United Services Automobile Association (usaa)

Uipco, LLC

United States Automobile (usaa)

Reynaldo Medina, Iii

Charles Lee Oakes, Iii

Bharat Prasad

Bradly Jay Billman

Minya Liang

Michael Patrick Bueche, Jr

Michael Frank Morris

Randy Ray Morlen

Gabriel Glenn Gavia

Arthur Quentin Smith

Jeffrey Neal Pollack

Frank Kyle Major

Greg Alan Harpel

Michael P Bueche, Jr

Andre Rene Buentello

Jose L Romero, Jr

Susan Elizabeth Wright

John Chandler Hopkins

Nandhini Sridaran

Christopher M Russell

Noe Alberto Martinez

Emily Kathleen Krebs

William Preston Culbertson, Ii

Cayley Danielle Collum

Mark Anthony Lopez

John C Hopkins

Teddy J Voutour

Adam Spencer Newman

Ronnie Allen Eichler

Kristopher Williams

Robert G Wood

Mario Gutierrez

William Barfield

Amy Daali

Ruthie D Lyle

Ashley Raine Philbrick

Yevgeniy Viatcheslavovich Khmelev

Nathan Lee Post

Gregory David Hansen

Stacy Callaway Huggar

Victor Kwak

Rickey Dale Burks

Carlos Jp Chavez

Brian Tougas

Christine Marie Brown

Jodi Jean Healy

Rod Gonzales

Subhalakshmi Selvam

Anto Chirayil Thomas

Robert Kenneth Dohner

Curtis Mark Bell

Nina Cooper

Benjamin Hunter Stotts

Mathew Cyriac Kottoor

Michael Patrick Bueché, Jr

Yuesheng Liu

Charlotte Thomas Creech

Keith Rodgers

Russell Colwell

Storme Shelton Briscoe

Michael Patrick Beuche, Jr

Ryan Thomas Russell

Oscar Guerra

Qunying Kou

Jon Daniel McEachron

Justin R Nash

Judy Margaret Cotter

Jon D Mceachron

Daniel Diaz

Breanna Nicole Allerkamp

Bradley J Billman

Carol Ann Walls

James Warren Middleton

David Sokolowski

Michael Martin Amati

R Bharat Nuggehalli

John James Sundberg

Matthew Wayne Prater

Aspects of the present disclosure are directed to resolving a latent status of document(s) that contain dense information using machine learning. Documents can be organized as a set of informational pages that together convey data associated with an organizational concept. Resolving a latent status from the pages of documents comprising dense information can be challenging, for example when indicator(s) of this latent status are hidden within the dense information. Implementations predict the latent status of document(s) via machine learning by performing a feature extraction processing pipeline. For example, a feature extraction processing pipeline can reduce the dimensionality of the document data, thus providing the machine learning model(s) a simplified problem. The machine learning model(s) can process the extracted data and, given the simplified problem, accurately predict the latent status of the document(s). In some implementations, the machine learning model(s) are trained using real-world training instances and synthetic training instances.

Resolving latent status from dense information using machine learning

A system and method for performing a transaction and managing transaction data. The system and method operate by scanning an item for purchase with a point of sale system and obtaining image data of the item with an image capture device of the point of sale system during the scanning. The system and method operate by proceeding to store the image data in a memory of the point of sale system and generating, with a processor of the point of sale system, an association of the image data with purchase data acquired at the point of sale during the purchase. Further, the system and method operate by providing the association, the image data, and the purchase data to a graphical user interface, which displays the image data and the purchase data such that the image data is visually linked with the purchase data based on the association.

Point of sale image capture and transactional data management system and method

A system may include one or more detectors configured to generate detector data based on signals received from one or more tags integrated in or disposed on one or more items. The system may include a processor configured to: receive the detector data; determine a first set of identification information corresponding to a first item of the one or more items based on the detector data; receive a list of tagged items for a first location, and the list of tagged items comprises a second set of identification information corresponding to the one or more items; identify a theft incident for the first item based on a comparison of the first and second sets of identification information; automatically send a notification relating to the theft incident to one or more devices; and determine one or more insurance policy decisions for the first item based on the theft incident.

Systems and methods for continuously monitoring items

A supply delivery system includes one or more processors and one or more memory devices storing instructions executable by the one or more processors to cause the one or more processors to instruct an aerial vehicle to travel within a geographical area, instruct an imaging device carried by the aerial vehicle to capture image data as the aerial vehicle travels through the geographical area, analyze the image data to identify an identification code on a physical target, instruct the aerial vehicle to dispense one or more items from the aerial vehicle at or near the physical target.

Systems and methods for targeted delivery of supplies during emergency events

A system comprises one or more modules to access a business rule, deconstruct the business rule into a condition and an associated action, determine a set of questions relevant to the condition, place the set of questions into a question queue, order the question queue, and present the question queue to a user. A system comprises one or more modules to determine a subject of the request received from a user, use the subject to obtain a set of relevant questions, examine each question and determine whether an answer to a current question is available in a storage area, and present the current question when the answer is not available. A system comprises one or more modules to access a decision tree, determine a current node, determine an estimated number of nodes between the current node and a leaf node, and present a representation using the estimated number of nodes.

