At&t Intellectual Property I, L.p.

At&t Mobility Ii LLC

Martin Patrick McEnroe

Eric Martin Zavesky

James H Pratt

Joshua Whitney

Joshua West

Sanjiv Singh

Gary Brian Temerowski, Ii

Rhonda Green

Mark D Austin

Yuan Ding

Tzvi Chumash

Ni An

Yunmiao Wang

Jason Decuir

Robert Gratz

Lauren Savage

Andrew Vishnyakov

William Knotts

Hristo Hristov

Kelly Dowd

Aarthi Reddy

Prateek Baranwal

Daniel Flynn

Anna Kay Rice

Ranjan Gupta

Jun Yan

Jami Carter Brooks Daly

Jami Daly

John Boehm

In a dataset exchange environment in which datasets are available for exchange or transformation, a dataset validation platform may be configured to update a cryptographically signed record based on each dataset that is available via the data exchange environment. The dataset validation platform may be further configured to control access to the datasets based on whether a request to access a particular dataset is compliant with an availability requirement of the particular dataset. The dataset validation platform may be further configured to update the cryptographically signed record based on requests to access the datasets, transformations that are based on the datasets, or modifications to the availability requirement of the datasets, such as a modification to a privacy limitation or other availability requirement indicating a criteria for usage of the requested dataset.

Controlling access to datasets described in a cryptographically signed record

An example method, executed by a processing system, includes receiving data from a data source, routing the data to a plurality of different data labelers to label the data, determining that an inflection point associated with an accuracy of the plurality of different data labelers is reached, re-routing additional data from the data source to a machine learning model, and activating the machine learning model to label the additional data.

Machine learning models with accurate data labeling

The present disclosure describes various methods, computer-readable media, and apparatuses for supporting customer service automation. The support for automation of customer service may be based on analysis of conversations between customers and customer service agents of a customer service center. The support for automation of customer service may be based on analysis of conversations between customers and customer service agents to identify conversation-level topics and utterance-level topics from the customer service conversations. The support for automation of customer service may be based on use of conversation-level topics and utterance-level topics identified from the customer service conversations to control initiation of customer service automation actions for supporting automation of customer service of the customer service center. The support for automation of customer service may be based on use of conversation-level and utterance-level topics identified from the customer service conversations to control selection, and design, of chatbots for the customer service center.

Supporting automation of customer service

A method and apparatus for detecting a photoacoustic light signal to prevent unauthorized voice commands for a microphone-controllable device are provided. The method includes receiving, by a processor, a signal, detecting, by the processor, that the signal is a photoacoustic signal generated by a thermal expansion and contraction of an object caused by at least one lightwave applied to the object, and activating, by the processor, a counter-measure to prevent the photoacoustic signal from reaching a microphone of a microphone-controllable device in response to detecting the photoacoustic signal.

Signal detection system for improved microphone-controllable device security

A method includes determining that a prioritized vehicle plans to traverse an intersection and receiving sensor data from a plurality of sources in a vicinity of the intersection. The method also includes, based on the sensor data, determining a traffic solution to enable the prioritized vehicle to traverse the intersection, the traffic solution identifying a traffic lane and, based on the traffic solution, controlling a traffic light to cause traffic in the traffic lane to disperse and controlling a second traffic light to instruct traffic in an adjacent traffic lane to stop. The method includes instructing the prioritized vehicle to travel via the traffic lane. The traffic in the traffic lane and the traffic in the adjacent traffic lane are traveling in a same direction.

Dynamic edge network management of vehicular traffic

Facilitating pre-positioning of streaming content onto communication devices is provided herein. A system can comprise a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations. The operations can comprise facilitating an identification of a first multimedia content stream and a second multimedia content stream. The identification can be based on a usage preference of a defined entity associated with a communication device. The operations can also comprise, in response to a determination that an available network satisfies a defined network criterion, facilitating pre-positioning, at a data store of the communication device, the first multimedia content stream and the second multimedia content stream.

