Voice-Guided GUI Input with Audio Confirmation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in controlling applications on devices using voice input without visual feedback, particularly when hands are occupied or unable to manipulate the device, leading to increased time and uncertainty in input selection due to varied user interfaces.
Innovation Solution
A method and apparatus that utilize voice inputs to guide users through application execution by outputting audio signals with induced inquiries for input fields, allowing users to set values without direct screen manipulation, and incorporating artificial intelligence and external databases for accurate input determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If voice input is used to control application without visual feedback, then hands-free operation is enabled, but user uncertainty about input selection increases
Solution Approach 1:
The system provides audio feedback by reading back the selected input values to the user through synthesized speech. When a user provides voice input for an input field, the system confirms the recognized value by speaking it back, allowing the user to verify correctness without visual screen access. This closed-loop feedback mechanism resolves the information loss caused by hands-free operation.
Solution Approach 2:
The system introduces an audio intermediary layer between the user and the application interface. Instead of direct visual interaction with UI elements, the user communicates through voice and receives confirmation through audio output. This intermediary audio channel compensates for the lack of visual feedback during hands-free operation.
2Ease of operation
If each user interface is controlled by voice input, then hands-free control is achieved, but time used for controlling application increases
Solution Approach 1:
The system performs preliminary action by pre-defining input field types and their associated voice recognition grammars before user interaction. Common input fields (name, address, phone number) are pre-configured with expected formats and valid values, allowing the voice recognition system to quickly process and validate user input without extensive real-time analysis, thereby reducing control time.
Solution Approach 2:
The system changes parameters by adapting the voice recognition complexity based on input field type. For simple fields like yes/no selections, the system uses simplified recognition with fewer possibilities. For complex fields, it employs more sophisticated grammars. This dynamic parameter adjustment optimizes recognition speed and accuracy, reducing overall control time.
3Measurement precision
If voice recognition rate is enhanced by using field information, then recognition accuracy improves, but system complexity increases
Solution Approach 1:
The system segments the voice recognition process into distinct components: input field identification, grammar selection, voice recognition execution, and result validation. Each component handles a specific aspect of the recognition task, allowing for modular implementation and reuse. This segmentation improves recognition accuracy while managing system complexity through organized, reusable modules.
Solution Approach 2:
The system implements universal voice recognition components that can handle multiple input field types through a common framework. The same voice recognition engine processes different field types by loading appropriate grammars, and the same audio output mechanism provides feedback for all field types. This multi-functionality approach improves recognition rates across diverse fields without proportionally increasing system complexity.
Data Source
Figure 1A~1B
Figure 2A~2B
Figure 3
AI summary
Provided is a device for executing an application including a graphics user interface (GUI) for receiving an input value of an input field, the device including an audio output unit, a user input unit receiving a user input to request execution of the application, and a control unit configured to output, through the audio output unit, an audio signal indicating an induced inquiry corresponding to the input field, based on whether the user input is a voice input, to receive a voice input indicating a response to the induced inquiry, and to execute the application by setting an input value for the input field based on the voice input indicating the response to the induced inquiry.