Capital One Services, LLC

Brian Lee

Eric Loucks

George Bergeron

Joshua S Edwards

Kevin Grant Osborn

Kyle Rankin Johnson

Austen Novis

Gaurang J Bhatt

Angelina Wu

Kyle Johnson

Systems, methods, and apparatuses are described herein for performing sentiment analysis on electronic communications relating to one or more image-based communications methods, such as emoji. Message data may be received. The message data may correspond to a message that is intended to be sent but has not yet been sent to an application. Using a first machine learning model, one or more subsets of the plurality of emoji may be determined. The one or more subsets of the plurality of emoji may comprise one or more different types and quantities of emoji, and may each correspond to the same or a different sentiment. Using a second machine learning model, one or more emojis may be selected from the one or more subsets. The one or more emojis selected may correspond to responses to the message.

Response prediction for electronic communications

Disclosed herein are system, method, and computer program product embodiments for providing an untrained machine learning model with a combined message and an appropriate emoji reaction icon. An embodiment operates by receiving a first and second user message. The first and second user comprises a first and second user text or a first and second user-inserted emoji reaction icon, respectively. The first or second user text is associated with a first or second system-specified emoji reaction icon, respectively. Thereafter, the first user message is determined to be associated with the second user message, the combined message is created based on the first and second messages, and the appropriate emoji reaction is identified as associated with the combined message. The combined message and associated appropriate emoji reaction icon are then sent to an untrained machine learning model configured to for training.

Combining multiple messages from a message queue in order to process for emoji responses

Systems and methods provided herein may include a card replacement system. The system may include an automated teller machine in data communication with a server. The automated teller machine may include an input device; a processor; a replacement card storage containing at least one replacement card, wherein the at least one replacement cards may include a magnetic stripe and a chip; a magnetic stripe writer; a chip writer; and an embossing device. The processor may be configured to: receive a replacement card request via the input device; request replacement card information from the server; encode replacement card information onto the replacement card using the magnetic stripe writer and the chip writer; and emboss user information onto the replacement card using the embossing device.

Systems and methods for ATM integrated card fabricator

Example embodiments of messaging systems and methods are provided. An example system includes a database containing a plurality of messages, a plurality of emoji responses, and a plurality of text reactions. The system further includes a predictive model trained using the plurality of messages and the plurality of emoji responses as inputs and the plurality of text reactions as outputs to determine a mapping relationship between the inputs and the outputs. The predictive model receives a message and one or more emoji responses to the message, combines and summarizes the one or more emoji responses to a text reaction to the message based on the mapping relationship, and transmits the text reaction to a user who initiates the message.

Systems and methods for combining and summarizing emoji responses to generate a text reaction from the emoji responses

A device may comprise a memory and a processor coupled to the memory. The processor may receive transaction information and entity information for a plurality of entities and may generate a first model based on the transaction information, the entity information, and information identifying an event, a theme, or a transaction parameter. The processor may process, using the first model, the transaction information and the entity information to identify a set of related entities and a type of relationship associated with the set of related entities. The processor may determine, using a second model, one or more modifications to a first set of accounts and a second set of accounts associated with the first and second entities based on the type of relationship and may perform one or more actions based on the one or more modifications.

Growing community of inventors

South Riding, VA, United States of America

Brian Lee