Cisco Technology, Inc.

Mark Ammar Rayes

Petre Dini

Michael Cheung

Carlos M Pignataro

Hazim Hashim Dahir

Cosmin Nicu Dini

David C White, Jr

Aeneas Sean Dodd-Noble

Om Prakash Suthar

Pradeep Kumar Kathail

Ralph Droms

Ian McDowell Campbell

Joel Abraham Obstfeld

Michael David Geller

Samer M Salam

Manuela Ionelia Popescu

Arman Rezaee

Jackson Shyu

John W Garrett, Jr

Hector G Trevino

Balaji R Venkatraman

Ibrahim Amir Darwish

Xinping Xu

This disclosure describes techniques for emulating the operations of a computer network. In some cases, a method includes receiving first configuration data associated with a first device and second configuration data associated with a second device in a network; determining a first device representation associated with the first device based on the first configuration data and a second device representation associated with the second device based on the second configuration data; determining, based on the first and the second device representations, a first device cluster, wherein the first device cluster comprises a plurality of clustered devices comprising the first device and the second device; determining a first device model associated with the first device cluster, wherein the first device model represents a first device behavior that is common across the plurality of clustered devices; and generating, based on the first device model, an emulation environment associated with the network.

Computer network emulation using network device clusters

Methods are provided for a collaborative, decentralized insight engineering based on exchanging telemetry vectors with peer network devices. Each network device independently detects a deviation in its functioning using machine learning of generated feature vectors. Specifically, the methods involve obtaining, from at least one peer network device, at least a first feature vector that represents at least one insight generated from telemetry data of a respective peer network device. The intermediate network device and the at least one peer network device are configured to forward packets of a traffic flow. The methods further involve determining whether a deviation related to one or more of the network devices, exists based at least on the first feature vector and performing the at least one predefined action based on determining that the deviation exists.

Collaborative telemetry engineering

Various implementations disclosed herein enable blockchain programming in NB-IoT devices. In various implementations, a method of blockchain authentication is performed by a computing device including one or more processors, and a non-transitory memory. In various implementations, the method includes maintaining a blockchain for a machine-to-machine network, wherein the machine-to-machine network is a narrowband internet of things network. In some implementations, the method includes receiving a request for a first set of data from the blockchain by a second device. In some implementations, the method includes determining based on the request, the first set of data from the blockchain by traversing a series of blocks from the blockchain. In some implementations, the method includes packaging the first set of data from the blockchain according to a protocol into a packaged data unit and transmitting the packaged data unit to the second device.

Blockchain-based NB-IoT devices

In one embodiment, a processor receives data indicative of a plurality of conversations involving a primary user. The processor identifies a subset of the plurality of conversations that are regarding a particular topic. The processor adds a conversation to the subset based on a match between one or more keywords in the conversation matching a list of keywords associated with the particular topic. The processor uses a machine learning-based model to identify one or more context characteristics of the conversations in the identified subset. The processor updates the subset of conversations by adding at least one of the conversations to the subset based on the at least one conversation having at least one context characteristic identified by the machine learning-based model. The processor provides data indicative of the updated subset of conversations to a user interface for review by the primary user.

Identification and logging of conversations using machine learning

Presented herein are techniques for automatically creating communities of network-connected devices, i.e., Internet of Thing (IoT) devices. One or more of a plurality of network-connected devices are identified based on one or more policies that define one or more communities of network-connected devices. A community of network-connected devices includes network-connected devices that share common functional, physical or relational attributes. Information is stored that indicates the one or more communities of which each of the one or more of the plurality of network-connected devices is a member based on the policies that define the one or more communities and functional, physical or relational attributes of the one or more of the plurality of network-connected devices.

Automatic creation and management of a community of things for Internet of Things (IoT) applications

Techniques are presented herein to monitor a plurality of big data sources in order to dynamically identify keywords. The big data sources are analyzed to classify the keywords as related to either a technical problem or to a solution to the technical problem. In addition, data associated with the keywords is weighted based on one or more attributes of the data and stored in a database in a problem-solution format.

Managing big data for services

The real time availability of a group of network elements is determined based upon both a real time availability value for each of the network elements and cooperation relationships between the network elements. The cooperation relationships reflect both the topological relationships between the network elements, i.e., how the network elements are connected, and the extent to which network elements interact with each other effectively. For relatively small groups of network elements, where the cooperation relationships are not overly complex, the real time availability is determined directly from the real time availability value for each of the network elements and cooperation relationships between the network elements. Decomposition and recombination are used to determine the real time availability of large groups of network elements based on specific formulas for basic network element topology models.

Approach for determining the real time availability of a group of network elements

A method is disclosed for a method for measuring the availability of a network element or service. For each network element N, a current real availability value CRAVand a current time value CTVare associated with network element N. Additionally, for each network element N, an operational state value OSVis associated with network element N. At a later time, indicated by a new time value NTV, a new real availability value NRAVfor network element N is determined based on the current availability value CRAV, the current time value CTV, the new time value NTV, and the operational state value OSV. The new real availability value NRAVis stored. Thus, each separate network element N may be associated with a separate real availability value that accurately reflects the availability of network element N specifically, regardless of any availability approximated for network element N's type.

Method and apparatus for measuring the availability of a network element or service

An isolation approach for network users associated with elevated risk is disclosed for protecting networks. In one approach a method comprises the computer-implemented steps of determining a user identifier associated with a network device that has caused a security event in a network; causing the network device to receive a network address that is selected from a subset of addresses within a specified pool associated with suspected malicious network users; and configuring one or more security restrictions with respect to the selected network address.

Isolation approach for network users associated with elevated risk

A method of determining an amount of bandwidth needed on a communication link is disclosed. According to one aspect of the method, instead of considering only user behavior or only traffic characteristics, the amount of bandwidth needed on the link is determined based on both user behavior and traffic characteristics. The determined amount is stored in memory. By accounting for both user behavior and traffic characteristics, the method determines the amount of bandwidth needed on a communication link more accurately.

Link sizing based on both user behavior and traffic characteristics

A method and a system for re-establishing the connection of a network device with a network, using viral communication, are provided. According to the various embodiments, a disconnected network device acts as a simple wireless device and contacts a neighboring network device to obtain configuration information. The request can be forwarded to a network management station (NMS) through one or more neighbors of the disconnected network device. Connectivity is obtained by executing the configuration instructions obtained from the NMS.

Growing community of inventors

San Ramon, CA, United States of America

Mark Ammar Rayes