Intelligent Call Routing via Knowledge Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current call routing systems rely on predefined scripts and simple distribution algorithms, which may not effectively match user intent with the most suitable agents, leading to suboptimal business outcomes and customer experiences.
Innovation Solution
The implementation of a method that uses machine learning models and knowledge graphs to dynamically determine user intent and classify agents based on similarity, providing personalized route recommendations that optimize for business objectives such as sales, satisfaction, and engagement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If predefined scripts and simple distribution algorithms are used for call routing, then the system complexity is reduced and ease of operation is improved, but the effectiveness of user-agent matching deteriorates
Solution Approach 1:
A knowledge graph serves as an intermediary between the simple distribution algorithm and the user-agent matching process. The knowledge graph enriches basic routing information with semantic relationships, agent expertise profiles, and contextual data, enabling effective matching without requiring complex routing logic throughout the entire system.
Solution Approach 2:
The system applies complex matching logic locally at the point of routing decisions through the knowledge graph, while maintaining simple distribution algorithms elsewhere in the system. This allows sophisticated user-agent matching to occur only where needed, preserving overall system simplicity while improving matching effectiveness.
2Reliability
If sophisticated machine learning models and knowledge graphs are used to dynamically determine user intent and classify agents, then the effectiveness of user-agent pairings is improved, but the device complexity increases
Solution Approach 1:
The system segments the call routing process into distinct components: intent determination using machine learning models, agent classification using knowledge graphs, and final routing decisions. This segmentation allows each component to be optimized independently, managing overall system complexity while achieving effective user-agent pairings.
3Ease of operation
If all available agents are considered equal using simple distribution algorithms, then the ease of operation is maintained, but the productivity of call center operations deteriorates
Solution Approach 1:
The system changes the parameters used to evaluate agents from simple availability status to multi-dimensional profiles including expertise areas, performance metrics, and contextual capabilities. This transformation is achieved through the knowledge graph, which structures and manages these parameters without complicating the underlying distribution algorithm.
Data Source
AI summary
A system and method for intelligently routing calls between customers and agents. The system and method use knowledge graphs to generate route recommendations for a route selection system. The system uses dynamically selected objective functions to generate the route recommendations. The objective functions may be selected according to the intent of the call. The system and method can also be used to reroute ongoing calls when the intent of the call changes.