Call Transfer Prediction Using Dialog Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Call centers face inefficiencies due to reliance on manual operator transfers, leading to repetitive questions and increased response times, as newly employed operators often require assistance from seniors, and specific process operators are not always utilized effectively.
Innovation Solution
A system that extracts features from dialog information records to create a transfer prediction model, determining a feature vector and transfer probability value to automatically or recommend transferring calls to the most appropriate operator based on previous call data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual operator transfer is used, then operators can handle calls with human judgment, but call transfer time increases and repetitive questions occur
Solution Approach 1:
The system performs preliminary analysis of dialog information records before transfer is needed. It extracts features, determines feature vectors, and calculates transfer probability values in advance, so when transfer is required, the system can immediately identify the most appropriate operator without delay.
Solution Approach 2:
The patent introduces an automated call transfer support system as an intermediary between the operator and the call routing process. This system acts as a mediator that analyzes dialog records, determines transfer probability, and recommends optimal operators, eliminating the need for manual operator selection and reducing transfer time.
2Ease of operation
If manual operator transfer is used, then operators can assess caller needs, but repetitive questions increase and efficiency decreases
Solution Approach 1:
The system enables self-service by automatically analyzing dialog information records and generating transfer recommendations without requiring operator intervention. The system extracts features, determines feature vectors, and identifies optimal operators autonomously, freeing operators to focus on complex customer interactions while the system handles routing decisions.
Solution Approach 2:
The system implements feedback by continuously analyzing dialog information records and using the extracted features to improve transfer accuracy. The feedback loop uses historical transfer data and dialog patterns to refine feature vector determination and transfer probability calculation, progressively enhancing call center efficiency while maintaining operational flexibility.
3Productivity
If automated transfer prediction is implemented, then call routing efficiency improves, but system complexity increases
Solution Approach 1:
The patent segments the call transfer process into distinct modular components: dialog information record retrieval, feature extraction, feature vector determination, and transfer probability calculation. Each module performs a specific function independently, making the overall system more manageable and easier to implement despite the increased automation capability.
Data Source
AI summary
A computer retrieves a dialog information records of the active call of the first operator. The computer extracts features from the dialog information records. The computer determines a feature vector from the extracted features and determines a transfer probability value based on the feature vector and previous call transfers to the second operator.