At&t Intellectual Property I, L.p.

Abhay Dabholkar

Vijayan Nagarajan

Alfonso Jones

Kevin Reese

Carl Sorrells

Christopher Tsai

Anoop Viswanath

Mengling Hettinger

Brad Ford

James H Pratt

Mark D Austin

Joshua Whitney

Lauren Savage

Parth Manoj Sutaria

Vladimir Sevastyanov

Nikhlesh Agrawal

Rudolph Mappus

Muhammad Sabir

Jeffrey B Saxon

Brian Lois

Nutan M Ranoliya

Billy Langston, Jr

Taylor Smith

Matthew Rosenbloom

Charles Drotar

Quan Nguyen

Rakhi Gupta

Caitlin Rose Gruis

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

Improving configuration of routing areas within an area of interest can include obtaining input data including a list of common language location identifiers within a defined area of interest and identification of a number of routing areas to be created within the area of interest; creating a bounding rectangle around the area of interest represented by the list of common language location identifiers; generating, within the bounding rectangle, a uniformly distributed sequence point; determining, from within the list of common language location identifiers, if the uniformly distributed sequence point is located in a particular common language location identifier of the list of common language location identifiers; if so, adding, to a list of kernel common language location identifiers the uniformly distributed sequence point; and if not, discarding the uniformly distributed sequence point.

Configuration of routing areas within an area of interest

Concepts and technologies disclosed herein are directed to optimizing and reducing redundant dispatch tickets via a network knowledge graph. According to one aspect disclosed herein, a network knowledge graph generation system ('NKGGS') can construct a machine learning model to determine a probability of an installation job needing a helper job to fulfill a service order. The NKGGS can execute the machine learning model to determine the probability. The machine learning model can determine the probability of the installation job needing the helper job to fulfill the service order based upon a network knowledge graph and a dependency score. The NKGGS can cluster the installation job with a plurality of installation jobs.

Optimizing and reducing redundant dispatch tickets via network knowledge graph

Aspects of the subject disclosure may include, for example, receiving a plurality of proposed machine learning solutions to a machine learning problem including receiving, for each respective proposed machine learning solution of the plurality of proposed machine learning solutions, one or more of a machine learning model, a dataset and a data pipeline output; automatically determining hybrid solutions to the machine learning problem, including combining, by the processing system, at least one of a first component from a first proposed machine learning solution with at least one of a second component from a second proposed machine learning solution; and ranking the hybrid solutions including determining a log loss score for each hybrid solution and sorting the hybrid solutions according to the log loss score for each hybrid solution. Other embodiments are disclosed.

System, method, and platform for auto machine learning via optimal hybrid AI formulation from crowd

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.

Modeling radio wave propagation in a fifth generation (5G) or other next generation network

Vehicular maintenance is predicted using real time telematics data and historical maintenance data. Different statistical models are used, and an intersecting set of results is generated. Environmental weather may also be used to further refine predictions.

Predictive maintenance

Techniques for desirably translating a document image to an editable electronic textual document are presented. Utilizing respective applications, a document processing management component (DPMC) can convert the document image to a grayscale document image, remove noise from such image, rotate such image to reduce or eliminate any skewing of such image, and perform character recognition on the rotated grayscale document image to extract the textual information from such document to generate an electronic textual document. DPMC can associate a document identifier with the electronic textual document, and such document and document identifier can be stored in a data store. When such document is related to a device or other item, a code or textual string can be associated with the device or item, wherein a communication device can scan the code or textual string. In response, DPMC can retrieve such document, or information relating thereto, from the data store.

Enhancing electronic documents for character recognition

A processing system may obtain historical job feature, network plant feature, and calendar feature data associated with customer premises installation jobs of a telecommunication network which include a dispatch of a customer premises technician. A plurality of the customer premises installation jobs may further include a dispatch of a network-based technician. The processing system may then generate, from the historical data, a prediction model for predicting whether additional customer premises installation jobs may include a dispatch of a network-based technician, apply the prediction model to job feature, network plant feature, and calendar feature data associated with a pending customer premises installation job, determine a likelihood score of whether the pending customer premises installation job may include a dispatch of a network-based technician based upon the prediction model, and assign the pending customer premises installation job to at least a first customer premises technician in accordance with the likelihood score.

Telecommunication network customer premises service dispatch optimization

A method and apparatus for identifying a cause for a fuel inefficiency of a vehicle are disclosed. For example, the method categorizes a plurality of vehicles into a plurality of peer groups, determines for each peer group a baseline of a vehicle operation efficiency, determines for each peer group a baseline of driving behavior, identifies at least one vehicle with a vehicle operation efficiency in one peer group of the plurality of peer groups that is an outlier as compared to the baseline of the vehicle operation efficiency associated with the one peer group, determines whether a driving behavior of a driver driving the at least one vehicle is an outlier as compared to the baseline of the driving behavior associated with the one peer group, and identifies a cause for the vehicle operation efficiency being an outlier.

Method and apparatus for identifying a cause for a fuel inefficiency of a vehicle via a network

Growing community of inventors

Allen, TX, United States of America

Abhay Dabholkar