Voice-Enabled Device Selection Using Directional Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current voice-enabled devices face challenges in accurately selecting the correct device to respond to a user's intention due to differences in device status and recognition methods among IoT devices, leading to communication overload and incorrect device activation.
Innovation Solution
A method that determines the position where a wakeup word is spoken by analyzing the direction and location information from multiple voice recognition devices, using a threshold situation detection and classification model to select the closest device positioned in the intended direction, thereby reducing communication load and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all IoT devices transmit voice signals to the home IoT server for selection, then the server can choose a response device, but communication overload occurs and computation becomes excessively large
Solution Approach 1:
The patent applies preliminary action by having IoT devices perform direction-based filtering before transmitting voice signals. Devices determine the direction from which they received the wakeup word and compare it with the predetermined direction (e.g., user's facing direction). Only devices whose reception direction matches the predetermined direction transmit voice signals to the server, reducing communication load while maintaining selection accuracy.
2Quantity of substance
If direction information is used to filter voice signals before transmission, then communication load is reduced, but device selection accuracy may be affected
Solution Approach 1:
The patent implements feedback by using the server to determine the user's predetermined direction (e.g., facing direction) and sending this information back to IoT devices. Devices then use this feedback to filter and transmit only those voice signals received from directions matching the predetermined direction, ensuring accurate device selection while reducing communication load.
3Adaptability or versatility
If multiple IoT devices have different recognition methods and statuses, then system versatility is improved, but correct device activation becomes difficult
Solution Approach 1:
The patent applies local quality by making each IoT device's transmission decision dependent on its local reception direction characteristics. Each device independently determines whether its wakeup word reception direction matches the predetermined direction, and only transmits if there is a match. This localized filtering approach maintains system versatility while ensuring that only relevant devices are activated.
Data Source
AI summary
A method and apparatus for selecting a voice-enabled device are disclosed. The voice-enabled device selecting apparatus may reduce the amount of communication load between a home IoT server and home IoT devices and minimize the amount of computation of the home IoT server by obtaining information related to the direction from which each voice recognition device receives a wakeup word from a plurality of voice recognition devices, determining the position where the wakeup word is spoken by using the information related to the direction from which the wakeup word is received, and selecting the voice recognition device closest to the speech position as a voice-enabled device. At least one of the voice enable device selecting apparatus, IoT device, and a server may be associated with an artificial intelligence (AI) module, an unmanned aerial vehicle (UAV) (or drone), a robot, an augmented reality (AR) device, a virtual reality (VR) device, and a device related to a 5G service.