公开(公告)号：US11769100B2

公开(公告)日：2023-09-26

申请号：US17329934

申请日：2021-05-25

Applicant: ADOBE INC.

Inventor： Atanu Sinha ,  Manoj Kilaru ,  Iftikhar Ahamath Burhanuddin ,  Aneesh Shetty ,  Titas Chakraborty ,  Rachit Bansal ,  Tirupati Saketh Chandra ,  Fan Du ,  Aurghya Maiti ,  Saurabh Mahapatra

IPC: G06Q10/0639 ,  G06F18/214 ,  G06F18/2321

CPC classification number: G06Q10/06393 ,  G06F18/214 ,  G06F18/2321

Abstract: Systems and methods for data analytics are described. One or more embodiments of the present disclosure receive target time series data and candidate time series data, where the candidate time series data includes data corresponding to each of a plurality of candidate metrics, train a prediction network to predict the target time series data based on the candidate time series data by setting temporal attention weights corresponding to a plurality of rolling time windows and by setting candidate attention weights corresponding to the plurality of candidate metrics, identify a leading indicator metric for the target time series data from the plurality of candidate metrics based on the temporal attention weights and the candidate attention weights, and signal the leading indicator metric for the target time series data.

公开(公告)号：US20220383224A1

公开(公告)日：2022-12-01

申请号：US17329934

申请日：2021-05-25

Applicant: ADOBE INC.

Inventor： Atanu Sinha ,  Manoj Kilaru ,  Iftikhar Ahamath Burhanuddin ,  Aneesh Shetty ,  Titas Chakraborty ,  Rachit Bansal ,  Tirupati Saketh Chandra ,  Fan Du ,  Aurghya Maiti ,  Saurabh Mahapatra

IPC: G06Q10/06 ,  G06K9/62

Abstract: Systems and methods for data analytics are described. One or more embodiments of the present disclosure receive target time series data and candidate time series data, where the candidate time series data includes data corresponding to each of a plurality of candidate metrics, train a prediction network to predict the target time series data based on the candidate time series data by setting temporal attention weights corresponding to a plurality of rolling time windows and by setting candidate attention weights corresponding to the plurality of candidate metrics, identify a leading indicator metric for the target time series data from the plurality of candidate metrics based on the temporal attention weights and the candidate attention weights, and signal the leading indicator metric for the target time series data.