Dynamic Call Learning for Real-Time Agent Skill Gaps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional call centers face inefficiencies due to agents lacking proficiency in specific topics, leading to prolonged calls and customer dissatisfaction, as existing systems fail to dynamically identify and address skill gaps in real-time.
Innovation Solution
A machine learning-based system that analyzes audio data from communication sessions to identify topics and sub-topics, dynamically joins additional agents for training, and routes calls to supervisors when necessary, using intelligent routing and dynamic learning models to enhance agent proficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If agents are assigned to handle various customer issues based on conventional routing, then call center operations can be maintained, but call duration increases and customer satisfaction decreases due to agents lacking proficiency in specific topics
Solution Approach 1:
The system dynamically identifies skill gaps during active calls using real-time audio analysis and machine learning models, then interrupts calls to join additional agents with relevant expertise. This dynamic adaptation allows the call center to transition from static agent assignments to flexible, real-time skill matching, reducing call duration while maintaining operational efficiency.
Solution Approach 2:
The system introduces an intermediary intelligent routing system that analyzes call audio data, identifies skill gaps, and mediates by joining additional agents to ongoing calls. This intermediary layer bridges the gap between conventional routing and optimal skill-matched routing, enabling real-time intervention without disrupting overall call center operations.
2Adaptability or versatility
If additional agents are joined to ongoing calls for training purposes, then agent knowledge is enhanced, but call complexity and system requirements increase
Solution Approach 1:
The system enables self-service learning by automatically identifying skill gaps through audio analysis and joining appropriate training agents without manual intervention. The intelligent routing system autonomously matches training needs with available expertise, reducing the need for complex manual scheduling and coordination while enhancing agent adaptability.
Solution Approach 2:
The intelligent routing system serves multiple functions: it acts as a conventional routing system, a real-time skill gap analyzer, a dynamic agent matcher, and a training coordinator. This multi-functionality reduces overall system complexity by consolidating multiple specialized systems into a single universal platform that handles both operational routing and skill development.
3Measurement precision
If real-time audio analysis is performed on communication sessions, then skill gaps can be identified accurately, but computational resources and processing time increase
Solution Approach 1:
The system performs partial audio analysis by focusing specifically on identifying skill gaps rather than analyzing all aspects of the conversation. The machine learning models are trained to detect specific indicators of skill deficiencies, allowing accurate skill gap identification while reducing overall computational processing requirements compared to comprehensive speech analysis.
Solution Approach 2:
The system performs preliminary actions by pre-training machine learning models on historical call data to recognize patterns indicating skill gaps. This preliminary training enables the system to quickly identify skill issues during live calls without requiring intensive real-time computation, as the models have already learned to recognize relevant patterns during the offline training phase.
Data Source
AI summary
Arrangements for machine learning-based dynamic learning are provided. In some examples, audio data associated with a plurality of calls may be received and analyzed to identify a topic and sub-topic of each call and metadata of each call. Feedback data may also be received. A machine learning model may be executed by inputting, to the model, the identified topic and sub-topic and metadata of each call, and the feedback data, to output one or more topics or sub-topics of concern. A plurality of ongoing calls may be monitored to identify an ongoing call related to one of: a topic or sub-topic of concern. A plurality of agents who are not subject matter experts in the identified topic or sub-topic of concern and are available may be identified and joined, via respective computing devices, to the ongoing call in a dynamic learning session.