AT&T Intellectual Property I, LP

Sbc Knowledge Ventures, L.p.

Sbc Technology Resources, Inc.

At&t Knowledge Ventures, LP

At&t Services, Inc.

Sbc Services, Inc.

Baofeng Jiang

Mehdi Malboubi

Xidong Wu

Raghvendra Savoor

Abhijeet Bhorkar

John Porter Van Slyke

Kaiyan Chen

Yew-Aik Lim

Jerold Osato

Peter Richard Wong

Yuhong Zheng

Jim Tidashi Otsuka

Jin Wang

Stuart Blackburn

Hyun Ok Lee

Andre Fuetsch

Mengfeng Tsai

Michael Yew-Aik Lim

Letian Chen

Christopher Du

John Matthew Cioffi

Yongdong Zhao

Frederick Armanino

Sun-Uk Park

David Kimble

G Keith Cambron

Rodney McTaggart

Sangho Oh

Raghbendra G Savoor

Jian Li

Donggen Zhang

Yu Liu

Mo Katibeh

Robert Michetich

Peter Aung Htut Wong

Juan G Flores

Jim Tadashi Otsuka

Eric Jung

Keith Cambron

Michael Lim

Aspects of the subject disclosure may include, for example, receiving a request from a mobile network entity for a key performance indicator (KPI) prediction over a portion of a mobile network, and obtaining a group of identifiers associated with the mobile network entity. Further embodiments can include obtaining a group of KPIs associated with the mobile network entity based on the group of identifiers, and determining a KPI prediction associated with the mobile network entity based on the group of KPIs. Additional embodiments can include allocating a group of network resources to the mobile network entity based on the KPI prediction. Other embodiments are disclosed.

Methods, systems, and devices for scalable and layered architecture for real-time key performance indicator (KPI) prediction in mobile networks

A method includes selecting a first machine learning model from a plurality of machine learning models that are trained for use in performing geolocation, wherein the first machine learning model is selected to perform geolocation within a first cell of a plurality of cells of a wireless network, acquiring event data from a plurality of wireless devices within the first cell, grouping the event data into a plurality of records, wherein each record of the plurality of records contains event data that indicates a common wireless device of the plurality of wireless devices, a common cell of the plurality of cells, and a common timestamp, and generating a predicted location of a first wireless device of the plurality of wireless devices, using the first machine learning model, wherein the first machine learning model outputs the predicted location in response to an input of a record of the plurality of records.

Geolocation of wireless network users

Aspects of the subject disclosure may include, for example, a method performed by a processing system; the method includes receiving a plurality of values of key performance indicators (KPIs) relating to performance of a cell on a communication network. The plurality of values of the KPIs includes labeled training data for training a machine learning (ML) model for the performance of the cell. The method further includes iteratively executing, using the labeled training data, a training procedure for the ML model; and testing the trained ML model. The labeled training data corresponds to ground truth data that may include a training data set, a validation data set and a test data set. The trained ML model, when deployed on a communication network, receives as input near-real time data regarding the performance of the cell and provides as output predictions of the performance of the cell. Other embodiments are disclosed.

Automatic and real-time cell performance examination and prediction in communication networks

The disclosed technology is directed towards partitioning data and distributing the data to different storage locations, which facilitates better data security. For example, a large database of source data can be partitioned into a small enabler partition and one or more large partitions, in which a full set of the partitions is needed to reconstruct the source data to its original state. The large partition can be maintained at an edge computing facility to reduce latency, or at a cloud computing facility to reduce storage expenses, with the smaller enabler partition only accessed when needed to reconstruct the data. A database is partitioned into a group of partitions, and the group of partitions is distributed to separate storage facilities. The separate storage and computing facilities/nodes are accessed to obtain datasets of the group of partitions, and merged to reconstruct the source data.

Storing data at edges or cloud storage with high security

The system allows real time collection and processing of massive data from many network elements. It has an elastic architecture that scales horizontally to support different network sizes. The system in a uniform data format for downstream consumption. It employs a pub/sub data distribution mechanism that supports multiple concurrent downstream subscribers efficiently in real-time.

Bulk data processing system

Aspects of the subject disclosure may include, for example, determining a group of coefficients for a digital filter, and configuring the digital filter according to the group of coefficients. Further embodiments can include processing a group of statistics associated with a first data flow utilizing the digital filter, and determining a first statistic from the group of statistics does not satisfy a statistical threshold resulting in a first determination. Other embodiments are disclosed.

Methods, systems, and devices for software defined network monitoring

Spatial-temporal informative patterns for users and devices associated with data networks can be predicted or determined. An information management component (IMC) can analyze respective groups of items of data stored in respective formats in respective databases. Some items of data can comprise respective signal measurement data representative of respective signal measurements associated with respective devices associated with a communication network. Based on the analysis results, IMC can determine a spatial-temporal pattern(s) associated with the respective groups of items of data, wherein the spatial-temporal pattern(s) can relate to a subject of interest. The IMC can utilize artificial intelligence and/or machine learning algorithms and models to facilitate determining the spatial-temporal pattern(s). In response to a query relating to the subject of interest, the IMC can provide information relating to the subject of interest and responsive to the query based on the spatial-temporal pattern(s).

