公开(公告)号：US12217178B2

公开(公告)日：2025-02-04

申请号：US18295153

申请日：2023-04-03

Applicant: Capital One Services, LLC

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

IPC: G06N3/08 ,  G06F17/18 ,  G06F40/166 ,  G06F40/284 ,  G06N20/10

Abstract: A method for training a neural network model includes generating a training dataset with a plurality of data types and word samples belonging to each data type. A plurality of character strings stored in a plurality of data fields in a first data file are received where the plurality of character strings includes at least one word belonging to at least one data type in the plurality of data types. The at least one word from each of the plurality of character strings in each of the data fields are split and matched to the at least one data type using the neural network model. An ad hoc second data file with a plurality of data vectors is constructed based on a user selection of data field labels where each data vector includes words matched to a data type with a respective data field label.

公开(公告)号：US12174871B2

公开(公告)日：2024-12-24

申请号：US18370936

申请日：2023-09-21

Applicant: CAPITAL ONE SERVICES, LLC

Inventor： Anh Truong ,  Fardin Abdi Taghi Abad ,  Austin Walters ,  Jeremy Goodsitt ,  Vincent Pham ,  Kate Key

IPC: G06F16/35 ,  G06F16/25 ,  G06F40/205 ,  G06N3/04 ,  G06N3/044 ,  G06N3/08

Abstract: The present disclosure relates to systems and methods for parsing unstructured data with neural networks. In one implementation, a system for parsing unstructured data may include at least one processor and at least one non-transitory memory storing instructions that, when executed by the at least one processor, cause the system to: receive unstructured data; apply a classifier to the unstructured data to identify a type of the unstructured data; based on the identification, select a corresponding neural network; apply the selected neural network to the unstructured data to obtain structured data; and output the structured data.

公开(公告)号：US12136122B2

公开(公告)日：2024-11-05

申请号：US17947216

申请日：2022-09-19

Applicant: Capital One Services, LLC

Inventor： Christopher Wallace ,  Grant Eden ,  Brian Barr ,  Samuel Sharpe ,  Anh Truong ,  Austin Walters

IPC: G06Q40/02 ,  G06F9/451 ,  G06F16/21 ,  G06F16/22 ,  G06F16/2453 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08

Abstract: Disclosed embodiments may include a method and system for automated incremental payments. The system may identify recurring charges from historical account data. Based on the recurring charges and an incremental period, the system may calculate an incremental amount and expected amount. At each iteration of the incremental period, the incremental amount may be assigned to a savings bucket. The value of the savings bucket may be subtracted from an actual account balance to calculate a reduced account balance. The system may generate and transmit a graphical user interface to a user device showing the reduced account balance. The system may receive current data containing a charge that corresponds to the recurring charges. The system may reduce the value of the savings bucket by the amount of the current data charge. If the current data charge is different from the expected amount, the system may adjust the incremental amount accordingly.

公开(公告)号：US12112268B2

公开(公告)日：2024-10-08

申请号：US18136830

申请日：2023-04-19

Applicant: Capital One Services, LLC

Inventor： Fardin Abdi Taghi Abad ,  Reza Farivar ,  Vincent Pham ,  Kenneth Taylor ,  Mark Watson ,  Jeremy Goodsitt ,  Austin Walters ,  Anh Truong

IPC: G06F40/10 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06N3/08 ,  G06F40/10 ,  G06N3/045

Abstract: A method for generating a dual-class dataset is disclosed. A single-class dataset and a context dataset are obtained. The context dataset can be labeled. A model can be trained using the combination of the single-class dataset and the labeled context dataset. The model can be run on the context dataset. The data points that are classified the same as the data points included in the single-class dataset, can be removed from the labeled context dataset and added to the single-class dataset. These steps can be repeated until no data points are classified by the model.

公开(公告)号：US20240256955A1

公开(公告)日：2024-08-01

申请号：US18163162

申请日：2023-02-01

Applicant: Capital One Services, LLC

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

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Systems, methods, and apparatuses for automatically generating reduced training datasets are described. A training dataset may be inputted into a machine learning model to train the machine learning model to output a label. The machine learning model may comprise nodes, and each of the nodes may be associated with a weight. Based on datapoints, changes to the weight associated with each node of the plurality of nodes may be determined. Using model explainability techniques and based on the changes to the weight associated with each node of the plurality of nodes, pathways that decrease an accuracy of the machine learning model are identified. A first set of the datapoints that correlate with pathways that decrease the accuracy of the machine learning model outputting the label may be determined. Furthermore, the first set of the datapoints may be removed from the training dataset to generate a reduced training dataset.

