公开(公告)号：US20230359706A1

公开(公告)日：2023-11-09

申请号：US17737065

申请日：2022-05-05

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Xi Yang ,  Larisa Shwartz ,  Ruchi Mahindru ,  Ian Manning ,  Ruchir Puri ,  MUDHAKAR SRIVATSA

IPC: G06K9/62

CPC classification number: G06K9/6277 ,  G06K9/6223 ,  G06K9/6232

Abstract: An approach for end-to-end anomaly detection and anomalous patterns identification is disclosed. The approach leverages the use of a GMM-LASSO (a selection operator-type, Lasso-type, generalized method of moments (GMM) estimator) algorithm and proposes a feedback loop where the window (i.e., anomalous window) is detected and then it is used to detect the anomalous patterns. For example, the approach can classify one or more sequential data; generates one or more vectors based on the one or more sequential data; clusters the one or more vectors into one or more clusters; determines a membership of the one or more vectors associated with the one or more clusters; updates the one or more clusters; and optimizes the one or more clusters with respect to a predefined threshold.

公开(公告)号：US20230359542A1

公开(公告)日：2023-11-09

申请号：US17662083

申请日：2022-05-05

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Xi Yang ,  Larisa Shwartz ,  Ruchi Mahindru ,  Yu Deng ,  Ian Manning

IPC: G06F11/34 ,  G06K9/62

CPC classification number: G06F11/3447 ,  G06K9/6267 ,  G06F2201/805 ,  G06F2201/835

Abstract: A method, a computer program product, and a computer system handle a data gap in sequential data. The method includes receiving the sequential data for a period of time. The method includes selecting the data gap in the sequential data at a timestamp. The method includes determining a sliding window associated with the data gap based on the timestamp for a duration of time. The sliding window includes dependent data from which the data gap depends. The method includes, as a result of the dependent data of the sliding window including at least one window data gap, generating extracted patterns based on the dependent data to mask the at least one window data gap. The method includes determining a prediction to fill the data gap using a prediction model that takes as input modified data based on the dependent data and the extracted patterns.