SME Availability Prediction Using Presence Data and Wait-Time Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contact centers lack efficient mechanisms to predict the availability of subject matter experts (SMEs), leading to unnecessary agent time wastage and delayed customer responses due to the inability to track back-office SME states and availability accurately.
Innovation Solution
A presence prediction system that utilizes a presence aggregator to collect SME status updates, runs algorithms on historic data, and predicts the time to availability by integrating a custom machine learning network, such as an LSTM RNN, to provide agents with estimated wait times and calendar information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional directory search is used to find SMEs, then the system is simple to operate, but agents waste time hunting for available SMEs and cannot predict availability
Solution Approach 1:
The system performs preliminary actions by continuously collecting SME status data in the background and pre-calculating predicted availability times using machine learning algorithms. This allows agents to receive ready-to-use prediction results without needing to perform complex manual searches or wait for real-time status checks.
Solution Approach 2:
The patent introduces a presence prediction system as an intermediary layer between agents and SMEs. This intermediary collects status data from SMEs, processes it through machine learning models, and delivers predicted availability information to agents, thereby reducing the direct search burden on agents while managing system complexity centrally.
2Measurement precision
If real-time SME status tracking is implemented, then availability information is accurate, but the system becomes complex and requires continuous data collection
Solution Approach 1:
The system implements feedback mechanisms by continuously collecting actual SME status data, comparing it with predicted availability times, and using the discrepancies to retrain and improve the machine learning models. This feedback loop enhances measurement precision over time while the automated process manages system complexity.
Solution Approach 2:
The presence prediction system serves itself by automatically collecting status data, processing it through machine learning algorithms, and generating predictions without requiring manual intervention. This self-service approach maintains high measurement precision while containing operational complexity within the automated system.
3Productivity
If agents manually check SME availability, then the system remains simple, but customer response time is delayed due to hunting for SMEs
Solution Approach 1:
The system performs preliminary computation of predicted availability times using machine learning models trained on historical data. This pre-processing allows agents to immediately see predicted availability information without performing manual status checks, thereby maintaining operational simplicity while significantly improving customer response speed.
Solution Approach 2:
The patent replaces the mechanical manual checking process with an automated machine learning-based prediction system. This substitution eliminates the need for agents to manually query SME availability while providing instant predicted availability information, thus improving productivity without sacrificing ease of operation.
4Reliability
If historical data is collected and processed with machine learning, then predicted availability is accurate, but data processing complexity increases
Solution Approach 1:
The data processing system serves itself by automatically collecting, storing, and processing historical SME status data through machine learning algorithms. This self-service approach maintains high prediction accuracy while the automated processing manages complexity within the system's operational framework.
Solution Approach 2:
The system uses feedback from actual SME availability data to continuously improve the machine learning models. By comparing predicted availability with actual status and retraining models accordingly, the system enhances reliability while the automated feedback loop manages the complexity of data processing.
Data Source
AI summary
A system automatically identifies wait times for a subject matter expert (SME). The system includes a cloud server in communication with an agent computer, an SME computer, and a database for storing presence data associated with the SME computer. Over a first period of time, the processor receives the presence data associated with the SME computer; stores the presence data in the database; and trains a custom machine learning network. The processor receives an input from the agent computer requesting contact with the SME computer, and solicits a status from the SME computer. If the status is not “Available”, the processor, using the trained custom machine learning network, predicts a wait time after which the status will be “Available” and reports the predicted wait time to the agent computer. If the status is “Available”, the system establishes a communication link between the agent computer and the SME computer.