Digital Commons Network^™

Fine-Grained View Interpolation In Multi-View And Light-Field Coding, Thomas Davies

Defensive Publications Series

Techniques are described for increasing the number and accuracy of views in multi-view, three-dimensional (3D), and light-field systems, by leveraging low resolution sensors to provide geometry and object location calibration when interpolating new views.

Use Of Nfc (Near Field Communication) To Transfer Networking Information Via Intermediary Devices, Hp Inc

Defensive Publications Series

This disclosure describes the use of NFC (Near Field Communication) technology

to enable phones and tablets to easily transfer network information between

devices.

In-Vehicle Infotainment (Ivi) System User Interface (Ui) Enhancement, Luis Delgado De Mendoza Garcia

Defensive Publications Series

This publication describes an application software that may be used in an in-vehicle infotainment (IVI) system with its associated user interface (UI) or a portable computing device such as a smartphone. The application software distinguishes a driver’s touch from that of a front-seat passenger’s touch by evaluating the angle of the user interacting with the UI. The ability of the application software to correctly interpret the user’s touch allows for optimal interaction with the UI and, in the case of the driver, helps reduce distracted driving. To conserve resources, machine learning (ML) may train the application software’s model remotely off-line.

Providing Readout Of Multimedia Content In Messages, Niyati Joshi, Vinh Ly, Okan Kolak

Defensive Publications Series

This disclosure describes techniques to automatically extract information from messages that include multimedia content, e.g., image, video, etc., and provide a readout of the message content to the recipient. Extraction of the content can be performed using machine learning. For example, readouts can be provided for multimedia messages received via short message service (SMS), chat or messaging applications, email, etc. The techniques can be implemented as part of a virtual assistant application. The readout is provided upon user request. Messages are accessed and analyzed upon specific permission of the user.

Integrated System For Notes And Lists, Amitabh Saikia

Defensive Publications Series

A flexible integrated system for management and maintenance of notes and lists is described. With user permission, notes and lists are stored by a central server, and can be updated using a variety of surfaces (e.g., virtual assistant) and providers (e.g., smartphone or desktop applications, browser-based interfaces, etc. A database coupled to the central server maintains a state of notes and lists associated with each user. Federated updates are utilized to keep the providers, surfaces, and the database in a synchronized state. A low-latency application program interface (API) is provided to enable two-way synchronization of lists and notes. Upon a …

Driver Training Using An Advanced Driver-Assistance System (Adas), Joe Johnson Jr

Defensive Publications Series

A driver-training assistant that accesses features of an Advanced Driver-Assistance System (ADAS) to train drivers is described. The driver-training assistant uses detection capabilities of the ADAS to determine a performance of the driver and indicate a correction to the driver. Such an indication may be provided to the driver through a visual, audible, or haptic aide.

Voice Search Capabilities For Lists And Notes, Amitabh Saikia

Defensive Publications Series

Different types of user interfaces are available on various computing devices to access lists and notes, e.g., a graphical user interface, a voice user interface, etc. A search engine stack is utilized to process user requests, e.g., voice queries, which enables available matches to be ranked and selected. Use of the search operation provides a superior user experience when compared to simple relational database searches. Integration of the search engine stack enables fuzzy matching of user requests to available notes and lists. If the user provides permission, past interactions are utilized. Interpretation or corrective action regarding a query, based on …

Unified Concurrent Write Barrier, Michael Lippautz, Ulan Degenbaev, Hannes Payer

Defensive Publications Series

In a programming language with support for garbage collection, a write barrier is a code snippet that maintains the key invariants of the garbage collector. The write barrier is typically executed after a write operation. The write barrier is computationally expensive and can impact program performance. This is true to a greater extent for languages where garbage collectors need to maintain multiple sets of invariants. For example, languages that employ garbage collection schemes with two collectors may maintain their invariants using multiple different write barriers. The techniques of this disclosure address the problem of maintaining multiple invariants by unifying the …

Resolving User Queries Using Contextual Information, Marcos Calvo, Karol Stosiek

Defensive Publications Series

When responding to a request from another person, human beings take into account non-verbal cues and relevant implicit contextual information to determine an appropriate response. In contrast, digital assistants do not currently take such contextual information into account. Thus, a digital assistant may provide a sub-optimal or contextually inappropriate response to the user’s request, or require the user to modify the original request iteratively until the user’s full intent is communicated. If the user permits, the techniques described in this disclosure enable a digital assistant to infer the user’s intent by using device and environmental sensors to extract available contextual …

Contextual User Interface For A Smartwatch, Matthew Tait

Defensive Publications Series

This disclosure describes a context dependent user interface. With user permission and express user content, the context of a smartwatch user is determined and utilized to provide a contextually appropriate user interface. The contextual user interface can include suggestions of commands, apps, controls, etc. that are suitable for the context, e.g., suggestions to look up recipes when the user is in the kitchen near dinner time. The location of the smartwatch is determined by use of wireless fingerprints associated with different locations, obtained with user permission.

