Digital Commons Network^™

Employing Assistive Device Audio Input To Detect And Mitigate Loud Noises, N/A

Defensive Publications Series

In dense environments, such as apartments, townhomes, etc., people are often bothered by loud sounds generated by neighbors or others nearby. Currently, alerting the source of the disturbance requires walking over to the person or manually messaging them via a suitable communication mechanism. This disclosure describes the use of an assistive device with ambient sound input capabilities to detect sound disturbances from the surrounding environment, locate the source(s) of the detected disturbance(s), and generate alerts for appropriate mitigating actions. The described techniques are implemented with specific user permission.

Temperature Controlled Stacked Board Cavity, Sean Korphi, Reza Ghajar

Defensive Publications Series

This publication describes techniques and apparatuses that decrease the temperature variation in a cavity created by an interposer that stacks two or more boards inside a smartphone. When operating electrical components, heat generation is inevitable. A way to minimize temperature variation is by embracing and managing a safe rise in temperature in and/or around the electrical components inside the cavity of the interposer. A safe rise in temperature may be a temperature between +25°C and +85°C (e.g., +55°C). That way, when the smartphone shifts from an idle state to normal operation, the cavity of the interposer and the electrical components …

Automated Restaurant Orders Using Digital Assistant, Sriram Bhargav Karnati, Sonali Mangal

Defensive Publications Series

This disclosure describes techniques that enable a user to place orders for food using a digital assistant. An order for restaurant food pickup or delivery is received from a user. The digital assistant obtains additional details of the restaurant, e.g., from the restaurant website with the use of machine learning techniques to extract text from the website or from other information sources. With user permission, a call is made by the digital assistant to the restaurant to confirm availability of requested items and to complete the order. Details such as an amount of payment to be made, estimated time of …

Automatic Correction Of Disfluent Spoken Queries, Manaal Faruqui, Siddharth Gopal

Defensive Publications Series

A user’s interaction with a virtual assistant typically involves spoken requests, queries, and commands which often includes disfluencies. This disclosure describes techniques to automatically correct disfluent queries. Per techniques of this disclosure, a disfluency correction machine learning model is utilized to convert a disfluent query to a corresponding fluent query. Lexical features extracted from the disfluent query are utilized to determine a portion of the query that is removed from the disfluent query to convert it to a fluent query. The model is trained using pairs of queries.

Distributed Location Processing Using Reverse Tracking And An Internet Of Things Platform, Jeff Apcar, Vinay Saini, Ankush Arora

Defensive Publications Series

The concept of location tracking is of great relevance in various enterprise and industrial environments. The techniques presented herein propose location tracking techniques that are independent from centralized servers and that use scalable technology and architectures to provide resiliency, faster location updates, reduced cost, and increases reliability.

Run Time Translation Of User Interface Text Via An Operating System Translation Service, Steffen Meschkat

Defensive Publications Series

User interface text labels are translated into multiple languages to support users who speak the corresponding languages. Software developers use translation services to generate translations of each label in the UI in multiple languages. The translated labels are packaged with the application when it is built. This approach provides a less than satisfactory user experience since the same text label may be translated differently in applications from different vendors. Further, user preferences are not taken into account when generating translated text labels. The techniques described in this disclosure generate translated labels by taking into account user preferences and serve to …

Smart Email Send Scheduling, Ashish Duggal

Defensive Publications Series

Although users can select a time and date to schedule an email, such selection is currently done manually. The inconvenience of manual scheduling is accentuated when there are multiple recipients or when a slot for transmission of email is to be selected across time zones. This disclosure describes techniques that automatically schedule the transmission of email based on available information pertaining to the recipients, e.g., information available on recipient calendars, on office productivity software, etc.

