice data into text data, which then serves as input for command determination or setting parameter acquisition. This intermediary layer enables flexible voice operation addition without requiring hard-coded program structures, as the conversion and determination process is handled through configurable units rather than fixed code.
2Adaptability or versatility
If multiple predefined voice commands are defined for different tasks, then various operations can be performed, but the number of voice commands becomes large and complex
Solution Approach 1:
The patent implements a universal voice operation framework where a single voice input can serve multiple purposes depending on the operational context. The conversion unit processes voice data into text data that can be used for either command determination or setting parameter acquisition, depending on the current system state. This multi-functional approach reduces the need for separate voice commands for different operations, as the same voice processing pipeline adapts its function based on context.
Solution Approach 2:
The system dynamically determines whether converted text data should be used for command determination or setting parameter acquisition based on the current operational context. The task determination unit identifies the current task type, and this dynamic state information is used by the conversion unit to route the text data appropriately. This dynamic routing reduces the need for static, predefined voice commands for every possible operation scenario.
3Ease of operation
If voice commands are executed without considering user situation, then simple command execution is achieved, but the system cannot adapt to different task contexts
Solution Approach 1:
The patent implements a feedback mechanism where the task determination unit continuously monitors the current operational situation and provides this information back to the conversion unit. This feedback loop enables the system to adapt its voice command processing based on the current task context. The conversion unit uses this feedback to determine whether the converted text data should be interpreted as a command or as a setting parameter, thereby achieving context-aware voice operation while maintaining simple execution flow.
Data Source
AI summary
A task determination unit determines a type of processing being operated, on the basis of an operation situation of an existing system. A conversion unit converts voice data input during a predetermined operation of an HID into text data, and determines whether the text data is used for a command determination or a setting parameter according to operation content of the HID. A command determination unit determines a command by using the text data and the type of processing being operated, when it is determined that the text data is used for the command determination. An operation unit executes an operation corresponding to the determined command with respect to the existing system by using the text data as a parameter, when it is determined that the text data is used for the setting parameter.