AI Meeting Query Handling for Missed Conversation Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Participants in videoconferencing meetings often miss discussions due to joining late or being distracted, requiring manual and time-consuming methods like asking others or reviewing meeting minutes to catch up, which can be embarrassing or inefficient.
Innovation Solution
An AI system that allows users to submit natural-language queries about missed conversation portions, using intent detection and machine-learning models to provide summaries or information based on intent, determining relevant conversation segments and generating appropriate responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If users manually review meeting minutes or recordings to catch up on missed discussions, then they can retrieve information about the conversation, but it is time-consuming and disruptive to others
Solution Approach 1:
The AI system enables users to query conversation information autonomously without requiring manual review of minutes or recordings. The system processes natural language queries and retrieves relevant information automatically, allowing users to catch up on missed discussions without time investment in manual reviewing.
Solution Approach 2:
The patent replaces the mechanical manual review process with an AI-based automated information retrieval system. Instead of users physically reviewing documents or recordings, the system uses natural language processing and machine learning models to automatically generate responses to queries about conversation content.
2Loss of information
If users manually review meeting minutes or recordings to catch up on missed discussions, then they can retrieve information about the conversation, but it disrupts meeting participants
Solution Approach 1:
The AI system allows users to retrieve conversation information independently without interacting with or disturbing meeting participants. Users can query about missed discussions at any time without requiring real-time attention from others in the meeting.
Solution Approach 2:
The AI system acts as an intermediary between users who need information and the actual conversation content. Instead of users directly accessing recordings or minutes (which would disrupt the meeting), the AI system mediates by processing queries and retrieving relevant information automatically.
3Measurement precision
If the AI system processes natural language queries and selects from multiple machine-learning models, then it can provide accurate and relevant information, but the system complexity increases
Solution Approach 1:
The AI system is segmented into distinct functional components: natural language processing module, intent detection module, multiple specialized machine-learning models, and response generation module. Each component handles a specific aspect of query processing, allowing for modular development and maintenance while achieving high accuracy through coordinated operation of specialized models.
Data Source
AI summary
Some examples involve an artificial intelligence (AI) system for handling a query about a conversation, such as a conversation between attendees of a videoconferencing meeting. As one example, the system can receive a query from a user about a conversation between attendees of a videoconferencing meeting. The system can determine a relevant portion of the conversation based on the query, determine an intent of the query by providing the query as input to an intent detection model, and select a machine-learning model from among a group of machine-learning models based on the intent of the query. The system can then provide the relevant portion of the conversation as input to the selected machine-learning model. The machine-learning model can generate an output based on the relevant portion of the conversation. The system can transmit the output to the user in a response to the query.