3D Modeling via Multimodal Fusion Without Mouse and Keyboard

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional geometric modeling methods require manual interaction with devices like a mouse and keyboard, leading to prolonged modeling times, potential system instability, and a cumbersome experience.

Innovation Solution

A three-dimensional modeling system and method utilizing multimodal fusion, incorporating electroencephalogram, electromyography, eye movement, gesture, and voice sensors to collect and fuse feedback data, enabling automatic modeling without manual device interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional manual interaction with mouse and keyboard is used for geometric modeling, then the operator can control the modeling process, but the modeling time is prolonged and the operation becomes cumbersome

Engineering Contradiction:
Improvemodeling efficiencyVSAvoidmodeling time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent replaces mechanical input devices (mouse, keyboard) with a brain-machine interface system that directly translates neural signals into modeling commands. This substitution eliminates the need for manual manipulation of interactive devices, thereby reducing modeling time and improving efficiency while maintaining operator control through intent-based command generation.

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

Solution Approach 2:

The system enables the operator to control the modeling process through thought alone, allowing the brain to directly serve the modeling function without intermediary manual devices. The neural signals automatically generate and transmit modeling commands, making the operator's intent directly actionable in the digital environment.

Inventive Principle:
Principle #25Self-service

2Ease of operation

If complex modeling commands are input through interactive devices, then precise control is achieved, but the operator experiences manipulation fatigue and reduced engagement

Engineering Contradiction:
Improvemanipulation easeVSAvoidmanipulation energy
Core Design Contradiction:
Ease of operationVSUse of energy by moving object

Solution Approach 1:

The patent substitutes mechanical manipulation of mouse and keyboard with neural signal-based control. This replacement eliminates the physical energy expenditure associated with hand movements and device manipulation, while preserving precise control through the direct translation of neural intent into modeling commands.

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

Solution Approach 2:

The operator's brain directly generates and transmits control signals without requiring physical manipulation. The system serves the operator's intent automatically, converting neural patterns into actionable commands without requiring manual energy investment, thereby reducing manipulation fatigue and enhancing engagement.

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If traditional modeling interface is used, then the system is simple to implement, but the modeling experience becomes boring and less immersive

Engineering Contradiction:
Improveinteraction experienceVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent replaces conventional mechanical input interfaces with a neural interface system. This substitution fundamentally transforms the interaction experience from manual manipulation to thought-based control, creating a more immersive and engaging modeling experience. The increased system complexity is justified by the significant improvement in adaptability and user engagement.

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

Data Source

PatentUS12632113B2Three-dimensional modeling system and modeling method based on multimodal fusion
Publication Date: 2026.05.19 NANJING UNIV OF POSTS & TELECOMM
  • US12632113B2 patent drawing
  • US12632113B2 patent drawing

AI summary

Disclosed are a three-dimensional modeling system and modeling method based on multimodal fusion. The method includes: separately collecting feedback data of an electroencephalogram sensor, an electromyography sensor, an eye movement sensor, a gesture sensor, and a voice sensor, conducting multimodal fusion on the feedback data, obtaining multimodal-fused model data, matching the model data with a database instruction, obtaining and analyzing an instruction set, obtaining and identifying a relevant modeling parameter, obtaining a modeling method, automatically conducting modeling according to the modeling method, and obtaining a visual entity model. Through the method of the present disclosure, multi-sense man-machine interaction is combined with traditional geometric modeling, and a complicated modeling command input operation does not require manipulation of interactive devices such as a keyboard and a mouse, such that modeling efficiency is improved, waste of manipulation energy of an operator is reduced, and further modeling experience of the operator is improved.