Real-Time Voice Signal Analysis for Contact Center Storage Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Contact centers face challenges in efficiently recording and analyzing voice signals due to high storage costs and delayed issue identification, missing opportunities to address problems in real-time, leading to potential customer dissatisfaction and loyalty loss.

Innovation Solution

Implementing a system that analyzes streaming voice signals in real-time to detect predetermined utterances, determining response-determinative significance, and initiating responsive actions, while deciding on short-term or long-term storage based on the analysis, allowing for improved reaction times to potential issues.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If contact centers record a small percentage of incoming calls for compliance and quality purposes, then storage costs are reduced, but the ability to identify issues or problems efficiently deteriorates

Engineering Contradiction:
Improvestorage costsVSAvoidissue identification efficiency
Core Design Contradiction:
Loss of energyVSProductivity

Solution Approach 1:

The system performs preliminary analysis of call content during the call itself, identifying keywords, phrases, and sentiment patterns that indicate potential issues. This preliminary action enables real-time detection of problems before the call ends, allowing immediate responsive actions to be taken while the customer is still engaged, rather than waiting for post-call review of recorded calls.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical approach of manually reviewing recorded calls with automated real-time speech analysis using speech-to-text conversion, natural language processing, and machine learning algorithms. This substitution enables efficient processing and analysis of call content without requiring manual listening and review, dramatically improving issue identification efficiency while reducing storage requirements.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If contact centers analyze calls after the fact, then compliance recording requirements are met, but the opportunity to address problems when they occur is lost

Engineering Contradiction:
Improvecompliance recordingVSAvoidresponse time to issues
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of call content during the call itself, identifying keywords, phrases, and sentiment patterns that indicate potential issues. This preliminary action enables real-time detection of problems before the call ends, allowing immediate responsive actions to be taken while the customer is still engaged, rather than waiting for post-call review of recorded calls.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system provides real-time feedback to agents during calls by analyzing speech content and providing alerts or suggestions about potential issues. This feedback loop enables agents to adjust their approach immediately, address customer concerns while they arise, and improve customer experience in real-time rather than waiting for post-call analysis.

Inventive Principle:
Principle #23Feedback

3Reliability

If contact centers record all incoming calls for compliance purposes, then compliance requirements are fully met, but storage costs increase significantly

Engineering Contradiction:
Improvecompliance recordingVSAvoidstorage costs
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system extracts only the essential elements of call content that are relevant for compliance and quality purposes, such as detected issues, customer sentiment, key topics discussed, and resolution outcomes. By extracting and analyzing only these critical elements in real-time, the system maintains compliance capabilities while avoiding the need to store entire call recordings, significantly reducing storage costs.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of storing complete call recordings, the system creates simplified digital representations or copies of call content in the form of transcribed text, extracted keywords, sentiment scores, and issue classifications. These compressed representations maintain the essential information needed for compliance and analysis while occupying minimal storage space compared to full audio recordings.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP2124425B1System for handling a plurality of streaming voice signals for determination of responsive action thereto
Publication Date: 2020.07.01 ACCENTURE GLOBAL SERVICES LTD
  • EP2124425B1 patent drawingFigure 1
  • EP2124425B1 patent drawingFigure 2~3
  • EP2124425B1 patent drawingFigure 4~5

AI summary

Streaming voice signals, such as might be received at a contact center or similar operation, are analyzed to detect the occurrence of one or more unprompted, predetermined utterances. The predetermined utterances preferably constitute a vocabulary of words and/or phrases having particular meaning within the context in which they are uttered. Detection of one or more of the predetermined utterances during a call causes a determination of response-determinative significance of the detected utterance(s). Based on the response-determinative significance of the detected utterance(s), a responsive action may be further determined. Additionally, long term storage of the call corresponding to the detected utterance may also be initiated. Conversely, calls in which no predetermined utterances are detected may be deleted from short term storage. In this manner, the present invention simplifies the storage requirements for contact centers and provides the opportunity to improve caller experiences by providing shorter reaction times to potentially problematic situations.