Digital Commons Network^™

Display Orientation User Experience (Ux) Enhancement Through A Sensor Array, Chilin Kuo, Chin-Kuo Huang

Defensive Publications Series

This publication describes a computing device that captures a user-initiated sound by incorporating a microphone array. The computing device analyzes the captured sound from each microphone by using a model capable of determining a variation in the sound power of the captured sound signal by each microphone. To conserve the resources of the computing device, machine learning trains the model remotely or off-line. The ability of the computing device to determine the user-initiated sound power variation captured by each microphone enables the device to determine the location of the user in respect to the device and, thus, allows the device …

Visual User Interface (Ui) Interaction Prediction, Victor Carbune, Daniel Keysers, Thomas Deselaers

Defensive Publications Series

This publication describes an operating system (OS) level framework functionality, which can predict a user’s future interaction with first-party and third-party application software. This provides the user with an enhanced user experience (UX) by enabling first-party and third-party software to dynamically change the display in the user interface (UI) to aid the user to more-easily carry out the task at hand. The framework functionality at the OS level predicts the user’s future interactions using machine learning (ML). With this prediction, the supported application software can dynamically change the UI by presenting the user with relevant application software functions in a …

Enhanced Dying Gasp In Network Nodes For Intuitive Monitoring Of Complex Networks, Karthik Babu Harichandra Babu, Manigandan B, Ananthakrishnan Rajamani

Defensive Publications Series

Techniques are provided herein for fixing existing Operations, Administration, and Maintenance (OAM) Dying Gasp (DG) mechanisms and providing guaranteed delivery of the DG packet to the remote/peer node.

Meeting-Aware Presentation Of A Home Screen User Interface For A Cloud-Based Content Management Platform, Ashish Duggal

Defensive Publications Series

A mechanism is proposed for intelligently presenting a home screen UI of a CBCM platform based on scheduled meetings. The method includes receiving a request to provide a home screen of the CBCM platform. The method also includes determining attributes of one more meetings scheduled in close proximity to receiving the request. Further, the method includes determining whether the request is associated with a meeting based on attributes of the meeting. The method furthermore includes, responsive to determining that the request is associated with the meeting, determining a type of the meeting based on the attributes of the meeting. The …

Targeted Artificial Personality Matching, Anonymous

Defensive Publications Series

The present disclosure describes a system for building an Artificial Intelligence (AI) assistant that mimics personalities of friends on a social media platform. A ranking module generates a ranked list of the friends based on a user’s frequency of communication with them. A data input module collects images and associated text posted by top-three friends from the ranked list of friends. A feature extractor extracts features of the images and the associated text provided by the data input module. A machine learning module is trained with sample images and their associated text posted by the users with known personality traits …

Location, Time, And Preference-Aware Multi-User Scheduling, William Li, Sophia Yang

Defensive Publications Series

This disclosure describes techniques to determine an optimal point-of-interest for multiple users to visit together. The optimality criteria include various user preferences, schedules, and routines, that are obtained and used with user permission. A point of interest can include a location of entertainment, business or leisure, e.g., a restaurant, a movie, an event, or other outing.

Integrated Security-Tagging For Deterministic Ethernet, Maik Seewald, Robert Barton

Defensive Publications Series

Techniques are described herein for enhancing Time-Sensitive Networking (TSN) in network fabrics by dynamically assigning Secure Group Tags (SGTs) based on the stream configuration in a TSN controller. The TSN controller communicates stream details to a policy engine which creates a policy and assigns an SGT for the stream. The TSN controller pushes regular stream scheduling to the network switches, but also pushes a function that maps the stream identification based on the multicast Media Access Control (MAC) to a specific SGT. The TSN stream is now protected by the correct SGTs end-to-end.

Deterministic Process Networks Based On Adaptive Traffic Policing And Filtering, Maik Seewald, Robert Barton

Defensive Publications Series

Techniques are described herein to facilitate deterministic networking based on Time-Sensitive Networking (TSN) for Substation Automation Networks (SANs). The use of adaptive configuration of filtering and policing for TSN-streams allows the implementation and operation of a secure converged process bus architecture and supports the approach of a fully digital substation.

