Voice Assistant Control for Multi-Room Privacy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Voice assistants in multi-room settings face challenges in protecting privacy, complying with data protection guidelines, and preventing unwanted disruptions, particularly when used by visitors or in environments with multiple individuals.

Innovation Solution

A method for voice assistance control that includes room detection, unit membership affiliation, and identification using acoustic signals from microphones, with speech differentiation and noise measurement, to determine the number of people and their affiliation, enabling secure data communication and multi-room service availability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If voice assistant devices are distributed throughout a room unit to enable multi-room usage, then the multi-room experience and accessibility are improved, but privacy protection and prevention of unwanted activation become more difficult

Engineering Contradiction:
Improvemulti-room experienceVSAvoidprivacy violations
Core Design Contradiction:
Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The system segments the room unit into multiple zones with different privacy levels. Each room is treated as a separate entity with its own voice assistant device that can independently detect and respond to voice commands. The system determines which room the user is in and routes voice commands to the appropriate device, enabling multi-room functionality while maintaining privacy boundaries between rooms.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The voice assistant device acts as an intermediary between the user and the smart home system. It detects voice commands, determines the user's location within the room unit, and routes commands to the appropriate services. This intermediary function allows the system to provide multi-room access while controlling which devices receive which commands based on user location and privacy settings.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Speed

If voice assistant devices activate on any acoustic signal to respond quickly, then the response time is improved, but unwanted activation from conversations or background noise increases

Engineering Contradiction:
Improveresponse timeVSAvoidunwanted disruptions
Core Design Contradiction:
SpeedVSObject-generated harmful factors

Solution Approach 1:

The system applies different activation thresholds and sensitivity levels to different voice assistant devices based on their local environment. Each device is configured with local quality parameters that determine its responsiveness to voice signals. This allows the system to maintain quick response times in quiet environments while reducing unwanted activation in noisier areas or when conversations are detected.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The activation characteristics of voice assistant devices are made dynamic rather than static. The system continuously monitors the acoustic environment and adjusts the sensitivity and activation threshold of each device in real-time. This dynamic adjustment allows the system to respond quickly when appropriate while avoiding unwanted activation during conversations or in noisy conditions.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If all voice assistant devices in a room unit are monitored to determine user location, then the accuracy of room detection is improved, but the system complexity and energy consumption increase

Engineering Contradiction:
Improveroom detection accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system uses partial monitoring of voice assistant devices rather than requiring all devices to be fully active. When a voice command is detected by any device, only the relevant devices in the user's current room need to process and respond to the command. This partial action approach maintains accurate room detection while reducing the overall system complexity and energy consumption compared to having all devices continuously monitoring and processing all commands.

Inventive Principle:
Principle #16Partial or excessive action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach effectively protects privacy, ensures data protection compliance, and prevents disruptions by only allowing authorized voice commands and services, while maintaining a seamless multi-room experience.

Implementation Method 1

the number of people located within the at least one room is determined on the basis of an acoustic signal determined by a microphone of the at least one voice assistance device

Methodology Applied
Scientific EffectAcoustic signal detection: Sound

Data Source

PatentEP4057165B1Voice assistance control
Publication Date: 2024.07.17 DEUTSCHE TELEKOM AG
  • EP4057165B1 patent drawingFigure 1
  • EP4057165B1 patent drawingFigure 2

AI summary

A method for voice assistant control of a spatial unit (1) comprising at least one room (2a, 2b, 2c, 2d), comprising the following steps: - a room detection step (101) in which the number of persons (3a, 3b, 3c, 3d, 3e, 3f, 3g) located within the at least one room (2a, 2b, 2c, 2d) is determined based on an acoustic signal detected by a microphone of the at least one voice assistant device (4a, 4b, 4c, 4d), - a spatial unit detection step (102) in which the affiliation of the at least one person (3a, 3b, 3c, 3d, 3e, 3f, 3g) to the spatial unit (1) is detected, and - an identification step (103) in which the at least one person in the at least one room (2a, 2b, 2c, 2d) person located (3a, 3b, 3c, 3d, 3e, 3f) is identified.