公开(公告)号：US12052391B2

公开(公告)日：2024-07-30

申请号：US17083241

申请日：2020-10-28

Applicant: Capital One Services, LLC

Inventor： Vincent Pham ,  Jeremy Goodsitt ,  Kate Key ,  Anh Truong ,  Austin Walters

IPC: H04M3/56 ,  G06F3/16 ,  G10L17/02 ,  G10L17/18 ,  G10L17/22

CPC classification number: H04M3/566 ,  G06F3/165 ,  G06F3/167 ,  G10L17/02 ,  G10L17/18 ,  G10L17/22

Abstract: Disclosed are methods, systems, and non-transitory computer-readable medium for automatically queuing participants during a conference call. For instance, the method may include receiving call data associated with a conference call; analyzing the call data to identify the participants on the conference call; and determining whether two or more participants of the plurality of participants are speaking at a same time. The method can also include tracking a first participant that continues speaking and a second participant that stops speaking; and displaying a queuing element on a graphical user interface (GUI) to indicate that the second participant is in a queue to speak once the first participant has finished speaking.

公开(公告)号：US12026459B2

公开(公告)日：2024-07-02

申请号：US18189818

申请日：2023-03-24

Applicant: Capital One Services, LLC

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

IPC: G06F16/34 ,  G06F40/117 ,  G06F40/169 ,  G06F40/197 ,  G06F40/30 ,  G06F40/40 ,  G06N3/00 ,  G06N20/00 ,  H04L67/02

CPC classification number: G06F40/197 ,  G06F16/345 ,  G06F40/117 ,  G06F40/169 ,  G06F40/30 ,  G06F40/40 ,  G06N3/00 ,  G06N20/00 ,  H04L67/02

Abstract: A method may include obtaining a document and using a first prediction model to generate text block scores for text blocks in the document, where a first text block of the text blocks is associated with a first text block score of the plurality of text block scores. The method also includes updating, in response to the first text block score for the first text block failing to satisfy a criterion, a modified version of the document with an indicator to set the first text block as a hidden text block in a presentation of the modified version. The method also includes generating a summarization of the first text block based on the words in the first text block and updating the modified version of the document to include the summarization. The method also includes providing the modified version of the document to a user device.

公开(公告)号：US11995098B2

公开(公告)日：2024-05-28

申请号：US18155551

申请日：2023-01-17

Applicant: Capital One Services, LLC

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

IPC: G06F16/00 ,  G06F16/22 ,  G06F16/25 ,  G06F40/18

CPC classification number: G06F16/258 ,  G06F16/2282 ,  G06F16/252 ,  G06F40/18

Abstract: Systems and methods for automatically profiling data a user selects to transfer to a paste area are described. Data may be automatically profiled the at the user selected target paste area to determine if sets of data are of the same data type. There may be a clarification for a target paste area or for identifying the data type. Additionally, there may be reformatting the selected data set to match the target data's format. Machine learning may trigger formatting or prompting actions according to one or more predetermined thresholds.

公开(公告)号：US20240169048A1

公开(公告)日：2024-05-23

申请号：US18536364

申请日：2023-12-12

Applicant: Capital One Services, LLC

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

IPC: G06F21/40 ,  G06F21/31 ,  G06F21/32 ,  G06F21/36 ,  G06F21/60 ,  G06N5/04 ,  G06N20/00

CPC classification number: G06F21/40 ,  G06F21/316 ,  G06F21/32 ,  G06F21/36 ,  G06F21/602 ,  G06N5/04 ,  G06N20/00 ,  G06F2221/2111 ,  G06F2221/2137

Abstract: Methods and systems disclosed herein describe using machine learning to lock and unlock a device. Machine learning may be trained to recognize one or more features. Once the device has been trained to recognize one or more features, a user may define an unlock condition for the device using the one or more trained features. After defining the unlock condition, the device may be locked by verifying the one or more features that the user defined as the unlock condition using machine learning. When verification is successful, the device may be unlocked and the user allowed to access the device.

公开(公告)号：US11929994B2

公开(公告)日：2024-03-12

申请号：US17851136

申请日：2022-06-28

Applicant: Capital One Services, LLC

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

IPC: H04L9/40 ,  G06F40/143 ,  G06F40/154 ,  H04L67/02 ,  H04L67/568

CPC classification number: H04L63/0428 ,  G06F40/143 ,  G06F40/154 ,  H04L67/02 ,  H04L67/568

Abstract: Randomizations of a web page may be generated in advance and provided to a client. The client may store the randomizations in its cache. Multiple randomizations for the same web page may be provided to the client and stored in the client's cache. When a request for a web page is made, it is determined if the client has any cached randomizations. Randomizations for the probable next web page to be requested by the client may be provided to the client for storage in the cache. For example, the probability that a link will be clicked or a website visited may be determined. Those web pages and websites with higher probabilities may be determined. Randomizations for those web pages are then provided to the client for use.