Digital Commons Network^™

Managed Health Care Billing, Douglas Simpkinson

Defensive Publications Series

A centralized billing system receives medical bill information associated with a patient from one or more medical service providers and/or from a mobile device associated with the patient. The centralized billing system communicates with one or more insurance systems associated with the patient to submit insurance claims and/or reconcile insurance claim resolution information provided by each respective insurance company with the medical bill information. The centralized billing system communicates with the mobile device to provide organized medical bills comprising an itemization of reconciled medical bill information for each medical bill associated with a single medical event for convenience of the …

Image Capture Via Multiple Optical Paths, Rick Bomber, Jake Stelman, Marc Thomas, Cheongyuen Tsang

Defensive Publications Series

The present disclosure describes systems and methods that can capture multiple images from multiple optical paths on a single image sensor. More particularly, the multiple optical paths can be directed to the single image sensor, and the image sensor can be partitioned into one or more separate regions to capture the multiple images. An assembly of optical path folding elements can be configured to select one or more images from the multiple optical paths, and allow the selected images to be imaged on a corresponding partitioned region of the single image sensor. The system can actuate the assembly of optical …

Inventory Location And Retrieval System, N/A

Defensive Publications Series

This disclosure describes scalable techniques to locate and retrieve inventory items or components from an inventory. Remote modules are co-located with inventory containers and deployed in a warehouse. The remote modules are constructed from low-cost, off-the-shelf equipment and communicate wirelessly with a central server. The central server publishes wirelessly a list of inventory items to remote modules. The module displays the number of items to be picked up using, e.g., color-coded and/or seven-segment LED displays. Once a worker picks up or places an item from a container, the corresponding remote module updates the count of items and returns status to …

Spherical Light Field Capture With Rotating Camera Array, Paul Debevec, Jessica Busch, Xueming Yu, Daniel Erickson

Defensive Publications Series

A light-field capture apparatus is provided that includes a camera housing having a plurality of cameras, each camera providing a different viewpoint of a scene. The apparatus may also include a drop-string mechanism coupled to a top portion of the camera housing and a rotary table pivotably coupled to a portion of the camera housing different than the top portion. The drop-string mechanism includes a string having a first end coupled to the top portion of the camera housing and a second end wound around a center column. The rotary table is rotatable around a center column to change horizontal …

A Method To Populate Search Auto-Suggests Across Platforms, Sofia Andrianakou, Yuanying Xie

Defensive Publications Series

A system and method are disclosed that populates search auto-suggests across platforms. The system stores user searches and visits to apps and websites, organizes them, and surfaces them as search auto-suggests across platforms for each individual user. When a user enters a search query on a specific search platform (mobile phone for example), the system executes the search process. The system then organizes and stores the search keywords. When the user executes the same search on another platform, the system auto-suggests relevant keywords from stored history. The system creates a cohesive experience with search functionality for the user.

Contextual Speech Recognition Using Rescore-Aware Pruning, Ian Williams, Petar Aleksic

Defensive Publications Series

A method for rescore aware pruning in speech recognition is disclosed. The method includes determining a set of possible words W_P that are reachable in a CLG state from an active hypothesis H_I. The CLG state may be mapped and dynamically assigned to CL state for determining W_P and then remapped to the CLG. Given this information, a backtrace state associated with H_i in the CLG is examined and the set of words W_R that will be rescored is determined. If W_P and W_R share an element, i.e., W_P ⋂ W …

Device For Achieving A Redundancy In, Daniel Hoppe

Defensive Publications Series

Device for achieving a redundancy in

the wheel speed sensor failure esp. For

piloted driving in traffic (fail operational)