Systems and methods for accessing a decision tree

A computing system acquires a plurality of gig-income models for a plurality of gig-workers, and each of the plurality of gig-income models includes a corresponding expected income for a respective gig-worker of the plurality of gig-workers over a period of time. The computing system identifies groups of gig-workers to join an income float pool based on the gig-income models of the gig-workers. The computing system transfers funds into or out from an account associated with a gig-worker in the income float pool in response to detecting, from one or more data sources, a difference between an actual income and an expected income of the gig-worker during an additional period of time. Thus, the gig-worker receives a relatively stable income.

Systems and methods for dynamically providing float funds for gig-economy workers

An image of a check that is in the field of view of a camera is monitored prior to the image of the check being captured. The camera is associated with a mobile device. When the image of the check in the field of view passes monitoring criteria, an image may be taken by the camera and provided from the mobile device to a financial institution. The image capture may be performed automatically as soon as the image of the check is determined to pass the monitoring criteria. The check may be deposited in a user's bank account based on the image. Any technique for sending the image to the financial institution may be used. Feedback may be provided to the user of the camera regarding the image of the check in the field of view.

System and method for mobile check deposit enabling auto-capture functionality via video frame processing

Systems and methods ingest extensive data regarding real-time transactions to determine correlation between a variety of parameters and possible fraud events. Possible fraud can be predicted, and notifications delivered to a fraud team. Correlations can be discovered using unsupervised machine learning, and particular systems and methods can utilize natural language processing to both receive and provide information concerning fraud risk and countermeasures.

Fraud detection using augmented analytics

Predictive mapping technology is used to route a telephone call from a user to a customer service representative. The disclosed technology can use any one or more of the following factors to map a telephone call from a user to a customer service representative: (1) a sentiment score based on a topic of conversation; (2) an experience score of the customer service representative with a topic of conversation; and (3) a performance score of the customer service representative in managing a topic of conversation.

Predictive mapping for routing telephone calls

Authentication techniques are described to allow a person to be authenticated to interact with an organization, where a type of authentication can be determined based on an environment in which the person is located. For example, an authentication server can collect a status information related to a safety setting of a mobile device. The safety setting can be enabled, e.g., if a person is driving a vehicle. When enabled, the safety setting can prevent the person from performing one or more operations on the mobile device. Based on the collected status information, the authentication server can request the person to provide user information via the mobile device so that the authentication server can determine whether the person is authenticated to interact with an organization.

Environment based authentication

An alignment guide may be provided in the field of view of a camera associated with a mobile device used to capture an image of a check. When the image of the check is within the alignment guide in the field of view, an image may be taken by the camera and provided from the mobile device to a financial institution. The alignment guide may be adjustable at the mobile device. The image capture may be performed automatically by the camera or the mobile device as soon as the image of the check is determined to be within the alignment guide. The check may be deposited in a user's bank account based on the image. Any technique for sending the image to the financial institution may be used.

Computer systems for updating a record to reflect data contained in image of document automatically captured on a user's remote mobile phone using a downloaded app with alignment guide

The disclosure describes a biometric authentication system that can authorize a transaction at a retail store using a person's biometric data and password. The biometric authentication system may include a point-of-sale device that can receive a biometric data (e.g., voice data, fingerprint data, or facial data) of a person that initiates a transaction. The biometric authentication system may also include one or more authentication systems that analyzes the received biometric data, and an authorization system that compares data obtained from the one or more authentication systems and the POS device to determine whether the information obtained from the person is related to that person's biometric and password information previously stored by the authorization system.

Biometric authentication system

The present application is directed to apparatuses, methods, and systems for remote deposit capture with enhanced image detection. In one form, a system includes a processor configured to extract an instrument image from an image that is associated with an account, where the instrument image is extracted by determining at least one corner of a plurality of corners of an instrument in the image, and to transmit the instrument image to a financial institution server to transfer funds between financial institution accounts.

Apparatuses, methods, and systems for remote deposit capture with enhanced image detection

Systems and methods are provided for sending and receiving encrypted submessages. A method for sending and receiving encrypted submessages includes generating a first submessage comprising a first portion of content stored onto a first computer, generating a second submessage comprising a second portion of the content, encrypting the first submessage and the second submessage, transmitting the encrypted first submessage to a second computer via a first path, transmitting the encrypted second submessage to the second computer via a second path, wherein the first submessage and the second submessage are transmitted to the second computer in a batched manner, transmitting an encryption key to the second computer, wherein the encryption key is transmitted to the second computer in real time, wherein the encryption key indicates a decrypting algorithm to decrypt the encrypted first submessage, and wherein the second computer recreates the content by decrypting the encrypted first submessage.

Systems and methods for sending and receiving encrypted submessages

Growing community of inventors

San Antonio, TX, United States of America

Reynaldo Medina, Iii