Virtual Assistant Activation via Combined Audio and Motion Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing digital assistants on handheld devices face challenges in energy efficiency, often consuming unnecessary power due to accidental activation from either audio or motion inputs alone, leading to reduced battery life and inefficient user interactions.

Innovation Solution

A method that detects both audio and motion inputs to initiate a virtual assistant session, eliminating the need for a spoken trigger and preventing inadvertent activation, thereby optimizing power usage and interaction efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the digital assistant is activated based on audio input alone, then the user can easily initiate the assistant, but accidental activation increases and energy efficiency decreases

Engineering Contradiction:
Improveease of initiationVSAvoidenergy efficiency
Core Design Contradiction:
Ease of operationVSLoss of energy

Solution Approach 1:

The patent combines audio input detection with motion sensor detection to initiate the digital assistant. The system requires both audio input (such as wake word) and corresponding motion input (device raised to mouth) to activate the assistant, preventing accidental activation while maintaining ease of use. This merging of multiple activation modalities resolves the contradiction by reducing false activations and energy waste without complicating the user interaction significantly.

Inventive Principle:
Principle #5Merging (Combining)

2Loss of energy

If the digital assistant is activated based on motion input alone, then accidental activation from audio alone is prevented, but the ease of operation decreases

Engineering Contradiction:
Improveenergy efficiencyVSAvoidease of initiation
Core Design Contradiction:
Loss of energyVSEase of operation

Solution Approach 1:

The system merges audio and motion detection requirements to activate the digital assistant. By requiring both modalities, the system maintains energy efficiency by preventing spurious activations while preserving ease of operation through intuitive combined gestures and speech. The motion sensor detects device raising toward the mouth, and the audio sensor detects the wake word, with both signals required for activation.

Inventive Principle:
Principle #5Merging (Combining)

3Loss of energy

If the digital assistant requires both audio and motion inputs, then energy efficiency improves and accidental activation is reduced, but the device complexity increases

Engineering Contradiction:
Improveenergy efficiencyVSAvoiddevice complexity
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

The patent applies multi-functionality by using the motion sensor system to serve dual purposes: detecting user gestures for activation and providing contextual information about device orientation and movement. The audio system similarly serves multiple functions including wake word detection and speech command recognition. This universal approach reduces the need for separate dedicated components for each function, thereby limiting the increase in device complexity while achieving improved energy efficiency.

Inventive Principle:
Principle #6Universality (Multi-functionality)

4Speed

If the digital assistant continuously monitors audio and motion inputs, then the response time is reduced, but power consumption increases

Engineering Contradiction:
Improveresponse timeVSAvoidpower consumption
Core Design Contradiction:
SpeedVSUse of energy by moving object

Solution Approach 1:

The system implements periodic monitoring of audio and motion inputs rather than continuous full-processing monitoring. The device periodically samples sensor data to detect activation patterns, and only initiates full audio processing and assistant activation when both motion and audio signals are detected within a time window. This periodic action reduces power consumption while maintaining fast response time for legitimate user activations.

Inventive Principle:
Principle #19Periodic action

Data Source

PatentUS11907436B2Raise to speak
Publication Date: 2024.02.20 APPLE INC
  • US11907436B2 patent drawing
  • US11907436B2 patent drawing
  • US11907436B2 patent drawing

AI summary

Systems and processes for operating an intelligent automated assistant are provided. An example process includes detecting input representing motion of an electronic device and sampling an audio input with a microphone of the electronic device. The example process further includes determining, based on the audio input and the input representing motion of the electronic device, whether to initiate a virtual assistant session. In accordance with a determination to initiate the virtual assistant session, the example process includes initiating the virtual assistant session. In accordance with a determination not to initiate the virtual assistant session, the example process includes forgoing initiating the virtual assistant session.