Brain-Computer Interface Menu Selection Without Training

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing brain-computer interface (BCI) systems for digital menu selection require initial training and have limited accuracy and throughput, necessitating reduced user intervention and improved selection precision.

Innovation Solution

A brain-based digital menu selection system that operates without initial training, utilizing continuous adaptation based on user brain activity, automatic correction of prediction errors, and Electroencephalogram pattern processing to enhance speed and accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional BCI systems require initial training to achieve accurate selection, then measurement precision is improved, but loss of time increases due to training requirements

Engineering Contradiction:
Improveselection accuracyVSAvoidtraining time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system pre-processes and stores EEG patterns during a brief initial period, creating a personalized database of brain activity patterns before actual menu selection begins. This preliminary action enables accurate predictions without requiring extensive training during operation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates copies of EEG patterns from the user's brain activity and stores them in a database for later comparison and prediction. These copied patterns are used to predict menu selections without requiring the user to undergo repeated training sessions.

Inventive Principle:
Principle #26Copying

2Productivity

If manual or semi-manual actions are required for menu selection, then device complexity is reduced, but productivity decreases due to limited throughput

Engineering Contradiction:
Improveinformation rateVSAvoiduser intervention
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The system performs menu selection automatically by analyzing EEG patterns and predicting user choices without requiring manual input. The BCI system serves itself by continuously monitoring brain activity and making selections based on predicted intent, eliminating the need for hands-on control.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system replaces manual mechanical actions (button presses, steering wheel inputs) with neural signal processing. EEG-based brain commands substitute for physical interactions, enabling fully automated menu navigation through neural pattern recognition.

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

3Measurement precision

If the system continuously adapts based on user brain activity, then measurement precision improves through personalized prediction, but device complexity increases

Engineering Contradiction:
Improveprediction accuracyVSAvoidsystem adaptation mechanism
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system dynamically adapts to individual users by continuously updating its prediction models based on observed EEG patterns. The classification models evolve over time to match each user's unique brain activity characteristics, improving personalized prediction accuracy.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback loops where prediction outcomes are continuously monitored and used to refine future predictions. Corrected predictions feed back into the classification models, enabling continuous improvement of measurement precision through learned adjustments.

Inventive Principle:
Principle #23Feedback

4Measurement precision

If prediction errors are automatically corrected, then measurement precision improves, but device complexity increases due to correction mechanisms

Engineering Contradiction:
Improveselection accuracyVSAvoiderror correction mechanism
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system implements feedback mechanisms where prediction errors are detected and corrected by comparing predicted selections with actual user choices. These corrections are fed back into the classification models to improve future prediction accuracy.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The error correction system operates autonomously without requiring user intervention. The BCI system self-corrects its predictions by analyzing discrepancies between predicted and actual selections, automatically refining its models to improve accuracy.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3956747B1Neural menu navigator and navigation methods
Publication Date: 2025.05.28 TOYOTA JIDOSHA KK
  • EP3956747B1 patent drawingFigure 1~2
  • EP3956747B1 patent drawingFigure 3
  • EP3956747B1 patent drawingFigure 4

AI summary

A system for brain-based digital menu selection is provided. The system includes an acquisition device configured to obtain one or more electrical signals corresponding to a brain response of an operator, a stimulation generation device configured to generate and present a first stimulus comprising one or more possible target options to the operator based on an initial system trigger caused by the operator, a first database comprising a first classification model, and a processor. The processor is configured to receive a first response from the acquisition device corresponding to a brain response of the operator to the first stimulus comprising the one or more possible target options, determine a probability of intended target for each of the one or more possible target options based on the first response and the first classification model, when the probability of intended target option for an intended target option of the one or more possible target options is higher than a predefined confidence threshold value, selecting the intended target option and presenting a second stimulus, or executing a final action, according to the selected target option, and storing the first response and the selected target option in the first database with a classification identifier identifying the operator.