公开(公告)号：US11606139B2

公开(公告)日：2023-03-14

申请号：US17195160

申请日：2021-03-08

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Ricky Perry

IPC: H04B10/071 ,  H04J14/02 ,  G01M11/00 ,  H04J3/16

Abstract: Aspects of the subject disclosure may include, for example, determining distinct timing offsets between an input port and output ports of a multiport optical device. An optical signal is injected at an input port of the device to obtain output signals at the output ports, which are injected into downstream fibers. An optical multipath return signal is received via the input port of the device, including a combination of measured events including reflections, backscatter, or both. A number of similar events expected in the number of downstream optical fibers is calculated to obtain an expected multipath signature based on configuration data. Results of the optical multipath return signal are then compared to the expected multipath signature to obtain comparison results. One of the measured events is distinguished from the others based on the first comparison results and the distinct timing offsets. Other embodiments are disclosed.

公开(公告)号：US20230075113A1

公开(公告)日：2023-03-09

申请号：US18055338

申请日：2022-11-14

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Vivek Kumar Rangarajan Sridhar

IPC: G06F40/232 ,  G06F40/58

Abstract: A system, method and computer-readable storage devices for providing unsupervised normalization of noisy text using distributed representation of words. The system receives, from a social media forum, a word having a non-canonical spelling in a first language. The system determines a context of the word in the social media forum, identifies the word in a vector space model, and selects an “n-best” vector paths in the vector space model, where the n-best vector paths are neighbors to the vector space path based on the context and the non-canonical spelling. The system can then select, based on a similarity cost, a best path from the n-best vector paths and identify a word associated with the best path as the canonical version.

公开(公告)号：US20230073668A1

公开(公告)日：2023-03-09

申请号：US17986289

申请日：2022-11-14

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Joseph Soryal

IPC: H04L9/40 ,  G06F9/455 ,  H04J3/06

Abstract: A man-in-the-middle protection module can monitor data traffic exchanged between a source and destination nodes over a source-destination link via a network. The module can utilize a traffic probe packet to determine a packet delay associated with the data traffic. The module can store the packet delay and can determine that the packet delay is greater than a normal packet delay. If so, the module can determine that an attacker has compromised the source-destination link. The module can command a virtual machine associated with the source node to be decommissioned. The module can instruct a virtualization orchestrator to create a new source node. The data traffic can be rerouted to be exchanged between the new source node and the destination node over a new source-destination link via the network. The module can create and send fake data traffic towards the MitM attacker over the source-destination link via the network.

公开(公告)号：US20230071309A1

公开(公告)日：2023-03-09

申请号：US17466084

申请日：2021-09-03

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Paul Giura ,  Mikhail Istomin

IPC: H04L29/06

Abstract: A method for privacy preserving vulnerability detection for devices. In an example, an apparatus may include a processor and memory coupled with the processor that effectuates operations. The operations may include receiving a type of a device; receiving a feature for the device; creating a first hash value based on the device type and the feature; receiving an indication that the first hash value matches a second hash value; and based on the indication that the first hash value matches the second hash function, sending an alert that the device has a vulnerability.

公开(公告)号：US20230071237A1

公开(公告)日：2023-03-09

申请号：US18056283

申请日：2022-11-17

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Zhi Cui ,  Paul Smith, JR. ,  Farooq Bari

IPC: H04L45/00 ,  H04W28/02

Abstract: Unlike smart devices, Internet of things (IoTs), such as meter readers, generate very low revenue per user. Traditional tunnel/bearer based connection-oriented architectures do not scale economically for billions of IoT devices due to the amount of signaling overhead associated with GTP tunnel setup/tear down and the states related to GTP tunnels maintained at various parts of the mobile network. However, the mobility network can efficiently support massive stationary and/or mobile IoTs by reducing the amount of signaling overhead, the state of the IoTs kept in network, and simplifying the data plane when possible.

