Automated Assistant Media Trigger Suppression

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In environments with multiple automated assistant devices, unintended activations can occur due to audio data from digital media being processed by one device triggering hotword detection in other nearby devices, leading to negative user experiences and resource wastage.

Innovation Solution

A system that detects and suppresses triggers in audio segments of digital media likely to activate nearby automated assistant devices by identifying active capabilities of nearby devices and modifying the media to prevent unintended activations, using techniques such as inserting digital watermarks or adjusting audio segments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If hotword detection is performed continuously by multiple automated assistant devices in an environment, then the ability to respond to user commands is improved, but unintended activations from digital media audio segments increase

Engineering Contradiction:
Improveresponse to user commandsVSAvoidunintended activations
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary detection of hotwords in digital media audio segments before playback occurs. By analyzing the media content in advance and identifying segments that contain hotwords or similar-sounding phrases, the system can suppress or modify these segments during playback to prevent unintended activations of automated assistants in the environment.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If audio data from digital media is processed by automated assistants, then the assistants can respond to commands, but computational resources are wasted on unintended activations

Engineering Contradiction:
Improvecommand response capabilityVSAvoidcomputational resources
Core Design Contradiction:
ProductivityVSLoss of energy

Solution Approach 1:

The system performs preliminary analysis of digital media audio segments to identify those containing hotwords before they are played back. By detecting and suppressing these problematic segments in advance, the system prevents wasted computational resources from being consumed by unintended hotword detection and processing operations.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system applies preliminary anti-action by suppressing or modifying audio segments that contain hotwords before they can trigger unintended automated assistant activations. This preventive measure counteracts the potential harmful effect of resource wastage by blocking the problematic audio data from reaching the automated assistants' processing systems.

Inventive Principle:
Principle #9Preliminary anti-action

3Adaptability or versatility

If multiple automated assistant devices are deployed in close proximity, then service coverage is improved, but cross-triggering from digital media increases

Engineering Contradiction:
Improveservice coverageVSAvoidcross-triggering
Core Design Contradiction:
Adaptability or versatilityVSObject-generated harmful factors

Solution Approach 1:

The system performs preliminary detection of hotwords in digital media before playback, enabling it to suppress or modify audio segments that would otherwise trigger cross-triggering between multiple automated assistant devices. This allows multiple devices to coexist in close proximity without causing unintended activations.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20240233735A1Detecting and suppressing commands in media that may trigger another automated assistant
Publication Date: 2024.07.11 GOOGLE LLC
  • US20240233735A1 patent drawing
  • US20240233735A1 patent drawing
  • US20240233735A1 patent drawing

AI summary

Techniques are described herein for detecting and suppressing commands in media that may trigger another automated assistant. A method includes: determining, for each of a plurality of automated assistant devices in an environment that are each executing at least one automated assistant, an active capability of the automated assistant device; initiating playback of digital media by an automated assistant; in response to initiating playback, processing the digital media to identify an audio segment in the digital media that, upon playback, is expected to trigger activation of at least one automated assistant executing on at least one of the plurality of automated assistant devices in the environment, based on the active capability of the at least one of the plurality of automated assistant devices; and in response to identifying the audio segment in the digital media, modifying the digital media to suppress the activation of the at least one automated assistant.