Wearable Vision-Guided Control for Ambiguous Voice Commands
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wearable devices struggle to control electronic devices when a user's voice command lacks specific information about the target device, leading to ambiguity in execution.
Innovation Solution
A wearable device uses vision information from a camera to identify the target device when voice commands are insufficient, combining image recognition with voice input to determine user intent and control the appropriate electronic device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If voice command recognition is used to control electronic devices, then ease of operation is improved, but reliability deteriorates when target device information is omitted or ambiguous
Solution Approach 1:
The patent combines voice recognition technology with image recognition technology to control electronic devices. The processor integrates both voice commands and visual information from the camera to determine target devices, merging multiple input modalities to resolve ambiguity when voice commands alone are insufficient.
Solution Approach 2:
The camera acts as an intermediary device that captures images of the environment and provides visual information to the processor. This intermediary helps bridge the gap between ambiguous voice commands and precise device identification by enabling the system to visually locate and identify target devices.
2Measurement precision
If vision information from camera is added to identify target devices, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system performs preliminary actions by capturing images of the environment in advance and pre-processing visual information before voice commands are fully processed. The camera continuously captures environmental data, and the processor prepares visual information for later comparison with voice command context, enabling faster and more accurate target device identification.
Data Source
AI summary
An electronic device may include: a camera configured to acquire a current image by capturing an image of an environment around the electronic device; a voice input device configured to receive a user utterance from a user; a processor; and a memory configured to store therein instructions to be executed by the processor, in which, when the instructions are executed by the processor, the processor may be configured to: determine a user's intent based on the received user utterance; determine a target device to be controlled corresponding to the determined intent; and control the determined target device based on the determined intent, and to determine the target device.