Intelligence Device Eye Tracking User Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Intelligence devices face difficulties in distinguishing the intended user from multiple individuals due to simultaneous voice input, leading to potential misinterpretation and incorrect reaction to non-users.

Innovation Solution

An intelligence device that captures images or videos of persons around, analyzes eye blinks, pupil shapes, and hand gestures using AI processing to determine the user's gaze direction and distance, and displays customized information to the selected user, with the option to split the screen for multiple users and recognize specific hand gestures for user selection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice recognition is used to identify users, then the device can respond to voice commands, but it cannot distinguish the intended user from multiple people around the device

Engineering Contradiction:
Improvevoice command recognitionVSAvoiduser identification accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent combines voice recognition with eye tracking technology to identify users. The capturing unit captures both voice signals and eye images simultaneously, and the processor integrates information from both modalities to determine the intended user, thereby resolving the ambiguity of voice-only recognition in multi-person environments.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces eye tracking as an intermediary mechanism to bridge the gap between voice input and user identification. By capturing eye images and analyzing gaze direction, the system mediates the connection between multiple voice sources and the correct user identity, enabling accurate user distinction.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Speed

If the device responds to any voice input, then it can maintain responsiveness, but it may react to non-users incorrectly

Engineering Contradiction:
Improveresponse speedVSAvoidresponse accuracy
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system performs preliminary user identification through eye tracking before processing voice commands. The capturing unit continuously captures eye images, and the processor analyzes gaze direction in advance to pre-identify the intended user, ensuring that subsequent voice responses are directed to the correct person and preventing misresponses to non-users.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If eye tracking is added to voice recognition, then user identification accuracy improves, but device complexity increases

Engineering Contradiction:
Improveuser identification accuracyVSAvoidsystem structure
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The capturing unit is designed to perform multiple functions: capturing voice signals, capturing eye images, and capturing facial images. This multi-functional design reduces the need for separate dedicated components for each sensing modality, thereby mitigating the increase in device complexity while enabling accurate user identification through combined analysis.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11514725B2Intelligence device and user selection method thereof
Publication Date: 2022.11.29 LG ELECTRONICS INC
  • US11514725B2 patent drawing
  • US11514725B2 patent drawing
  • US11514725B2 patent drawing

AI summary

Disclosed are an intelligence device and a method of selecting a user of the intelligence device. According to an embodiment of the disclosure, the intelligence device may analyze the eye blinks and pupil shapes of persons and select the person gazing at the intelligence device as a user. According to an embodiment, the intelligence device may be related to artificial intelligence (AI) modules, robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.