Video Conferencing Engagement Scoring From Group Utterance Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital communication platforms lack analytics and metrics for engagement analysis during remote communication sessions, particularly in sales meetings, failing to provide insights into customer interaction and engagement levels.
Innovation Solution
A system that analyzes transcripts of communication sessions to calculate engagement metrics, assigns weights to these metrics, and determines an engagement score by associating utterances with different groups, using statistical modeling and linguistic features to assess interaction and engagement levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If analytics and metrics for engagement analysis are added to digital communication platforms, then customer engagement insights are improved, but system complexity increases
Solution Approach 1:
The patent introduces an intermediary engagement analysis system that sits between the communication platform and users. This system automatically processes communication data, calculates engagement metrics, and presents insights without requiring users to manually analyze raw data, thus providing engagement information while managing system complexity through automation.
Solution Approach 2:
The engagement analysis system performs self-service by automatically collecting data from communication sessions, processing transcripts, calculating engagement metrics, and generating reports without continuous human intervention. The system serves itself by maintaining and updating engagement models and metrics autonomously.
2Loss of information
If engagement metrics are calculated and presented in real-time, then customer interaction insights are improved, but processing time increases
Solution Approach 1:
The system performs preliminary actions by pre-processing communication transcripts during or immediately after sessions, extracting relevant features, and calculating baseline engagement metrics in advance. This allows for faster retrieval and presentation of engagement insights when needed, reducing perceived processing time for users.
Solution Approach 2:
The patent replaces manual engagement analysis with automated computational processing. Machine learning models and algorithms automatically analyze communication patterns, replacing what would otherwise require manual review of transcripts, thereby reducing processing time while maintaining or improving insight quality.
Data Source
AI summary
In one embodiment, the system connects to a communication session with a number of participants; receives a transcript of a conversation between the participants; extracts utterances from the transcript; associates a subset of the utterances with a first group of speakers and the remaining subset of the utterances with a second group of speakers; calculates one or more statistical metrics for a number of engagement metrics based on the utterances of the first group of speakers and the utterances of the second group of speakers; assigns a weight to each of the engagement metrics; determines an engagement score for the communication session based on the assigned weights for the engagement metrics; and presents, to one or more users, the engagement score for the communication session.