Voice-Guided Object Identification Using Representative Properties
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to accurately determine objects indicated by voice commands in augmented and mixed reality environments, limiting the effectiveness of services like the metaverse.
Innovation Solution
An electronic device is equipped with computer-executable instructions to detect candidate objects, determine a representative property, and output feedback based on a specified property value, allowing precise identification of objects through voice commands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If voice commands are used to identify objects in AR/MR environments, then user interaction convenience is improved, but object identification accuracy deteriorates due to ambiguity in voice commands
Solution Approach 1:
The system provides feedback by outputting candidate objects and their representative properties to the user, then uses the user's additional commands to refine the selection. This feedback loop continues until the target object is accurately identified, resolving the contradiction between convenient voice input and accurate object identification.
Solution Approach 2:
The system performs preliminary actions by detecting candidate objects and determining their representative properties before the final object is identified. This preliminary filtering and presentation of options reduces the ambiguity of voice commands while maintaining ease of use.
2Measurement precision
If multiple candidate objects are detected and presented, then object identification accuracy is improved, but system complexity increases due to additional processing steps
Solution Approach 1:
The system extracts only the representative properties from multiple candidate objects and presents them to the user. By focusing on key distinguishing properties rather than all possible attributes, the system maintains high identification accuracy while reducing processing complexity.
Solution Approach 2:
The system performs partial action by selecting and presenting only the most relevant representative properties of candidate objects rather than analyzing all possible properties. This selective approach improves identification accuracy while avoiding excessive processing complexity.
Data Source
AI summary
An electronic device is provided. The electronic device includes memory storing one or more computer programs, and one or more processors communicatively coupled to the memory, wherein the one or more computer programs include computer-executable instructions that, when executed by the one or more processors, cause the electronic device to detect, based on a voice command obtained from a user, candidate objects in a viewing region of the user, determine a representative property among candidate properties of the detected candidate objects, output, for each of the detected candidate objects, feedback based on a property value of the representative property of a corresponding candidate object, and determine, based on obtaining an additional command that specifies a property value of the representative property from the user, an object indicated in the voice command as a candidate object having the property value of the representative property specified by the additional command.