Augmented Reality Voice Command Recognition via Object Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users of electronic devices with numerous applications and functions face difficulty in recognizing voice commands due to the vast number of options, making it challenging to perform intended actions without a separate interface for voice commands.
Innovation Solution
An electronic device equipped with an augmented reality module that recognizes external objects and displays corresponding text, allowing users to provide voice commands to execute specific applications or functions by recognizing external objects and displaying relevant text through a display module, and processing voice commands to execute corresponding actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the electronic device provides numerous applications and functions, then the device functionality is improved, but the user's ability to recognize voice commands deteriorates
Solution Approach 1:
The patent segments the large set of voice commands by associating them with external objects in the user's field of view. Instead of presenting all commands at once, the system divides them into object-specific groups, making recognition easier while maintaining comprehensive device functionality.
Solution Approach 2:
The patent introduces external objects as intermediaries between the user and voice commands. Objects serve as visual mediators that help users identify and select appropriate commands without needing to remember all available options, thus improving ease of operation while preserving device versatility.
2Ease of operation
If a separate interface for voice commands is provided, then voice command recognition is improved, but the device complexity increases
Solution Approach 1:
The patent merges the voice command interface with the existing augmented reality display by overlaying command information on top of the visual field. This integration allows voice command recognition to improve without adding a separate physical interface, thereby avoiding increased device complexity.
Solution Approach 2:
The patent adds a visual dimension to voice command interaction by displaying text overlays in the user's field of view. This dimensional addition provides command information without requiring a separate physical interface layer, improving recognition while maintaining interface simplicity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic device is provided. The electronic device includes a display configured to display information, and an augmented reality module that is implemented by a processor, the augmented reality module configured to recognize an external object for the electronic device, and display at least one text corresponding to a voice command corresponding to an application or function related to the external object, through the display.