Adaptive Biometric Authentication Model for Non-Standard User Profiles

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing biometric authentication systems face challenges in accurately authenticating users with non-generalized genuine and imposter score distributions, leading to potential authentication failures even when using biometric information from genuine users.

Innovation Solution

An electronic device with a sensor unit to detect biometric information, a security module to generate and update a biometric authentication model based on genuine scores, and a controller to manage operations based on authentication results, optimizing the authentication process by adjusting the authentication threshold score.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If a fixed biometric authentication model based on statistically generalized human biometric information is used, then the authentication system can be implemented with a standardized approach, but user authentication may fail when the user's genuine score distribution or imposter score distribution is not general

Engineering Contradiction:
Improveease of implementing authentication systemVSAvoidauthentication reliability
Core Design Contradiction:
Ease of manufactureVSReliability

Solution Approach 1:

The patent applies dynamics by transitioning from a fixed authentication model to a dynamic one that adapts to individual users. The system starts with a generalized model and progressively refines it through multiple authentication attempts, adjusting the authentication threshold based on each user's specific score distribution patterns. This allows the model to evolve from static to adaptive, resolving the contradiction between standardized implementation and individualized reliability.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent implements parameter changes by modifying the authentication threshold dynamically. The system changes the threshold parameter based on the user's genuine and imposter score distributions observed during multiple authentication attempts. This parameter adaptation allows the system to maintain high reliability for users with non-generalized biometric characteristics while preserving the standardized model structure.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If the authentication threshold is set to ensure high security, then false authentications are minimized, but genuine users with non-generalized biometric information may experience authentication failures

Engineering Contradiction:
Improvesecurity accuracyVSAvoidauthentication success rate
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent applies feedback by using the results of authentication attempts to adjust the authentication threshold. When a genuine user fails authentication, the system collects their score distribution data and uses it to refine the threshold parameter in subsequent attempts. This feedback loop ensures that the threshold adapts to individual users' characteristics, balancing security requirements with actual authentication success rates.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent implements preliminary action by collecting biometric score data from multiple authentication attempts before finalizing the authentication threshold. The system performs preliminary measurements of genuine and imposter score distributions during initial authentication attempts, using this preliminary data to establish an optimized threshold that accommodates the specific user's characteristics before strict authentication begins.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11341221B2Electric device and control method thereof
Publication Date: 2022.05.24 LG ELECTRONICS INC
  • US11341221B2 patent drawing
  • US11341221B2 patent drawing
  • US11341221B2 patent drawing

AI summary

The electronic device includes: a sensor unit configured to detect biometric information, a security module to extract a genuine score from the detected biometric information and generate a biometric authentication model, and perform user authentication based on feature points acquired from the detected biometric information and the biometric authentication, and a controller to control an operation of the electronic device based on a result of the user authentication, wherein the security module determines whether or not the biometric information used for the user authentication is biometric information acquired from a genuine user when the user authentication fails, and updates the biometric authentication model based on the genuine score extracted from the acquired biometric information. The present invention may provide an electronic device performing complex biometric authentication by using TOT (Internet of Things).