Log data condensation for interoperability with language models
WO2025244719A1PCT designated stage Publication Date: 2025-11-27MICROSOFT TECHNOLOGY LICENSING LLC
Patent Information
- Application Number
- PCT/US2025/019273
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-05-22
- Filing Date
- 2025-03-11
- Publication Date
- 2025-11-27
AI Technical Summary
Technical Problem
Large log files generated by computing platforms incur significant processing costs and resource consumption when analyzed by transformer-based large language models, and existing methods like chunking lead to inaccurate analysis due to data loss.
Method used
A system that converts log files into directional knowledge graphs, condensing them into a format compatible with large language models, preserving relevant information and reducing processing times.
Benefits of technology
The directional knowledge graph format enables efficient analysis by large language models, reducing resource consumption and processing times while maintaining accuracy.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure US2025019273_27112025_PF_FP_ABST
Abstract
The techniques disclosed herein provide a system for condensing large log files to enable interoperability with transformer-based large language models in automated failure analysis. In various contexts such as enterprise cloud services, log files can be large oftentimes containing millions of lexical units that can incur significant processing time and resource consumption. As such, the disclosed techniques provide a system for producing a directional knowledge graph representing a condensed form of a log file for automated failure analysis. Firstly, the log file is preprocessed to filter information that is irrelevant to the failure that previously occurred. The filtered lexical units are then used to generate a directional knowledge graph comprising a plurality of vertices which correspond to individual lexical units, and which are connected by edges representing the semantic connection between the lexical units. In this way, the directional knowledge graph significantly reduces processing times and improves resource consumption.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Systems and methods for artificial intelligence-based root cause analysis of service incidents
US20220358005A1