Machine Learning-Based Generation Of Contextual Frequently Asked Questions For Problem Analysis In Support Engagements, Chidambaram Arunachalam, Hazim Dahir, Alka Luqman

Defensive Publications Series

Techniques are described herein to automatically generate Frequently Asked Questions (FAQs) during the initial problem analysis of a given issue. The conversation transcripts of successfully resolved recent cases are analyzed using a supervised machine learning model to predict the initial problem analysis phase of a conversation and to extract FAQs asked during this phase. The extracted FAQs are displayed to the customer at the time the case is opened, thereby accelerating the problem solving process and augmenting the support engineer's troubleshooting capabilities.

Enhanced Presentation Experience For Color Blind Meeting Attendees, Murray Mar, Alan Gatzke, Kian Shahla, Uday Srinath

Defensive Publications Series

Techniques are described for adding support to an online meeting client or collaboration infrastructure, which allows a presentation media stream in an online meeting to be converted to a "color blind" friendly palette in real-time. A configuration "wizard" would be included in the online meeting client, which would guide the color blind attendee to select the palette best suited for their individual experience.

Augmented Reality Based User Guidance For Optimal Collaboration Experience In A Wifi Network, Sukri Dasgupta, Santosh Pandey

Defensive Publications Series

Techniques are described herein for recommending locations to users that are close to them based on the users' current application requirement and current network conditions. Augmented Reality (AR) is then used to guide the user towards an area of good service. Metadata is shared back with a network controller for future requirements and guidance of other users.

Creating A Legal Collaborative Experience, Shankar Ramanathan, Muhilan Natarajan, Robert Barton, Jerome Henry

Defensive Publications Series

Techniques are described for adding trust/reliability quotients to video conversation recordings by creating a secure ledger-based legal recording mechanism. The legal recording mechanism is tamper proof, faster than documenting the agreement, and legally binding.

A Method To Verify Signature Of Digitally Signed Documents On Printer And Enable Print, Hp Inc

Defensive Publications Series

It is a common practice in enterprises such that when sending confidential documents across, it has to be digitally

signed to maintain both the integrity, confidentiality and establish sender identity.

When there is need to print such digitally signed document, user need to verify the signature on the PC first and then

has to give it for print. When the document is directly sent to the recipient or to the web enabled printer as e-print job

through cloud, there is no way he can verify validity and integrity on printer itself as of today.

The proposed solution addresses the need …

Interactive Internet Of Things Robotic Device, Melissa Daniels

Defensive Publications Series

Aspects of the present disclosure are directed to a robotic device that includes appendages that can move and lighting elements that can activate and change color in response to movement and other indicators of user presence. As one particular example, the robotic device of the present disclosure can include a structure in the shape of a jellyfish that can be mounted on a surface (e.g., a floor or ceiling) and which can make various movements and/or lighting effects.

Reproduction Of Captured Imagery Via Machine Learning And Device Locomotion, Melissa Daniels, Ryan Bae

Defensive Publications Series

Aspects of the present disclosure are directed to mobile robotic devices that are capable of reproducing captured imagery (e.g., images captured by a camera that is on-board the robotic device) through the use of device locomotion. For example, the robotic device can capture (or be operated to capture) an image (e.g., a self-portrait photograph which is also known as a “selfie”) and can then reproduce the image (e.g., a stylized version thereof) by controlling motion of at least a part of the robotic device to draw at least a portion of the captured scene onto a medium. For example, the …

Interactive, Mobile Internet Of Things Device With Image Capture Capability, Melissa Daniels, Matthew Bennice, Denia Del Cid, Brittany M. Wilbert, Vaas Krishnamurthy

Defensive Publications Series

Aspects of the present disclosure are directed to an interactive, mobile Internet of Things (IoT) device with image capture capability. In particular, one example embodiment of the present disclosure is a “life-size” (e.g., around 4-6 feet in height) anthropomorphic device that can move around an environment and interact with humans and/or other devices in the area. For example, the device can respond to commands and/or capture images of and/or with humans in the area. As one example, the captured images can be in the style of a self-portrait photograph (also known as a “selfie”) and can depict the device positioned …

Interactive Device That Performs Output Based On Human Movement And/Or Human Emotion Detected Via Machine Learning, Melissa Daniels, Nhat Vu, Daniele Midi, Ed Coyne, Jiyoung Ko, Bill N. Schilit, George Bacon

Defensive Publications Series

Generally, the present disclosure is directed to a device capable of providing an output that is specific to and/or based on nearby human movement and/or human emotion detected by one or more machine-learned models.

Internet Of Things Three-Dimensional Printer System, Ed Coyne

Defensive Publications Series

Aspects of the present disclosure are generally directed to a custom three-dimensional (3D) printer system that allows for the offloading of timing sensitive operations for performance by a microcontroller. In particular, the present disclosure is directed to a 3D printer system that can include multiple classes of processors that are used to perform operations associated with three-dimensional (3D) printing, thereby showcasing a heterogeneous computing system which uses two classes of processor to collaborate to solve a complex problem. In particular, the 3D printer system can facilitate the process of providing 3D printer instructions to a 3D printer.

