Radiotelephony Message Verification via Biometric Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current communication systems in control centers, such as those used in aviation, face challenges in accurately identifying and assigning voice radio messages due to incorrect pronunciation and poor voice connections, leading to potential dangerous situations.

Innovation Solution

A method that transforms spoken identifiers into digital identifiers using voice recognition and biometric data records, which are stored and matched for accurate assignment, reducing the probability of incorrect assignments by comparing biometric data sets and considering the reliability of speech recognition probabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If speech recognition is used to transform spoken identifiers into digital identifiers, then automation of message assignment is improved, but measurement precision of identifier recognition deteriorates due to incorrect pronunciation and poor voice connections

Engineering Contradiction:
Improveautomation of message assignmentVSAvoidprecision of identifier recognition
Core Design Contradiction:
Extent of automationVSMeasurement precision

Solution Approach 1:

The patent introduces biometric data records as an intermediary verification layer between speech recognition and final message assignment. The system first performs speech recognition to obtain a digital identifier, then verifies this identifier by comparing biometric data from the voice message against stored biometric profiles. This intermediary step resolves the contradiction by maintaining automation while improving recognition precision through biometric validation.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback by using biometric verification results to confirm or correct speech recognition outcomes. When speech recognition produces an identifier, the biometric verification provides feedback on its accuracy by comparing voice characteristics against known profiles. This feedback mechanism allows the system to maintain high automation while correcting errors that would otherwise reduce measurement precision.

Inventive Principle:
Principle #23Feedback

2Device complexity

If only speech recognition is used for identifier transformation, then device complexity is reduced, but reliability of message assignment deteriorates due to incorrect pronunciations and poor connections

Engineering Contradiction:
Improvecomplexity of identification systemVSAvoidreliability of message assignment
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent merges two identification methods: speech recognition and biometric verification. Instead of relying on speech recognition alone, the system combines it with biometric analysis of voice characteristics. This merging resolves the contradiction by maintaining relatively simple device architecture while significantly improving reliability through the complementary nature of the two methods.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The identification system uses a composite approach by combining speech recognition technology with biometric verification technology. Just as composite materials combine different materials to achieve superior properties, this composite identification system combines two different recognition methods to achieve reliability that exceeds either method alone, while keeping overall system complexity manageable.

Inventive Principle:
Principle #40Composite materials

3Reliability

If biometric verification is added to speech recognition, then reliability of identifier assignment is improved, but device complexity increases

Engineering Contradiction:
Improvereliability of message assignmentVSAvoidcomplexity of identification system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary action by storing biometric data records during the message assignment process. Rather than requiring complex real-time biometric analysis for every message, the system pre-processes and stores biometric profiles during initial message exchanges. This preliminary action reduces the complexity burden during verification while maintaining high reliability through the pre-established biometric references.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3117428B1Method for identifying and verifying radiotelephony messages
Publication Date: 2018.11.28 FREQUENTIS
  • EP3117428B1 patent drawingFigure 1~5
  • EP3117428B1 patent drawingFigure 3~7

AI summary

The invention relates to a method and to a radiotelephony system for identifying and verifying radiotelephony messages (M1...M3) and for associating radiotelephony messages (M1...M3) with vehicles (F1...F3). An announcer specifies the identification (K) at a predetermined point of each radiotelephony message (M1...M3). According to the invention, a) a number of delivered radiotelephony messages (M1...M3) are recorded. Each identification (K) containing the radiotelephony message (M1...M3) is transformed by voice recognition (0) into a digital identification (Kd). Radiotelephony messages (M1...M3) are extracted, each one being associated with the same digital identification, a biometric data set (B1...B3) is extracted, and said biometric data set (B1...B3) is associated with the respective digital identification (Kd), and b) then an additional radiotelephony message (M4) is recorded. From the additional radiotelephony message (M4), an additional biometric data set (B4) is extracted. From the recorded biometric data sets (B1...B3)), the biometric-dataset (B1) which best matches the additional biometric data set (B4) and the radiotelephony message (M4) of the vehicle (F1) is searched for and the associated identification (Kd) is associated with said biometric data set (B1).