Connected Grid Mesh Deployment With Multiple Virtual Bridges, Xiaopu Zhang, Yuping Wang, Dapeng Zhu, Zhanwu Wang

Defensive Publications Series

Techniques are described herein for a Virtual Connected Grid Module (VCGM) which can be used in a Connected Grid Mesh (CG-Mesh) deployment so as to meet smart Terminal Transformer Unit (TTU) requirements. This can balance cost and complexity very well.

Cross-Dataset Malicious Actors Identification, Jan Jusko, Danila Khikhlukha

Defensive Publications Series

Techniques are described herein for convicting malicious actors across datasets of different origins. The algorithm allows correlation of the available ground truth knowledge from one dataset with observations in another dataset. In the network/endpoint security field this algorithm allows for conviction of malicious network traffic and identification of Command and Control infrastructure of newly detected malware, even if no direct communication between binaries and domains is observed.

Controlling Routing For Power Outage Notification Transmission, Zaochun Zhang, Rui Huang, Zhanwu Wang, Xiaopu Zhang

Defensive Publications Series

Techniques are described herein to equip backup power for some key nodes and form the local Directed Acyclic Graphs (DAGs) rooted at the first hop node with backup power. Nodes have different preferred parents in different work states. In normal state, nodes behave like existing mesh networks and have no performance sacrifice. In Power Outage Notification (PON) state, nodes can unicast the PON messages to their PON state’s parents to improve PON message transmission efficiency and reliability.

Audio Stream Blending In Multi Input Stream Headsets, Hp Inc

Defensive Publications Series

With the multiplication of personal devices, individual users are now using more and more

devices simultaneously: one or more phones (business and personal), computers, tablets, Television

sets…

This change in use led to changes in communication protocols used by accessories to these

devices (such as Bluetooth multipoint) so that a single accessory could be connected to more than one

device at the same time.

The invention described here relate to headset as accessories to personal devices.

Dynamic Adjustment Of Hotword Detection Threshold, Tanmay Wadhwa, Neil Dhillon

Defensive Publications Series

Many devices allow users to speak a hotword to activate the device, e.g., a virtual assistant application, which then responds to the user command. With user permission, incoming speech data is analyzed to determine whether a hotword was uttered. First, coarse hotword detection is performed. If coarse detection indicates that the hotword was spoken, fine hotword detection is performed to confirm that the hotword was spoken. Per techniques described herein, when fine hotword detection is unsuccessful, the threshold for fine hotword detection is reduced for a short time window. Such reduction improves the likelihood of recognition of the next utterance …

Leveraging App Relationships And Distribution Patterns To Identify Malicious Software, Florian Tramer, Mo Yu, Sai Deep Tetali

Defensive Publications Series

Software distributors, such as the operators of online software repositories or stores, scan and analyze the software they host to flag potentially harmful applications (PHAs). The scans are typically performed offline and are based solely on app-level features and do not take into account structural relationships between different apps and devices. This disclosure describes an app ecosystem-based approach to detect PHAs via analysis of contextual information, such as app install statistics and installation distribution patterns. Relevant contextual information about each app obtained user permission is leveraged to build a machine learning pipeline to flag PHAs for further review. The ecosystem-based …

An Adoptive And Resilient Segment Routing Version 6 Policy To Address Tight Service Level Agreement Requirements In 5g Networks, Clarence Filsfils, Pablo Camarillo, Francois Clad, Zafar Ali

Defensive Publications Series

There is ongoing work positioning Segment Routing version 6 (SRv6) as a replacement to General Packet Radio Service (GPRS) Tunneling Protocol User Plane (GTP-U). The main benefits of using SRv6 include coupling of the mobility overlay with the underlay (transport Traffic Engineering (TE)) and service chaining (GiLAN) and reusing high performance routers with SRv6 capabilities as User Plane Functions (UPFs). Techniques are described herein for enabling the creation of specific network slices where in the underlay a high resiliency is achieved with zero packet loss for tight Service Level Agreement (SLA) enterprise premium traffic. This same mechanism may be reused …

