Parsing Electronic Conversations for Voice Interface Presentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional messaging systems fail to efficiently interpret and present non-verbal conversation elements in alternative interfaces, leading to inefficient use of resources and poor user experience, as they often provide literal voice outputs for non-verbal items and lack conversational framing.

Innovation Solution

A method and system that parse electronic conversations to identify and group objects by type, apply conversational framing, and generate a voice interface presentation, converting non-verbal objects into textual descriptions using object recognition and lookup tables, thereby providing a more efficient and user-friendly alternative interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional messaging systems provide literal voice outputs for non-verbal items, then alternative interface presentation is achieved, but computational resources and power consumption increase inefficiently

Engineering Contradiction:
Improvealternative interface presentationVSAvoidcomputational resources and power consumption
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The patent extracts only the essential information from non-verbal objects (images, videos, URLs) rather than processing them literally. Object recognition technology identifies key content and extracts only necessary textual descriptions, eliminating unnecessary computational overhead while maintaining effective communication in alternative interfaces.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the conversation into different object types (verbal and non-verbal) and applies different processing strategies to each. Non-verbal objects are segmented and processed through object recognition to generate efficient textual representations, while verbal objects are handled differently, optimizing overall resource usage.

Inventive Principle:
Principle #1Segmentation

2Device complexity

If conventional messaging systems lack conversational framing for non-verbal objects, then system complexity is reduced, but user experience deteriorates

Engineering Contradiction:
Improvesystem complexityVSAvoiduser experience
Core Design Contradiction:
Device complexityVSEase of operation

Solution Approach 1:

The patent introduces conversational framing as an intermediary layer between non-verbal objects and voice output. This framing provides contextual information and natural language transitions that enhance user understanding without significantly increasing system complexity, as it builds upon existing object recognition capabilities.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of information

If visual displays are used for electronic conversations in contexts like driving, then information presentation is complete, but safety deteriorates

Engineering Contradiction:
Improveinformation presentation completenessVSAvoidsafety
Core Design Contradiction:
Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the visual display mechanism with an audio-based alternative interface. By converting non-verbal conversation elements into voice outputs through object recognition and textual description, the system maintains information completeness while eliminating the safety hazard of visual distraction during driving.

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

4Ease of manufacture

If literal voice output is used for non-verbal objects, then implementation is simple, but information effectiveness deteriorates

Engineering Contradiction:
Improveimplementation simplicityVSAvoidinformation effectiveness
Core Design Contradiction:
Ease of manufactureVSLoss of information

Solution Approach 1:

The patent changes the parameter of information representation from literal to descriptive. Instead of directly outputting literal voice representations of non-verbal objects, the system transforms them into effective textual descriptions through object recognition, maintaining implementation feasibility while dramatically improving information effectiveness.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3612926B1Parsing electronic conversations for presentation in an alternative interface
Publication Date: 2023.07.26 GOOGLE LLC
  • EP3612926B1 patent drawingFigure 1
  • EP3612926B1 patent drawingFigure 2
  • EP3612926B1 patent drawingFigure 3A~3B

AI summary

Some implementations can include a computer-implemented method and/or system for parsing an electronic conversation for presentation at least partially in an alternative interface (e.g., a non-display interface) such as a voice interface or other non-display interface.