知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

45 records (took 0.026 seconds)

    Method of controlling for undesired factors in machine learning models
    25.
    发明授权
    Method of controlling for undesired factors in machine learning models 有权

    公开(公告)号：US11501133B1

    公开(公告)日：2022-11-15

    申请号：US16893041

    申请日：2020-06-04

    Applicant: State Farm Mutual Automobile Insurance Company

    Inventor： Jeffrey S. Myers ,  Kenneth J. Sanchez ,  Michael L. Bernico

    IPC: G06N3/04 ,  G06N3/08 ,  G06Q40/08 ,  G06Q30/02

    Abstract: A method of training and using a machine learning model that controls for consideration of undesired factors which might otherwise be considered by the trained model during its subsequent analysis of new data. For example, the model may be a neural network trained on a set of training images to evaluate an insurance applicant based upon an image or audio data of the insurance applicant as part of an underwriting process to determine an appropriate life or health insurance premium. The model is trained to probabilistically correlate an aspect of the applicant's appearance with a personal and/or health-related characteristic. Any undesired factors, such as age, sex, ethnicity, and/or race, are identified for exclusion. The trained model receives the image (e.g., a “selfie”) of the insurance applicant, analyzes the image without considering the identified undesired factors, and suggests the appropriate insurance premium based only on the remaining desired factors.

    Method of controlling for undesired factors in machine learning models
    27.
    发明授权
    Method of controlling for undesired factors in machine learning models 有权

    公开(公告)号：US11348183B1

    公开(公告)日：2022-05-31

    申请号：US16893525

    申请日：2020-06-05

    Applicant: State Farm Mutual Automobile Insurance Company

    Inventor： Jeffrey S. Myers ,  Kenneth J. Sanchez ,  Michael L. Bernico

    IPC: G06K9/62 ,  G06Q40/08 ,  G06N3/08 ,  H04N7/18 ,  G06V10/44 ,  G06V10/75 ,  G06V30/194

    Abstract: A method of training and using a machine learning model that controls for consideration of undesired factors which might otherwise be considered by the trained model during its subsequent analyses of new data. For example, the model may be a neural network trained on a set of training images to evaluate an insurance applicant based upon an image or audio data of the insurance applicant as part of an underwriting process to determine an appropriate life or health insurance premium. The model is trained to probabilistically correlate an aspect of the applicant's appearance with a personal and/or health-related characteristic. Any undesired factors, such as age, sex, ethnicity, and/or race, are identified for exclusion. The trained model receives the image (e.g., a “selfie”) of the insurance applicant, analyzes the image without considering the identified undesired factors, and suggests the appropriate insurance premium based only on the remaining desired factors.

    Method of controlling for undesired factors in machine learning models
    30.
    发明授权
    Method of controlling for undesired factors in machine learning models 有权

    公开(公告)号：US10769518B1

    公开(公告)日：2020-09-08

    申请号：US15383499

    申请日：2016-12-19

    Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

    Inventor： Jeffrey S. Myers ,  Kenneth J. Sanchez ,  Michael L. Bernico

    IPC: G06N3/04 ,  G06N3/08 ,  G06Q40/08 ,  G06Q30/02

    Abstract: A method of training and using a machine learning model that controls for consideration of undesired factors which might otherwise be considered by the trained model during its subsequent analyses of new data. For example, the model may be a neural network trained on a set of training images to evaluate an insurance applicant based upon an image or audio data of the insurance applicant as part of an underwriting process to determine an appropriate life or health insurance premium. The model is trained to probabilistically correlate an aspect of the applicant's appearance with a personal and/or health-related characteristic. Any undesired factors, such as age, sex, ethnicity, and/or race, are identified for exclusion. The trained model receives the image (e.g., a “selfie”) of the insurance applicant, analyzes the image without considering the identified undesired factors, and suggests the appropriate insurance premium based only on the remaining desired factors.

Patent Agency Ranking