Self-Learning Meeting Recommender for Group Dynamics Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for analyzing data generated during online meetings fail to substitute for the deficiency in non-verbal communication, particularly in providing insights into group dynamics, participant behavior, and meeting efficiency.
Innovation Solution
A system that dynamically generates and analyzes metadata from online meetings using machine learning algorithms to calculate key performance indicators (KPIs) and provides real-time recommendations for improving meeting effectiveness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If online meetings are used to facilitate communication and collaboration among geographically dispersed participants, then accessibility and convenience are improved, but the ability to experience and participate in non-verbal communication deteriorates
Solution Approach 1:
The patent introduces an AI-based analysis system as an intermediary that processes meeting data (audio, video, chat) to extract and analyze non-verbal communication signals. This intermediary compensates for the loss of non-verbal information by automatically detecting and interpreting cues such as facial expressions, gestures, and tone of voice, then providing insights back to participants without requiring direct human interpretation of these subtle signals.
2Loss of information
If existing methods analyze meeting data, then some insights are provided, but the ability to substitute for non-verbal communication deficiency deteriorates
Solution Approach 1:
The patent creates a multi-functional analysis system that simultaneously performs multiple functions: extracting non-verbal communication signals, analyzing group dynamics, evaluating participant behavior, and providing actionable insights. This universal system handles diverse analysis tasks through integrated AI models that process audio, video, and chat data together, rather than requiring separate specialized tools for each type of analysis.
Solution Approach 2:
The system employs self-learning algorithms that automatically improve their analysis capabilities over time without requiring manual reconfiguration. The AI models continuously learn from new meeting data, adapting to different communication styles and contexts, which allows the system to maintain high analytical accuracy while reducing the need for complex manual setup and adjustment by users.
3Loss of information
If detailed analysis of participant behavior and group dynamics is performed, then meeting efficiency insights are improved, but processing time and computational resources worsen
Solution Approach 1:
The patent implements preliminary processing of meeting data by extracting and organizing key features (such as speaker identification, turn-taking patterns, and emotional tone) during or immediately after the meeting. This preliminary action prepares the data in advance for deeper analysis, allowing the system to quickly generate efficiency insights without performing computationally intensive processing from scratch each time analysis is needed.
Solution Approach 2:
The analysis system segments meeting data into distinct components (individual participant behaviors, pair-wise interactions, group-level patterns) and processes each segment separately using specialized AI models. This segmentation allows parallel processing of different data types and reduces the computational burden on any single processing component, enabling faster overall analysis while maintaining comprehensive coverage of meeting dynamics.
Data Source
AI summary
A system for dynamically generating and analyzing metadata for online meetings is provided. The system is programmed to: a) receive at least one stream of at least one of audio and video of an online meeting, wherein the at least one stream includes a plurality of participants participating in the online meeting; b) extract a plurality of metadata from the at least one stream; c) perform diarization on the at least one stream and the plurality of metadata the at least one stream to generate diarization information; d) analyze the diarization information to calculate one or more key performance indicators (KPIs); e) determine a recommendation to change the one or more KPIs; and/or f) generate visualization of at least one of the key performance indicators and the recommendation to be displayed to one or more participants in the online meeting.