Resource Allocation for Digital Contact Centers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for resource allocation in digital contact centers struggle to handle the complexity of multiple concurrent communications across various digital channels, leading to inefficiencies in staffing requirements and service quality.
Innovation Solution
A method that combines search algorithms with machine learning algorithms to iteratively adjust resource allocation assignments based on forecasted workloads and required service metrics, ensuring optimal staffing levels across multiple channels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional Erlang C formula or simulation methods are used to approximate staffing requirements, then the system can handle voice-only environments with maximum concurrency equal to 1, but the system cannot effectively handle digital contact centers where agents must divide attention across multiple concurrent communications over multiple channels
Solution Approach 1:
The patent changes the fundamental parameters used for staffing predictions from traditional voice-call metrics to digital-era metrics including concurrent communication handling capacity, multi-channel service levels, and agent availability across different communication modes. This allows the system to adapt to digital contact centers while maintaining prediction accuracy through parameter transformations that reflect modern work patterns.
Solution Approach 2:
The system dynamically adjusts staffing requirements based on real-time workload fluctuations across multiple channels (voice, email, chat, SMS). Rather than static Erlang C calculations, the system continuously updates service level predictions and staffing needs to reflect the dynamic nature of digital communications where agents can handle multiple concurrent interactions.
2Device complexity
If average handling time (AHT) is used to approximate service level, then the system can provide simple staffing estimates, but the system lacks the ability to capture the complexity of digital mediums and different user communication patterns
Solution Approach 1:
The patent segments service level measurements into channel-specific metrics (voice service level, email response time, chat resolution time, SMS delivery time) rather than using a single AHT metric. This segmentation allows the system to capture the unique characteristics of each digital communication channel while maintaining measurement precision through channel-appropriate performance indicators.
Solution Approach 2:
The system creates a universal service level framework that works across all digital communication channels (voice, email, chat, SMS, WhatsApp) by defining common performance dimensions (response time, resolution time, service level percentage) that can be measured and optimized consistently across different mediums, enabling generalized recommendations for all users.
3Adaptability or versatility
If the system tries to generalize staffing recommendations to all users, then it can provide broad applicability, but it becomes very hard to account for different tenant-specific communication patterns and channel usage variations
Solution Approach 1:
The system performs preliminary actions by collecting and analyzing historical communication data from each tenant during an onboarding or learning phase. This preliminary data gathering allows the system to establish tenant-specific baselines and patterns before generating staffing recommendations, enabling both generalization across tenants and customization for individual communication patterns.
Solution Approach 2:
The system implements feedback mechanisms that continuously monitor actual service levels and communication patterns across different tenants. This feedback loop allows the system to learn from tenant-specific variations and adjust staffing recommendations accordingly, balancing generalizability with tenant-specific customization through data-driven adaptations.
Data Source
AI summary
A method for allocating resources for a plurality of time intervals, including: receiving a forecasted workload and at least one required service metric value; applying a search algorithm to identify an initial allocation assignment; inputting the assignment to a machine learning algorithm, the machine learning algorithm trained on historic data of past intervals; predicting an expected service metric value provided by the initial allocation assignment; adjusting the initial allocation assignment based on a difference between the expected service metric value and the corresponding required service metric value; iteratively repeating the applying, inputting, predicting, and adjusting operations until one of: the expected service metric value predicted for an adjusted allocation assignment is within a predetermined distance of the corresponding at least one required service metric value for the interval; or a predetermined time has elapsed.