Selective Notifications Based On Location And Calendar Information, Jeff Palm

Defensive Publications Series

This disclosure describes techniques to notify individuals that are likely to have been present at a particular location, e.g., a meeting room, based on calendar information, obtained with user permission. For example, a corporate campus can include several meeting rooms with associated calendars that are used for meetings. A person that finds a forgotten item in a meeting room can access a portal to report the item, along with the location and time that the item was found, e.g., via a portal. The portal can then access, with user permission, calendar information of the meeting room and/or other individuals to …

Enhanced Telephony Using Human Inaudible Data Over Voice Channel, Asher Segel-Brown, Stefan Zinke-Allmang, Honna Segel

Defensive Publications Series

A telephone, such as a mobile phone, places a telephone call to another telephone by transmitting a signal (e.g., digital or analog) indicative of a sound wave. The signal indicative of the sound wave encodes sound data over a voice channel. The sound data includes human audible data, such as data indicative of sounds (e.g., voice) captured by a microphone. That is, the frequency of the sound wave that encodes the human audible data is within a frequency range audible by humans. The sound data also includes human inaudible data, such as a telephone number of the calling device, an …

Spoof Detection For Fingerprint Sensors, Firas Sammoura, Jean-Marie Bussat

Defensive Publications Series

This publication describes methods, techniques, and apparatuses that can achieve spoof detection in fingerprint sensors by confirming that a person is present and authorized to gain access to a mobile device, door entrance, vault, application software, physical locations, and/or or virtual activities that the person wants guarded. To do so, machine-learned models may be used to match at least one of a fingerprint residual on the glass covering the fingerprint sensor to a live fingerprint, a fingerprint coloration due to the hemodynamics of the pad of the finger, or a distortion pattern of the fingerprint due to the rotation of …

Virtual Assistant For Planning And Booking Holiday Trips, Miglė Padegimaitė, Sandro Feuz

Defensive Publications Series

Booking and planning holidays is a time consuming activity that is performed multiple times by most users. This disclosure provides a virtual assistant that intelligently simplifies holiday planning and booking. A discovery and booking flow specifically designed for booking holidays is implemented to offer multiple options that the user can choose from at each step, or a limited set of complete plans are displayed based on user requirements determined based on user context, obtained with user permission.

Preprocessing Logic To Enhance Videotelephony Services During Suboptimal Network Conditions, Chinmay Dhodapkar

Defensive Publications Series

This publication describes processes and techniques, implemented on a computing device, directed at enhancing videotelephony services during suboptimal network conditions. In an aspect, a several-stepped process employs a machine-learned technique through which captured frames (e.g., images captured by a videotelephony application) can be segmented and altered, such that an object of interest can be presented with a static background. The entirety of this process referred to herein as preprocessing logic, occurs prior to encoding.

Robust Adhd Testing By Applying Clustering Techniques To Survey Responses Or Speech Data, Lingyi Zhang, Cliff Chin Ngai Sze

Defensive Publications Series

Existing tests for attention deficit hyperactivity disorder (ADHD) may exhibit some bias. Also, these tests require filling in a survey with subjective responses, which can lead to misdiagnosis. The techniques described herein reduce bias in ADHD tests by seeking clusters in test-parameter space conditioned on certain characteristics of a person. Clustering is performed using machine learning techniques. With user permission, speech data is obtained via one or more devices such as a phone, smart speaker, etc. an is used to make objective diagnoses of ADHD.

Dynamically Generated And Targeted Augmented Reality Shopping Campaigns, Aiko Nakano, Diane Wang, Max Spear

Defensive Publications Series

In augmented reality (AR) shopping, a user points a mobile device camera at a specially-designed poster (or other object) and receives information or shopping deals. Today, AR shopping content, e.g., QR-code-based AR or time-triggered ad filters, is largely templated, static, and one-to-one between a specific target and a specific result. A gap exists between users looking at an ad and actually making a purchase. This disclosure describes techniques that enable a suite of dynamically generated and targeted AR shopping campaigns that directly link to products based on inventory conditions. Facility is provided for contextual deals, e.g., location-specific, time-based, and/or chance-based …

Network-Connected Locker Kiosk For Device Delivery, Anonymous

Defensive Publications Series

Many organizations provide devices to various users. The issuance and tracking of such devices can impose a burden on the organization’s information technology group. Further, users may not be able to obtain devices on-demand due to manual processes to issue or return devices. This disclosure provides a smart, network-connected locker kiosk that can identify and authenticate users to issue devices or accept device returns.

