Neural Network Log Parser for O-RAN Error Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In open networks like O-RAN, where devices from different manufacturers are used, log data is reported in various formats, making it difficult for network managers to analyze and identify errors across different devices, especially when access is limited due to security constraints.
Innovation Solution
A network management system that utilizes a trained neural network to parse log data from different formats into a unified model language (UML) format, allowing for the generation of UML diagrams that help determine the presence of errors in network components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If log data from different manufacturers is analyzed in various formats, then device compatibility and network diversity are improved, but analysis complexity and error identification difficulty increase
Solution Approach 1:
The patent introduces an intermediary translation layer that converts log data from various manufacturer formats into a standardized internal format. This mediator component handles the format conversion automatically, allowing the system to maintain compatibility with diverse devices while keeping the core analysis logic simple and uniform.
Solution Approach 2:
The system dynamically adjusts parsing parameters and patterns based on the detected log format type. By changing the interpretation parameters according to the specific manufacturer format, the system can efficiently process diverse log structures without increasing overall analysis complexity.
2Measurement precision
If manual analysis of log data is performed to identify errors, then analysis precision can be maintained, but time consumption and productivity decrease
Solution Approach 1:
The patent replaces manual mechanical analysis with an automated electronic processing system. The system uses structured parsing rules and pattern matching algorithms to automatically extract and analyze error information from log data, achieving both high precision and rapid processing speeds without human intervention.
Solution Approach 2:
The system performs preliminary organization and structuring of log data before detailed error analysis. By pre-processing the log data into a standardized format with extracted key fields, the system prepares the information in advance for rapid and accurate error identification, reducing the time needed for actual error detection.
3Reliability
If network managers are restricted to analyzing only their assigned devices, then security and workload distribution are improved, but error detection capability across the network decreases
Solution Approach 1:
The patent adds a new dimension of hierarchical access to error detection. While maintaining security restrictions at the device level, the system provides network-level managers with aggregated error views and cross-device pattern recognition capabilities, allowing them to detect errors across multiple devices without compromising security boundaries.
Solution Approach 2:
The system implements a universal error analysis platform that can operate at multiple levels: individual device analysis for security-compliant operations, and aggregated network-wide analysis for broader error detection. This multi-functional capability allows network managers to switch between analysis scopes based on their authorization level and specific needs.
Data Source
AI summary
A network management system includes a non-transitory computer readable medium configured to store instructions thereon. The network management system further includes a processor connected to the non-transitory computer readable medium. The processor is configured to execute the instructions for receiving first log data from a first component in a network, wherein the first log data includes first log information; and parsing the first log data using a trained neural network to define parsed log data, wherein parsing the first log data includes organizing the first log information into a predefined sequence of information, and the parsed log data includes at least a signal source and a signal message. The processor is configured to execute the instructions for generating a unified model language (UML) diagram based on the parsed log data; and determining whether an error is present in the first component based on the UML diagram.