Arista Networks, Inc.

Aruba Networks, Inc.

Avenda Systems, Inc.

Krishna Prabhakar

Venkatesh Ramachandran

Santhosh Cheeniyil

Rajesh Kumar Ganapathy Achari

Madhusudhan Chitradurga Sethuram Setty

Anoop Kumaran Nair

Rajarao Bhagya Prasad Nittur

Michael Fine

A method of operating a server is provided that includes providing, with the server, one or more services relating to network access control and management of a network, predicting a network configuration failure associated with the network with a failure prediction model, and generating a network configuration recommendation based on the predicted network configuration failure to avoid the predicted network configuration failure. The failure prediction model can be a machine-learning based network configuration failure prediction model that is trained on past network configuration failure events. Operated in this way, erroneous network configuration issues can be automatically identified and addressed in a timely fashion.

Predictive model for handling network configuration failures

A method of operating a network is provided that includes receiving a query, using a first language model to determine an intent or purpose of the query, using a second language model to extract a named entity from the query, and obtaining search results by searching for the extracted named entity on a named entity list corresponding to a particular tenant. The method can further include generating a response based on the search results. The query can be a natural language query, and the first language model can be a natural language model. The second language model for extracting the named entity can be a network-related language model that is trained on network records associated with a plurality of tenants. The network records associated with the plurality of tenants can be stored on a multi-tenant database.

Processing natural language network queries

A method of operating a network is provided that includes identifying a plurality of client devices connected to the network, categorizing the client devices into respective client groups based on device characteristics of each of the client devices, analyzing traffic patterns among the client groups and assigning the client groups to respective network segments based on the observed traffic patterns, and generating one or more network access policy for at least one of the network segments based on the traffic patterns or baseline behavior associated with a portion of the client devices belonging to the at least one of the network segments.

Automatic generation of network access policies

A method and apparatus for integrating various network access control frameworks under the control of a single policy decision point (PDP). The apparatus supports pluggable protocol terminators to interface to any number of access protocols or backend support services. The apparatus contains Trust and Identity Mediators to mediate between the protocol terminators and a canonical policy subsystem, translating attributes between framework representations, and a canonical representation using extensible data-driven dictionaries.

Method and apparatus for policy-based network access control with arbitrary network access control frameworks

A method for provisioning client devices securely and automatically by means of a network provisioning system is disclosed. Provisioning occurs before the client is granted access to the network. The provisioning is determined dynamically at the time a client connects to the network and may depend on a multitude of factors specified by data dictionaries of the provisioning system.

Growing community of inventors

Los Altos Hills, CA, United States of America

Krishna Prabhakar