Digital Commons Network^™

Machine Learning For Accurate Battery Run Time Prediction, Liang Jia

Defensive Publications Series

Generally, the present disclosure is directed to using machine learning to manage state of charge of a battery. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to predict future energy consumption and optimal charging rate of a battery based on battery characteristics and expected user routine.

Removing Breathing Artifacts From Audio, N/A

Defensive Publications Series

Generally, the present disclosure is directed to removing breathing artifacts from audio. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to generate a clean audio sample based on audio data from the audio sample.

Configuring Music Variation In A Music Compilation, Thomas Price

Defensive Publications Series

Generally, the present disclosure is directed to determining an optimal level of music variation in an assortment of music such as, for example, a music streaming service. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to predict an optimal level of music variation based on historical level of music variation preferences and/or listening data.

Discovering Employment Listings From Imagery, Charles Armstrong

Defensive Publications Series

Generally, the present disclosure is directed to discovering employment listings from imagery. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to identify employment listings based on image data.

Stylizing Map Based On Examples Of Representative Styling, Joshua Schpok

Defensive Publications Series

Generally, the present disclosure is directed to stylizing a map based on one or more examples of representative styling. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to predict map styling rules based on one or more examples of representative styling.

Improving Advertisement Delivery In Video Streaming, Mary Witkowski, Marshall Witkowski

Defensive Publications Series

Generally, the present disclosure is directed to improving advertisement delivery based on the content of a video. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to predict a non-intrusive location for an advertisement based on the content of a video.

Predicting Search Queries Based On Personal Routines, Greg Hartrell

Defensive Publications Series

Generally, the present disclosure is directed to a computing system for predicting user intent in operation of a device based on personal routines. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to predict user intent in operation of a device based on past and/or current operation of the device and routine of the user.

Allocating System Resources In Display Of Advertisements, Bin Liu, Jiefu Zheng

Defensive Publications Series

Generally, the present disclosure is directed to predicting whether bid data of a present ad query (e.g., the largest cost per thousand impressions provided by a bid responsive to the ad query) will satisfy a threshold (e.g., a threshold cost per thousand impressions) based on bid data from one or more previous ad queries and/or characteristics of the present ad query. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to predict whether bid data of an ad query will satisfy a threshold based on bid …

Predicting Categorical Information For New Content In Application Recommender Systems, Jun Hong, Xiao Zhang

Defensive Publications Series

Generally, the present disclosure is directed to predicting categorical information for newly created content in an application recommender system. In particular, in some implementations, the systems and methods of the present disclosure can include or otherwise leverage one or more machine-learned models to predict categorical information of new applications in an applications marketplace based on screenshots of such new applications in the applications marketplace.

Task-Focused User Interface, Christopher Farrar

Defensive Publications Series

Computer or mobile device users that try focusing on a single task often become distracted or interrupted by other applications, notifications or tasks. Also, users may distract themselves while working on a project by thinking about a task from another project. When users are distracted or interrupted, they switch context from one task to another, which may impact the quality of the tasks they are trying to complete and also increases the time needed for task completion.

The described techniques provide a task-focused user interface that, with express user permission and consent, temporarily restricts the user to a single task …

Control Of Jitter Buffer Size Using Machine Learning, Ivo Creusen, Oliver Walter, Henrik Lundin

Defensive Publications Series

Determining the size of a jitter buffer for calls conducted over the network involves a trade-off between the probability of buffer under-runs and user-perceived delay, which impedes communication. Techniques of this disclosure perform data-driven optimization of the jitter buffer of audio and/or video calls conducted over the internet. Event logs that contain data about network conditions experienced during completed calls are used to calculate optimal jitter buffer size using an optimizer. The output of the optimizer is used as a target for offline training of a machine-learning model to calculate optimal jitter buffer size. The trained model is employed to …

Navigation Of Blogs Related By A Tag, Sergey Babkin

Defensive Publications Series

Techniques of this disclosure automatically add links to a blog post that enable navigation within a collection of related posts, e.g., posts related by a tag. Blog readers can navigate directly within the linked posts. In a static implementation, the links to posts are automatically updated and stored in a database whenever any post changes. In dynamic implementation, the links to other posts corresponding to a tag are generated when the post is rendered as a web page or upon user selection of a particular tag.