Browser With Smart Scrolling Based On User Context, Matthew Sharifi

Defensive Publications Series

This disclosure describes smart scrolling functionality for a web browser such that the user experience for scrolling a web page is improved to aid the user in locating information within the page that is likely of interest for the task at hand. To infer the user’s intent, the user’s ongoing tasks and context are determined, with user permission. Content of web pages viewed by the user is examined to determine content within the page that is likely to be of relevance to the user’s information need. Pieces of content likely to be of relevance to the user are highlighted via …

Speeding Up Web Page Content Updates Using Server-Side Page Versioning, Alessio Centazzo

Defensive Publications Series

In response to a page refresh request from a user, a web browser application often requests and downloads a previously loaded page again, even when the amount of updated content is small. As a result, bandwidth and time is wasted. This disclosure describes use of page versioning techniques to reduce the amount of data and time needed to update a web page. A web server implements page versioning to assign a unique identifier to different versions of a web page. The unique identifier is sent to the web browser along with the page content. Refresh requests received from the browser …

Automatic Problem Detection During Audio Or Video Call, Dhruv Bakshi, Jakob Foerster

Defensive Publications Series

Participants in an audio or video call over a network often face problems such as being unable to hear or see each other. With user permission, speech data from the call is automatically analyzed by a classifier to identify whether call participants are facing a problem. If a problem is identified, a message indicating a possible solution is provided, or if the call participant permits, automatic action is taken to fix the source of the problem. Users are provided with options to turn off the techniques.

Attribution To Ad Campaigns Of User Interaction With Product Demo Units, Peter Lewis

Defensive Publications Series

Online advertisers, such as brick-and-mortar retail advertisers, or consumer product brands that sell through such retailers face a challenge in attributing consumer actions, such as visiting a store, to advertising campaigns. The techniques of this disclosure make advantageous use of product demo mode of products displayed in-store to transmit a signal that boosts visit detection. The solution is robust to products being moved around a store or removed from display, since the product itself broadcasts the signal. The techniques also utilize the ability of a product to establish facts about its surroundings that enable richer reporting on store visits.

Automatic Context Determination For Answering User Queries, Ruxandra Davies, Scott Davies

Defensive Publications Series

Virtual assistant applications enable users to specify a query. When the virtual assistant receives a query without relevant context, determining the appropriate answer is not possible. In these situations, it is necessary that the user respond to follow-up questions and provide the context. This disclosure describes techniques to automatically obtain the query context, when permitted by the user, and create a seamless user experience. Based on the obtained context, the query is answered which reduces back-and-forth with the user.

Click-To-Call Conversion Measurement Based On Transcribing Conversation, Alex Jacobson

Defensive Publications Series

The conversion metric, which is the ratio of sales (or other predefined result) to advertisement impressions or clicks, is a key measure for advertisers to assess the value derived from digital advertising. In click-to-call ads, which show a link for mobile users to initiate a call to an advertiser, conversions, if any, occur over the phone after the user clicks the ad. Conversions that occur over the phone are difficult to document, in turn making it difficult to accurately measure the conversion metric. This disclosure describes use of machine learning techniques to transcribe, with user and advertiser permission, the call …

Countering Phishing Attacks By Automated Responses, Brian Shucker, Brian Brewington

Defensive Publications Series

This disclosure describes techniques to automatically respond to phishing attacks received via communication channels such as email, chat, SMS, etc. A large number of automated responses require the attacker to differentiate between automated responses and human responses which can require substantial effort. In this manner, the described techniques actively disincentivize phishing attacks by causing an increase in the cost for an attacker to conduct such attacks.

Automatic Translation In Voice Calls, Sooraj Sasindran, Naveen Kalla

Defensive Publications Series

Participants in a voice call do not always have a common language. This can pose problems since participants may not be able to understand each other during the call. Some current techniques to address this problem involve incorporating a machine translator that can perform translation. However, for machine translation to be provided to all participants, such techniques require a machine translator mechanism to be provided at each participant’s end, which is not always possible.

