利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

16 records (took 0.021 seconds)

    REAL TIME DEVELOPMENT OF AUTO SCORING ESSAY MODELS FOR CUSTOM CREATED PROMPTS
    1.
    发明申请
    REAL TIME DEVELOPMENT OF AUTO SCORING ESSAY MODELS FOR CUSTOM CREATED PROMPTS 审中-公开

    公开(公告)号：US20200005157A1

    公开(公告)日：2020-01-02

    申请号：US16544745

    申请日：2019-08-19

    Applicant: Pearson Education, Inc.

    Inventor： Mark Rosenstein ,  Kyle Habermehl ,  Scott Hellman ,  Alok Baikadi ,  Peter Foltz ,  Lee Becker ,  Luis M. Oros ,  Jill Budden ,  Marcia Derr

    IPC: G06N5/00 ,  G06N5/02 ,  G06N20/00

    Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.

    SYSTEMS AND METHODS FOR REAL-TIME MACHINE LEARNING MODEL TRAINING
    2.
    发明申请
    SYSTEMS AND METHODS FOR REAL-TIME MACHINE LEARNING MODEL TRAINING 审中-公开

    公开(公告)号：US20170364832A1

    公开(公告)日：2017-12-21

    申请号：US15629422

    申请日：2017-06-21

    Applicant: Pearson Education, Inc.

    Inventor： Kyle Habermehl ,  Karen Lochbaum ,  Robert Sanders ,  Walter Denny Way ,  Ryan Calme

    IPC: G06N99/00

    CPC classification number: H04L51/26 ,  G06N20/00 ,  G06Q10/00 ,  G06Q10/101 ,  G06Q30/0201

    Abstract: Systems and methods for automated evaluation system routing are described herein. The system can include a memory, which can include a model database and a correlation database. The system can include a first user device and a second user device. The system can include at least one server. The at least one server can: receive a response communication from the user device; generate an initial evaluation value according to an AI model; determine a correlation between the initial evaluation value and evaluation range data; accept the initial evaluation value when the correlation exceeds a threshold value; and route the response communication to the second user device for generation of an elevated evaluation value when the correlation does not exceed the threshold value.

    SYSTEMS AND METHODS FOR AUTOMATED MACHINE LEARNING MODEL TRAINING QUALITY CONTROL
    4.
    发明申请
    SYSTEMS AND METHODS FOR AUTOMATED MACHINE LEARNING MODEL TRAINING QUALITY CONTROL 审中-公开

    公开(公告)号：US20190258900A1

    公开(公告)日：2019-08-22

    申请号：US16281014

    申请日：2019-02-20

    Applicant: Pearson Education, Inc.

    Inventor： Alok Baikadi ,  Scott Hellman ,  Jill Budden ,  Stephen Hopkins ,  Kyle Habermehl ,  Peter Foltz ,  Lee Becker ,  Mark Rosenstein

    IPC: G06K9/62 ,  G06N20/00 ,  G06F16/904

    Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.

    SYSTEM AND METHOD FOR AUTOMATED EVALUATION SYSTEM ROUTING
    5.
    发明申请
    SYSTEM AND METHOD FOR AUTOMATED EVALUATION SYSTEM ROUTING 审中-公开

    公开(公告)号：US20170366496A1

    公开(公告)日：2017-12-21

    申请号：US15629382

    申请日：2017-06-21

    Applicant: Pearson Education, Inc.

    Inventor： Kyle Habermehl ,  Karen Lochbaum ,  Robert Sanders ,  Walter Denny Way ,  Ryan Calme

    IPC: H04L12/58 ,  G06N99/00

    Abstract: Systems and methods for automated evaluation system routing are described herein. The system can include a memory, which can include a model database and a correlation database. The system can include a first user device and a second user device. The system can include at least one server. The at least one server can: receive a response communication from the user device; generate an initial evaluation value according to an AI model; determine a correlation between the initial evaluation value and evaluation range data; accept the initial evaluation value when the correlation exceeds a threshold value; and route the response communication to the second user device for generation of an elevated evaluation value when the correlation does not exceed the threshold value.

    SYSTEMS AND METHODS FOR INTERFACE-BASED AUTOMATED CUSTOM AUTHORED PROMPT EVALUATION
    7.
    发明申请
    SYSTEMS AND METHODS FOR INTERFACE-BASED AUTOMATED CUSTOM AUTHORED PROMPT EVALUATION 审中-公开

    公开(公告)号：US20190258716A1

    公开(公告)日：2019-08-22

    申请号：US16281033

    申请日：2019-02-20

    Applicant: Pearson Education, Inc.

    Inventor： Lee Becker ,  William Murray ,  Peter Foltz ,  Mark Rosenstein ,  Alok Baikadi ,  Scott Hellman ,  Kyle Habermehl ,  Jill Budden ,  Stephen Hopkins ,  Andrew Gorman

    IPC: G06F17/27 ,  G06N20/00

    Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.

    SYSTEMS AND METHODS FOR AUTOMATED MACHINE LEARNING MODEL TRAINING FOR A CUSTOM AUTHORED PROMPT
    8.
    发明申请
    SYSTEMS AND METHODS FOR AUTOMATED MACHINE LEARNING MODEL TRAINING FOR A CUSTOM AUTHORED PROMPT 审中-公开

    公开(公告)号：US20190258715A1

    公开(公告)日：2019-08-22

    申请号：US16280984

    申请日：2019-02-20

    Applicant: Pearson Education, Inc.

    Inventor： Scott Hellman ,  Lee Becker ,  Samuel Downs ,  Alok Baikadi ,  William Murray ,  Kyle Habermehl ,  Peter Foltz ,  Mark Rosenstein

    IPC: G06F17/27 ,  G06N20/00

    Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.

Patent Agency Ranking