Network Data Transformation for Machine Learning Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Network service providers face challenges in improving network infrastructure and managing traffic flow due to increasing demand, leading to potential decreases in service quality, latency, and packet loss, as existing machine learning models struggle with processing diverse data types and formats, and generating predictions for streaming data.
Innovation Solution
A network management platform that transforms performance statistics and ticket information into standardized values using natural language processing, trains machine learning models, and generates recommendations for resource allocation and traffic routing to enhance network performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If machine learning models are used to process network data, then predictions and classifications can be made, but the models struggle with processing diverse data types and formats
Solution Approach 1:
The patent introduces an intermediary data transformation layer that converts diverse network data (performance statistics, ticket information, logs) into a standardized format suitable for machine learning models. This intermediary processing step mediates between the heterogeneous data sources and the ML models, enabling them to handle diverse data types without requiring complex model architectures.
Solution Approach 2:
The system transforms raw network data parameters into standardized numerical representations that machine learning models can process. Performance statistics, ticket information, and other network data are converted into consistent parameter formats, allowing the models to effectively process diverse data types through parameter standardization rather than through complex adaptive mechanisms.
2Reliability
If network infrastructure is expanded to meet increasing demand, then service quality can be maintained, but resources are consumed
Solution Approach 1:
The system performs preliminary analysis of network data using machine learning models to predict potential performance issues, faults, and optimization opportunities before they manifest as actual problems. By taking preliminary actions based on predictions (such as proactive resource allocation or preventive maintenance), the system maintains service quality without requiring continuous expansion of network infrastructure.
Solution Approach 2:
The patent implements a feedback loop where machine learning models continuously analyze network performance data, generate predictions and recommendations, and these recommendations are applied to optimize resource allocation. This closed-loop feedback system enables dynamic resource management that maintains service quality while minimizing resource consumption by allocating resources only where and when needed.
Data Source
AI summary
A device may receive one or more data models that have been trained using a first set of values that are in a format capable of being processed by the one or more data models. The first set of values may be associated with a set of historical network performance indicators relating to a set of network devices. The device may receive network data that includes network ticket information and performance statistics for the one or more network devices. The device may determine a set of network performance indicators relating to the one or more network devices. The device may convert the set of network performance indicators into a second set of values that are in the format capable of being processed by the one or more data models. The device may use the second set of values to generate one or more recommendations associated with improving network performance.