Voice Modulated Speech Injection for Call Center Efficiency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Call center agents face the burden of repeatedly stating common information across numerous calls, leading to inefficiencies and increased caller wait times, as existing systems do not effectively manage the injection of personalized and consistent responses.

Innovation Solution

A computer-implemented method and system that allows agents to inject recorded statements or computer-generated speech modulated in their voice into ongoing calls, reducing the need for repetitive statements and enabling concurrent handling of multiple calls.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If agents manually state common information in each call, then callers receive personalized interaction, but agent productivity decreases due to repetitive tasks

Engineering Contradiction:
Improvepersonalized interactionVSAvoidagent productivity
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The system creates copies of the agent's voice recordings and inserts them into call streams, allowing the same personalized speech to be reused across multiple calls without requiring the agent to repeat statements manually

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The agent records statements in advance during non-call periods, and the system prepares and inserts these pre-recorded statements automatically during calls, eliminating the need for real-time repetition

Inventive Principle:
Principle #10Preliminary action

2Productivity

If agents handle multiple calls concurrently, then productivity increases, but maintaining consistent personalized response becomes difficult

Engineering Contradiction:
Improveconcurrent call handlingVSAvoidresponse consistency
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system generates accurate copies of the agent's recorded statements and inserts them into multiple concurrent call streams, ensuring identical personalized responses are delivered consistently across all simultaneous calls

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The speech insertion system acts as an intermediary between the agent and multiple callers, automatically managing the insertion of consistent personalized statements into concurrent calls without requiring direct agent intervention in each call

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If automated speech insertion is implemented, then productivity increases, but system complexity increases

Engineering Contradiction:
Improvecall handling efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system introduces a speech insertion component that mediates between existing call management systems and audio output, adding automated speech insertion capability without fundamentally redesigning the entire call center infrastructure

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary actions by recording agent speech in advance and preparing it for automatic insertion, reducing the complexity of real-time speech generation and insertion during active calls

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3633965B1Edge injected speech in call centers
Publication Date: 2021.06.09 UNITED SERVICES AUTOMOBILE ASSOCIATION (USAA)
  • EP3633965B1 patent drawingFigure 1
  • EP3633965B1 patent drawingFigure 2
  • EP3633965B1 patent drawingFigure 3

AI summary

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving an input from an agent during a call with a caller where the input directs one or more processors to inject a recorded statement in the agent's voice into the call, and where the recorded statement in the agent's voice is stored in a computer-readable file. Obtaining the recorded statement in the agent's voice based on data associated with the input and in response to receiving the input. And causing the recorded statement in the agent's voice to be inserted into a media stream of the call.