Conversation-Guided AR Interface for Natural Speech Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing augmented reality systems require manual or predetermined verbal commands for interaction, which are cumbersome and time-consuming, limiting user engagement and efficiency in controlling augmented reality experiences.

Innovation Solution

A conversation-based augmented reality system that allows users to interact with augmented reality experiences using natural conversational input, processed by a speech recognition engine that interprets user commands without stringent formats, and updates augmented reality elements based on user preferences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional AR interfaces are used, then users can access digital information, but the experience feels disconnected and requires manual navigation

Engineering Contradiction:
ImproveInterface navigationVSAvoidContextual continuity
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The system continuously monitors user speech and environmental context, providing real-time feedback by updating AR content based on conversation topics. This creates a closed-loop system where user dialogue directly influences the displayed information, maintaining contextual continuity without manual navigation

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The AR interface automatically detects and responds to conversation topics without requiring user initiation or manual control. The system serves itself by autonomously filtering, selecting, and presenting relevant information based on ambient audio analysis, freeing users from interface navigation tasks

Inventive Principle:
Principle #25Self-service

2Ease of operation

If speech recognition is continuously active, then natural conversation guidance is enabled, but energy consumption increases

Engineering Contradiction:
ImproveNatural interactionVSAvoidProcessor energy
Core Design Contradiction:
Ease of operationVSUse of energy by moving object

Solution Approach 1:

Instead of continuously processing all audio data, the system performs partial speech recognition by identifying only key phrases and topics that trigger AR content updates. This selective processing approach maintains natural interaction capability while significantly reducing computational energy consumption

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The speech recognition system operates periodically rather than continuously, activating processing only when conversation keywords are detected or when contextual changes occur. This periodic operation mode enables natural interaction while minimizing energy consumption during idle periods

Inventive Principle:
Principle #19Periodic action

3Adaptability or versatility

If multiple AR applications are integrated, then experience customization is improved, but system complexity increases

Engineering Contradiction:
ImproveExperience customizationVSAvoidSystem integration
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal conversation-guided AR framework that can accommodate multiple applications and content types through a single integrated system. This multi-functional architecture enables experience customization across different scenarios without requiring separate complex systems for each application

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

Solution Approach 2:

The system segments the AR experience into modular components (speech recognition module, topic detection module, content delivery module) that can be independently configured and combined. This segmentation allows multiple applications to be integrated through standardized interfaces, reducing overall system complexity while maintaining versatility

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4396669B1Conversation guided augmented reality experience
Publication Date: 2026.05.20 SNAP INC
  • EP4396669B1 patent drawingFigure 1
  • EP4396669B1 patent drawingFigure 2
  • EP4396669B1 patent drawingFigure 3

AI summary

Systems and methods are provided for providing an augmented reality experience. The systems and methods perform operations comprising: generating, for display by a messaging application, an image comprising one or more augmented reality elements, the one or more augmented reality elements being associated with a configurable entity; receiving, by the messaging application, speech input from a user; determining a schema associated with the one or more augmented reality elements; causing the speech input to be processed by a speech understanding model in accordance with the schema to determine one or more configurable state entity update values; updating the configurable entity associated with the one or more augmented reality elements based on the one or more configurable state entity update values; and modifying the one or more augmented reality elements in the image based on the updated configurable entity.