Quick-Change Unit - Battery For Vehicle, Daniel Hoppe

Defensive Publications Series

QUICK-CHANGE UNIT - BATTERY FOR VEHICLE

WITH E-DRIVE

Steering Wheel Equipped With Large, Daniel Hoppe

Defensive Publications Series

STEERING WHEEL EQUIPPED WITH LARGE

SENSORY AREA FOR ACTIVATION OF SHORTCUTS

Steering Wheel Equipped With Large, Daniel Hoppe

Defensive Publications Series

STEERING WHEEL EQUIPPED WITH LARGE

SENSORY AREA FOR ACTIVATION OF SHORTCUTS

Fas Intelligent Electronic Exterior, Daniel Hoppe

Defensive Publications Series

FAS INTELLIGENT ELECTRONIC EXTERIOR

MIRRORS

Brake Recuperation / Increase In Braking, Daniel Hoppe

Defensive Publications Series

BRAKE RECUPERATION / INCREASE IN BRAKING

POWER DUE TO THERMAL STORAGE

Monitoring The Vitality Parameters Of A, Daniel Hoppe

Defensive Publications Series

MONITORING THE VITALITY PARAMETERS OF A

VEHICLE OCCUPANT

Individualization Of The Exit Thrives (Speed, Daniel Hoppe

Defensive Publications Series

INDIVIDUALIZATION OF THE EXIT THRIVES (SPEED

LIMITS) OF AERODYNAMIC VEHICLE ELEMENTS BY

THE CUSTOMER

Variable Footrest / Leg Pad For Automated, Daniel Hoppe

Defensive Publications Series

VARIABLE FOOTREST / LEG PAD FOR AUTOMATED

DRIVING LEVEL 3

Disk Wiper As A Status Indicator For, Daniel Hoppe

Defensive Publications Series

DISK WIPER AS A STATUS INDICATOR FOR

CHARGING CONDITION OR TANK CONTENT

Dashboard With Child Seat Reception, Daniel Hoppe

Defensive Publications Series

DASHBOARD WITH CHILD SEAT RECEPTION

Sil Test Environment For Autosar, Daniel Hoppe

Defensive Publications Series

SIL TEST ENVIRONMENT FOR AUTOSAR

SOFTWARE COMPONENTS BASED ON A C-PARSER

Mapping Walkable Spaces Using Activity Recognition, N/A

Defensive Publications Series

The present disclosure describes systems and methods that use activity recognition detection (e.g., step detection) and machine-learned course prediction models to generate user path approximations from sensor data obtained by a user computing device, which is particularly beneficial when GPS devices are unavailable. User paths generated from a plurality of different mobile computing devices can be utilized collectively to build maps of walkable spaces. Keywords associated with the present disclosure include: mapping; locations; walkable spaces; machine learning; model; training; GPS; sensors; activity recognition; sensor fusion; crowdsourcing; collaborative learning; user path; path generation; course prediction.

Incremental Sharing Using Machine Learning, Victor Cărbune, Sandro Feuz, Daniel Keysers, Thomas Deselaers

Defensive Publications Series

Generally, the present disclosure is directed to incrementally sharing resources, e.g., documents, media, etc., using machine-learned models. In particular, in some implementations, when the user provides permission to access user data, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to suggest files on a device or in the cloud that a user can share based on documents or other media that the user has already shown intent to share.

Machine learning is used to determine resources, e.g., documents, media, links, etc., that have features with correlation with the resource the …

Automatic Management Of Multiple Contexts, Jt Dimartile Iii, Benny Schlesinger

Defensive Publications Series

Users interacting with computing devices often multi-task across and navigate between multiple contexts. Users often report distraction and fatigue due to such switching of contexts. For example, it is hard for users to remember an earlier context and resume work at a later time. It has been argued that a user is better off focusing on one context at a time to improve productivity. However, current computers are blind to the different contexts for a user. Applications and programs relating to several current contexts are displayed without taking into account potential for distractions.

Techniques of this disclosure enable automatic grouping …

Selective Notifications Based On Message Priority Determination, Annika Matta, Hannah Keiler, Carmen Klett-Wilkinson, Jacob Bank, Timothy Sohn, Kaushik Roy, Yi Zhou

Defensive Publications Series

Users of computing devices, e.g., smartphones, wearables, tablets, personal computers, etc. that choose to be notified about incoming messages, e.g., email are often overwhelmed with notifications. Currently, there is no differentiation between notifications for high priority and low priority messages. Too many notifications can overwhelm or distract users. The techniques of this disclosure selectively provide notifications about email messages that are determined to be of priority or importance. The techniques utilize a trained machine-learning model that determines notification thresholds based on user preferences and user-permitted factors. Implementation of these techniques can reduce interruptions and distractions.

