At&t Intellectual Property I, L.p.

At&t Mobility Ii LLC

Hyundai Motor Company

Kia Corporation

At&t Global Network Services Belgium Luxembourg Sprl

James H Pratt

Eric Martin Zavesky

Marc Andrew Sullivan

Steven M Belz

Nigel Bradley

Ari Craine

Timothy Innes

Robert A Koch

Behzad Shahraray

Robert Raymond Miller, Ii

Horst Juergen Schroeter

Yupeng Jia

Troy C Meuninck

Kevin Ansia Li

Gregory Wesley Edwards

Michael Lattanzi

Constance Missimer

Nikhil Shreerang Marathe

Keith Aubrey Crowe

Barrett Morris Kreiner

Walter Cooper Chastain

Robert Torrence Moton, Jr

Adrianne Binh Luu

Randolph Wohlert

Jason Decuir

Paul Van Vleck

Garrett L Stettler

Sarah Everett

Greg W Edwards

Miranda Huet

Donald Perciful

James Jackson

John Oetting

Terrel Lecesne

Michael Gonzales

Bhumit Patel

Robert Gratz

David Crawford Gibbon

Milap V Majmundar

Robert Dailey

Martin Patrick McEnroe

William Knotts

Aaron Bangor

Mark Stockert

Guido Corona

Curtis Stephenson

Linda Baughman

Pamela Stuckman

Elizabeth Pratt

Sanjiv Singh

Parimal Pandya

Emily Williams

Zhi Cui

Larry B Pearson

Kurt M Joseph

Eric Petajan

Prince Paulraj

Abhay Dabholkar

Roger Drew Wickes

Wiley C Wilkins

Ni An

Kelly Dowd

Prateek Baranwal

Nicholas Cassioppi

Taylor Gift

Jing Sasha Guo

Jessica R Owensby

Vladimir Sevastyanov

Barkha Pathik Patel

Nikhlesh Agrawal

Seyed Amir Mir Bagheri

Vivek Rajasekharan

Samir Bhatt

James Carlton Bedingfield, Sr

Jeffrey L Brandt

Virginia Seid Ng

Jeffrey Paul Johnson

Ana Armenta

Edmond J Abrahamian

Subhabrata Majumdar

Abhigyan Sharma Abhigyan

John R Craig

Christopher Kim

Christophe Closset

Michael R Albrecht

Antoine Diffloth

Paul Carver

Sherry Simon

Rakhi Gupta

Catherine Lefèvre

Jason Allen DeCuir

Morgan Friske

Robert F Williams

Terrel Michael LeCesne

Cuong Vo

Prathiba Sugumaran

Brian Bachman

Kostikey Mustakas

Michael L Hunter

Andrew Kell

A method performed by a processing system including at least one processor includes detecting that new data has been added to a repository of reusable machine learning models and machine learning model features, applying data protection to the new data, testing the new data for bias, merging at least a portion of the new data with stored data from the repository to build a new machine learning model in which the data protection is preserved, and publishing the new machine learning model in the repository.

Governance mechanisms for reuse of machine learning models and features

The technologies described herein are generally directed to allocating a resource to perform a task based on a predicted capacity of the resource. For example, a method described herein can include identifying a selected capacity associated with completion of tasks of a particular task type. Further, the method can include, evaluating a result of work by a worker resource performing a task of the particular task type. The method can further include, based on the result, predicting that the worker resource has the selected capacity and, based on this prediction, assign the worker resource to perform another task of the particular task type.

Utilization of a resource to perform a task based on a predicted capacity of the resource

A processing system may determine a plurality of aspects of a trip of a user, each of the plurality of aspects associated with a travel service provider of a plurality of travel service providers, identify a plurality of travel service provider applications that are available on the mobile computing device and that are associated with the plurality of travel service providers, and obtain an authorization of the user of the mobile computing device to interact with the plurality of travel service provider applications in connection with the trip. The processing system may then detect an event associated with the trip and perform, in response to detecting the event, at least one task via a second travel service provider application using a first set of data from at least a first of the plurality of travel service provider applications, where the second travel service provider application is available on the mobile computing device.

Mobile device cross-service broker

Services for trust conveyances of entities can be provided and managed. In connection with a transaction between first and second devices, a trust management component (TMC) can indicate trust levels of entities associated with the devices with regard to the transaction and/or an action attempted by an entity. With regard to an action attempted by the first entity, the trust level of the first entity can be evaluated to determine whether it is high enough to allow the action to proceed or to have the second entity respond to the action accordingly. If it is not high enough, the second entity, using the second device, can request a trust conveyance from the first entity via the TMC. The TMC can adjust the respective trust levels based on the outcome(s) of the action(s) of the respective entities with regard to executing the transaction.

Services for entity trust conveyances

Aspects of the subject disclosure may include, for example, a device that has a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including receiving a request for an observation of an overhead viewing area from an observer location; discovering an interference of a satellite with the observation of the overhead viewing area; determining possible solutions to the interference; selecting a solution of the possible solutions; receiving the observation from one or more satellites responding to the solution selected; and providing a response to the request including the observation received. Other embodiments are disclosed.

System and method for satellite-based masking and amplification

Concepts and technologies disclosed herein are directed to anticipatory supply chain coordination with connected vehicle fleet and unmanned aerial vehicle ('UAV') integrations. According to one aspect disclosed herein, an energy provider system can obtain connected vehicle information from a connected vehicle. The connected vehicle information can include a vehicle identifier that uniquely identifies the connected vehicle, an energy capacity remaining for the connected vehicle, and a current location of the connected vehicle. The energy provider system can obtain order information from an inventory management system. The order information can include a destination location to which a physical order is to be delivered. The energy provider system can determine a route to the destination location based, at least in part, upon the energy capacity remaining and the current location. The energy provider system can then provide the route to the connected vehicle.

