Conferencing App Action Item Extraction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face challenges in capturing and remembering action items during audio or video conferencing sessions due to the distraction of note-taking and the cumbersome process of transcribing sessions post-meeting, leading to inaccuracies and inefficiencies.

Innovation Solution

A conferencing application with an action item trigger UI mechanism that allows users to select an action item trigger, which analyzes preceding audio data to automatically generate action items using speech recognition, natural language processing, and machine learning techniques to identify relevant content and exclude self-referential data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If users take notes manually during conferencing sessions, then they can record important information, but their attention is divided and they are distracted from the session contents

Engineering Contradiction:
Improveimportant informationVSAvoiduser attention
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system performs automatic note-taking and action item extraction without requiring user intervention. The conferencing application automatically processes audio data, identifies action items, and generates notes, allowing users to passively capture information without manual note-taking activities that would divide their attention.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent introduces an automatic action item extraction system as an intermediary between the conferencing audio and the user. This intermediary automatically processes the audio stream, extracts relevant action items using speech recognition and natural language processing, and presents them to users, eliminating the need for users to manually transcribe or note information.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If users speak during conferencing sessions, then they can participate in the discussion, but it becomes difficult to take notes simultaneously

Engineering Contradiction:
Improveuser participationVSAvoidaction items
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The system automatically extracts action items from the conference audio without requiring the speaking user to pause or switch tasks. The automatic processing occurs in the background, allowing users to freely participate in discussions while the system independently captures and processes all spoken content for action item identification.

Inventive Principle:
Principle #25Self-service

3Loss of information

If users obtain and analyze transcripts after conferencing sessions, then they can identify important information, but the process is cumbersome, error-prone, and time-consuming

Engineering Contradiction:
Improveimportant informationVSAvoidpost-session analysis time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs action item extraction and analysis during the conferencing session itself, rather than requiring post-session processing. By automatically processing audio data in real-time and identifying action items as they are discussed, the system eliminates the need for time-consuming post-session transcript analysis.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The automatic action item extraction system performs the entire analysis process without user intervention. It automatically processes conference audio, applies speech recognition and natural language processing, identifies action items, and generates structured outputs, eliminating the manual, error-prone process of obtaining and analyzing transcripts after sessions.

Inventive Principle:
Principle #25Self-service

4Productivity

If the discussion moves quickly during conferencing sessions, then the session progresses efficiently, but accurate note taking becomes difficult or impossible

Engineering Contradiction:
Improvesession progressVSAvoidnote accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The automatic action item extraction system processes the audio stream in real-time without being constrained by the speed of discussion. Using speech recognition and natural language processing, the system automatically captures and analyzes spoken content at any pace, maintaining accuracy regardless of how quickly participants are speaking.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4060971B1Generating action items during a conferencing session
Publication Date: 2024.08.28 MITEL CORP
  • EP4060971B1 patent drawingFigure 1
  • EP4060971B1 patent drawingFigure 2
  • EP4060971B1 patent drawingFigure 3

AI summary

Receiving an action item trigger by a user of a conferencing application; and in response to receiving the action item trigger, search spoken words from audio data of a session of the conferencing application for a previous predetermined number of sentences spoken before receiving the action item trigger; normalizing the spoken words; generating higher-level representations of the normalized spoken words; determining semantic similarities of the higher-level representations of the normalized spoken words and higher level representations of normalized action words of an action word list; ranking options for top spoken words and action words based at least in part on the semantic similarities; identifying candidates for action words and/or phrases from the top spoken words and action words; and parsing the candidates to generate one or more action items.