中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

15 records (took 0.01 seconds)

    Predicting leading indicators of an event
    1.
    发明授权
    Predicting leading indicators of an event 有权

    公开(公告)号：US11262743B2

    公开(公告)日：2022-03-01

    申请号：US16276876

    申请日：2019-02-15

    Applicant: SAP SE

    Inventor： Rashmi Shetty B ,  Leonard Brzezinski ,  Lauren McMullen ,  Harpreet Singh ,  Karthik Mohan Mokashi ,  Simon Lee ,  Lukas Carullo ,  Martin Weiss ,  Patrick Brose ,  Anubhav Bhatia

    IPC: G05B23/02

    Abstract: Provided is a system and method for predicting leading indicators for predicting occurrence of an event at a target asset. Rather than rely on traditional manufacturer-defined leading indicators for an asset, the examples herein predict leading indicators for a target asset based on actual operating conditions at the target asset. Accordingly, unanticipated operating conditions can be considered. In one example, the method may include receiving operating data of a target resource, the operating data being associated with previous occurrences of an event at the target resource, predicting one or more leading indicators of the event at the target resource based on the received operating data, each leading indicator comprising a variable and a threshold value for the variable, and outputting information about the one or more predicted leading indicators of the target resource for display via a user interface.

    Orchestrator for machine learning pipeline
    3.
    发明授权
    Orchestrator for machine learning pipeline 有权

    公开(公告)号：US11586986B2

    公开(公告)日：2023-02-21

    申请号：US16284291

    申请日：2019-02-25

    Applicant: SAP SE

    Inventor： Lukas Carullo ,  Patrick Brose ,  Kun Bao ,  Anubhav Bhatia ,  Leonard Brzezinski ,  Lauren McMullen ,  Simon Lee

    IPC: G06F15/173 ,  G06N20/20 ,  G06F16/35

    Abstract: Provided is a system and method for training and validating models in a machine learning pipeline for failure mode analytics. The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase. In one example, the method may include receiving an identification of a machine learning model, executing a machine learning pipeline comprising a plurality of services which train the machine learning model via at least one of an unsupervised learning process and a supervised learning process, the machine learning pipeline being controlled by an orchestration module that triggers ordered execution of the services, and storing the trained machine learning model output from the machine learning pipeline in a database associated with the machine learning pipeline.

    PREDICTING LEADING INDICATORS OF AN EVENT
    4.
    发明申请
    PREDICTING LEADING INDICATORS OF AN EVENT 审中-公开

    公开(公告)号：US20200159203A1

    公开(公告)日：2020-05-21

    申请号：US16276876

    申请日：2019-02-15

    Applicant: SAP SE

    Inventor： Rashmi Shetty B ,  Leonard Brzezinski ,  Lauren McMullen ,  Harpreet Singh ,  Karthik Mohan Mokashi ,  Simon Lee ,  Lukas Carullo ,  Martin Weiss ,  Patrick Brose ,  Anubhav Bhatia

    IPC: G05B23/02

    Abstract: Provided is a system and method for predicting leading indicators for predicting occurrence of an event at a target asset. Rather than rely on traditional manufacturer-defined leading indicators for an asset, the examples herein predict leading indicators for a target asset based on actual operating conditions at the target asset. Accordingly, unanticipated operating conditions can be considered. In one example, the method may include receiving operating data of a target resource, the operating data being associated with previous occurrences of an event at the target resource, predicting one or more leading indicators of the event at the target resource based on the received operating data, each leading indicator comprising a variable and a threshold value for the variable, and outputting information about the one or more predicted leading indicators of the target resource for display via a user interface.

    ORCHESTRATOR FOR MACHINE LEARNING PIPELINE
    5.
    发明公开
    ORCHESTRATOR FOR MACHINE LEARNING PIPELINE 审中-公开

    公开(公告)号：US20230206137A1

    公开(公告)日：2023-06-29

    申请号：US18111839

    申请日：2023-02-20

    Applicant: SAP SE

    Inventor： Lukas Carullo ,  Patrick Brose ,  Kun Bao ,  Anubhav Bhatia ,  Leonard Brzezinski ,  Lauren McMullen ,  Simon Lee

    IPC: G06N20/20 ,  G06F16/35

    CPC classification number: G06N20/20 ,  G06F16/355

    Abstract: Provided is a system and method for training and validating models in a machine learning pipeline for failure mode analytics. The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase. In one example, the method may include receiving an identification of a machine learning model, executing a machine learning pipeline comprising a plurality of services which train the machine learning model via at least one of an unsupervised learning process and a supervised learning process, the machine learning pipeline being controlled by an orchestration module that triggers ordered execution of the services, and storing the trained machine learning model output from the machine learning pipeline in a database associated with the machine learning pipeline.

