Voice Recognition Device Network Coordination via Local Suitability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In environments with multiple voice recognition devices, independent operation leads to undesirable duplicative actions and increased latency due to the need for a master device to coordinate commands, which can fail if the master device is offline.

Innovation Solution

Each device in a network independently determines whether it is best suited to process speech-based commands by evaluating metadata such as timing, input quality, and content, allowing for local selection and processing without the need for a master device, thereby reducing duplicative actions and ensuring system reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a master device coordinates among multiple voice recognition devices, then command processing coordination is improved, but system latency increases and reliability decreases when master device is offline

Engineering Contradiction:
Improvesystem coordination reliabilityVSAvoidcommand processing latency
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent extracts the coordination function from a centralized master device and distributes it to all voice recognition devices. Each device independently evaluates its suitability to process commands using metadata such as audio signal strength, distance to user, and current task status, eliminating the need for master device mediation and reducing latency while maintaining coordination reliability

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The coordination system is segmented into independent decision-making units where each voice recognition device autonomously determines whether to process commands based on local metadata evaluation. This segmentation eliminates the single point of failure (master device) and reduces coordination latency while maintaining system-wide coordination

Inventive Principle:
Principle #1Segmentation

2Productivity

If multiple voice recognition devices operate independently, then processing speed is improved, but duplicative actions occur causing harmful effects

Engineering Contradiction:
Improvecommand processing speedVSAvoidduplicative actions
Core Design Contradiction:
ProductivityVSObject-generated harmful factors

Solution Approach 1:

The patent implements feedback mechanisms where each voice recognition device evaluates metadata including audio signal strength, distance to user, and current task status to determine suitability for command processing. This feedback loop enables independent devices to coordinate implicitly by selecting the most suitable device, preventing duplicative actions while maintaining fast processing speed

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system changes parameters used for device selection dynamically, considering metadata such as audio signal strength, distance to user, and current task status. This parameter-based selection ensures that only the most suitable device processes each command, preventing duplicative actions while maintaining high processing speed

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3407348B1Coordination among multiple voice recognition devices
Publication Date: 2022.07.27 HARMAN INT IND INC
  • EP3407348B1 patent drawingFigure 1
  • EP3407348B1 patent drawingFigure 2
  • EP3407348B1 patent drawingFigure 3

AI summary

One embodiment of the invention sets forth a mechanism for selecting a voice recognition device included in a network of such devices for processing audio commands corresponding to a detected speech event. The voice recognition devices in the network individually determine which one of the devices is best suited to process the audio commands corresponding to the speech event. In operation, each of the voice recognition devices that detected the same speech event independently selects the same device for processing the audio command. Since each of the voice recognition devices, including the selected device, selects the same device for processing the audio command, the voice recognition devices do not need to share information related to the selected device with each other.