Support Request Assignment Using Conversation Pace Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Customer service providers face challenges in effectively managing support requests due to inefficiencies in assigning operators based on the pace of conversation, leading to potential frustration and dissatisfaction among customers.
Innovation Solution
A computer-implemented method that performs textual analysis of user inputs during current and previous support sessions to classify users into predefined classes describing the pace of conversation, allowing for dynamic assignment of support requests to appropriate operators, thereby improving customer satisfaction and resource management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If support requests are assigned using static or simple routing methods, then device complexity is reduced, but customer satisfaction deteriorates due to mismatched operator-user pace compatibility
Solution Approach 1:
The system dynamically changes the parameter of operator assignment based on the detected pace of conversation. By calculating a pace metric from user inputs and matching it with operator characteristics, the system adapts the assignment decision to current conditions, resolving the contradiction between simple routing and satisfied customers.
Solution Approach 2:
The assignment system transitions from static to dynamic operation by continuously monitoring user inputs during support sessions and adjusting assignments in real-time. This dynamic adaptation allows the system to maintain customer satisfaction without requiring overly complex predetermined routing structures.
2Measurement precision
If textual analysis is performed on all user inputs in real-time, then assignment accuracy is improved, but processing time increases
Solution Approach 1:
The system performs textual analysis selectively on key user inputs rather than processing every single input with equal depth. By focusing analysis on inputs that most significantly indicate pace of conversation, the system achieves sufficient classification accuracy without incurring excessive processing time penalties.
Solution Approach 2:
The system performs preliminary textual analysis on user inputs during the support session to detect pace of conversation early. This preliminary classification enables timely operator assignment without requiring exhaustive analysis, balancing accuracy with processing efficiency.
3Productivity
If operators are assigned without considering pace of conversation, then resource allocation is simplified, but productivity decreases due to longer resolution times
Solution Approach 1:
The system incorporates pace of conversation as a dynamic parameter in the operator assignment decision. By calculating pace metrics from user inputs and matching them with operator capabilities, the system optimizes resolution efficiency without requiring complex manual assignment management.
Solution Approach 2:
The system automatically performs textual analysis, pace detection, and operator selection without requiring manual intervention. This self-service approach to assignment management improves productivity while keeping the complexity hidden within the automated system rather than requiring complex external management processes.
Data Source
AI summary
Aspects discussed herein include a computer-implemented method comprising receiving a support request from a user, and during a current support session responsive to the support request, performing textual analysis of one or more inputs provided by the user during one or both of: (i) the current support session and (ii) one or more previous support sessions. The method further comprises applying one or more features determined by the textual analysis to a model to classify the user into a first class of a predefined plurality of classes that describe a pace of conversation during the current support session. The method further comprises, based on the classification of the user, assigning the support request to be fulfilled by a first operator of a predefined plurality of support operators.