    ORCHESTRATOR FOR MACHINE LEARNING PIPELINE
    6.
    发明申请
    ORCHESTRATOR FOR MACHINE LEARNING PIPELINE 审中-公开

    公开(公告)号：US20200272947A1

    公开(公告)日：2020-08-27

    申请号：US16284291

    申请日：2019-02-25

    Applicant: SAP SE

    Inventor： Lukas Carullo ,  Patrick Brose ,  Kun Bao ,  Anubhav Bhatia ,  Leonard Brzezinski ,  Lauren McMullen ,  Simon Lee

    IPC: G06N20/20 ,  G06F16/35

    Abstract: Provided is a system and method for training and validating models in a machine learning pipeline for failure mode analytics. The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase. In one example, the method may include receiving an identification of a machine learning model, executing a machine learning pipeline comprising a plurality of services which train the machine learning model via at least one of an unsupervised learning process and a supervised learning process, the machine learning pipeline being controlled by an orchestration module that triggers ordered execution of the services, and storing the trained machine learning model output from the machine learning pipeline in a database associated with the machine learning pipeline.

    FAILURE MODE ANALYTICS
    7.
    发明申请
    FAILURE MODE ANALYTICS 审中-公开

    公开(公告)号：US20200272112A1

    公开(公告)日：2020-08-27

    申请号：US16284369

    申请日：2019-02-25

    Applicant: SAP SE

    Inventor： Lukas Carullo ,  Patrick Brose ,  Kun Bao ,  Anubhav Bhatia ,  Rashmi Shetty B ,  Leonard Brzezinski ,  Lauren McMullen ,  Harpreet Singh ,  Karthik Mohan Mokashi ,  Simon Lee

    IPC: G05B13/02 ,  G06N7/00 ,  G06N20/20 ,  G06F9/54

    Abstract: Provided is a system and method for training and validating models in a machine learning pipeline for failure mode analytics. The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase. In one example, the method may include receiving a request to create a machine learning model for failure mode detection associated with an asset, retrieving historical notification data of the asset, generating an unsupervised machine learning model via unsupervised learning on the historical notification data, wherein the unsupervised learning comprises identifying failure topics from text included in the historical notification data and mapping the identified failure topics to a plurality of predefined failure modes for the asset, and storing the generated unsupervised machine learning model via a storage device.

    Failure mode analytics
    9.
    发明授权
    Failure mode analytics 有权

    公开(公告)号：US11567460B2

    公开(公告)日：2023-01-31

    申请号：US16284369

    申请日：2019-02-25

    Applicant: SAP SE

    Inventor： Lukas Carullo ,  Patrick Brose ,  Kun Bao ,  Anubhav Bhatia ,  Rashmi Shetty B ,  Leonard Brzezinski ,  Lauren McMullen ,  Harpreet Singh ,  Karthik Mohan Mokashi ,  Simon Lee

    IPC: G05B13/02 ,  G06F9/54 ,  G06N20/20 ,  G06N7/00

    Abstract: Provided is a system and method for training and validating models in a machine learning pipeline for failure mode analytics. The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase. In one example, the method may include receiving a request to create a machine learning model for failure mode detection associated with an asset, retrieving historical notification data of the asset, generating an unsupervised machine learning model via unsupervised learning on the historical notification data, wherein the unsupervised learning comprises identifying failure topics from text included in the historical notification data and mapping the identified failure topics to a plurality of predefined failure modes for the asset, and storing the generated unsupervised machine learning model via a storage device.

    INGESTION OF MASTER DATA FROM MULTIPLE APPLICATIONS
    10.
    发明申请
    INGESTION OF MASTER DATA FROM MULTIPLE APPLICATIONS 有权

    公开(公告)号：US20220058166A1

    公开(公告)日：2022-02-24

    申请号：US17000057

    申请日：2020-08-21

    Applicant: SAP SE

    Inventor： Anubhav Bhatia ,  Patrick Brose ,  Lukas Carullo ,  Martin Weiss ,  Leonard Brzezinski

    IPC: G06F16/21 ,  G06F16/25 ,  G06F16/2455 ,  G06F16/22

    Abstract: Techniques and solutions are provided for integrating master data from multiple applications. Master data from multiple applications can be integrated for use in processing data associated with internet of things (IOT) devices, such as by joining master data with timeseries data (including aggregated values). Integrating master data from multiple applications can include converting master data from a schema used by an application into an analytics schema. New or updated master data can be indicated in a message sent by an application. In processing the message, additional master data, or data used to determine how master data should be processed, can be retrieved.

Patent Agency Ranking