知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

224 records (took 0.032 seconds)

    USING A TUNABLE PRE-TRAINED DISCRIMINATOR TO TRAIN A GENERATOR AND AN UNTRAINED DISCRIMINATOR
    3.
    发明公开
    USING A TUNABLE PRE-TRAINED DISCRIMINATOR TO TRAIN A GENERATOR AND AN UNTRAINED DISCRIMINATOR 审中-公开

    公开(公告)号：US20240095497A1

    公开(公告)日：2024-03-21

    申请号：US17947778

    申请日：2022-09-19

    Applicant: Capital One Services, LLC

    Inventor： Austin Walters ,  Galen Rafferty ,  Jeremy Goodsitt ,  Anh Truong

    IPC: G06N3/04 ,  G06N3/08

    CPC classification number: G06N3/0454 ,  G06N3/08

    Abstract: Systems as described herein may implement a tunable pre-trained discriminator in a machine learning model, such as a general adversarial network. A server may generate training data using a generator of the machine learning model. The server may send the training data to a first discriminator (e.g., a pre-trained discriminator) and a second discriminator (e.g., an untrained discriminator). The server may receive a first set and a second set of labels from the first discriminator and the second discriminator, respectively. The server may select a label from either the first or the second set of labels. Accordingly, the server may provide the selected labels and the corresponding data records to further train the generator of the machine learning model.

    System to utilize user's activities pattern as additional authentication parameter
    5.
    发明授权
    System to utilize user's activities pattern as additional authentication parameter 有权

    公开(公告)号：US11893097B2

    公开(公告)日：2024-02-06

    申请号：US17870126

    申请日：2022-07-21

    Applicant: Capital One Services, LLC

    Inventor： Vincent Pham ,  Jeremy Goodsitt ,  Anh Truong ,  Austin Walters ,  Galen Rafferty ,  Reza Farivar

    IPC: G06F21/31

    CPC classification number: G06F21/316

    Abstract: Various embodiments for a system to utilize user's location pattern as an authentication parameter are disclosed. An embodiment operates by retrieving a location history of a user based on past locations of a user equipment (UE) device at various times and traffic data associated with the location history. A request to access a protected application is received and a present location of the UE device at a time associated with the request is determined. A locational pattern is generated based on both the location history of the user and the traffic data. The present location of the UE device is compared with the locational pattern, and it is determined that a level of authentication necessary to grant access to the protected application is satisfied based on both the comparing and a determination that the present location falls within the locational range generated based on the traffic data.

    Digital statement muting and obscuration
    7.
    发明授权
    Digital statement muting and obscuration 有权

    公开(公告)号：US11818103B2

    公开(公告)日：2023-11-14

    申请号：US17116968

    申请日：2020-12-09

    Applicant: Capital One Services, LLC

    Inventor： Galen Rafferty ,  Anh Truong ,  Jeremy Edward Goodsitt ,  Austin Walters ,  Vincent Pham

    IPC: H04L9/40 ,  G06Q40/02 ,  G06F3/0484

    CPC classification number: H04L63/0407 ,  G06Q40/02 ,  G06F3/0484

    Abstract: Systems and methods for selectively obscuring data in a digital statement are disclosed. The systems and methods can relate to multiple user accounts that access a shared account. The systems can include means to determine which account completed a transaction. Device location tracking and hardware characteristics of the devices can be used to determine which account completed the transaction. Information related to transactions that fall outside of expected spend categories can be selectively obscured on the digital statement of the non-transacting account. The information related to the transaction can be selectively viewable by non-transacting account.

    Systems and methods for increasing accuracy in categorizing characters in text string
    8.
    发明授权
    Systems and methods for increasing accuracy in categorizing characters in text string 有权

    公开(公告)号：US11816432B2

    公开(公告)日：2023-11-14

    申请号：US17171270

    申请日：2021-02-09

    Applicant: Capital One Services, LLC

    Inventor： Jeremy Edward Goodsitt ,  Galen Rafferty ,  Anh Truong ,  Austin Walters

    IPC: G06F40/279 ,  G06N3/08 ,  G06N3/04

    CPC classification number: G06F40/279 ,  G06N3/04 ,  G06N3/08

    Abstract: Disclosed embodiments may include a method that includes setting an influence level for each index that a neural network can accept in one sample to a same level for a neural network, receiving a training corpus including training input samples and a corresponding correct training prediction samples, generating, using the neural network, prediction samples, identifying an accuracy for each index by comparing the prediction samples with the corresponding correct training prediction samples, adjusting the influence level for each index based on the accuracy for each index, identifying one or more poorly accurate indexes for the neural network, receiving a first input sample including one or more characters, generating one or more normalized first input samples by applying one or more buffers to the one or more poorly accurate indexes, and generating, using the neural network, a categorization of each character in the one or more normalized first input samples.

    SYSTEMS AND METHODS FOR ARCHITECTURE EMBEDDINGS FOR EFFICIENT DYNAMIC SYNTHETIC DATA GENERATION
    9.
    发明公开
    SYSTEMS AND METHODS FOR ARCHITECTURE EMBEDDINGS FOR EFFICIENT DYNAMIC SYNTHETIC DATA GENERATION 审中-公开

    公开(公告)号：US20230350860A1

    公开(公告)日：2023-11-02

    申请号：US18350211

    申请日：2023-07-11

    Applicant: Capital One Services, LLC

    Inventor： Austin Walters ,  Jeremy Goodsitt ,  Anh Truong ,  Galen Rafferty ,  Grant Eden

    IPC: G06F16/21 ,  G06N5/025 ,  G06F16/2457

    CPC classification number: G06F16/21 ,  G06N5/025 ,  G06F16/24575

    Abstract: Systems and methods for architecture embeddings for efficient dynamic synthetic data generation are disclosed. The disclosed systems and methods may include a system for generating synthetic data configured to perform operations. The operations may include retrieving a set of rules associated with a first data profile and generating, by executing a hyperparameter search, a plurality of hyperparameter sets for generative adversarial networks (GANs) that satisfy the set of rules. The operations may include generating mappings between the hyperparameter sets and the first data profile and storing the mappings in a hyperparameter library. The operations may include receiving a request for synthetic data, the request indicating a second data profile and selecting, from the mappings in the hyperparameter library, a hyperparameter set mapped to the second data profile. The operations may include building a GAN using the selected hyperparameter set and generating, using the GAN, a synthetic data set.

Patent Agency Ranking