Support Case Prediction Model Using Telemetry Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computing devices experience failures due to limitations in hardware and software components, leading to inefficient resolution of support cases.
Innovation Solution
A method and system for managing support cases by obtaining contextual information and client telemetry data, selecting relevant training data, generating a prediction model using a classification algorithm, and generating predictions to resolve support cases efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional support case resolution methods are used, then manual analysis and resolution processes are simple to implement, but the resolution efficiency is low and time-consuming
Solution Approach 1:
The system performs preliminary actions by collecting and storing training data from historical support cases, contextual information, and client telemetry data before actual support cases occur. This pre-processing enables the machine learning model to make rapid predictions when support cases arise, resolving the contradiction between quick resolution and complex analysis by doing the heavy lifting in advance
Solution Approach 2:
The patent introduces a machine learning prediction model as an intermediary between the raw support case data and the resolution process. This intermediary automatically analyzes telemetry data, contextual information, and support case details to generate predictions, replacing manual analysis and enabling efficient resolution without requiring direct human intervention in the analysis phase
2Measurement precision
If comprehensive data analysis is performed for each support case, then prediction accuracy improves, but processing time increases
Solution Approach 1:
The system performs preliminary data collection and model training before actual predictions are needed. Historical training data, contextual information templates, and telemetry data structures are all prepared in advance, allowing the model to make accurate predictions quickly when support cases occur without performing comprehensive analysis from scratch each time
Solution Approach 2:
The patent applies local quality by selecting and weighting different data sources based on their relevance to specific support case types. The system doesn't treat all data equally but rather focuses analysis on the most relevant contextual information and telemetry metrics for each particular case, improving accuracy while reducing unnecessary processing
Data Source
AI summary
Techniques described herein relate to a method for managing support cases of clients. The method may include obtaining a support case associated with a client of the clients; in response to obtaining the support case, obtaining contextual information associated with the support case; obtaining client telemetry data associated with the support case; selecting a portion of training data that is similar to the support case based on the client telemetry data, the contextual information, and the support case; generating a prediction model using the portion of the training data and a classification algorithm; andgenerating predictions using the prediction model, the client telemetry data, the contextual information, and the support case.