User Choice In Conversational Advertisements, Dario Rapisardi, Hema Manickavasagam, Amit Fatnani

Defensive Publications Series

Current advertising formats are displayed at the edges of content, e.g., website content, mobile application content, etc. Such advertisements can interrupt the flow of conversation in a conversational application and are therefore unsuitable for such use. This disclosure describes techniques to provide user choice in advertisements in conversational applications, e.g., during interaction between a user and a chat bot. The advertisements are provided in two parts - a user choice portion and one or more second portions that include creative assets of the advertisement. The second portion(s) are displayed upon user selection to view the advertisement. This enables the advertisement …

Interactive Video Content Playback, Indusekar Ponnapa Reddy, Kusum Madarasu

Defensive Publications Series

Users sometimes play online content, e.g., video and video advertisements, without paying attention to the content. In such instances, the viewership metrics for the content may be inaccurate. This disclosure describes an online content platform that hosts interactive content, such as video and video advertisements. Video content and advertisements are divided into multiple parts and users are provided with interactive options to select the next part to view. Video content is stored as a graph, with nodes corresponding to content parts, and edges corresponding to valid paths to view the video. Interactivity in this manner can provide increased engagement, better …

Advertising Using Augmented Reality, Catherine Cardinal, Chin Ngai Sze

Defensive Publications Series

Heads-up displays have been gradually implemented in automobiles. These displays can provide information to drivers, such as speed, temperature, remaining fuel, navigation, and more, while minimizing distraction. Some vehicle heads-up displays add turn by turn directions based on GPS information onto a real-time street view. This disclosure describes techniques to show advertisements to passengers in vehicles using windows capable of implementing augmented reality (AR) - AR-capable windows.

Automatic Slide Progression During A Presentation, Emmanuel M. Arriaga

Defensive Publications Series

Advancing slides during a presentation requires human input, e.g., via a clicker, or other input device. Such input requires the presenter or a human assistant to take explicit action. This disclosure describes automatic slide-progression techniques to advance a presentation, e.g., presentation slides, to pages or slides that match a presenter’s current speech. With user permission, a machine learning model analyzes the presentation content. It matches the content with speech from the presenter and automatically presents an appropriate slide. The techniques enable the correct slide to be displayed without explicit input from the presenter.

Verbrauchsoptimierung, Daniel Hoppe

Defensive Publications Series

FUEL CONSUMPATION OPTIMIZATION BY APPROXIMATION

OF IMPULATIONS IN PARTICLE FILTER FOR

SPARK IGNITION ENGINE CONCEPTS

Method For The Surface Hardening Of A Ball Stud, Daniel Hoppe

Defensive Publications Series

METHOD FOR THE SURFACE HARDENING OF A BALL STUD

Wheelhouse Protector, Daniel Hoppe

Defensive Publications Series

Wheelhouse protector

Integration Of A Wheelchair Occupant In A Vehicle When Using A Detachable Wheelchair Seat Shell, Daniel Hoppe

Defensive Publications Series

Integration of a wheelchair occupant in a vehicle when using a detachable wheelchair seat shell

Throttle Grip: Potentiometer With Integrated, Daniel Hoppe

Defensive Publications Series

THROTTLE GRIP: POTENTIOMETER WITH INTEGRATED

RESET SPRING IN HANDLE VARIANT 2

Active Spoiler With Integrated Brake Cooling, Daniel Hoppe

Defensive Publications Series

ACTIVE SPOILER WITH INTEGRATED BRAKE COOLING

CHANNEL

Dynamic Adjustment Of Power Consumption Based On A Time Or Event Goal, Thomas Price, Justin Lewis

Defensive Publications Series

Users of mobile devices often experience a scenario where the available battery power is low, while a user activity is ongoing. Currently, users take actions such as reducing display brightness, turning off connectivity options, etc. to conserve battery power. However, such actions may not ensure that enough battery power is available to complete the user activity. This disclosure describes techniques to selectively enable smartphone power-saving features to achieve a user activity goal, or a desired amount of operating time to remain. The techniques can be enabled by a user of the device, or with user permission, can be enabled automatically. …

