ML Queue Positioning via Self-Support Actions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users have little incentive to utilize self-service options for troubleshooting, and once they contact a service center, they rarely use self-service tools, leading to inefficiencies and resource wastage.
Innovation Solution
A support platform that utilizes machine learning to determine support queue positions based on self-support actions, assigning weights to these actions and modifying queue positions to incentivize users to perform self-support, thereby reducing waiting times and conserving resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If users are provided with self-service options for troubleshooting, then resource consumption at service centers is reduced, but users have little incentive to utilize these options
Solution Approach 1:
The system enables users to perform self-support actions such as troubleshooting steps and diagnostic tasks independently. The platform tracks these actions and integrates them into queue position determination, allowing users to serve themselves while maintaining engagement through incentive mechanisms.
Solution Approach 2:
The system dynamically changes the parameter of queue position based on user performance of self-support actions. By weighting and scoring different self-support actions, the system modifies the traditional first-come-first-served parameter to incorporate user initiative, thereby creating incentive without requiring complex manual intervention.
2Device complexity
If support queue positions are determined by arrival time only, then queue management is simple, but waiting times increase and efficiency decreases
Solution Approach 1:
The queue position determination transitions from a static first-come-first-served model to a dynamic system that continuously adjusts positions based on user performance of self-support actions. The machine learning model processes ongoing user actions and recalculates queue positions in real-time, optimizing waiting times while maintaining manageable system complexity through automated scoring.
Solution Approach 2:
The system implements feedback loops where user self-support actions are tracked, weighted, and scored. This feedback is continuously fed into the queue position determination algorithm, allowing the system to respond to user behavior and adjust queue positions accordingly. The feedback mechanism operates automatically through machine learning models, preventing complexity from becoming unmanageable.
3Measurement precision
If self-support actions are tracked and weighted with machine learning, then queue position accuracy improves, but system complexity increases
Solution Approach 1:
The machine learning model serves as an intermediary layer between user self-support actions and queue position determination. Instead of directly complexifying the queue management system, the ML model abstracts the complexity by processing user actions, assigning weights, and generating scores that feed into the queue position calculation. This intermediary approach maintains measurement precision while containing system complexity within the ML module.
4Loss of substance
If users perform more self-support actions, then resource wastage is reduced, but the burden of troubleshooting shifts to users
Solution Approach 1:
The system empowers users to perform self-support actions independently, shifting some troubleshooting burden to users. By tracking these actions and incorporating them into queue position determination with positive weighting, the system transforms what could be seen as additional user burden into an incentivized self-service opportunity, reducing overall resource wastage while maintaining user engagement.
Data Source
AI summary
A device receives a communication associated with a support issue encountered by a user, and receives information identifying one or more self-support actions performed by the user in relation to the support issue. The device assigns the communication to a position in a support queue. The support queue includes information identifying positions of other communications received from other users, when the other communications are received, and self-support actions performed by the other users. The device associates the information identifying the one or more self-support actions with information identifying the position of the communication, and applies respective weights to the one or more self-support actions. The device generates a score for the communication based on applying the respective weights, and modifies the position of the communication based on the score. The device performs one or more actions based on modifying the position of the communication.