T-mobile Usa, Inc.

Meta Platforms Technologies, LLC

Ting Zhang

Le Roy Munar

Tanya Renee Jonker

Hrvoje Benko

Muhammad Tawhidur Rahman

Pablo Tapia

Prem Kumar Bodiga

Sudhanshu Pandey

Aakar Gupta

Vikas Ranjan

Aditi Saluja

Arundhati Ghosh

Xiao Zhang

Huijae Kim

Dawn Donnenwirth

Juan Murillo Pacheco

Baquer Ali Chabuk Savar

Doris Ho

Marcello Giordano

Raymond Wu

Piradee Nganrungruang

Anastasios Kostopoulos

Peiqi Tang

Tianyi Wang

Maozheng Zhao

Ran Tan

Alec Pierce

Sebastian Freitag

Naveen Sendhilnathan

The disclosed computer-implemented method may include capturing, by a computing device, a current position of a wearable device and a current position of user eye gaze at a current time. The method may also include determining that a user eye gaze is at a fixation position based on a speed of gaze movement. Additionally, the method may include calculating a direction of cursor movement by comparing a current cursor position with a previous cursor position at a previous time. Furthermore, the method may include calculating a likelihood of the fixation position being a target cursor position based on a difference between the direction of cursor movement and a direction from the current cursor position to the fixation position. Finally, the method may include increasing a speed of cursor movement toward the fixation position based on the likelihood. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods for gaze-assisted gesture control

Techniques for adaptively visualizing content in an artificial environment based on the attention of a user. In one particular aspect, a computer-implemented method is provided that includes obtaining input data from a user, inferring content that is of interest to the user based on features gathered from the user's attention in the input data, identifying virtual content data based on the content that is of interest to the user, determining modifications to be applied to the virtual content data based on relevancy, applying the modifications to the virtual content data to generate a final format for the virtual content data, and rendering virtual content in the extended reality environment displayed to the user based on the final format for the virtual content data. The virtual content rendered from relevant virtual content data is more prominently displayed as compared to the virtual content rendered from semi-relevant and non-relevant virtual content data.

Attention-based content visualization for an extended reality environment

In particular embodiments, a computing system may receive an image comprising one or more virtual elements associated with a virtual environment and one or more real-world elements associated with a real-world environment. The system may determine a first metric and a second metric indicative of a measure of clutter in the virtual environment and the real-world environment, respectively. The system may determine gaze features associated with a user based on a user activity and predict, using a machine learning model, a reaction time of the user based on the gaze features. The system may determine a third metric indicative of the measure of clutter in the image based on predicted reaction time. The system may compute an overall clutter metric based on the first, second, and third metrics. The system may perform one or more actions to manage the clutter in the image based on the overall clutter metric.

Managing visual clutter in artificial reality environments

The disclosed computer-implemented method may include (1) receiving information associated with a real-time output of a recognition model adapted to recognize at least one behavior of a user, (2) determining, based on the information, a level of uncertainty associated with the real-time output, (3) modulating at least one attribute of feedback based on the level of uncertainty, and (4) presenting the feedback to the user substantially contemporaneous with the real-time output of the recognition model. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods for communicating recognition-model uncertainty to users

Presented here is a method to predict whether a user of a wireless telecommunication network will report a problem or issue associated with the wireless telecommunication network. A processor can obtain multiple key performance indicators (KPIs) describing a user experience with the wireless telecommunication network. The processor can calculate at least a daily value of each KPI according to a rule specific to the KPI. The processor can create an image representing a value of each KPI, where a first axis of the image identifies the KPI, and where a second axis of the image represents the daily value of the KPI. The processor can predict whether the user of the wireless telecommunication network will report the problem by providing the image to a machine learning model and receiving a prediction from the machine learning model whether the user of the wireless telecommunication network will report the problem.

Predicting whether a user of a wireless telecommunication network will report a problem

The disclosed system identifies and resolves telecommunication network problems and/or problems with devices utilizing the network. The system segments the user devices into groups having similar characteristics, by grouping together devices more likely to leave the network, and devices less likely to leave the network. Each group of devices has a trained machine learning model, to predict the NEX score for each device. The system focuses on devices with a low NEX score. The system determines whether the problem is with the network and/or the problem is with the device. The system gathers information from network monitoring software and determine which tower caused, for example, the call to drop. The system determines technological capability of the device from the device TAC number. The system suggests solutions to the network problems by suggesting adding a sector, tuning an antenna, etc., or if the device has problems, adjusting phone settings.

Identifying and resolving telecommunication network problems using network experience score

Presented here is a method to predict whether a user of a wireless telecommunication network will report a problem associated with the wireless telecommunication network. A processor can obtain multiple key performance indicators (KPIs) describing a user experience with the wireless telecommunication network. The processor can calculate at least a daily value of each KPI according to a rule specific to the KPI. The processor can create an image representing a color-coded value of each KPI, where a first axis of the image identifies the KPI, and where a second axis of the image represents the daily value of the KPI. The processor can predict whether the user of the wireless telecommunication network will report the problem by providing the image to a machine learning model and receiving a prediction from the machine learning model whether the user of the wireless telecommunication network will report the problem.

Described herein are one or more self-organizing network (SON) components configured to determine QoS factors associated with QoS classes for a node of a telecommunication network based at least in part on performance metrics, network configuration, or network fault information. The one or more SON components may receive the performance metrics, network configuration, or network fault information from the node, and the performance metrics, network configuration, or network fault information may be associated with communication of traffic of the QoS classes by the node. Upon determining the QoS factors, the one or more SON components may transmit indications of the QoS factors to the node.

Performance-based optimization of QoS factors

A system and method for improving network coverage is discussed herein. The system and method can improve network coverage based on lack of coverage key performance indicators generated by disconnection data when user equipment (UE) disconnects from and reconnects to a wireless network. The system determines if the disconnection is associated with a lack of coverage by the wireless network or some other reason. When the disconnection is due to lack of coverage, once the UE reconnects to the wireless network, lack of coverage data associated with the lack of coverage can be used to generate key performance indicators which can be used to improve network coverage. For example, an additional network site can be added to the network, a network site operating parameter can be adjusted, or the like.

Telecommunications network coverage

Systems and methods are described herein for determining dropped call rates (DCR) for various communications networks, such as IP Multimedia Networks (IMS), which include Voice over LTE (VoLTE) networks. For example, the systems and methods utilize data (e.g. abnormal cause codes) generated by layers of the IMS networks, such as a Session Initiation Protocol (SIP) layer of the IMS network, when determining dropped call rates for IMS networks.

Determining dropped call rates in IP multimedia networks

Systems and methods are described herein for analyzing the performance of a communications network (e.g., a mobile telecommunications network) using customer-centric and/or subscriber-centric data and information. In some embodiments, the systems and method may determine key performance indicators for a communications network by accessing call detail records from multiple communications network sources, generating a database of one or more customer stats table (CSTs) based on the accessed call records, wherein the CSTs include records for each individual customers of the communications network, and determining one or more key performance indicators (KPIs) for the overall network based on the records stored by the one or more customer stats tables.

Growing community of inventors

Bellevue, WA, United States of America

Ting Zhang