Automated Wrap-Up Notes and Outcome Coding From Interaction Transcripts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional customer engagement center systems rely on manual generation of interaction notes and outcome codes by agents, which is time-consuming and prone to errors, limiting the utility of interaction data.
Innovation Solution
A system utilizing machine learning to predict outcome codes and contact notes by training predictive models on historical interaction data, including audio and transcript analysis, to automate the generation of wrap-up information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If agents manually generate contact notes and outcome codes, then the data can be created with human judgment and nuance, but the process is time-consuming and reduces agent productivity
Solution Approach 1:
The system performs preliminary analysis of interaction data during or immediately after the customer interaction, generating draft contact notes and outcome codes before the agent needs to finalize them. This preliminary action captures the data generation process while the interaction context is still fresh, reducing the time agents need to spend on manual documentation.
Solution Approach 2:
An automated natural language processing system acts as an intermediary between the customer interaction and the final recorded data. This intermediary analyzes the interaction transcript, identifies key information, and generates contact notes and outcome codes, freeing agents from manual data entry while maintaining data quality through automated processing.
2Reliability
If agents manually create interaction records, then human understanding and context can be applied, but errors and inconsistencies occur due to manual entry
Solution Approach 1:
The system performs self-service by automatically analyzing interaction transcripts and generating contact notes and outcome codes without requiring manual agent intervention. This self-service approach eliminates human errors in data entry while maintaining consistency through automated processing rules and machine learning models trained on historical data.
Solution Approach 2:
The system incorporates feedback mechanisms where generated contact notes and outcome codes are reviewed and refined based on agent corrections and performance metrics. This feedback loop continuously improves the accuracy and consistency of automated data generation while maintaining the benefits of automation.
3Adaptability or versatility
If manual wrap-up processes are used, then agents can apply judgment to complex interactions, but the time required to complete wrap-up reduces overall system throughput
Solution Approach 1:
The system performs preliminary analysis of complex interaction elements during the interaction itself, identifying key issues, customer sentiment, and required actions before wrap-up is needed. This preliminary processing handles the complex analysis work in advance, allowing agents to review and finalize decisions quickly rather than analyzing everything from scratch during wrap-up.
Solution Approach 2:
The patent replaces the mechanical manual process of analyzing and documenting interactions with an automated natural language processing system. This substitution handles complex pattern recognition, sentiment analysis, and information extraction automatically, maintaining the ability to handle interaction complexity while dramatically reducing the time required for wrap-up activities.
Data Source
AI summary
A system for generating wrap-up information is capable of learning how interactions are transformed into contact notes and outcome codes using natural language processing and can generate the contact notes and outcome codes for new incoming interactions by applying prediction models trained on interaction data, contact notes and outcome codes. The system for generating wrap-up information receives interaction data, including interaction audio data, interaction transcripts, associated contact notes and associated outcome codes. The interaction transcripts are generated from the previous interactions between agents and customers. The contact notes and outcome codes are generated by agents during the associated previous interactions. The system processes and uses the interaction data to train prediction models to analyze interaction audio data and interaction transcripts and predict appropriate contact notes and outcome codes for the interaction. Once trained the prediction model(s) can generate appropriate contact notes and outcome codes for new interactions.