Voice Interface For Interaction With Notifications, Victor Cărbune, Thomas Deselaers

Defensive Publications Series

This disclosure describes techniques for a user to interact with notifications using voice commands, e.g., when the user is unable to provide touch inputs to a device, such as when driving, cooking, or engaged in other activities. At an initial stage, templatized voice commands are used and additional commands are learned using machine learning techniques. Actions such as scrolling through notifications, filtering notifications by criteria, dismissing notifications, acting on notifications, etc. are made available via voice commands. Notifications are displayed or read out based on whether the user is in a context where they can view a display. A tutorial …

Virtual Assistant Toy Block With Scanner And Display, N/A

Defensive Publications Series

Toy blocks are used to teach children creativity, vocabulary, arithmetic, and to develop dexterity. Current toy blocks are typically not very interactive. This disclosure describes a toy block that includes a scanner and display, and has a virtual assistant built-in. The virtual assistant provides an interactive educational experience for users. With user and parent permission, the virtual assistant can answer spoken questions and play audio games with users. The toy block enables users to perform visual queries via the integrated camera. Information related to the scanned object is retrieved and provided to the user on the display and/or via audio.

Toy Robot With Customized Virtual Assistant Personality, N/A

Defensive Publications Series

This disclosure describes a toy robot with a customized virtual assistant personality. The virtual assistant is displayed as a face on a robot with a screen. The personality, tone of spoken responses, and the displayed avatar of the virtual assistant can be customized for different users. With user and parent permission, the virtual assistant can use an on-board camera to perform visual searches. The virtual assistant provides responses that include audio and graphics, with little to no text.

Virtual Assistant User Interface With Customizable Personality, N/A

Defensive Publications Series

Current wearable device virtual assistant user response interfaces are primarily text-based and designed for adults. This disclosure describes a virtual assistant for wearable devices that provides audio and/or graphical responses, with little to no text. When the virtual assistant is used by a child, a face of a character is used as the main user interface. The personality of the character, e.g., the tone of the audio response, the character visuals, etc. can be customized by a parent. With user and parent permission, the virtual assistant character can detect and react to the surrounding environment or other cues.

Secure Internet Of Things Onboarding Using Public Key Cryptography And Diffie-Hellman Integrated Encryption Scheme, Niranjan M. M, Nagaraj Kenchaiah, Ramachandra Murthy, Vijay Kothamasu

Defensive Publications Series

Techniques are described for using public key cryptography and blockchain methods to automatically and securely on-board Internet of Things (IOT) devices. This is an improvement over typical approaches in which IOT devices are on-boarded to Wi-Fi® networks with a pre-shared key that could be built-in or configured through out-of-band connectivity (e.g., Bluetooth®, Wi-Fi Protected Setup (WPS), etc.).

Media Access Control Security Key Distribution Using Blockchain And Public Key Cryptography, Niranjan M. M, Nagaraj Kenchaiah, Vijay Kothamasu

Defensive Publications Series

Techniques are described herein for sophisticated authentication and encryption methods that do not require manual configuration or a centralized server. These techniques use blockchain and public key cryptography to exchange Media Access Control security (MACsec) keys securely between router links and thereby by avoid manual configuration for MACsec. This simplifies existing MACsec key configuration approaches, which use static security mode with manually-configured security keys and dynamic security mode with keys distributed from a centralized Authentication, Authorization, and Accounting (AAA) server over Extensible Authentication Protocol Transport Layer Security (EAP-TLS).

Providing Real-Time Captured Information Input To A Machine-Learned Model To Improve Query Services, Perumaal Shanmugam, Felipe Leme, Julian Odell

Defensive Publications Series

This publication describes techniques and methods that a computing device uses to provide improved query services (e.g., autofill suggestions, speech biasing for automatic speech recognition) to applications on the computing device. To this end, an information collector on the computing device collects application activity information, information displayed on a display, and event information. This collected information can be provided as input to a machine-learned model implemented on the computing device. Responsive to the input received, the machine-learned model can classify the collected information to determine relevant attributes (e.g., keywords, searched locations, names) and make suggestions for utilization by query services …

Signal Quality-Based Buffering Of Media Data Using An Intermediate Device, Jonathan Hurwitz

Defensive Publications Series

This publication describes systems and techniques to buffer media data at an intermediate device based on a channel quality between a media source device and a media presentation device. In some environments with significant user movement, such as the gym or home, media packets may be dropped because a condition of a radio-frequency (RF) channel becomes worse over time. Consequently, media presentation may be interrupted. Users often have, however, multiple devices with different amounts of resources. For example, a user may have a smartphone, a smartwatch, and wireless headphones. The latter two are typically carried on a user’s person, but …

