Self-learning Adaptive Routing System for Call Centers

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Call centers face inefficiencies and high costs due to generic routing rules, leading to incorrect agent transfers and customer dissatisfaction, as well as the expense of maintaining sophisticated systems for tailored routing.

Innovation Solution

A self-learning adaptive routing system that uses machine learning to create specialized routing rules based on customer interactions, including co-browsing previews, to route customers to the correct agents without transferring them, minimizing incorrect transfers over time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If generic routing rules are used to reduce costs, then device complexity and maintenance cost are reduced, but routing accuracy and customer satisfaction deteriorate

Engineering Contradiction:
Improverouting system complexityVSAvoidrouting accuracy
Core Design Contradiction:
Device complexityVSManufacturing precision

Solution Approach 1:

The routing system automatically learns and creates routing rules through machine learning algorithms that analyze customer interaction data and contact resolution outcomes. The system self-updates routing rules without requiring manual configuration, enabling it to develop specialized routing knowledge while maintaining low operational complexity and costs

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system dynamically adjusts routing parameters based on learned patterns from customer interactions. By changing routing decisions based on analyzed data patterns rather than static rules, the system achieves high routing accuracy while keeping the underlying system structure simple and cost-effective

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If sophisticated tailored routing rules are implemented to improve routing accuracy, then routing precision is improved, but device complexity and maintenance cost increase

Engineering Contradiction:
Improverouting accuracyVSAvoidrouting system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system automatically generates and updates routing rules through machine learning without requiring manual intervention for rule creation or maintenance. This eliminates the complexity and costs associated with developing and maintaining sophisticated tailored routing rules while preserving high routing accuracy

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system uses feedback from contact resolution outcomes to continuously improve routing rules. By analyzing whether contacts were successfully resolved and incorporating this feedback into rule creation, the system achieves sophisticated routing accuracy automatically without manual rule development

Inventive Principle:
Principle #23Feedback

3Device complexity

If manual rule maintenance is neglected to reduce costs, then maintenance cost is reduced, but routing reliability deteriorates

Engineering Contradiction:
Improvemaintenance effortVSAvoidrouting reliability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system automatically maintains and updates routing rules through machine learning algorithms that continuously analyze customer interaction data. This self-maintenance capability ensures routing reliability is preserved without requiring manual rule maintenance efforts

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The machine learning system continuously learns from incoming customer interactions and updates routing rules in real-time. This continuous learning process ensures routing rules remain current and reliable without interruption or manual intervention

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentEP3622458B1Self-learning adaptive routing system
Publication Date: 2024.03.27 ORACLE INT CORP
  • EP3622458B1 patent drawingFigure 1
  • EP3622458B1 patent drawingFigure 2
  • EP3622458B1 patent drawingFigure 3

AI summary

A method for self-learning adaptive routing can include receiving a contact along with a sequence of events from a customer via a graphical user interface on a web page within a browser window. A universal resource locator ("URL") of the web page can be captured and mapped with the sequence of events to the contact. A matching routing rule can be used to route the contact to an appropriate customer service queue. An agent associated with the customer service queue can view a co-browsing preview of the customer's desktop, which the agent can use to transfer the contact to a different customer service queue. A machine learning algorithm can create a new routing rule based on the URL of the web page, the sequence of events, the co-browsing preview, the second routing, and the determination that the second agent associated with the second customer service queue resolved the contact.