Capital One Services, LLC

Other

Phoebe Atkins

Cruz Vargas

Vyjayanthi Vadrevu

Joshua S Edwards

Lin Ni Lisa Cheng

Michael Saia

Max Miracolo

Alexander Lin

Tyler Maiman

Rajko Ilincic

Brian McClanahan

Kathryn Tikoian

Deny Daniel

Lukiih Cuan

Matthew Peroni

Abdelkader M'Hamed Benkreira

Xiaoguang Zhu

Leeyat Bracha Tessler

Abhay Donthi

Mia Rodriguez

Michael Wolf

Ray Cheng

Michael Bakr Mossoba

Salik Shah

Lea Cody

Daniel John Marsch

Andrea Montealegre

Matthew Horton

Imren Johar

Negar Kalbasi

Louis Buell

William C Prior

Nagaraju Gaddigopula

In some implementations, a system may generate a first exchange profile for a first user and a second exchange profile for a second user. The first exchange profile may identify one or more characteristics of an exchange behavior of the first user based on exchange data of the first user, and the second exchange profile may identify one or more characteristics of an exchange behavior of the second user based on exchange data of the second user. The system may receive, from a first device of the first user, a request for a selection for the first user. The system may determine, based on the first exchange profile and the second exchange profile, an entity that is relevant to the first user. The system may transmit, to the first device of the first user, information indicating the selection for the first user, where the selection identifies the entity.

Peer-based selection using machine learning

Disclosed embodiments pertain to provisioning a virtual payment card for an authorized user in a browser. A primary cardholder can request the addition of an individual as an authorized user on the primary cardholder's account. Further information regarding the individual can be solicited and utilized to compute a risk score associated with adding the individual as an authorized user. Further processing of the request, including whether to terminate or continue, can be based on comparing the risk score to a predetermined threshold. If processing is continued, a virtual payment card linked to the primary cardholder account is generated. Next, the virtual card can be added as a payment method to a browser profile of the individual on a network-accessible computing resource. Subsequently, the authorized user can access the virtual card to make online shopping payments with a web browser personalized with the browser profile.

Browser provisioned virtual payment card for an authorized user

A modular transaction card assembly includes a card frame having the traditional dimensions of a credit card, and a transaction card that is smaller than a traditional card and that fits into a receptacle of the card frame. Each of the card frame and the transaction card may be capable of performing contactless data transactions individually. In some instances, the combined assembly of the card frame with the transaction card may detect a proximity of a mobile device to the assembly and generate an authentication credential that is unique to the combination of the card frame, the transaction card, and the mobile device. The authentication credential may be used to authentic the transaction card when conducting a data transaction.

Transaction card assembly

In some implementations, a server may receive, from a first user, an indication of a first set of times and receive, from the second user, an indication of a second set of times. The server may determine a first location associated with the first user and a second location associated with the second user. Accordingly, the server may identify a set of events based on the first location, the second location, the first set of times, and the second set of times. The server may further select a subset of events, from the set of events, based on first event data associated with the first user and second event data associated with the second user. Based on a selected event from the subset of events, the server may identify an API associated with the selected event and may trigger a call to the identified API.

User pairing and triggering activities using event data

Systems and methods of the present disclosure enable database search. The systems and/or methods may include receiving a search query that includes an input document having text. Word embeddings are generated within the input document, where the word embeddings include vector representations of words in the text of the input document. An average input document word embedding vector is determined for the word embeddings of the input document. A set of stored documents is accessed, where each stored document includes a stored text has a particular average stored document word embedding vector. A similarity model is used to determine a similarity metric measuring the similarity between the input document and each stored document based on the average input document word embedding vector and the particular average stored document word embedding vector of each stored document.

Systems for database searching and database schemas management and methods of use thereof

A modular transaction card assembly includes a card frame having the traditional dimensions of a credit card, and a transaction card that is smaller than a traditional card and that fits into a receptacle of the card frame. The card frame may include a window in which contact pads of the transaction card are positioned and flush with the surface of the card frame when the transaction card is secured in the receptacle. The card frame and transaction card assembled together may form a uniform assembly that appears and functions as a traditional transaction card (e.g., credit card).

