Asynchronous Messaging Session Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Asynchronous communication channels lack clear indications of session endings, making it difficult for contact centers to determine when interactions have concluded, leading to inefficiencies and challenges in managing customer interactions and agent allocation.

Innovation Solution

A system that analyzes customer interactions using content and metadata analysis to determine topic changes and engagement levels, allowing contact centers to intelligently route conversations to appropriate agents, whether human or chatbot, and manage agent workload effectively by identifying when a conversation is paused or completed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If asynchronous communication channels are used to enable flexible customer interactions, then customer convenience and accessibility are improved, but the ability to determine session endings and manage interactions efficiently deteriorates

Engineering Contradiction:
Improvecustomer convenienceVSAvoidinteraction management complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system implements feedback mechanisms by analyzing customer messages with AI to generate predictions about conversation status and topic changes. This feedback loop allows the contact center to automatically adjust agent assignments and manage interactions based on real-time analysis of communication patterns, resolving the complexity of managing asynchronous channels while maintaining customer convenience.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system enables self-service by automatically analyzing messages, predicting conversation status, and routing interactions without requiring manual monitoring. The AI-driven analysis and automatic agent assignment allow the system to manage itself, reducing the operational complexity of handling asynchronous communications while preserving ease of customer interaction.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If manual monitoring of asynchronous conversations is implemented to determine session endings, then interaction management accuracy is improved, but time consumption and operational efficiency worsen

Engineering Contradiction:
Improvesession detection accuracyVSAvoidtime for interaction management
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system replaces manual mechanical monitoring with automated AI-driven analysis. The AI model processes messages and predicts conversation status automatically, eliminating the need for human operators to manually review each interaction. This substitution maintains high detection accuracy while dramatically reducing the time required for interaction management.

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

Solution Approach 2:

The AI analysis system acts as an intermediary between customer messages and agent assignment decisions. It processes and interprets communication patterns, generating predictions about session status and topic changes that guide automatic routing decisions. This intermediary layer provides accurate session detection without requiring direct human intervention in monitoring each conversation.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If AI-driven topic analysis is used to determine conversation status, then agent allocation efficiency is improved, but system complexity increases

Engineering Contradiction:
Improveagent allocation efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The AI system performs multiple functions including message analysis, topic identification, conversation status prediction, and routing recommendations within a single integrated platform. This multi-functional approach improves agent allocation efficiency while managing system complexity by consolidating various analytical tasks into one universal system rather than requiring separate specialized components.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system performs preliminary analysis of customer messages using AI to predict conversation status and identify topic changes before agent assignment is required. This advance preparation of analysis results enables efficient agent allocation by having readiness information prepared beforehand, improving productivity while the automated nature of the preliminary action helps manage the complexity burden.

Inventive Principle:
Principle #10Preliminary action

4Reliability

If conversation context is saved for extended periods to enable seamless resumption, then customer experience quality is improved, but resource consumption and system load increase

Engineering Contradiction:
Improveconversation continuityVSAvoidcomputational resource consumption
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system applies partial action by selectively saving and maintaining conversation context based on predicted continuity needs. Rather than universally preserving all conversation data indefinitely, the AI analysis identifies which conversations are likely to be resumed and prioritizes context retention for those cases. This approach maintains reliable conversation continuity for relevant interactions while reducing overall resource consumption by not retaining context for all conversations equally.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3771159B1Enhanced digital messaging
Publication Date: 2024.11.06 AVAYA MANAGEMENT LP
  • EP3771159B1 patent drawingFigure 1
  • EP3771159B1 patent drawingFigure 2
  • EP3771159B1 patent drawingFigure 3A

AI summary

Embodiments of the disclosure provide a method of processing messages received in an asynchronous communication system. In some embodiments, the method includes determining that a conversation is established with a customer communication device using an asynchronous communication channel, analyzing one or more messages exchanged over the asynchronous communication channel to determine a likelihood of communication disengagement, comparing the likelihood of communication disengagement with a predetermined disengagement threshold, and based on the comparison of the likelihood of communication disengagement with the predetermined threshold, updating a graphical user interface of an agent communication device being used to engage in the conversation.