Intent-Driven Contact Center Routing via AI Intermediary
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current communication systems fail to efficiently route natural language queries to the most suitable agents, as static routing methods do not account for variations in communication topics, agent availability, and channel types, leading to suboptimal response times and accuracy.
Innovation Solution
A computer-implemented method that parses natural language communications to identify operative words, correlates them with pre-defined intents, and selects agent profiles based on the quality of association, ensuring that communications are routed to agents knowledgeable in the relevant intent, using artificial intelligence and intent models to facilitate accurate routing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If static routing methods are used to route communications, then system simplicity is maintained, but routing accuracy and response quality deteriorate because the system cannot account for variations in communication topics, agent availability, and channel types
Solution Approach 1:
The patent introduces an AI platform as an intermediary component between the communication system and agents. This platform parses natural language communications, identifies operative words, correlates them with pre-defined intents, and selects appropriate agent profiles based on quality of association. The intermediary handles the complexity of dynamic routing analysis, allowing the overall system to achieve high routing accuracy without requiring every component to be complex.
2Reliability
If AI-based intent analysis is implemented to parse natural language communications and select agent profiles, then routing quality and response accuracy improve, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-defining intents and their associated operative words before actual communications arrive. The AI platform has already established the framework for analyzing communications, so when a natural language query arrives, the system can quickly match it against pre-defined intents rather than creating analysis frameworks in real-time. This reduces processing time while maintaining high response quality.
3Ease of operation
If dynamic agent profile selection based on intent correlation is used, then customer service quality improves, but the complexity of agent profile management and intent model maintenance increases
Solution Approach 1:
The system implements feedback mechanisms where the AI platform continuously analyzes the quality of association between operative words and pre-defined intents, and between agent profiles and intents. This feedback allows the system to learn from past interactions and improve routing decisions over time. The feedback loop automates the adjustment of routing strategies, reducing the manual complexity of profile management while maintaining high customer service quality.
Data Source
AI summary
The present disclosure relates generally to providing an intent-driven contact center. The contact center according to some embodiments analyzes intents to determine to which device or agent to route a communication. The analyzed intent information can also be used to formulate reports and analyze the accuracy of the identified intents with respect to the received communication.