Voice Input Processing for Personalized User Command Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Voice-activated devices, designed for multi-user environments, face challenges in managing user preferences and settings due to their universal nature, leading to unintended changes when multiple users interact with the device.

Innovation Solution

The device identifies and learns from historical user data and environmental factors to customize user commands, modifying actions based on user-specific and environmental characteristics, ensuring personalized interactions without the need for login systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice-activated devices are designed for multi-user environments with universal interface, then ease of operation is improved, but user preference management deteriorates leading to unintended changes

Engineering Contradiction:

Improveease of operationVSAvoiduser preference management

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system segments users by analyzing voice characteristics and interaction patterns to divide the multi-user environment into individual user profiles. Each user receives customized responses based on their segment, resolving the conflict between universal accessibility and personalized preference management.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes parameters such as voice tone, response style, and command interpretation based on identified user characteristics. By dynamically adjusting these parameters, the device maintains ease of operation for all users while ensuring reliable preference management through personalized interactions.

Inventive Principle:

Principle #35Parameter changes

2Ease of operation

If device uses natural language processing for voice commands, then ease of operation is improved, but difficulty of detecting and measuring user intent worsens

Engineering Contradiction:

Improveease of operationVSAvoiduser intent detection

Core Design Contradiction:

Ease of operationVSDifficulty of detecting and measuring

Solution Approach 1:

The system employs feedback mechanisms by analyzing user responses and interaction patterns to refine intent detection. Natural language commands are processed with contextual feedback from previous interactions, improving accuracy in detecting user intent while maintaining the ease of natural language operation.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary analysis of voice characteristics and contextual factors before processing commands. By pre-processing and categorizing input data, the device reduces the difficulty of detecting user intent while preserving the natural ease of operation.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10796693B2Modifying input based on determined characteristics

Publication Date: 2020.10.06 LENOVO SWITZERLAND INTERNATIONAL GMBH

AI summary

One embodiment provides a method, including: receiving, at a device, input; processing, using a processor, the input to identify at least one user command; identifying, using a processor, a characteristic related to the at least one user command; and performing an action based on the at least one command and the characteristic. Other aspects are described and claimed.