AI Voice Recognition Device Selection System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In environments where multiple voice recognition devices from the same manufacturer are deployed, users face difficulties in accurately selecting the intended device to operate, leading to unnecessary power consumption and increased error rates due to shared starting words and signal-to-noise ratio-based responses.
Innovation Solution
A system and method that utilize artificial intelligence learning to identify users, analyze their intentions, and select the appropriate voice recognition device based on time and location, incorporating user identification, setting storage, and data learning units to differentiate between specific and common user intentions and device selections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If the same starting word is set for multiple voice recognition devices, then brand recognition is improved, but device selection accuracy deteriorates
Solution Approach 1:
The patent segments the single starting word recognition into multiple stages: first recognition (detecting any starting word), second recognition (identifying which specific device the user intends). This segmentation allows maintaining a common starting word for brand recognition while adding device-specific identification mechanisms to resolve ambiguity.
Solution Approach 2:
The patent introduces an intermediary selection process between the starting word detection and device execution. When multiple devices detect the same starting word, the system uses additional criteria (user position, device location, historical data) as intermediaries to determine the intended target device, preventing direct activation of wrong devices.
2Speed
If signal-to-noise ratio based selection is used, then response speed is improved, but user intention accuracy deteriorates
Solution Approach 1:
The patent performs preliminary actions beyond just SNR measurement. Before finalizing device selection, the system pre-processes additional information such as user position relative to devices, historical usage patterns, and device capability matching. This preliminary multi-criteria assessment ensures accurate intention recognition while maintaining responsive performance.
3Adaptability or versatility
If multiple voice recognition devices operate simultaneously, then service coverage is improved, but power consumption increases
Solution Approach 1:
The patent implements periodic action by putting voice recognition devices into sleep mode when not selected, and activating only the chosen device for processing. Instead of continuous operation of all devices, the system periodically activates only the necessary device based on user intention recognition, significantly reducing overall power consumption while maintaining service availability.
Data Source
AI summary
Disclosed is a device for controlling a plurality of voice recognition devices for determining and selecting a first voice recognition device that a user wants to use based on a point in time when the voice of the user is spoken or a place where the user spoke the voice. The device for controlling a plurality of voice recognition devices according to the present disclosure may be associated with an artificial intelligence module, a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to 5G service, etc.