Eye Tracking Agent Oversight for AI Contact Center Content

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

As contact centers increasingly incorporate artificial intelligence, there is a need for improved methods to ensure proper oversight of AI-generated content by human agents to maintain customer satisfaction without diminishing the advantages of AI assistance.

Innovation Solution

A system using eye tracking to monitor human agents' review of AI-generated content in contact center communication sessions, where the generated content is presented to agents for review through a user interface, and an indication of their attention level is stored as Key Performance Indicators (KPIs), allowing for reports based on these metrics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If AI components are used to generate content in contact center sessions, then productivity is improved, but reliability deteriorates due to insufficient agent oversight

Engineering Contradiction:
ImproveAI content generation efficiencyVSAvoidContent quality assurance
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system implements feedback by monitoring agent eye movements and providing data about whether agents are reviewing AI-generated content. This feedback mechanism allows the system to assess the quality of human oversight and potentially adjust processes to ensure content reliability while maintaining productivity benefits.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent replaces traditional mechanical monitoring methods with eye tracking technology. Instead of manually reviewing agent behavior or using complex surveillance systems, the patent uses optical eye tracking to automatically detect and measure agent attention to AI-generated content, resolving the contradiction between automation efficiency and oversight quality.

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

2Reliability

If agents review all AI-generated content, then reliability is improved, but productivity deteriorates due to increased time consumption

Engineering Contradiction:
ImproveContent review thoroughnessVSAvoidAgent throughput
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent replaces time-consuming manual content review with automated eye tracking technology. The system objectively measures whether agents are reviewing content by tracking eye movements, eliminating the need for lengthy manual verification processes while ensuring reliability through objective monitoring of agent attention.

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

Solution Approach 2:

The system enables self-service monitoring where the eye tracking technology automatically tracks and records agent behavior without requiring additional human intervention or time. The monitoring process occurs passively in the background, allowing agents to maintain their normal workflow while their review behavior is captured and analyzed.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If eye tracking monitoring is implemented, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
ImproveAgent attention measurementVSAvoidEye tracking system integration
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces eye tracking technology as an intermediary between the agent and the content review process. This intermediary device objectively measures agent attention without interfering with the natural interaction between the agent and AI-generated content, providing precise measurement while maintaining system simplicity through non-intrusive monitoring.

Inventive Principle:
Principle #24Intermediary (Mediator)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach ensures appropriate oversight of AI-generated content, preventing customer dissatisfaction from inadequate review while optimizing the use of AI assistance by providing actionable insights into agent performance.

Implementation Method 1

An eye tracking system associated with the agent device can monitor review of the generated content by the human agent

Methodology Applied
Scientific EffectEye tracking:

Data Source

PatentEP3448005B1Monitoring agent oversight of artificial intelligence content in a contact center
Publication Date: 2021.10.06 AVAYA INC
  • EP3448005B1 patent drawingFigure 1~2
  • EP3448005B1 patent drawingFigure 3
  • EP3448005B1 patent drawingFigure 4

AI summary

Embodiments provide an oversight mechanism using eye tracking to monitor a human agent's review of artificial intelligence generated contact in a contact center communication session. Content generated by an artificial intelligence engine for each session can be presented to the human agent through a user interface for review by the human agent. While the generated content is being presented, an eye tracking system associated can monitor review of the generated content by the human agent. An indication of the human agent's level of attention to the generated content can be generated based on monitoring the review of the content by the human agent. The indication of the human agent's level of attention can be stored in a set of Key Performance Indicators (KPIs) for the human agent. One or more reports can be provided based on the KPIs.