Repeated-Information-Request Score for Contact Center Quality Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contact centers face challenges in identifying and addressing repeated information requests during interactions, which impact Average Answer Time (AAT) and agent performance, leading to increased costs and inefficiencies.
Innovation Solution
A computerized method and system for calculating a Repeated-Information-Request (RIR) score, using a processor and data storage to count and calculate RIR scores based on interaction recordings and metadata, with a Natural Language Understanding (NLU) module to identify repeat requests, and a Repeat Request Threshold (RRT) to filter interactions for evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual review of all interactions is performed for quality evaluation, then comprehensive quality assessment is achieved, but evaluation time and resources are excessively consumed
Solution Approach 1:
The system performs self-evaluation by automatically calculating RIR scores for interactions using AI/ML models, enabling the quality management system to assess its own data without requiring manual review of every interaction. This self-service mechanism identifies problematic interactions that need human evaluation.
Solution Approach 2:
An automated RIR scoring system acts as an intermediary between raw interaction data and human evaluators. The system calculates RIR scores and filters interactions, presenting only those below threshold values to human reviewers, thereby reducing evaluation workload while maintaining quality standards.
2Reliability
If all interactions are evaluated for repeated information requests, then complete quality monitoring is achieved, but processing complexity and costs increase
Solution Approach 1:
The system extracts only the critical feature (RIR score) from complete interaction data using AI/ML models. By calculating a single RIR score that encapsulates repeated information request patterns, the system simplifies complex interaction analysis into a manageable metric for filtering and evaluation.
Solution Approach 2:
The system transforms complex interaction data into a simplified RIR score parameter. By changing the representation from full interaction transcripts to a single numerical score, the system enables efficient filtering and comparison while maintaining the essential quality information.
3Productivity
If interactions with high repeated information requests are identified and addressed, then agent performance improves, but the system requires sophisticated analysis capabilities
Solution Approach 1:
The system replaces manual analysis mechanisms with automated AI/ML models that calculate RIR scores. This substitution enables sophisticated analysis of repeated information requests without requiring human experts to manually review and interpret every interaction, making advanced analysis scalable and accessible.
Data Source
AI summary
There is thus provided a computerized-method for calculating a Repeated-Information-Request (RIR) score of an interaction in a contact center, by which a related interaction-recording is filtered for evaluation. The computerized-method is operating in a computerized-system which includes a processor, a data-storage and a memory to store the data-storage. The processor is operating a RIR score calculation module. The operating of the RIR score calculation module includes: (i) retrieving from the data-storage an interaction-recording and an interaction-recording-length thereof; (ii) operating a module on the retrieved interaction-recording to count a number of requests to repeat information; (iii) calculating a RIR score according to the number of requests to repeat information and the interaction-recording-length; and (iv) storing the RIR score of the retrieved interaction-recording in the data-storage. The RIR score is sent to a platform by which the platform is preconfigured to distribute the interaction-recording for evaluation, based on the RIR score.