Systems and methods for efficient transfer of log data

    公开(公告)号:US11734012B2

    公开(公告)日:2023-08-22

    申请号:US17301377

    申请日:2021-03-31

    摘要: According to one general aspect, a non-transitory computer readable medium includes instructions that, when executed by at least one processor, cause a computing device to read a string of a log file for an application, where the log file comprises multiple strings of log data, compare the string to signatures stored in a memory to find a matching signature, where each of the signatures is encoded with a signature identifier (ID), determine a deviation between the string and the matching signature, encode the string with the signature identifier (ID) of the matching signature and the deviation, and transfer the string to a destination computing device using the signature identifier (ID) of the matching signature, the deviation, and a timestamp of the string.

    SYSTEMS AND METHODS FOR EFFICIENT TRANSFER OF LOG DATA

    公开(公告)号:US20220318019A1

    公开(公告)日:2022-10-06

    申请号:US17301377

    申请日:2021-03-31

    摘要: According to one general aspect, a non-transitory computer readable medium includes instructions that, when executed by at least one processor, cause a computing device to read a string of a log file for an application, where the log file comprises multiple strings of log data, compare the string to signatures stored in a memory to find a matching signature, where each of the signatures is encoded with a signature identifier (ID), determine a deviation between the string and the matching signature, encode the string with the signature identifier (ID) of the matching signature and the deviation, and transfer the string to a destination computing device using the signature identifier (ID) of the matching signature, the deviation, and a timestamp of the string.

    EFFICIENT TRAINING OF MACHINE LEARNING MODELS FOR LOG RECORD ANALYSIS

    公开(公告)号:US20240330143A1

    公开(公告)日:2024-10-03

    申请号:US18194190

    申请日:2023-03-31

    IPC分类号: G06F11/34

    CPC分类号: G06F11/3476

    摘要: A plurality of log records characterizing operations occurring within a technology landscape may be received. The plurality of log records may be clustered into at least a first cluster of log records and a second cluster of log records, using at least one similarity algorithm. A first dissimilar subset of log records within the first cluster of log records, and a second dissimilar subset of log records within the second cluster of log record may be identified, using the at least one similarity algorithm. At least one machine learning model may be trained to process new log records characterizing the operations occurring within the technology landscape, using the first dissimilar subset and the second dissimilar subset.