Dynamic Weighted Call Routing System for Customer Care Centers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated call routing systems in customer care centers, such as those using fixed prompt/response hierarchies and natural-language interpretation based call vectoring, often route calls inappropriately and lack prioritization or classification, leading to inefficiencies and high error rates.
Innovation Solution
A system that uses a telephony interface, prompt generation, and response processing units to assign weights to caller responses, determining appropriate CSR routing through a data compilation and call routing unit, employing heuristic methods like simulated-annealing and traveling salesman problem solutions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a fixed prompt/response hierarchy is used for call routing, then the system structure is simple and easy to implement, but the call routing accuracy deteriorates and inappropriate CSR routing occurs
Solution Approach 1:
The patent transforms the static fixed hierarchy into a dynamic weighting system where routing decisions are based on real-time calculation of weights assigned to different call attributes and CSR attributes. The system continuously adjusts routing based on the sum of weights rather than following predetermined fixed paths.
Solution Approach 2:
The patent introduces weight parameters that can be assigned to different call attributes (e.g., call type, customer priority) and CSR attributes (e.g., specialization, availability). By changing these parameter values dynamically, the system optimizes routing accuracy without requiring complex structural changes.
2Adaptability or versatility
If natural-language interpretation based call vectoring is used, then the system can handle varied speech patterns, but the error rate increases to over 10%
Solution Approach 1:
The patent introduces an intermediary weighting layer between speech recognition and routing decisions. Instead of directly mapping speech patterns to routing outcomes, the system converts both call attributes and CSR attributes into weighted scores, which then guide the routing decision. This intermediary step reduces errors by providing a more robust decision framework.
Solution Approach 2:
The system incorporates feedback mechanisms where routing outcomes and call attributes are continuously evaluated and used to adjust weight assignments. This allows the system to learn from past routing decisions and improve accuracy over time while maintaining adaptability to varied speech patterns.
3Reliability
If prioritization of premium customer calls is implemented, then customer service quality improves, but the routing system complexity increases
Solution Approach 1:
The patent implements prioritization by assigning higher weight values to premium customer attributes and high-priority call types. This allows the system to naturally prioritize these calls through the weight summation process without requiring separate complex prioritization subsystems. The same weighting framework handles both routine routing and prioritization needs.
Data Source
AI summary
A method and system for routing incoming calls by assigning weights to the call. A method in accordance with an embodiment of the invention comprises receiving an incoming call, generating one or more prompts to solicit respective responses from the caller and receiving, from the caller, the respective responses. The method further comprises assigning one or more respective weights to the call, the one or more respective weights corresponding to each of the one or more responses, processing the weights to determine one or more overall weights of the call, and routing the call to an appropriate location based, at least in part, on the overall weights of the call.