ML Survey Generation for Technician Technique Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current survey methods used by companies to assess user satisfaction after interactions with support technicians are often generic and fail to capture the specific techniques used by faster-resolving technicians, leading to these techniques not being shared with others, and may not address actual pain points in the support process.
Innovation Solution
A server uses machine learning to analyze the steps taken by support technicians to resolve issues, identifying faster techniques and creating customized surveys to incentivize technicians to share their methods, while also identifying and addressing actual pain points in the support process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If generic predetermined survey questions are used, then survey implementation is simple and quick, but the questions fail to capture specific techniques used by faster-resolving technicians and do not address actual pain points
Solution Approach 1:
The system performs preliminary analysis of support cases and technician performance data before creating survey questions. By pre-processing case data, identifying pain points, and analyzing resolution patterns in advance, the system generates customized survey questions that are highly relevant to specific techniques and pain points, resolving the contradiction between question relevance and creation complexity
Solution Approach 2:
The system creates customized survey questions by copying and adapting templates based on analyzed case patterns. Instead of creating entirely new questions from scratch, the system replicates and modifies proven question structures to match specific case characteristics, reducing creation complexity while maintaining high relevance to actual techniques and pain points
2Loss of information
If customized surveys analyzing specific techniques are created, then specific techniques and pain points can be identified, but the survey creation and processing becomes more complex
Solution Approach 1:
The system replaces manual survey creation and analysis processes with automated machine learning algorithms. The ML models automatically analyze case data, identify techniques, generate customized questions, and process responses without manual intervention, capturing detailed technique information while reducing processing complexity through automation
Solution Approach 2:
The survey system serves itself by automatically generating questions, selecting appropriate templates, and analyzing responses based on embedded case data. The system autonomously adapts to different case types and techniques without requiring external configuration or manual processing, reducing complexity while maximizing information capture
3Measurement precision
If manual analysis of support cases is performed to identify techniques, then detailed analysis can be conducted, but time and resources are consumed
Solution Approach 1:
The system replaces manual case analysis with automated machine learning algorithms that rapidly process support case data. The ML models achieve high precision in identifying techniques and pain points by analyzing patterns in case data, timestamps, and resolution information, delivering accurate results in minutes rather than hours of manual analysis
Solution Approach 2:
The system performs continuous automated analysis of support cases as they occur, rather than batch processing or manual review. The ML models continuously learn from new cases and generate survey questions in real-time, maintaining high analysis precision while minimizing time loss through uninterrupted automated processing
Data Source
AI summary
In some examples, a server may determine that a case, created to address an issue of a computing device, is closed and perform an analysis of steps in a process used to close the case. The analysis may determine a length of time of each step and determine that a time to close the case or complete a particular step was at least a predetermined amount faster than average. The server may use machine learning to create a survey question to determine a technique used to close the case or complete the particular step faster than average and to determine one or more incentives to provide a technician that closed the case. An answer from the technician to the survey question may include the technique used to close the case or complete the particular step faster than average. The technique may be shared with other technicians.