知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

105 records (took 0.029 seconds)

    Systems and methods to identify and profile a vehicle operator
    81.
    发明授权
    Systems and methods to identify and profile a vehicle operator 有权
    识别和描述车辆操作员的系统和方法

    公开(公告)号：US08738523B1

    公开(公告)日：2014-05-27

    申请号：US13897646

    申请日：2013-05-20

    Applicant: State Farm Mutual Automobile Insurance Company

    Inventor： Kenneth J. Sanchez ,  Aaron S. Chan ,  Matthew R. Baker ,  Matthew Zettinger ,  Brian Fields ,  John A. Nepomuceno

    IPC: G06Q40/00

    CPC classification number: G06Q40/08 ,  G06Q40/00

    Abstract: A method for assessing risk associated with a driver of a vehicle includes receiving a plurality of risk variables associated with a driver, the plurality of risk variables being gathered when the driver operates the vehicle. A driver is then identified based on the plurality of risk variables, and a risk profile is developed for the driver. The development of the risk profile involves determining the risk associated with at least some of the risk variables and generating a risk index, the risk index being a collective measure of risk associated with the driver.

    Abstract translation: 用于评估与车辆驾驶员有关的风险的方法包括接收与驾驶员相关联的多个风险变量，所述多个风险变量在驾驶员操作车辆时收集。 然后基于多个风险变量来识别驾驶员，并为驾驶员开发风险简档。 风险概况的发展涉及确定与至少一些风险变量相关联的风险并产生风险指数，风险指数是与驾驶员相关的风险的集体度量。

    Method of controlling for undesired factors in machine learning models
    82.
    发明授权
    Method of controlling for undesired factors in machine learning models 有权

    公开(公告)号：US12299748B2

    公开(公告)日：2025-05-13

    申请号：US18134373

    申请日：2023-04-13

    Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

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

    IPC: G06Q40/08 ,  G06N3/04 ,  G06N3/08 ,  G06N20/00 ,  G06V10/82 ,  G06V30/19 ,  G06V40/16 ,  H04N7/18 ,  G06Q30/0207

    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
    87.
    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
    89.
    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.

    System and method for improving the security of stored passwords for an organization
    90.
    发明授权
    System and method for improving the security of stored passwords for an organization 有权

    公开(公告)号：US11321448B1

    公开(公告)日：2022-05-03

    申请号：US15976530

    申请日：2018-05-10

    Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

    Inventor： Kenneth J. Sanchez

    IPC: G06F21/46 ,  H04L9/08 ,  G06F21/31 ,  H04L9/06

    Abstract: A computer-implemented method for authentication using a hashed fried password may include receiving a password value of a user, a salt key, a pepper key, and/or a temporary and randomly generated fry key, or otherwise modifying/appending the password with the salt key, pepper key, and/or fry key. The method may include hashing the modified password, such as performing a hash operation similar to Hash (Password, Salt Key, Pepper Key, Temporary Fry Key). The randomly generated fry key is not saved or otherwise stored, either locally or remotely. A remote server attempting to authenticate the user's password may check for each possible fry key, such as checking against a set of preapproved fry keys, that the hashed fried password may have been modified with in parallel. As a result, an online customer experience requiring a password is not impacted or impeded, while an attacker's attempts to learn the password are frustrated.

Patent Agency Ranking