In-Ear Device Customization via Machine Learning Ear Geometry

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional in-ear devices and eyewear frames often fail to fit comfortably and effectively due to variations in users' ear and head shapes, leading to discomfort and degraded audio quality, especially in passive acoustic attenuation.

Innovation Solution

A machine learning-based system generates customized 3D geometries of users' ears and heads from anthropometric data, enabling the design of in-ear devices and eyewear frames that fit uniquely, with a shell designed to seal within the ear canal and coupling elements that rotate and bend to fit the user's head.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If standard shape and size of in-ear device is used, then manufacturing cost is reduced and production is simplified, but fit quality and audio performance deteriorate

Engineering Contradiction:

Improvefit qualityVSAvoidcustomization complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary scanning of the user's ear anatomy to create a 3D model before device manufacturing. This advance measurement and modeling enables customization without adding complexity to the manufacturing process itself, as the custom geometry is already determined prior to production

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The invention creates a digital 3D copy of the user's ear canal geometry from scanning data. This digital replica serves as the basis for designing the custom in-ear device shell, allowing precise fit without requiring physical prototypes or complex manual molding processes

Inventive Principle:

Principle #26Copying

2Reliability

If standard in-ear device design is used, then device complexity is reduced, but passive acoustic attenuation performance deteriorates

Engineering Contradiction:

Improveacoustic attenuation performanceVSAvoiddevice customization

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The in-ear device shell is customized with local variations in geometry to match the specific contours of the user's ear canal. This localized adaptation of the shell shape ensures optimal sealing and passive acoustic attenuation for each individual user, rather than using a uniform design for all users

Inventive Principle:

Principle #3Local quality

3Ease of operation

If customized in-ear device is generated for each user, then comfort and audio quality are improved, but manufacturing time and process complexity increase

Engineering Contradiction:

Improveuser comfortVSAvoidmanufacturing time

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The invention replaces traditional mechanical measurement and manufacturing methods with automated optical scanning and digital modeling. The scanning system rapidly captures ear geometry data, and software automatically generates the custom shell design, eliminating time-consuming manual measurement and prototyping steps

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11783475B2In ear device customization using machine learning

Publication Date: 2023.10.10 META PLATFORMS TECHNOLOGIES LLC

AI summary

A design system generates a design for an in-ear device customized for a user. The in-ear device produces audio content for the user. The design system captures anthropometric data of the user. Using machine learning techniques, the design system determines features of an ear of the user from the anthropometric and generates a three dimensional (3D) geometry of the user's ear. A design for the in-ear device is generated based on the 3D geometry of the user's ear and includes a shell configured to fit in at least a portion of an ear canal of the user.