Voice Sensitive Information Interruption via Noise Cancellation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users often inadvertently disclose sensitive information to digital assistants, which can be intercepted by third parties, highlighting a need for secure protection mechanisms to prevent such unauthorized disclosure.

Innovation Solution

A system and method that analyze vocalizations to detect sensitive information and output noise canceling sounds to prevent its receipt by secondary devices, using a primary device equipped with a microphone, processing circuit, and speaker to compare vocal content against stored sensitive information data and intervene when sensitive information is detected.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users interact with digital assistants using voice commands, then ease of operation is improved, but sensitive information may be inadvertently disclosed

Engineering Contradiction:
Improvevoice interactionVSAvoidsensitive information disclosure
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

A primary device is introduced as an intermediary between the user and the secondary device. This primary device includes a microphone to detect vocalizations, processing circuitry to analyze the content, and a speaker to output noise canceling sounds. The intermediary actively monitors and blocks sensitive information from reaching the secondary device while allowing legitimate interactions to pass through.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary analysis of vocalizations before they reach the secondary device. By detecting and analyzing the content of voice commands in advance, the system can identify sensitive information and preemptively block it using noise canceling sounds, preventing the harmful disclosure before it occurs.

Inventive Principle:
Principle #9Preliminary anti-action

2Reliability

If noise canceling sounds are output to block sensitive information, then protection of sensitive information is improved, but user comfort may be degraded

Engineering Contradiction:
Improveprotection of sensitive informationVSAvoiduser comfort
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The noise canceling sound is applied locally and selectively only when sensitive information is detected. The system maintains normal audio quality and user comfort during regular operations, while activating the noise canceling function only in specific local instances where sensitive information is identified, thus balancing protection with comfort.

Inventive Principle:
Principle #3Local quality

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

Effectively prevents the disclosure of sensitive information to secondary devices, enhancing user privacy by interrupting the transmission of sensitive data and educating users about their disclosures.

Implementation Method 1

controlling, based on determining that the voice input contains some sensitive information, a speaker of the primary device to output a noise canceling sound configured to prevent the secondary device from receiving any subsequently vocalized sensitive information

Methodology Applied
Scientific EffectNoise canceling: Acoustic Absorption

Data Source

PatentUS12158972B2Interrupting receipt of sensitive information
Publication Date: 2024.12.03 WELLS FARGO BANK NA
  • US12158972B2 patent drawing
  • US12158972B2 patent drawing
  • US12158972B2 patent drawing

AI summary

A method includes detecting an initial vocalization by a user in an environment including a primary device and a secondary device, analyzing the initial vocalization to determine whether a future vocalization is likely to contain sensitive information based on the initial vocalization where the future vocalization is a potential future vocalization, and controlling, based on determining that the future vocalization is likely to contain sensitive information, a speaker of the primary device to output a noise canceling signal configured to prevent the secondary device from detecting the future vocalization.