Hearing Device Automatic Pairing via Context-Aware Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users of hearing devices face difficulties in manually establishing and managing wireless data communication connections with partner devices, leading to cumbersome and privacy-invasive situations due to the lack of automatic pairing and context-aware connectivity.

Innovation Solution

A method that generates context data from sensor inputs and uses a machine learning algorithm to classify potential partner devices, automatically establishing or disconnecting connections based on user context, such as location and environmental factors, to optimize power consumption and connection efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual pairing is used for hearing devices, then connection reliability is improved, but ease of operation deteriorates

Engineering Contradiction:

Improveconnection reliabilityVSAvoidease of operation

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The hearing device automatically detects partner devices and establishes connections without user intervention. The system monitors sensor data (audio streams, ambient noise) to autonomously determine appropriate pairing decisions, eliminating the need for manual user input while maintaining connection reliability through context-aware selection.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary detection and classification of potential partner devices before establishing connections. By analyzing sensor data in advance and pre-classifying suitable partners based on context, the hearing device prepares connection decisions beforehand, enabling reliable automated pairing without requiring user action at the moment of connection.

Inventive Principle:

Principle #10Preliminary action

2Ease of operation

If automatic pairing is implemented, then ease of operation is improved, but device complexity increases

Engineering Contradiction:

Improveease of operationVSAvoiddevice complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

A machine learning algorithm acts as an intermediary between the hearing device's sensor data and the pairing decision. This intermediary component processes complex sensor inputs (audio streams, ambient noise characteristics) and translates them into automated pairing decisions, managing the complexity through a dedicated processing layer rather than integrating it throughout the entire system.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces manual mechanical pairing operations with an automated computational system. Instead of requiring physical user actions to establish connections, the system uses machine learning algorithms to process sensor data and automatically determine pairing decisions, substituting mechanical user interaction with intelligent automated processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Use of energy by moving object

If manual connection management is used, then power consumption is reduced, but loss of time increases

Engineering Contradiction:

Improvepower consumptionVSAvoidconnection time

Core Design Contradiction:

Use of energy by moving objectVSLoss of time

Solution Approach 1:

The hearing device continuously monitors sensor data and maintains readiness for automatic pairing without requiring continuous user intervention. The system keeps detecting and classifying potential partners in the background, so when a connection is needed, the decision is already prepared, eliminating connection time delays while maintaining acceptable power consumption through efficient background processing.

Inventive Principle:

Principle #20Continuity of useful action

4Productivity

If context-aware automatic pairing is implemented, then productivity is improved, but use of energy increases

Engineering Contradiction:

Improveconnection efficiencyVSAvoidpower consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The system performs partial analysis of sensor data rather than processing all possible data continuously. By selectively monitoring and analyzing only the most relevant sensor inputs for pairing decisions (such as audio stream characteristics and ambient noise levels), the hearing device achieves efficient automated connection while minimizing unnecessary energy consumption from comprehensive data processing.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentEP3866489B1Pairing of hearing devices with machine learning algorithm

Publication Date: 2023.11.22 SONOVA AG

Figure 1~2
Figure 3

AI summary

A hearing device (12) is capable of establishing a data communication connection with other devices (36, 14) with a data communication interface (24) and for receiving an audio data stream from the other devices (36, 14) via the data communication interface (24). A method for determining partner devices (36) for the hearing device (12) worn by a user comprises: generating context data (48) from sensor data (46) recorded by the hearing device (12); inputting the context data (48) into a machine learning algorithm (50), which has been trained with historical context data to classify potential partner devices (36, 36'); and outputting at least one classification (52) by the machine learning algorithm (50), the classification classifying the potential partner devices (36, 36'), whether the user expects a data communication connection with them.