公开(公告)号：US11601209B2

公开(公告)日：2023-03-07

申请号：US17104759

申请日：2020-11-25

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Jeffrey B. Saxon ,  Brian Lois ,  Abhay Dabholkar ,  Muhammad Farooq Sabir

IPC: H04W4/00 ,  H04B17/391 ,  G06N3/04 ,  H04W4/02 ,  H04B17/318

Abstract: The technologies described herein are generally directed to modeling radio wave propagation in a fifth generation (5G) network or other next generation networks. For example, a method described herein can include based on a graphical representation of a layout of a geographic area, identifying, by equipment comprising a processor, a feature of the geographic area relevant to propagation of a signal propagated from a signal point on the layout, resulting in an identified feature. The method can further comprise based on the identified feature and the signal point, generating, by the equipment, a feature map for the geographic area by employing a neural network, wherein the feature map comprises a map depicting estimates of the propagation of the signal at locations within the geographic area.

公开(公告)号：US20230069178A1

公开(公告)日：2023-03-02

申请号：US17463817

申请日：2021-09-01

Applicant: AT&T Intellectual Property I, L.P. ,  The University of Connecticut

Inventor： Subhabrata Sen ,  Bing Wang ,  Yanyuan Qin

IPC: H04L29/06 ,  H04L12/14 ,  H04L12/811

Abstract: Aspects of the subject disclosure may include, for example, embodiments that comprise obtaining a data budget associated with a communication session for streaming video content over a communication network from a video content server, determining a first portion of the data budget that is associated with a first segment of the video content, and obtaining quality information associated with the video content from the video content server over the communication network. Further embodiments can include identifying a first group of tracks for the first segment, and determining a first target quality for the first segment based on the first portion of the data budget and the quality information. Other embodiments are disclosed.

公开(公告)号：US20230064719A1

公开(公告)日：2023-03-02

申请号：US17410721

申请日：2021-08-24

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Huahui Wang ,  Yuning Yang ,  Ye Ge ,  Wenjie Zhao

IPC: H04W28/20 ,  H04W72/08 ,  H04W16/10 ,  H04W16/18 ,  H04W24/02

Abstract: Intelligent, automated, fixed wireless internet planning (e.g., using a computerized tool) is enabled. For instance, a system can comprise a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising: determining, for a user equipment determined to be within a defined coverage area, a signal to interference and noise ratio, based on the signal to interference and noise ratio, determining a spectral efficiency value corresponding to the user equipment, based on the spectral efficiency value and a total available bandwidth of a network via which the defined coverage area is enabled, determining an available throughput corresponding to the user equipment, and in response to a determination that the available throughput exceeds a threshold throughput, designating the user equipment, in a data store, as being covered within the defined coverage area by the total available bandwidth of the network.

公开(公告)号：US20230063988A1

公开(公告)日：2023-03-02

申请号：US18045451

申请日：2022-10-10

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Jean-Francois Paiement ,  David Crawford Gibbon ,  Tan Xu ,  Eric Zavesky

IPC: H04R1/10 ,  G06F3/01 ,  G10L17/06

Abstract: A processing system including at least one processor may capture data from a sensor comprising a microphone of a wearable device, the data comprising external audio data captured via the microphone, determine first audio data a first audio source in the external audio data, apply the first audio data to a situational detection model, and detect a first situation via the first situational detection model. The processing system may then modify, in response to detecting the first situation via the first situational detection model, the external audio data via a change to the first audio data in the external audio data to generate a modified audio data, in accordance with at least a first audio adjustment corresponding to the first situational detection model, where the modifying comprises increasing or decreasing a volume of the first audio data, and present the modified audio data via an earphone of the wearable device.

公开(公告)号：US20230063510A1

公开(公告)日：2023-03-02

申请号：US18045461

申请日：2022-10-10

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Bo Han ,  Vijay Gopalakrishnan ,  Tan Xu

IPC: H04N21/218 ,  G06F3/01 ,  G06F3/04815 ,  H04N19/597 ,  G06N20/20 ,  H04N19/17

Abstract: A method for streaming a 360 degree video over a communications network, wherein the video is streamed in a plurality of chunks, includes selecting a prediction window during which to predict a field of view within the video, the field of view is expected to be visible by a viewer at a time of playback of a next chunk of the video, wherein a duration of the prediction window is based on at least one condition within the communications network, selecting a machine learning algorithm to predict the field of view based on a head movement of the viewer, wherein the machine learning algorithm is selected based on the duration of the prediction window, predicting the field of view based on the head movement of the viewer and the machine learning algorithm, identifying a tile of the next chunk that corresponds to the field of view, and downloading the tile.