Anticipatory supply chain coordination with connected vehicle fleet and unmanned aerial vehicle integrations

A processing system including at least one processor may obtain at least a first identifier associated with an endpoint device of a user at a location, determine, based on the at least the first identifier, that the user is an authorized participant of at least one service at the location, and provide an identity token to the endpoint device, where the identity token is for use at the location in connection with the at least one service, provide to the endpoint device a list of other identity tokens associated with endpoint devices of other users at the location, detect a communication between the endpoint device of the user and an endpoint device of the other user in accordance with the identity token and another identity token, from among the other identity tokens, and record information characterizing the communication in an electronic ledger associated with the at least one service.

Temporary identifiers for network and service access and for transaction recordation

The described technology is generally directed towards emotion detection and translation for electronic communications. An emotional state of a first communication participant can be detected, e.g., through face recognition, biometric information, and/or communication content analysis. The emotional state can be encoded in metadata that can accompany the communication content. The metadata can be translated into one or more embellishments that represent the emotional state, and the embellishments can be inserted into the communication content. The embellished communication content can then be delivered to a second communication participant.

Emotion detection and translation for electronic communications

Methods, computer-readable media, and systems for enhancing food service operations using Internet of Things-enabled dinnerware are disclosed. One method performed by a processing system including at least one processor includes obtaining data about a food item that is being prepared for a consumer, forwarding the data about the food item to an internet of things-enabled item of dinnerware, receiving, from the internet of things-enabled item of dinnerware, data about consumption of the food item by the consumer, and providing feedback to an endpoint device of a person who prepared the food item for presentation to the person who prepared the food item, in response to the data about the consumption of the food item by the consumer.

Internet of things-enabled dinnerware to enhance food service operations

Aspects of the subject disclosure may include, for example, identifying an uncrewed aerial vehicle (UAV) for route planning and power management, obtaining information regarding the UAV, a present location of the UAV, a destination location for the UAV, or a combination thereof, determining, based on the information, a need for the UAV to recharge a power source of the UAV as part of a journey of the UAV from the present location of the UAV to the destination location for the UAV, responsive to the determining the need, identifying a recharging station associated with a network for recharging the power source of the UAV, and calculating a flight path for the UAV in accordance with the identifying the recharging station. Other embodiments are disclosed.

Method and system for routing/orchestration/management of aerial vehicles or data on a network

The technology described herein is generally directed towards determining that a user is passively attending a meeting via a connected device, collecting data created during the meeting, and outputting information based on the collected data for the user to monitor the meeting. Join criteria can be associated with passive meeting attendee, and if the collected meeting data satisfies the join criteria, the attendee can transition to an active attendee. Keyword data can be used to represent information relevant to a meeting attendee. Based on collected and monitored meeting data presented during the meeting and the keyword data, the meeting can be determined to have reached a relevance/pertinence level by which action is taken to change the user from a passive attendee to an active attendee. This can include a transition period that allows a user to catch up on previous meeting information before becoming an active attendee.

Virtual meeting management

Concepts and technologies disclosed herein are directed to automated optimization of events by engagement and format. According to one aspect disclosed herein, an event management system can create an event for a specified topic based upon input provided, at least in part, by an event creator. The input can identify initial event content, a plurality of event attendees, a location for the event, and an event presenter. The event management system can receive a selection of a desired audience for the event. The event management system can accept the initial event content to be presented during the event and can determine a time for the event. The event management system can perform engagement sampling during the event. The event management system can utilize the selection, the time, and the engagement sampling to optimize the event. The event management system can determine a follow-up action to be performed after the event.

Automated optimization of events by engagement and format

The disclosed technology is directed towards detection of personal threats to a user based on information known to a user's device and other information. A device with a personal threat application program and server communicate information, including data describing the user's current physical situation, e.g., including current location. The server and/or application program obtain data describing environmental conditions around the user's location, e.g., corresponding to a defined personal zone. The personal zone size automatically can vary based on current factors. Based on the situation and environmental data reaching a threshold threat level, a potential threat to the user can be predicted and the prediction, used to take some action, such as to send an alert to the user and/or otherwise output a warning signal. Historical data such as statistics related to the user's current location can be accessed to assist with the prediction.

Predictive personal threat levels via user device

Facilitating selection of the most significant set of categorical features in machine learning is provided herein. Operations of a system include determining a list of unique values of a categorical variable. The operations also include calculating respective mean values, of a target variable, for unique values of the list of unique values of the categorical variable. Further, the operations include sorting the list of unique values by the respective mean values, resulting in a sorted list. The operations also include calculating respective derivatives of the respective mean values in the sorted list considering the respective mean values as a function and a number of the respective mean values in the sorted list as an independent variable. Additionally, the operations include determining a minimum derivative value over the sorted list and outputting the minimum derivative value as a resulting variable significance value.

Facilitating selection of categorical features in machine learning

A processing system including at least one processor may obtain a first input data set associated with a telephone number from a first service provider that implements a multi-factor authentication process for permitting an access to a service of the first service provider and may apply at least the first input data set to a machine learning model implemented by the processing system to obtain a risk score associated with the telephone number for a subscriber identity module swap of a subscriber identity module, where the machine learning model is trained to generate the risk score associated with the telephone number in accordance with at least the first input data set. The processing system may then perform at least one remedial action associated with the telephone number and the subscriber identity module, in response to the risk score.

Machine learning model feature sharing for subscriber identity module hijack prevention

Growing community of inventors

Round Rock, TX, United States of America

James H Pratt