At&t Intellectual Property I, L.p.

At+t Corp.

Other

Wisconsin Alumni Research Foundation

At&t Mobility Ii LLC

University of Minnesota

Nicholas G Duffield

Carsten Lund

Subhabrata Bapi Sen

Mikkel Thorup

Lee Breslau

Alexandre Gerber

Edith Cohen

Oliver Spatscheck

Albert Gordon Greenberg

Yin Sheng Zhang

Balachander Krishnamurthy

Patrick Guy Haffner

Cheng Ee

Jacobus Erasmus Van Der Merwe

Haim Kaplan

Matthew Roughan

Kadangode K Ramakrishnan

Sumeet Singh

Yu Jin

Amogh Dhamdhere

Partho Pratim Mishra

Jeffrey Erman

Christopher J Chase

Pawan Goyal

John Gregory Klincewicz

Neal Shackleton

Paul Robert Barford

Yu Gu

Amos Ron

Darryl Neil Veitch

Balachaner Krishnamurthy

Matthias Grossglauser

Haakon Andreas Ringberg

Joel Sommers

Vijay Arya

Amy Ruth Reibman

Tirunell V Lakshman

Graham Cormode

Zhi-Li Zhang

Dimitrios Stiliadis

Frederick True

Don Towsley

Vyas Sekar

Weibo Gong

Adam Hersh

Robert Manzo

William Ramirez

Changchun Zou

Jacobus Frasmus Van Der Merwe

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for approximating an accent source. A system practicing the method collects data associated with customer specific services, generates country-specific or dialect-specific weights for each service in the customer specific services list, generates a summary weight based on an aggregation of the country-specific or dialect-specific weights, and sets an interactive voice response system language model based on the summary weight and the country-specific or dialect-specific weights. The interactive voice response system can also change the user interface based on the interactive voice response system language model. The interactive voice response system can tune a voice recognition algorithm based on the summary weight and the country-specific weights. The interactive voice response system can adjust phoneme matching in the language model based on a possibility that the speaker is using other languages.

System and method for customized voice response

Described is a system and method for determining a classification of an application that includes initiating a stress test on the application, the stress test including a predetermined number of stress events, wherein the stress events are based on a network impairment. A response by the application to each stress event is identified and the application is classified as a function of the response into one of a first classification and a second classification, the first classification indicative of a normal application and the second classification indicative of an undesired application. If, the application is in the second classification, a network response procedure is executed.

System and method for inferring traffic legitimacy through selective impairment

A system to detect anomalies in internet protocol (IP) flows uses a set of machine-learning (ML) rules that can be applied in real time at the IP flow level. A communication network has a large number of routers equipped with flow monitoring capability. A flow collector collects flow data from the routers throughout the communication network and provides them to a flow classifier. At the same time, a limited number of locations in the network monitor data packets and generate alerts based on packet data properties. The packet alerts and the flow data are provided to a machine learning system that detects correlations between the packet-based alerts and the flow data to thereby generate a series of flow-level alerts. These rules are provided to the flow time classifier. Over time, the new packet alerts and flow data are used to provide updated rules generated by the machine learning system.

Systems and methods for rule-based anomaly detection on IP network flow

A method and apparatus for detecting and localizing an anomaly for a network are disclosed. For example, the method sends a first set of probe packets on at least one path of the network, and detects a performance anomaly on a first path of the at least one path. The method then identifies at least one link on the first path that is responsible for the performance anomaly by applying a second set of probe packets.

Method and apparatus for detecting and localizing an anomaly for a network

A traffic classifier has a plurality of binary classifiers, each associated with one of a plurality of calibrators. Each calibrator trained to translate an output score of the associated binary classifier into an estimated class probability value using a fitted logistic curve, each estimated class probability value indicating a probability that the packet flow on which the output score is based belongs to the traffic class associated with the binary classifier associated with the calibrator. The classifier training system configured to generate a training data based on network information gained using flow and packet sampling methods. In some embodiments, the classifier training system configured to generate reduced training data sets, one for each traffic class, reducing the training data related to traffic not associated with the traffic class.

Scalable traffic classifier and classifier training system

A system to detect anomalies in internet protocol (IP) flows uses a set of machine-learning (ML) rules that can be applied in real time at the IP flow level. A communication network has a large number of routers that can be equipped with flow monitoring capability. A flow collector collects flow data from the routers throughout the communication network and provides them to a flow classifier. At the same time, a limited number of locations in the network monitor data packets and generate alerts based on packet data properties. The packet alerts and the flow data are provided to a machine learning system that detects correlations between the packet-based alerts and the flow data to thereby generate a series of flow-level alerts. These rules are provided to the flow time classifier. Over time, the new packet alerts and flow data are used to provide updated rules generated by the machine learning system.

Methods, apparatus, and articles of manufacture are disclosed to sample signed weighted updates. Example methods disclosed herein include identifying a first key associated with a data update obtained by sampling a stream of data received from a plurality of nodes in a network, the first key being representative of a first node in the plurality of nodes, adjusting a first value associated with the first key based on a weight associated with the data update, the weight being positive when the data update corresponds to opening of a new data connection with the first node, the weight being negative when the data update corresponds to closing of an existing data connection with the first node, and estimating a status of the first node based on the first value.

Methods and apparatus to sample data connections

In one embodiment, the present disclosure is a method and apparatus for classifying applications using the collective properties of network traffic. In one embodiment, a method for classifying traffic in a communication network includes receiving a traffic activity graph, the traffic activity graph comprising a plurality of nodes interconnected by a plurality of edges, where each of the nodes represents an endpoint associated with the communication network and each of the edges represents traffic between a corresponding pair of the nodes, generating an initial set of inferences as to an application class associated with each of the edges, based on at least one measured statistic related to at least one traffic flow in the communication network, and refining the initial set of inferences based on a spatial distribution of the traffic flows, to produce a final traffic activity graph.

Method and apparatus for classifying applications using the collective properties of network traffic in a traffic activity graph

A system and method to use network flow records to generate information about changes in network routing and to understand the impact of these changes on network traffic. The inferences made can be determinative, if sufficient information is available. If sufficient information is not available to make determinative inferences, inferences may be made that narrow the range of possible changes that may have occurred to network traffic and the underlying network.

System and method for determination of routing information in a network

Disclosed are method and apparatus for characterizing the temporal loss characteristics of a packet data network by multicast-based inference. Multicast probes are transmitted from a source node to a plurality of receiver nodes, which record the arrivals of the multicast probes. From the aggregate data comprising recorded arrivals of the end-to-end paths from the source node to each receiver node, temporal loss characteristics of individual links within the network may be calculated. In a network with a tree topology, the complexity of calculations may be reduced through a process of subtree partitioning.

Multicast-based inference of temporal loss characteristics in packet data networks

Certain exemplary embodiments comprise a method comprising: for selected traffic that enters a backbone network via a predetermined ingress point and is addressed to a predetermined destination, via a dynamic tunnel, automatically diverting the selected traffic from the predetermined ingress point to a processing complex; and automatically forwarding the selected traffic from the processing complex toward the predetermined destination.

Systems, methods, and devices for monitoring networks

Growing community of inventors

New York, NY, United States of America

Nicholas G Duffield