Real-Time Audio Log System for Conference Clarification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Participants in conversations, such as conference calls or lectures, often face difficulties understanding unfamiliar topics due to varying levels of knowledge among participants, leading to inefficient communication as real-time clarification is challenging without disrupting the flow.

Innovation Solution

A system that captures audio, converts it to text, identifies key terms, and uses an intelligent agent to search for multimedia content relevant to the listener's knowledge base, providing immediate context information and links to enhance understanding.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If the listener interrupts the conversation to ask for clarification, then understanding of key terms is improved, but the flow of conversation is broken

Engineering Contradiction:
Improveunderstanding of key termsVSAvoidflow of conversation
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The system introduces an intermediary component (automatic log generation system) that mediates between the speaker and listener. The system captures audio, converts it to text, identifies key terms, and provides context information through a separate channel (display device) without requiring the listener to interrupt the conversation flow.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary actions by pre-processing the conversation audio into text, pre-identifying key terms, and pre-generating context information before the listener needs it. This allows the information to be ready and available immediately when displayed, eliminating the need for post-conversation research.

Inventive Principle:
Principle #10Preliminary action

2Loss of information

If the listener takes notes and looks up information after the conference call, then understanding of key terms is improved, but real-time clarification is lost

Engineering Contradiction:
Improveunderstanding of key termsVSAvoidreal-time clarification
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs all information processing actions preliminarily - converting audio to text, identifying key terms, and preparing context information - so that when the listener needs information during the conversation, it is already prepared and can be delivered instantly through the display device.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system establishes a feedback loop where the listener receives context information about key terms in real-time through the display device, allowing immediate understanding without waiting for post-conversation review. The system continuously monitors the conversation and provides relevant information as it is generated.

Inventive Principle:
Principle #23Feedback

3Loss of information

If the listener simultaneously searches for information using search engines, then understanding of key terms is improved, but attention is diverted from the discussion

Engineering Contradiction:
Improveunderstanding of key termsVSAvoidattention focus
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system moves the information search and display function to a different dimension - from the auditory channel (conversation) to the visual channel (display device). This allows the listener to receive context information without diverting attention from the spoken discussion, as the information is presented peripherally rather than requiring focused search effort.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS7844460B2Automatic creation of an interactive log based on real-time content
Publication Date: 2010.11.30 MOTOROLA SOLUTIONS INC
  • US7844460B2 patent drawing
  • US7844460B2 patent drawing
  • US7844460B2 patent drawing

AI summary

A system [100] includes an audio reception device [105] to receive audio from a person speaking and convert the audio to a text format. An intelligent agent [110] receives the text format and detects at least one key term in the text format based on predetermined criteria. A logic engine [115] compares the at least one key term with a listener knowledge base [125] corresponding to a listener to determine context information corresponding to the at least one key term. A search device [135] searches for multimedia content corresponding to the context information. A communication device [150] communicates display content comprising at least one of: the multimedia content, and a link to the multimedia content to an electronic display device [155] adapted to display the display content.