Gaze-Guided Voice Control for Reliable Apparatus Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems struggle to accurately specify a unique apparatus for operation based on driver voice recognition, leading to potential incorrect operations.

Innovation Solution

An information-processing device that specifies a target apparatus using line-of-sight data to determine the direction of a user's gaze and generates control commands based on voice data after apparatus selection, reducing the need for vocal designation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice recognition alone is used to specify the target apparatus, then the ease of operation is improved, but the reliability of apparatus specification deteriorates due to inability to uniquely identify the target

Engineering Contradiction:
Improveease of operationVSAvoidreliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent combines voice recognition with line-of-sight detection to specify the target apparatus. The voice recognition unit receives voice data and the line-of-sight detection unit receives line-of-sight data, and the target specification unit integrates both inputs to uniquely identify the target apparatus. This merging of multiple recognition methods resolves the contradiction by maintaining ease of voice-based operation while adding line-of-sight confirmation to ensure reliable target identification.

Inventive Principle:
Principle #5Merging (Combining)

2Device complexity

If only voice data is used for apparatus specification, then the device complexity is reduced, but the measurement precision of target identification deteriorates

Engineering Contradiction:
Improvedevice complexityVSAvoidmeasurement precision
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent merges voice data processing with line-of-sight data processing in the target specification unit. The voice recognition unit processes voice data while the line-of-sight detection unit processes line-of-sight data, and both are integrated to precisely identify the target apparatus. This combination improves measurement precision of target identification while keeping device complexity manageable through modular unit design.

Inventive Principle:
Principle #5Merging (Combining)

3Ease of operation

If voice recognition is used without line-of-sight confirmation, then the ease of operation is improved, but the loss of information about user intent increases

Engineering Contradiction:
Improveease of operationVSAvoidloss of information
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The patent implements feedback by using line-of-sight detection to confirm user intent. The line-of-sight detection unit provides visual attention information that feedbacks to the target specification unit, which integrates this with voice recognition results. This feedback mechanism reduces information loss about user intent by confirming which apparatus the user actually intends to operate, while maintaining ease of voice-based operation.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4234339B1Information processing device and information processing method
Publication Date: 2026.04.01 NISSAN MOTOR CO LTD
  • EP4234339B1 patent drawingFigure 1
  • EP4234339B1 patent drawingFigure 2

AI summary

In an information-processing device and an information-processing method, each involves specifying a target apparatus to be operated from a plurality of apparatuses based on line-of-sight data pertaining to a user's line of sight direction, acquiring voice data to generate a control command for the target apparatus to be operated during a predetermined time span, and controlling the target apparatus to be operated.