Service Message Classification Using LLM Features and ML Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing and optimizing large volumes of dynamic data objects generated by complex application frameworks, such as Jira®, is computationally expensive and strains computing resources, making it difficult to gain real-time insights into user problems and inefficiencies.
Innovation Solution
Utilizing supervised and unsupervised machine learning models, particularly natural language processing models like BERT, to analyze service message data objects, extract features, classify service tickets, and generate dashboard visualizations for efficient resource management and insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional computing resources are used to manage and analyze large volumes of service message data objects, then data processing capacity is maintained, but computing resource usage becomes excessive and system performance degrades
Solution Approach 1:
The patent replaces traditional mechanical computing approaches with machine learning models (supervised and unsupervised NLP models like BERT) to process service message data objects. This substitution enables the system to handle large volumes of data more efficiently by leveraging pattern recognition and automated classification capabilities of ML models, thereby maintaining high productivity while reducing excessive computing resource consumption through smarter, more optimized processing algorithms.
2Loss of information
If manual analysis methods are used to gain insights into user problems, then interpretability is maintained, but time consumption and labor resources increase significantly
Solution Approach 1:
The patent implements automated machine learning models that perform analysis of service message data objects without requiring manual intervention. The supervised and unsupervised NLP models autonomously extract features, classify data objects, and generate insights about user problems and system inefficiencies. This self-service capability maintains high-quality interpretable insights while dramatically reducing the time and labor resources that would be required for manual analysis.
3Measurement precision
If complex machine learning models are applied to service message data objects, then analysis accuracy and insight quality improve, but device complexity and implementation difficulty increase
Solution Approach 1:
The patent introduces an intermediary processing layer that includes feature extraction modules and preprocessing steps between the raw service message data objects and the complex machine learning models. This intermediary layer simplifies the input data structure, extracts relevant features, and prepares data in an optimized format for the NLP models, thereby maintaining high classification accuracy while reducing the overall system complexity and making implementation more manageable.
Data Source
AI summary
Methods, apparatuses, or computer program products that process service message data objects via large language modeling and classification machine learning to provide service message classifications. In some examples, a large language model is applied to a plurality of service message data objects associated with an application framework to generate a feature set for the plurality of service message data objects, a classification machine learning model is applied to the feature set to generate a plurality of classification data objects associated with the plurality of service message data objects that classify a respective service message data object as belonging to a predefined class of a plurality of predefined classes, and a rendering of a dashboard visualization is initiated via an electronic interface based at least in part on the plurality of classification data objects.