Contact Center ACW Factor Calculation Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current contact center systems lack an effective method to identify and evaluate interactions with unusual After-Call-Work (ACW) times, which are crucial for agent performance evaluation and operational efficiency, as ACW time can vary significantly based on business domain, call characteristics, and other factors, making it difficult to determine if the time is long or short without context.
Innovation Solution
A computerized system that calculates an ACW factor by using a machine learning model to predict ACW time based on interaction and customer data, then compares it to the actual ACW time, providing a positive, negative, or zero value to indicate if the interaction should be evaluated for completeness, training needs, or if it falls within a preconfigured threshold, thereby filtering interactions for evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If ACW time is reduced to improve productivity, then agent productivity increases, but evaluation precision deteriorates because it becomes difficult to determine if the time is appropriate without context
Solution Approach 1:
The patent changes the evaluation parameter from absolute ACW time to relative ACW factor, which adjusts the benchmark dynamically based on interaction characteristics, business domain, and call type. This allows productivity improvement through ACW reduction while maintaining evaluation precision through contextual comparison.
Solution Approach 2:
The patent adds contextual dimensions (business domain, interaction type, call characteristics) to the ACW evaluation, transforming it from a one-dimensional absolute time measurement to a multi-dimensional relative assessment. This enables precise evaluation while allowing productivity gains.
2Reliability
If all interactions are evaluated to ensure quality, then evaluation completeness improves, but loss of time increases due to the large volume of calls
Solution Approach 1:
The patent applies partial evaluation by selecting only interactions with unusual ACW factors for detailed review. Instead of evaluating all interactions, it focuses on the subset that deviates from the norm, thereby maintaining quality control while significantly reducing the time investment required.
Solution Approach 2:
The patent extracts and isolates interactions with abnormal ACW characteristics from the bulk of normal interactions. By separating these outliers for targeted evaluation, the system ensures quality monitoring of problematic cases without wasting time on routine evaluations.
3Loss of information
If ACW time is increased to ensure completeness of information logged, then information quality improves, but productivity decreases
Solution Approach 1:
The patent introduces dynamic adjustment of ACW expectations based on interaction characteristics. Rather than enforcing a static time requirement, the system adaptively determines appropriate ACW duration for each interaction type, allowing agents to spend more time on complex cases requiring detailed logging while moving quickly through simpler interactions.
Data Source
AI summary
A computerized-method for calculating an After-Call-Work (ACW) factor of an interaction in a contact center, by which a related recording may be filtered for evaluation is provided herein. The method includes an After-Call-Work (ACW) factor calculation module. The operating of the ACW factor calculation module includes: (i) receiving agent recording of the interaction. (ii) aggregating data fields associated with: (a) the interaction; and (b) the customer; (iii) retrieving ACW time of the interaction; (iv) forwarding the aggregated data fields to a machine learning model; (v) operating the machine learning model to calculate a predicted ACW time, based on the aggregated data fields; (vi) calculating an ACW factor based on the received time of ACW and the calculated predicted ACW time; and (vii) sending the calculated ACW factor to a platform by which the platform is preconfigured to distribute the interaction for evaluation, based on the ACW factor.