Pre-positioning of streaming content onto communication devices for future content recommendations

The present disclosure describes various methods, computer-readable media, and apparatuses for supporting automation of customer service. The automation of customer service may be based on support for automation of conversations between customers and customer service agents. The automation of customer service based on support for automation of conversations between customers and customer service agents may be based on use of images provided by the customers to control the conversations between customers and customer service agents. The support for automation of conversations between customers and customer service agents based on use of images provided by the customers may include processing the images to obtain information for the conversations between the customers and the customer service agents and controlling the conversations between the customers and the customer service agents based on the information for the conversations between the customers and the customer service agents.

Supporting conversations between customers and customer service agents

A visual indicator system includes a sensor system, a visual indicator, a processing system coupled to the sensor system and the visual indicator, and a memory system that is coupled to the processing system and that includes instructions that, when executed by the processing system, cause the processing system to provide a visual indicator module. The visual indicator module receives first sensor data via the sensor system and determines based on the first sensor data that a first condition is satisfied. In response to the first condition being satisfied and via a first portion of the visual indicator, the visual indicator module provides a first visual indication that is associated with the first condition to a physical environment.

Autonomous vehicle signaling system

A method for providing training data for a machine learning model includes: monitoring a specific user as the specific user reads electronic documents on a display to determine indications of pauses in reading for greater than a specified period of time; correlating objects on each of the displayed plurality of electronic documents to the pauses in reading; identifying features for the machine learning model based on the objects and textual analysis of each of the plurality of electronic documents; presenting information related to each identified feature to the specific user; obtaining from the specific user a descriptor defining each of the identified features and a value for each of the identified features indicating a relative importance or applicability of each of the identified features; and associating obtained descriptors and values with each of the identified features.

Document analysis using machine learning and neural networks

A trust-less system for sharing event information among autonomous nodes may include: a plurality of autonomous nodes, each of which creates an event related to a condition, a first ledger configured to collect and store a record of each event; a second ledger configured to store reputation information for the plurality of autonomous nodes; and a bookmaker module operable to determine a reward and a penalty for each event. The bookmaker module may be operable to modify the reputation information based on a status of the condition determined by subsequent events created by autonomous nodes where the subsequent events either validate or invalidate the condition.

Method and system for stake-based event management with ledgers

Concepts and technologies disclosed herein are directed to a field-programmable gate array ('FPGA')-based biometric sampling system for improving biometric data reusability. The system can include one or more FPGAs, each of which can include a plurality of configurable input/output ('I/O') blocks, a plurality of configurable logic blocks, and a plurality of configurable interconnects that connect the plurality of configurable I/O blocks to the plurality of configurable logic blocks. The FPGA(s) can be configured based upon a hardware description language model to receive biometric input data associated with a user, to apply a sampling scheme to the biometric input data to extract, from the biometric input data, an enrollment biometric data sample, and to cause the enrollment biometric data sample to be stored in a database.

Field-programmable gate array-based biometric sampling system for improving biometric data reusability

A traffic management system that manages policy agreements between operators and visual indicator devices receives first sensor data from a physical environment. The traffic management system computationally processes the first sensor data to identify a first visual indication in the sensor data and determines that the first visual indication is associated with first policy agreement. The traffic management system then determines, based on the first sensor data, that a first visual indicator system that provided the first visual indication is violating a first policy included in the first policy agreement and, in response, provides a policy violation notification that the first visual indicator system is violating the first policy.

Traffic management system

Various embodiments disclosed herein provide for adjustment of throughput threshold of network devices based on requested quality of service received from a mobile device. According to some embodiments, a system can comprise receiving request data representative of a throughput adjustment request for a throughput adjustment. The system can further comprise, based on the throughput adjustment request, determining a connection device that is compelled to adjust throughput, and in response to the determining the connection device that is compelled to adjust throughput and based on the throughput adjustment request, requesting the connection device to adjust a throughput range from a first throughput range to a second throughput range.

Growing community of inventors

Plano, TX, United States of America

Martin Patrick McEnroe