基于检索增强的日志问答系统OA

[Objective]In the field of AI for IT Operations(AIOps),log question answering is a critical task that helps support teams and system administrators efficiently locate and resolve system is-sues.However,the application of large language models to log question answering faces chal-lenges such as discrepancies between training corpora and log content,as well as insufficient accuracy in retrieving the contextual information required for answering questions.This study aims to propose a novel approach to improve the performance and generalization capability of log question answering systems.[Coverage]This article focuses on reviewing the current state of research on log question answering tasks in the AIOps domain,with an emphasis on analyzing the limitations of existing large language models in processing system logs.[Methods]This paper introduces a retrieval-enhanced log question answering system named LogMind.The system employs an iterative feedback mechanism to jointly train the re-trieval model and the large language model,while also incorporating a robust training strategy.[Results]Experi-ments conducted on 16 system log datasets across 6 domains demonstrate that the LogMind framework signifi-cantly improves the accuracy of both the retrieval model and the large language model.Additionally,the frame-work exhibits strong cross-model generalization capabilities.[Limitations]This study primarily evaluates the proposed method in offline scenarios.Further exploration is needed to address real-time performance and scalabil-ity in production environments.[Conclusions]The LogMind framework provides a reliable and intelligent solu-tion for log question answering in the AIOps domain,offering critical support for advanced system management.It also presents new perspectives for the research and application of log question answering tasks.