Voice Recognition Device Segmentation for Cross-Device Activation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The activation of voice recognition in multiple devices can lead to malfunctions when similar names or keywords are used, causing unintended activation of voice recognition functions, especially with the increasing use of mobile and wearable terminals.

Innovation Solution

A system where devices can modify their stored voice recognition information based on relationships with other devices, including distance and communication, to prevent erroneous activation by sharing and updating activation words and dictionaries, thus avoiding unintended voice recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If multiple devices use the same voice recognition activation word, then voice recognition can be activated conveniently, but unintended activation of other devices occurs causing malfunctions

Engineering Contradiction:

ImproveVoice recognition activation convenienceVSAvoidVoice recognition accuracy

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent segments the voice recognition system by device, assigning unique identification information to each device. The activation word recognition is segmented into device-specific recognition, where each device recognizes only its own activation word combined with its unique identification, preventing cross-device misactivation while maintaining convenient voice-based activation for each device.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces unique identification information as an intermediary element between the activation word and device activation. This intermediary distinguishes which device should be activated when an activation word is spoken, allowing multiple devices to use similar activation words without causing unintended activation, thus resolving the contradiction between convenience and reliability.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Device complexity

If similar names are given to devices for differentiation, then device identification is simplified, but erroneous activation of wrong devices occurs

Engineering Contradiction:

ImproveDevice naming complexityVSAvoidDevice activation accuracy

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent segments the device identification into two parts: a simple name (activation word) and a unique identification code. This segmentation allows devices to have simple, similar names for easy differentiation by users, while the system internally uses the unique identification to ensure accurate device activation, preventing erroneous activation despite similar names.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent creates a composite identification system combining a simple activation word (name) with a unique identification code. This composite structure allows the device to maintain user-friendly simple names while incorporating the precision of unique identifiers, resolving the contradiction between simplicity and accuracy in device differentiation.

Inventive Principle:

Principle #40Composite materials

Data Source

PatentUS10490192B2Apparatus, method, non-transitory computer-readable medium and system for modifying voice recognition information

Publication Date: 2019.11.26 SONY GROUP CORP

AI summary

There is provided an apparatus including a communication unit configured to transmit information permitting a second apparatus to modify stored voice recognition information based on a relationship between the first apparatus and the second apparatus.