Autonomous Guidance Devices, Charles L. Chen, Jongyeong Lee, Tiruvilwamalai Raman

Defensive Publications Series

This disclosure describes autonomous guidance devices that help users navigate complex indoor spaces such as airports and large shopping centers. The devices are in the form of trolleys, shopping carts, luggage, etc. The devices provide information (e.g., by responding to voice queries) and guidance to the user (e.g., by escorting users to destinations) in such locations. Autonomous guidance devices are equipped with obstacle avoidance, path planning, guidance systems and indoor/outdoor maps. Applications oLE-0773-01-Df these devices can also span advertising and mapping services as well as assistance to visually impaired users and senior citizens.

Interface For Exploring Videos, Christopher Pentoney, Rodrigo De Oliveira, Anshuman Kumar, Mary Cassin, Joshua Lewandowski

Defensive Publications Series

Searching and browsing for videos is a common task. Search engines attempt to provide a quality user experience by showing the most relevant results at the top of a results page. However, efficiency and relevancy can sometimes be less of a concern, e.g., when browsing for interesting content, such as videos, e.g., without entering a search query. When users browse or search for videos, showing a hierarchical list of search results does not enable easy discovery of other content that they may enjoy.

This disclosure describes techniques to improve user enjoyment when browsing videos, e.g., directly, or after performing a …

Artificial Intelligence Powered Brand Identification And Attribution For On Screen Content, Ravi Solanki, Devraj Mehta

Defensive Publications Series

The method detailed herein relates to second screen experiences for a smart television (TV). The method includes capturing one or more frames from a video (e.g., movie, television show, advertisement) playing on the smart TV and sending the captured frames to a cloud platform for image processing. The method further includes using machine learning, via the cloud platform, to identify objects (e.g., people, products, brands, and places) in the received frames. The method includes pushing, from the cloud platform, a notification to a mobile device including information relating to the identified objects.

Automatic Identification And Ranking Of Knowledge Sources, Pedro Gonnet, Victor Cărbune

Defensive Publications Series

While authoring content, users can benefit from being able to provide citations and to verify statements that include facts. This disclosure describes techniques described to provide citations and/or corrections for user text, e.g., in a document, within an authoring application. Trained machine learning models are used to generate a feature vector based on user text which is matched to feature vectors of known information sources. Citations and corrections are provided based on identifying reliable sources such as academic publications, reliable news sources, etc. along with a visual indicator of the quality of the source.

Secure Web Proxy Resistant To Probing Attacks, Benjamin Schwartz

Defensive Publications Series

Secure web proxies are popular for sending internet traffic via alternative paths. Access to a secure web proxy is typically password protected. A malicious third party that does not know a username or password can detect a secure web proxy server by attempting a connection and observing a distinctive response from the proxy server, e.g., an HTTP 407 Proxy Authentication Required response. Traffic from clients that utilize web proxy servers that are detected in this manner can then be blacklisted.

The techniques of this disclosure enable secure web proxies that are resistant to probing attacks. The output of distinctive signals …

Deterministic Patch File Generation For Deflate Streams, Amin Hassani, Ryan Hitchman, Sen Jiang

Defensive Publications Series

This disclosure describes efficient techniques to generate small and deterministic patch files for Deflate compressed files. A transform is utilized to perform decompression of the Huffman part of the Deflate stream of the file while the structure of the LZ77 coding in the file is left unchanged. A corresponding reverse transform is utilized to deterministically obtain the original Deflate stream from the generated stream. Implementation of the techniques requires low amounts of memory and computation time. The techniques are compatible with many compression techniques. The techniques can be used to deliver software updates over a network.

Time-Delayed Casual Telepresence Interaction, Curtis Galloway, David Karam

Defensive Publications Series

This disclosure describes techniques to use a system of audiovisual equipment to aid in facilitating casual interactions between workers of different offices and time zones through time-shifted playback of brief video clips of actions by workers from common spaces of one office on a screen at another office. Live actions to share in video clips are determined based on whether a user interacts with the camera. The video clips are played back in other locations at a different time in the day based on time zone differences between locations.