State Animation Interface for Voice-Only Participant Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In video conferences where participants use voice-only communication due to bandwidth limitations or privacy concerns, it is difficult to recognize the interest or state of other participants, leading to challenges in achieving smooth communication.

Innovation Solution

A communication assistance system that integrally displays identification information and state animations representing the communication targets, using animations such as ear movements to convey the state of participants, which can be imitated by animals, and operates based on voice and image data to accurately reflect the participants' states.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If voice-only communication is used due to bandwidth limitations or privacy concerns, then communication privacy and bandwidth efficiency are improved, but the ability to recognize the state of other participants deteriorates

Engineering Contradiction:
Improvecommunication privacyVSAvoidparticipant state recognition
Core Design Contradiction:
Loss of informationVSDifficulty of detecting and measuring

Solution Approach 1:

The patent introduces an intermediary system that processes voice data and generates state animations representing participant states. This mediator translates raw voice signals into visual representations (animations showing speech, listening, thinking states) without exposing actual voice content, thus maintaining privacy while enabling state recognition. The intermediary acts as a bridge between the conflicting requirements of privacy preservation and state detectability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of energy

If voice-only communication is used due to bandwidth limitations or privacy concerns, then bandwidth consumption is reduced, but communication smoothness and participant engagement deteriorate

Engineering Contradiction:
Improvebandwidth consumptionVSAvoidcommunication smoothness
Core Design Contradiction:
Loss of energyVSEase of operation

Solution Approach 1:

The patent creates simplified visual copies (animations) that represent participant states instead of transmitting actual video or audio streams. These animation copies convey essential communication state information (who is speaking, who is listening, thinking states) using minimal data, thus maintaining bandwidth efficiency while significantly improving communication smoothness and participant engagement through visual feedback.

Inventive Principle:
Principle #26Copying

3Difficulty of detecting and measuring

If state animations are added to voice-only communication, then participant state recognition is improved, but system complexity increases

Engineering Contradiction:
Improveparticipant state recognitionVSAvoidsystem complexity
Core Design Contradiction:
Difficulty of detecting and measuringVSDevice complexity

Solution Approach 1:

The patent changes the parameter representation of participant states from raw audio/video signals to simplified animation parameters. By transforming complex multimedia data into discrete state parameters (speech state, listening state, thinking state represented by simple animations), the system achieves improved state recognition while keeping the complexity manageable through parameter simplification and standardization.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS12517697B2Communication assistance program, communication assistance method, communication assistance system, terminal device, and non-verbal expression program
Publication Date: 2026.01.06 SUMITOMO ELECTRIC INDUSTRIES LTD
  • US12517697B2 patent drawing
  • US12517697B2 patent drawing
  • US12517697B2 patent drawing

AI summary

A communication assistance program is a communication assistance program assisting communication of a user, the communication assistance program causing a computer to perform a step of integrally displaying identification information that can be used for identifying a communication target and a state animation representing a state of the communication target.