Robo-Calling Prevention With Software-Defined Networking In A Wide Area Network Policy For Unified Communication, Balaji Sundararajan, Anand Oswal, Vivek Agarwal, Rong Wang, Palak Desai

Defensive Publications Series

Techniques are described herein for blocking robo-calls, spam calls, and telemarketing calls, which are becoming an industry menace. Such calls are blocked by tightly integrating a Software-Defined Networking in a Wide Area Network (SDWAN) controller with a Do Not Call registry. Analytics are used to analyze traffic call patterns, security insights are leveraged such as known malicious Internet Protocol (IP) and domain addresses, and a Call Barring feature may also be applied. This information may be pushed to edge devices to ensure robo-calls do not terminate on SDWAN-led voice endpoints.

Tur As An Input Device To Communicate With The Printer, Hp Inc

Defensive Publications Series

Large format printers that are capable of printing in roll‐to‐roll mode usually have a Take‐Up Reel

(TUR) that is located in a low position of the printer. For this reason, if the user wants to operate the

TUR, usually it has to bend down to a position from where it is not possible to reach the front panel

of the printer. In these cases, during TUR operation it is not possible to command the printer unless

there are some devices in the TUR module (such as buttons, levers, switches, … that allow the user

to do it. Generally, though, these …

Measuring And Visualizing User Sentiment Changes Over Multiple Channels, Xinjun Zhang, Qihong Shao, Changyong Zhao, Antonio Nucci

Defensive Publications Series

Techniques are provided to simultaneously infer approximately where a speaker is looking and the speaker's emotion during a conversation. Due to privacy concerns, only the speaker's approximate facial features may be estimated. The inferred face may be converted into a cartoon face that retains the main facial features. This may enhance user interaction experience even when a speaker does not turn on video in teleconference.

The Use Of Discontiguous Interposers To Stack Multiple Printed Circuit Boards, Reza Ghajar, Vijay L. Asrani

Defensive Publications Series

This publication describes systems and techniques directed to the use of discontiguous interposers to facilitate the stacking of multiple printed circuit boards (PCBs). In some aspects, an architecture of a subassembly of a system is described that uses the discontiguous interposers to stack multiple PCBs. The architecture is beneficial to heat transfer characteristics while accommodating electromagnetic shielding performance needs of the system. In other aspects, a manufacturing technique is described that panelizes the discontiguous interposers in a fashion that results in manufacturing efficiency gains.

Adaptive Biasing Of Radio-Frequency Power Amplifiers, Ming Sun, Fei He, Mike Kincaid

Defensive Publications Series

Radio-frequency (RF) power amplifiers (PA) have a nearly linear response only at small input amplitudes, with their outputs gradually saturating as input amplitudes increase. This slightly sub-linear transfer characteristic gives rise to out-of-band emissions, which can potentially interfere with other users of the RF spectrum. Regulatory requirements place limits on the maximum out-of-band emissions by a device. In turn, these translate to operating the PA at a highly linear region, e.g., at low input amplitudes compared to the dynamic range of the PA. However, low input amplitudes are associated with low PA efficiencies. This disclosure describes techniques to adapt the …

Switch Strategy For Smart Utility Network Orthogonal Frequency-Division Multiplexing Phy Based On Reinforcement Learning In Low-Power And Lossy Networks, Ling Wei, Wenjia Wu, Chuanwei Li, Leo Yu

Defensive Publications Series

Techniques are described herein for a switch strategy based on actor-critic reinforcement learning. This depends on not only the Received Signal Strength Indicator (RSSI) and packet loss rate but also on the distribution of error segments in a packet. The states, actions, and values for the actor-critic model may be defined to fit the switch strategy. The mechanism of dynamical adjustment may depend on the different PHY formats.

Warning Mobile Device Camera Users Of Potential Dangers, N/A

Defensive Publications Series

This publication describes methods of warning a user of a mobile device camera application of potentially dangerous locations and situations. In aspects, a danger warning manager on the mobile device acquires context signals (e.g., captured images, global navigation satellite system location information, social media history for a location) and analyzes these context signals to determine a level of risk. Upon determining that the user is potentially in danger, the danger warning manager causes the mobile device to present warning notifications to the user.