How AI Cleans Up Irrelevant Topics in Recorded Phone Calls

A system that automatically identifies and removes 'noisy' or irrelevant topics from call center transcripts by analyzing how consistently and broadly those words appear.

What it covers

This patent describes a way to make AI-powered call analysis more accurate by filtering out 'extraneous' topics that don't provide useful business insights. It works by looking at call transcripts and calculating two specific metrics for each identified topic: a vocabulary score (based on the entropy of word distributions) and a consistency score (how often that topic appears across different calls). If a topic is too broad or lacks consistency, the system flags it as noise. It then automatically updates the AI model to either remove that topic from the results or visually separate it, ensuring that human analysts only see the most relevant conversation data.

What it doesn't cover

• —Does not cover general speech-to-text transcription methods.
• —Does not cover manual topic tagging performed by human agents.
• —Does not cover sentiment analysis or emotion detection in calls.
• —Does not cover real-time audio processing (it requires pre-stored transcripts).

The clever bit

The system uses 'burst concentration' and entropy-based vocabulary scoring to mathematically define what makes a topic 'extraneous,' effectively turning a subjective human judgment (is this topic noise?) into a repeatable, automated filter.

Why it matters

In call centers, AI models often get distracted by 'filler' topics like standard greetings or background noise, which dilutes the value of data analytics. By automating the cleanup of these topics, Invoca's system helps businesses focus on actionable insights, such as specific customer pain points or sales objections, without needing manual data scrubbing.

Real-world examples

• 1.Call center analytics platforms
• 2.Automated customer service quality assurance software
• 3.Sales intelligence tools for tracking prospect objections