Topic-Segmented Talking Speed Analysis for Communication Sessions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital communication platforms lack the capability to provide talking speed analysis per topic segment in communication sessions, which is crucial for organizations to improve performance metrics, particularly in sales meetings.
Innovation Solution
A system that analyzes a communication session transcript to determine meeting types, generates topic segments, calculates word count per unit of time for each participant, and presents this data to client devices, utilizing AI models for meeting type determination and automatic speech recognition for transcript generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If digital communication platforms provide comprehensive communication recording and basic transcription, then communication documentation is improved, but advanced performance analysis capability remains lacking
Solution Approach 1:
The patent segments the communication session into distinct topic segments based on meeting type determination. The system divides the transcript into multiple topic segments (e.g., introduction, product demonstration, Q&A) and calculates talking speed metrics separately for each segment, enabling granular performance analysis rather than providing only aggregate data.
Solution Approach 2:
The patent introduces AI models as intermediary components between the basic transcription and the performance analysis. Specifically, meeting type determination models and topic segmentation models serve as intermediaries that process the transcript and generate structured data, which then enables the talking speed calculation and performance metrics generation.
2Measurement precision
If the system calculates talking speed metrics for all participants, then performance measurement is improved, but data processing complexity increases
Solution Approach 1:
The system segments the analysis by first determining meeting type and then dividing the transcript into topic segments. This segmentation allows the calculation of talking speed metrics to be performed in organized stages rather than as a single complex operation, reducing processing complexity while maintaining measurement precision.
Solution Approach 2:
The system automatically determines meeting type and generates topic segments without requiring manual intervention. The AI models self-service the transcript processing by automatically identifying meeting contexts and structuring the content, which reduces the complexity burden on the overall system architecture.
3Loss of information
If the platform provides detailed per-topic talking speed analysis, then performance insights are improved, but implementation capability of existing platforms is insufficient
Solution Approach 1:
The patent creates a multi-functional system that can handle different meeting types (sales meetings, technical discussions, general conversations) using the same underlying architecture. The meeting type determination model automatically adapts the analysis approach based on the detected meeting type, making the platform versatile across different communication scenarios while providing detailed performance insights.
Solution Approach 2:
The system changes parameters dynamically based on meeting type. Different meeting types trigger different topic segmentation strategies and analysis parameters. For example, sales meetings may be segmented into prospecting, presentation, and closing phases, while technical discussions may be segmented by technical topic, allowing the platform to adapt its analysis depth and granularity to suit different contexts.
Data Source
AI summary
Methods and systems provide for presenting the results of talking speed analysis per topic segment in a communication session. The system connects to a communication session with a number of participants; receives a transcript of a conversation between the participants produced during the communication session, the transcript including timestamps for each utterance of a speaking participant; determines, based on analysis of the transcript, a meeting type for the communication session; generates, based on the meeting type, a number of topic segments for the conversation and respective timestamps for the topic segments; for each topic segment, determines a word count per unit of time for each speaking participant associated with a prespecified organization; and presents, to one or more client devices, data on the topic segments, each data including the word count per unit of time for each speaking participant within the topic segment.