The techniques of this disclosure incorporates machine translation techniques on a participant device such that the device can perform local translation of speech in a call. …

Automatic Removal Of Unwanted Objects From Images, Daniel Citron, Lachlan (Locke) Dunn

Defensive Publications Series

It is sometimes necessary to remove a person or other object from an image. Per current techniques, the removal of a person from an image, e.g., via manual cropping, produces a crude result, e.g., an image with discontinuities, an image with visible cropping boundaries, etc. Some image management and photo sharing applications/ services include features that enable users to remove specific persons from being categorized or surfaced in images; however, such solutions simply de-lists photos with the specified persons.

This disclosure describes techniques that enable a user to remove specified individuals or other objects from images. The portion of the …

Thermal Downlink Throttle Ue Specific Approach, Blake Kragten, Shivank Nayak, Siddharth Ray

Defensive Publications Series

During operation, temperatures of a mobile communication device of an end user (user equipment or “UE”) can increase to high levels. In particular, UE temperatures can rise when receiving large amounts of data during downlink communication with a network. Generally, there is no ability to limit the amount of downlink throughput when the UE device is in single carrier mode. However, downlink throughput throttling can be used to thermally mitigate increasing UE temperatures. As the temperature of the UE increases, the network can be notified to decrease the amount of downlink throughput, thus reducing the power levels and the temperature …

In-Page Search Over Text And Images In A Web Page, Matthew Sharifi

Defensive Publications Series

Browser applications provide users with the ability to search within a webpage. Such searches are limited to textual content of the page and do not take into account content depicted as images within the webpage. This disclosure describes techniques to enable search to be performed over the entire webpage, including image content. With user permission, images on a webpage are analyzed to determine presence of text within the image. If text is detected, OCR techniques are applied to recognize characters in the text. When the user enters a search query for searching within the page, the text content of the …

User Authentication Via Lip Reading, Horacio Hernan Moraldo

Defensive Publications Series

This disclosure describes techniques to prevent unauthorized access to information via a facial recognition interface. With user permission, a live video of the user attempting to access the information is obtained via a camera to perform facial recognition and determine the presence of the user. The user is instructed to dictate a randomly generated passphrase while facing the camera. Lip reading techniques are applied to validate the dictation of the randomly generated passphrase. Access to the information is granted only upon successful validation.

Auto-Recovery Of Micro-Services In A Large Distributed Appliance Model, Kshitij Tanay, Raghu Rajendra Arur, Taj Uddin

Defensive Publications Series

In large distributed application-based systems, an ensemble of co-existing micro-services perform individual functions and communicate with other micro-services. As these interactions and individual behaviors can be complex, it may be necessary to monitor micro-services for any abnormalities. Manual monitoring of all such micro-services, or establishing individual rule-based alerts for micro-services can be time-consuming. In addition to maintaining functionality of micro-services, it is important to prevent micro-services from becoming a performance bottleneck for other micro-services. In such situations, an alert may not suffice. For example, if a micro-service serves as a data store for all other services, a bottleneck at that …

Virtualized Intelligent Honeypot Agent, Plamen Nedeltchev, Mani Kesavan, Hugo Latapie, Enzo Fenoglio

Defensive Publications Series

A honeypot system is described that can expand to any attack surface as it learns and grows with the changing device landscape. The system also takes into account the human elements that originated the attack. By using adversarial training mechanisms, the system may be quickly trained to become a doppelganger and attract attacks. Moreover, a unique quantum cognitive framework provides a robust adaptivity to ever-changing attacker strategies. Virtualized intelligent honeypot agents may be introduced into the network, device, or server, to connect and share knowledge to facilitate federated learning for similar type of agents. The agents may also be operated …

Intelligent Editing Assistant, Emmanuel Arriaga

Defensive Publications Series

A technique is proposed for assisting writing or editing an online document supported by a cloud-content based platform. An editing assistant service provided by the cloud-content based platform determines a writing style designated for the online document. The editing assistant service determines a subset of content in the online document. Then, the editing assistant service determines whether the subset of the content in the online document is consistent with the writing style. Responsive to determining that the subset of the content in the online document is not consistent with the writing style, the editing assistant service predicts one or more …