AI Microlearning System for Agent Training Retention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Customer service agents face challenges in retaining training information due to lengthy documents, leading to increased reliance on online help and colleagues, affecting call handling time and customer experience.
Innovation Solution
An AI-based microlearning system that identifies training needs from conversational insights, uses a deep learning model to extract micro content, and provides personalized coaching moments to agents through a user interface, leveraging knowledge management databases and chatbots to offer timely training.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If agents study long training documents, then they learn new policies and procedures, but they cannot retain the information and must refer to online help frequently
Solution Approach 1:
The patent segments long training documents into short, focused microlearning modules (3-5 minutes each) that address specific topics or skills. This segmentation makes training content more manageable and memorable, reducing information loss while maintaining comprehensive coverage of policies and procedures.
Solution Approach 2:
The system provides microlearning content in advance of when agents need to apply knowledge, and also delivers just-in-time training during or between calls. This preliminary and timely delivery ensures information is fresh in agents' minds, improving retention without requiring lengthy study sessions that lead to forgetting.
2Reliability
If agents refer to online help and knowledge management frequently, then they can resolve customer issues, but call handling time increases
Solution Approach 1:
The system enables agents to self-serve through targeted microlearning modules that build knowledge and confidence, reducing dependence on external knowledge management systems and colleagues. Agents progressively develop self-sufficiency in handling customer issues without frequent reference to online help.
Solution Approach 2:
The system incorporates feedback mechanisms that track agent performance, identify knowledge gaps, and recommend personalized microlearning content. This continuous feedback loop improves agent competence over time, enabling more reliable issue resolution with reduced need for external references.
3Reliability
If agents turn to colleagues for help, then customer issues can be resolved, but overall customer experience deteriorates
Solution Approach 1:
The microlearning system empowers agents to independently acquire and apply knowledge, reducing reliance on colleagues for routine issues. This self-sufficiency enables faster, more consistent service without disrupting the agent-customer interaction flow, thereby improving customer experience.
Solution Approach 2:
By providing training content in advance and in between calls, the system ensures agents have necessary knowledge ready before customers need assistance. This preparation reduces the need for real-time consultations with colleagues, maintaining smooth customer interactions and improving overall experience.
4Loss of information
If traditional long-form training is used, then comprehensive coverage of policies is achieved, but learning retention is poor
Solution Approach 1:
The patent divides comprehensive training curricula into numerous short microlearning modules, each covering a specific topic or skill point. This segmentation maintains comprehensive coverage of all policies and procedures while presenting content in brief, memorable units that improve retention significantly compared to long continuous documents.
Data Source
AI summary
In some aspects, the techniques described herein relate to a method and a system comprising one or more processors and one or more storage devices storing instructions that when executed by one or more processors, cause the processor to receive a text of a plurality of conversations between a plurality of customers and an agent; identify a context of one conversation of the plurality of conversation from one or more conversational insights; identify an intent of the one conversation from one or more conversational insights; and identify an area for training the agent based on the intent and the context.