Internet Of Things Device With Controllable Lighting Elements, Melissa Daniels, Rachel Weinstein Petterson, Carson Holgate, Aieswarya Sayee Manicka

Defensive Publications Series

Aspects of the present disclosure are directed to a device with controllable lighting elements or other output elements such as audio, vibratory, gaseous/liquid, and/or olfactory output elements. In particular, the interactive device of the present disclosure can include a structure fashioned in the shape of some fauna or flora (e.g., a tree) that can selectively operate the output elements (e.g., illuminate the lighting elements) based on collected sensor data regarding the surrounding environment. The structure can also respond to specific user interactions and/or receive predetermined control signals that control the output elements.

Internet Of Things Vending Device, Melissa Daniels

Defensive Publications Series

Aspects of the present disclosure are directed to a vending device that counts and/or identifies objects dispensed by the vending device. In particular, the vending device of the present disclosure can include a machine-learned model that has been trained to count and identify objects dispensed by the vending device.

Wearable Internet Of Things Badge Device, Kiana Mcnellis, Aleks Rozman, Melissa Daniels

Defensive Publications Series

Aspects of the present disclosure are directed to a device that is wearable by a user and responsive to beacon devices or other Internet of Things (IoT) devices. In particular, aspects of the present disclosure are directed to the application of beacon devices and corresponding portable (e.g., wearable) badge devices to create an IoT system that can be used to enhance user interactions with other users and the environment in which they are present.

Interactive Surface-Mounted Internet Of Things Device, Melissa Daniels, Matthew Bennice, Rachel Weinstein Petterson, Vaas Krishnamurthy, Priya Kasirajan, Brittany M. Wilbert

Defensive Publications Series

Aspects of the present disclosure are directed to an interactive lighting device that includes sensor-equipped lighting elements that respond to users. In one particular example, the interactive lighting device of the present disclosure can include a structure (e.g., a custom designed structure) fashioned in the shape of a planter (e.g., a container for live plants) that can be mounted on a surface (e.g., a wall) and which can provide various lighting effects based on events (e.g., the presence or movement of users) detected by sensors of the interactive lighting device. For example, the interactive lighting device can control lighting elements …

Entertainment Device With Detection Of Projectile Impact, N/A

Defensive Publications Series

Aspects of the present disclosure are directed to an entertainment device that includes a display that changes a displayed image based on detection of impacts on the display. For example, the entertainment device can include a large display area that displays a rectangular grid or some irregular pattern of geometric shape. Using impact sensors, the entertainment device can detect impact on the surface of the display area and change the image displayed on the display area in an area surrounding the portion of the display area on which the impact was detected.

Projection Device For Generating Augmented Reality User Interfaces, Melissa Daniels, Nhat Vu, Tianchun Yang, Michael Delgaudio, Jiyoung Ko

Defensive Publications Series

Aspects of the present disclosure are directed to a projection device that projects images onto surfaces and detects interactions with the images on the surfaces. For example, the projection device can include a projector that can project images onto a surface, a camera that can capture imagery of user interactions with the images on the surface, and a processing system (e.g., that includes one or more machine-learned models) that can process the imagery to understand the user interactions, thereby receiving user input. The images projected onto the surface can include still images, moving images, or a user interface that includes …

Robotic Game Playing Internet Of Things Device, Melissa Daniels, George Bacon

Defensive Publications Series

Generally, the present disclosure is directed to a robotic device that can play certain games with a user, such as, for example, interactive hand-gesture-based games such as rock-paper-scissors, gesture matching, and/or gesture mirroring. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage an Internet of Things (IoT) system or device to control a robotic hand based on inputs from a camera that are processed by a machine-learned model such as a gesture recognition model.

Gesture-To-Speak, Minghung Hsieh

Defensive Publications Series

This document describes an easy-to-use communication system that converts a received gesture into audible, spoken words and phrases. The communication system includes a mobile device having a gesture-to-speak manager application that associates gestures received through an interface of the mobile device to audio files containing pre-recorded phrases. The gesture-to-speak manager application directs the mobile device to play the audio files, as associated to the received gestures, through an audio output of the mobile device.

Restricting Access To Files By Application Programs, Sandro Feuz, Thomas Deselaers

Defensive Publications Series

This disclosure describes techniques to enable users to restrict private data from display. Such private data can include images, videos, documents, and other files, by a user device. Private files can be manually or automatically designated, and the content of these files is hidden from user interfaces provided by application programs. Automatic designation is performed using user-permitted techniques for automatic analysis of files. Further, a variety of settings allow the user to control access to private data for display by designated application programs. Such features restrict another user that is viewing a device screen from viewing private data. Described techniques …

Method Of Selecting An Optimal Set Of Citizens Broadband Service Devices (Cbsds), Evan Tyra, Naveen Kalla, Sooraj Sasindran, Radhika Agrawal

Defensive Publications Series

This publication describes an algorithm that enables a user equipment (UE) to use scattered citizens broadband radio service (CBRS) networks while reducing the need for the UE to continuously scan for CBRS coverage and limiting stored data for the numerous citizens broadband radio service devices (CBSDs). The algorithm allows the UE to decrease battery use and optimize the UE’s use of its memory resources.