Audio Context Detection for Communication Terminals

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current communication networks struggle to accurately determine user context, leading to inappropriate content or service selections due to incomplete or inaccurate user profiles and lack of consideration for the user's environment and situation.

Innovation Solution

A device and method that utilize audio signal analysis to identify predefined elementary contexts, combining these to determine refined contexts, allowing for more precise user profiling and context-based service offerings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If user profiles are used for content selection, then automated content selection is enabled, but the precision of user context information is insufficient

Engineering Contradiction:
Improveautomated content selectionVSAvoiduser context precision
Core Design Contradiction:
Extent of automationVSMeasurement precision

Solution Approach 1:

The patent replaces manual profile creation and static user information with automatic audio-based context detection. The system uses audio signal processing to automatically detect user environment and situation, substituting the mechanical process of manual profiling with an automated acoustic detection system that continuously updates context information.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the audio processing system to automatically detect and interpret user context without external intervention. The microphone captures audio signals, the processor analyzes them to determine environment and situation, and the system automatically adjusts content selection based on this self-detected context information.

Inventive Principle:
Principle #25Self-service

2Device complexity

If only location information is used for context determination, then geographical positioning is simplified, but the global context understanding is incomplete

Engineering Contradiction:
Improvecontext determination complexityVSAvoidglobal context information
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The patent merges location information with audio-based environment and situation detection. Instead of relying solely on GPS coordinates, the system combines spatial data with acoustic analysis of the user's surroundings, merging multiple information sources to create a comprehensive context profile that includes both where the user is and what their environment entails.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system segments context determination into multiple independent components: location detection, audio signal capture, environment classification, and situation recognition. Each component processes specific aspects separately and feeds results to a unified context model, allowing complex global context to be built from simpler segmented elements.

Inventive Principle:
Principle #1Segmentation

3Measurement precision

If audio signal analysis is implemented for context detection, then user environment and situation are accurately identified, but device complexity increases

Engineering Contradiction:
Improvecontext detection accuracyVSAvoidaudio processing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential audio features needed for context detection rather than processing the entire audio signal spectrum. The system identifies and extracts key acoustic characteristics such as noise levels, speech presence, and environmental sound patterns, discarding redundant information to simplify processing while maintaining detection accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system introduces an intermediary audio processing layer that translates raw microphone signals into meaningful context parameters. This intermediary processing stage converts complex audio waveforms into simplified environment and situation classifications, mediating between the raw audio input and the application-level context requirements.

Inventive Principle:
Principle #24Intermediary (Mediator)

4Productivity

If real-time context monitoring is implemented, then content selection relevance is improved, but energy consumption increases

Engineering Contradiction:
Improvecontent selection relevanceVSAvoidterminal energy consumption
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The system implements periodic audio sampling rather than continuous monitoring. The microphone captures audio signals at intervals, and the processor analyzes these periodic samples to update context information. This periodic action maintains content selection relevance while reducing energy consumption compared to continuous real-time analysis.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system performs partial audio analysis by focusing only on specific audio features and contexts that are most relevant for content selection. Rather than analyzing all aspects of the audio environment equally, it selectively processes only the partial information necessary for determining user situation and environment, reducing computational load and energy usage.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP2058802B1Device and method for obtaining the contexts of users of communication terminals, based on audio signals captured in their environment
Publication Date: 2010.12.22 ALCATEL LUCENT SA
  • EP2058802B1 patent drawingFigure 1~2

AI summary

The device (D) has an analyzing unit (MA) arranged in a social environment for comparing received audio signals with sequences of audio signals recorded and associated with pre-defined elementary contexts, in case of receiving the audio signals captured by a microphone (MI) of a terminal (T). The analyzing unit delivers a basic message designating each context associated with each elementary sequence corresponding to the received audio signals and associated with the terminal in case of correspondence between the received audio signals and one of the sequences. An independent claim is also included for a method for obtaining a context relative to a user of a communication terminal equipped with a microphone and connected to a communication network.