Digital Assistant Output Concealment via Contextual Filtering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing solutions fail to dynamically filter audible responses from digital assistants based on user classification, surrounding context, or preconfigured privacy settings, leading to potential public disclosure of confidential information.

Innovation Solution

An information handling device receives an indication to provide output, identifies if the output contains confidential information, and alters it to conceal such information if it may be heard by others, using methods like adjusting volume, output device selection, or altering content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If digital assistants broadcast audible responses to user queries, then information accessibility and user experience are improved, but confidential information may be inadvertently disclosed to unauthorized individuals

Engineering Contradiction:
Improveinformation accessibilityVSAvoidconfidential information disclosure
Core Design Contradiction:
Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary classification of information to identify confidential content before broadcasting the audible response. This advance identification allows the system to prepare appropriate concealment measures, ensuring that confidential information is protected before it can be overheard by unauthorized individuals.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary processing layer between the digital assistant's response generation and the audible output. This intermediary analyzes the response content, identifies confidential information, and applies appropriate concealment techniques such as masking or summarization, thereby mediating between information accessibility and privacy protection.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Object-affected harmful factors

If the system alters output to conceal confidential information, then privacy protection is improved, but the completeness and accuracy of information transmission deteriorates

Engineering Contradiction:
Improveprivacy protectionVSAvoidinformation completeness
Core Design Contradiction:
Object-affected harmful factorsVSLoss of information

Solution Approach 1:

The system applies local quality by selectively concealing only the confidential portions of the response while leaving non-confidential information intact. This targeted approach ensures that privacy protection is applied precisely where needed, maintaining the completeness and accuracy of the overall information transmission.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent employs parameter changes by dynamically adjusting the level of information disclosure based on the presence of confidential content. The system can modify response parameters such as verbosity, detail level, or masking intensity to balance privacy protection with information completeness, altering the output characteristics rather than simply truncating information.

Inventive Principle:
Principle #35Parameter changes

3Object-affected harmful factors

If the system monitors and classifies output content, then confidential information protection is improved, but computational complexity and processing time increase

Engineering Contradiction:
Improveconfidential information protectionVSAvoidcomputational complexity
Core Design Contradiction:
Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The system segments the output analysis process into distinct stages: initial scanning for confidential keywords, detailed classification of identified content, and final determination of concealment requirements. This segmentation allows the system to apply computational resources selectively, reducing overall complexity while maintaining effective confidential information protection.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements self-service by enabling the system to automatically classify and identify confidential information using pre-configured criteria and machine learning models. This automated self-service approach reduces the need for complex manual monitoring and classification processes, thereby lowering computational complexity while maintaining protection effectiveness.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS10936276B2Confidential information concealment
Publication Date: 2021.03.02 LENOVO SWITZERLAND INTERNATIONAL GMBH
  • US10936276B2 patent drawing
  • US10936276B2 patent drawing
  • US10936276B2 patent drawing

AI summary

One embodiment provides a method, including: receiving, at an information handling device, an indication to provide output; identifying that the output comprises confidential information; determining, using a processor, that the output may be heard by at least one other user; and altering, responsive to the determining, the output to conceal the confidential information. Other aspects are described and claimed.