Emotion Detection in Voice Signals for Dynamic Call Center Scripts

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing call center systems fail to detect and adapt to customer emotions in real-time, leading to suboptimal customer service experiences as they do not dynamically modify scripts based on emotional cues from customers.

Innovation Solution

A computer-implemented method that extracts Mel-Frequency Cepstral coefficients from voice signals, uses a machine learning model to predict customer emotions, and generates a confidence score to dynamically modify call center agent scripts, allowing for real-time adjustments in response to customer emotions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If real-time emotion detection and dynamic script modification are implemented, then customer satisfaction and service effectiveness are improved, but system complexity and computational requirements increase

Engineering Contradiction:

Improvecustomer satisfactionVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces an emotion detection system as an intermediary component that bridges the gap between customer interactions and agent support systems. This mediator analyzes voice signals in real-time and translates emotional states into actionable insights, enabling dynamic script modifications without requiring direct complex integration between all system components.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional rule-based script modification systems with machine learning models that automatically detect emotions and generate script recommendations. This substitution of mechanical/rule-based systems with intelligent algorithms reduces the need for manual system configuration and complex integration logic.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Speed

If emotion detection is performed continuously during calls, then response timeliness is improved, but computational energy consumption increases

Engineering Contradiction:

Improveresponse timelinessVSAvoidcomputational energy consumption

Core Design Contradiction:

SpeedVSUse of energy by moving object

Solution Approach 1:

The patent implements periodic emotion detection by analyzing voice signals at specific intervals during customer interactions rather than continuously processing every audio sample. This periodic approach maintains timely response capability while significantly reducing computational energy consumption compared to continuous analysis.

Inventive Principle:

Principle #19Periodic action

Solution Approach 2:

The system performs partial emotion detection by focusing analysis on critical moments in the interaction or selectively monitoring specific voice parameters, rather than processing the entire audio stream with full computational intensity. This partial action approach balances timeliness with energy efficiency.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS11349989B2Systems and methods for sensing emotion in voice signals and dynamically changing suggestions in a call center

Publication Date: 2022.05.31 GENPACT USA INC

AI summary

Systems and methods for sensing emotion in voice signals and dynamically changing suggestions in a call center are disclosed. According to one embodiment, a computer-implemented method comprises receiving a call from a customer at a call center. A sample of the call is recorded and the Mel-Frequency Cepstral coefficient is extracted from the sample. A machine learning model predicts an emotion of the customer and generates a confidence score for the emotion. A script of a call center agent is modified based on the emotion and the confidence score.