Methods and systems disclosed herein describe customizing searching. Search queries may be customized according to a user's preferences. A user may emphasize or indicate that additional weight should be given to one or more terms in a search query. Terms that are weighted higher may have a larger impact on the results that are returned in response to the search query. In addition to changing the terms in a search query, a user may provide a weight for each term. Each term in a search query may be weighted to varying degrees, giving a user more control over the results that are returned. The weights may be used with machine learning techniques to generate a vector representation of a search query. The vector representation of the search query may be compared with vector representations of search objects to determine results that match the search query.

Customizing search queries for informational retrieval

A modular transaction card assembly includes a card frame having the traditional dimensions of a credit card, and a transaction card that is smaller than a traditional card and that fits into a receptacle of the card frame. Each of the card frame and the transaction card may be capable of performing contactless data transactions individually. The combined assembly of the card frame with the transaction card secured in the receptacle is also capable of performing contact data transactions. The transaction card and/or the card frame may include one or more visual or tactile regions that allow the transaction card and card frame to be distinguished from other cards and/or to be properly oriented and aligned with one another when combined to form the card assembly.

Disclosed embodiments may include a system for converting a physical meeting into a virtual meeting. The system may receive scheduling and location data associated with a first user. The system may determine whether the first user has an upcoming meeting at a physical location, and responsive to such determination, may determine a proximity of the first user to the upcoming meeting. The system may determine, by an MLM and based on the proximity, a probability that the first user will be late to the upcoming meeting. The system may determine whether the probability exceeds a predetermined threshold, and responsive to such determination, may convert the upcoming meeting to a virtual meeting by generating a virtual meeting link, and may transmit, to user device(s), a notification comprising the virtual meeting link.

Systems and methods for converting physical meetings into virtual meetings

Systems and methods for implementing an automated process for detection of a shared recurring bills and identification of a set of corresponding person-to-person transactions associated with shared portions of the recurring bill. The identification process is prediction-based and contingent upon an analysis of a user's transaction records. A key aspect of the analysis is directed towards transaction amount data (fraction test) and occurrence patterns, derived from the transaction records, in order to identify a shared bill and a set of person-to-person (P2P) transfer transactions associated therewith. Upon identification of a set of P2P transfer transactions associated with a recurrent shared bill, an automation option may be provided to the user.

Systems and methods for identification and automation of shared recurrent transactions based on transaction pattern detection

Transaction card

Disclosed embodiments relate to a smart video conference environment. A live video of a conference participant can be segmented into a foreground, including the participant, and a background that excludes the participant. The background can be replaced by a virtual background determined based on one or more factors. The factors can include context data acquired from a calendar, content based on the context data, and transaction history. Further, interaction amongst conference participants can be monitored and utilized to update the background in one instance based on topics of conversation. Interactive content presented in the virtual background permits interaction by participants with the background. Furthermore, content can also be overlaid on the participant and the background in one instance.

Smart video conference environment

Disclosed embodiments may include a system that may receive an interaction message associated with an interaction a user has with an application or website, the interaction message may include an error message or a repeated action message. The system may identify, using a first machine learning model, one or more issues associated with the interaction message, retrieve one or more troubleshooting steps mapped to the one or more issues, and generate a first message comprising the one or more troubleshooting steps and a feedback request on an effectiveness of the one or more troubleshooting steps. The system may transmit the first message to the user, receive feedback from the user in response to the feedback request, and determine whether the feedback is negative. When the feedback is negative, the system may transmit a second message to a representative requesting the representative call the user.

System and methods for identifying and troubleshooting customer issues to preempt customer calls

A processor may receive data and generate a quantified representation of the data by processing the data using at least one machine learning (ML) algorithm, the quantified representation of the data indicating a sentiment of content of the data. The processor may automatically revise the content of the communications data. The revising may include determining a reaction to the content of the communications data, generating a quantified representation of the reaction, determining a difference between the quantified representation of the reaction and the quantified representation of the communications data, identifying, based on the difference, a portion of the content having an unintended sentiment, and replacing the portion of the content with different content.

Feedback control for automated messaging adjustments

Exemplary embodiments may provide keys for unlocking access to a location, like a user room, a secure location, a door at an employee location, a trunk, a closet or other locked location or item, on a payment card. Examples of a payment card include but are not limited to a credit card, a debit card, a smart card, an employee identification card, etc. A secure token that acts as digital key may be uploaded to the payment card. The payment card may then be put in close proximity of a wireless reader at the lock. The wireless reader obtains the secure token and extracts the contents. If the contents are proper, the lock is unlocked. Otherwise, the lock remains locked.

Growing community of inventors

Rockville, VA, United States of America

Phoebe Atkins