Machine Learning Model for Automated Support Case Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional support center technologies are inefficient in automatically resolving support issues due to lack of automation and manual intervention, leading to increased time and cost in addressing device-related problems across various industries.
Innovation Solution
A machine learning training model is developed using auto-labelled historical support data to identify problem categories and relevant solutions, enabling automated processing and resolution of support issues by representing support cases as vectors within a virtual space and extracting feature sets for efficient matching and solution provision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual intervention is used to process support requests, then flexibility and adaptability are maintained, but time consumption and operational costs increase significantly
Solution Approach 1:
The system enables self-service through automated support agents that independently analyze support requests, retrieve historical resolutions, and provide solutions without human intervention. The machine learning model automatically processes requests by extracting features, comparing them with historical data, and generating resolutions, thereby eliminating manual processing while maintaining operational effectiveness.
Solution Approach 2:
The patent replaces manual mechanical processing with an automated machine learning system. The mechanical system of human agents reviewing and resolving support requests is substituted with an electronic system that uses machine learning models to automatically analyze requests, extract features, compare with historical data, and generate resolutions, dramatically reducing time consumption.
2Productivity
If conventional support center technology is used, then existing processes are maintained, but automation capability and efficiency are insufficient
Solution Approach 1:
The patent replaces manual mechanical processing with an automated machine learning system. The mechanical system of human agents reviewing and resolving support requests is substituted with an electronic system that uses machine learning models to automatically analyze requests, extract features, compare with historical data, and generate resolutions, dramatically reducing time consumption.
Solution Approach 2:
The system implements feedback mechanisms where the machine learning model continuously learns from new support requests and resolutions. The model is trained on historical data and updated with new information, improving its accuracy and effectiveness over time. This feedback loop enables the system to adapt and enhance its automated processing capability continuously.
3Measurement precision
If comprehensive historical support data is stored and analyzed, then solution accuracy is improved, but data processing complexity and computational resources increase
Solution Approach 1:
The system extracts only the most relevant features from comprehensive historical support data rather than processing all available information. The machine learning model identifies and extracts key features such as problem descriptions, device types, and resolution outcomes, filtering out unnecessary data. This extraction process maintains high solution matching accuracy while significantly reducing data processing complexity and computational resource requirements.
Solution Approach 2:
The patent segments the comprehensive historical data into structured components including support requests, device information, problem descriptions, and resolutions. By organizing data into discrete, manageable segments with defined schemas, the system can efficiently query and analyze specific portions of the data without processing the entire dataset, thereby reducing computational complexity while maintaining accuracy.
Data Source
AI summary
Computing technology for managing support requests are provided. The technology includes a processor executable application programming interface (API) that receives a support case indicating a problem associated with a device. The API utilizes a training model to predict a problem category for the support case. The training model predicts the problem category based on a feature extracted from information included in the support case. The training model further identifies a plurality of proximate support cases based on a distance between the support case and the proximate support cases within a virtual space assigned to the predicted problem category; determines relevance of each proximate support case to the support case; and outputs a resolution code for the support case based on the determined relevance of each proximate support case.