Automatic Annotations In Communication Applications, Matthew Sharifi, Jakob Foerster

Defensive Publications Series

This disclosure describes techniques to insert hyperlinks into user communications (e.g., email, chat, etc.) that can provide a ready reference to other communications relevant to the context. With user permission, contents of email and chat messages are analyzed and classified according to the topics of the messages, e.g., with the use of a trained machine learning model. When a new message is received, it is analyzed and hyperlinks are automatically inserted that enable the user to navigate to other relevant messages.

Adding Visual Features To Improve Accessibility Of Text, Lukas Muzika

Defensive Publications Series

A significant percentage of humans suffer from reading difficulties caused by dyslexia. While the difficulties may differ across different individuals, some common problems include seeing letters as backwards or upside down; having trouble distinguishing between letters with similar shapes, e.g., b, p, q, and d; and conflating running letters, e.g., an r next to an n misread as an m. These difficulties are sometimes traced to an apparent inability to recognize a letter and its misoriented form, e.g., “b” and “upside-down b,” as distinct objects.

Techniques of this disclosure introduce a uniformly oriented visual feature (e.g., a tick mark) to …

Active Vitality Control, Daniel Hoppe

Defensive Publications Series

Active vitality control

Emergency Behavior For A Connected Smartphone, Noah Coccaro, Adam Champy

Defensive Publications Series

Smartphones today are capable of being connected to one or more devices via wireless communication technologies, such as Bluetooth®. While a smartphone is connected (or “paired”) with a device, an audio-distribution profile of the smartphone governs routing of audio to and from mechanisms (e.g., speakers, microphones) of either the smartphone or a device to which the smartphone is paired. A protocol that routes audio, based on an input telephone number being an emergency telephone number, is described.

Intelligent Routing Methodology For Iot, Grace Priscilla Nambi

Defensive Publications Series

There is a rapid shift to the internet of things in the fast moving world of technology and there could be billions of heterogeneous entities communicating to one another within a span of 10 years. The IOT market is still evolving initiating changes that is triggering growth in various aspects for virtualization and cloud computing. In spite of all the progress made thus far, it is tough to get into the various operational fields and complexity involved in multiple divergent areas of intercommunication.

The purpose of action involving these field also vary. In this situation it will become hard to …

Track Asynchronous Graph Traversal Completion Using Time Moving Window Aggregators, Syed Abu Saleh, Arun Kumar Sivaraj

Defensive Publications Series

In today’s virtualized cloud infrastructure and advanced technology era, there are resources that are represented as an interconnected graph with root node and child nodes. These resources are growing exponentially on day-to-day basis and adding to the complexity of traversing and processing all the nodes in the graph. Major challenge involved is to traverse and process each child node asynchronously and mark the completion of all the nodes in the graph. Disclosed is an approach of tracking asynchronous traversal completion of a graph with indefinite nodes, using a time series moving window aggregator. This idea will address the graph traversal …

Few-Shot Learning Using Generative Modeling, King Hong Leung, Alexander Toshev, Narayan Hegde, Yair Movshovitz-Attias

Defensive Publications Series

In many machine learning tasks, the available training data has a skewed distribution- a small set of training classes for which a large number of examples are available (“base classes”), and many classes for which only a limited number of examples are available (fewshot classes). This is known as the long-tail distribution problem. Few-shot learning refers to understanding new concepts from only a few examples. Training a classifier on these fewexample classes is known as the few-shot classification task. Techniques disclosed herein improve classification accuracy for few-shot classes by leveraging examples from the base classes. A generative machine-learning model is …

Connection Quality Analysis For Live Video, Thomas Price, Justin Lewis

Defensive Publications Series

Video chat or streaming applications depend on the availability of reliable and high-speed network connections to maintain quality. When the quality is poor, it is often difficult for users to diagnose the cause, and hence, the poor quality of experience may be misattributed to the video chat or streaming application. This disclosure describes use a trained classifier model to detect low quality during a video call or video streaming session. With user permission, the classifier model is trained using data from prior video calls or sessions. When low quality is detected, the classifier model determines one or more likely causes …