Determining spatial-temporal informative patterns for users and devices in data networks

Resources associated with a responder communication network and a communication network can be managed in an effective manner. In connection with an event, a resource management component (RMC) can analyze network-related data associated with the networks and external data relating to the event or a geographic area related thereto. In connection with the event, based on the analysis, RMC can desirably manage the resources, in part, by determining locations or adjustments for portable base stations, sensors, and/or devices associated with the responder communication network to facilitate high quality communication of information, determining traffic routes and other path planning for vehicles or personnel, creating network slices for high quality communication of information, and/or performing monitoring and intelligent troubleshooting with regard to the networks. RMC can employ artificial intelligence or machine learning techniques and models to facilitate making desired predictions or inferences relating to the event or networks.

Intelligent support framework usable for enhancing responder network

Concepts and technologies are disclosed herein for using user equipment data clusters and spatial temporal graphs of abnormalities for root cause analysis. User equipment data can be obtained from a cellular network. A filter having a threshold can be applied to the user equipment data to obtain records. A determination is made whether the threshold is to be adaptively adjusted. If a determination is made that the threshold is not to be adjusted, the records can be added to a record set. The records in the subset of records can be correlated based on a key to obtain a filtered and correlated version of the record set, a spatial temporal graph of abnormalities associated with the cellular network can be generated based on the filtered and correlated version of the record set, and a root cause of a failure can be determined based on the spatial temporal graph of abnormalities.

Using user equipment data clusters and spatial temporal graphs of abnormalities for root cause analysis

Aspects of the subject disclosure may include, for example, a method in which a processing system coupled to a communication network identifies, based on base station unit (BSU) performance measurements and network key performance indicator (KPI) measurements, a set of BSUs experiencing interference. The method further includes selecting BSUs from the identified set that are to be provided with an auxiliary antenna array; and computing, for each BSU in the identified set, parameters to be used by modules of the BSU that are local to the BSU and configured to perform interference detection, interference estimation, and/or interference cancellation; the computed parameters are used in a reconfiguration procedure for the modules of the BSU. Other embodiments are disclosed.

Network centric interference and noise cancellation in wireless networks

Aspects of the subject disclosure may include, for example, a method in which a processing system identifies a set of target users of user equipment communication devices (UEs), based on reports from the UEs regarding a quality of service (QoS) experienced by the respective UEs; obtaining from internal sources a set of key performance indicators (KPIs) for the communication network; correlating information received from external sources with the data obtained from the internal sources to validate the reports from the UEs; and recommending, in accordance with data records generated by the correlating, an action to improve the QoS for a UE of the set of UEs, where the action includes a modification of the UE and/or a reconfiguration of the network. Other embodiments are disclosed.

Intelligent customer oriented mobility network engineering at edges

The end-to-end troubleshooting system may use machine learning models to predict the network quality degradation and provide resolution recommendations. The end-to-end troubleshooting system may be a self-evolving closed loop system that helps monitor the network health, provide real-time prediction of network health, and anticipate potential network outages. This intelligent system may provide recommendation resolutions based on the analysis of prediction results.

End to end troubleshooting of mobility services

Resources associated with a responder communication network and a communication network can be managed in an effective manner In connection with an event, a resource management component (RMC) can analyze network-related data associated with the networks and external data relating to the event or a geographic area related thereto. In connection with the event, based on the analysis, RMC can desirably manage the resources, in part, by determining locations or adjustments for portable base stations, sensors, and/or devices associated with the responder communication network to facilitate high quality communication of information, determining traffic routes and other path planning for vehicles or personnel, creating network slices for high quality communication of information, and/or performing monitoring and intelligent troubleshooting with regard to the networks. RMC can employ artificial intelligence or machine learning techniques and models to facilitate making desired predictions or inferences relating to the event or networks.

Concepts and technologies are disclosed herein for using user equipment data clusters and spatial temporal graphs of abnormalities for root cause analysis. User equipment data can be obtained from a cellular network. A filter having a threshold can be applied to the user equipment data to obtain a records. A determination is made whether the threshold is to be adaptively adjusted. If a determination is made that the threshold is not to be adjusted, the records can be added to a record set. The records in the subset of records can be correlated based on a key to obtain a filtered and correlated version of the record set, a spatial temporal graph of abnormalities associated with the cellular network can be generated based on the filtered and correlated version of the record set, and a root cause of a failure can be determined based on the spatial temporal graph of abnormalities.

Growing community of inventors

Pleasanton, CA, United States of America

Baofeng Jiang