Cisco Technology, Inc.

David C White, Jr

Jay Kemper Johnston

Magnus Mortensen

Christopher Blayne Dreier

Rama Darbha

Carlos M Pignataro

Chidambaram Arunachalam

Christopher Shaun Roberts

Kevin J Klous

Iqlas Maheen Ottamalika

Michael Robertson

Madhusudan Challa

John Matthew Swartz

Qihong Shao

Matthew R Engle

Felipe De Mello

Jerome Henry

Robert E Barton

Joseph Michael Clarke

Gurvinder Singh

Zizhen Gao

Doosan Jung

Josh Viktorov

Deon Anthony Pillsbury

Necati Cehreli

Matthew Aaron Silverman

Robert T Bell

Brian C Powell

Joel Abraham Obstfeld

Amit Prakash Barave

Michael P O'Brien

Mark Ammar Rayes

Carl Nathan Buckles

Vivek Santuka

Muhilan Natarajan

John W Garrett, Jr

Jeffrey Dominick Jackson

Sofia Karygianni

Steven Robert Ochmanski

Patrick Tsunehiro

Omar Santos

Felix Khouri

Ryan Alan MacLennan

Mohammed Hamzeh

Pengfei Sun

Tiffany Kristine Pham

Vaishnavi Rao

Nitesh Arora

Kevin D McCabe

Allison Renner Walton

Ana Andrijic

Jazzmine Marie White

Xinping Xu

Mariusz Kaźmierski

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

A platform dynamically detects a user persona and facilitates a user objective in a user session. The platform obtains user activity of users across multiple historical sessions. The platform clusters similar user activity across the historical sessions to determine personas being used in the historical sessions. The platform mines sequential patterns in a set of user activity data associated with one of the personas and determines at least one predictive rule associated with that persona. Each predictive rule includes an initial activity among the set of user activity data and at least one subsequent activity in the set of user activity data.

Dynamically detecting user personas of network users for customized suggestions

A computer executed process for mimicking human dialog, referred to herein as a 'humanoid' or “humanoid process software,” can be configured to participate in multi-parry conversations. The humanoid can monitor electronic communications in a conversation involving the humanoid and at least one other party. The humanoid can model the electronic communications by uniquely identifying each of the electronic communications as a stream of data. For example, the data can be labeled and sorted in a database and/or arranged in a nodal graph representation. The humanoid can participate in the conversation based on the modeling.

Modeling communication data streams for multi-party conversations involving a humanoid

This disclosure describes techniques for diagnosing a presence or malfunction of a network node. In an example method, a first network node receives an indication of a diagnostic transmission originating from a second network node. The second network node further receives a forwarded transmission corresponding to the diagnostic transmission. The first network node diagnoses at least one of a presence or a malfunction of an intermediary node between the first network node and the second network node based on at least one of the indications of the diagnostic transmission or the forwarded transmission.

Diagnosing intermediary network nodes

A method is provided to determine administrator users associated with network devices in a network. The method includes sending to one or more network devices in a network or to an entity that manages or controls access to the one or more network devices, a query to identify one or more administrator users for each of the one or more network devices. The method involves obtaining a response to the query, the response including an identifier of each the one or more administrator users for a respective network device of the one or more network devices. The method may then involve using the identifier of each of the one or more administrator users for each of the one or more network devices to send a notification to the one or more administrator users.

Targeted notification in heterogenous network environments

Methods are provided in which a cloud portal, serving as an orchestrator device, obtains a request for diagnostics data to monitor performance of a cloud-based service executing in a provider cloud network and accessed by a client device in an enterprise network and obtains service information about a plurality of assets involved in providing the cloud-based service. The plurality of assets are managed by at least a first cloud-based management entity and a second cloud-based management entity. The methods further include collecting the diagnostics data about the plurality of assets based on the service information, aggregating the diagnostics data to form a multi-cloud diagnostics data, and determining the performance of the cloud-based service based on the multi-cloud diagnostics data.

Case deflection using visibility into multi-product clouds

Techniques for identifying a trusted SSID for a wireless network are disclosed. Prior to establishing a connection with a wireless network, a first network message is received from a first access point (AP) identifying a first service set identifier (SSID) associated with a first wireless network, a second network message is received from a second AP identifying a second SSID associated with a second wireless network, and a visual similarity is determined between a first visual representation of the first SSID and a second visual representation of the second SSID. The second SSID is designated as suspicious based on the determined visual similarity.

Identifying trusted service set identifiers for wireless networks

This disclosure describes techniques for providing notifications about events that occur during an online meeting. For instance, a system may establish an online meeting, such as a video conferencing meeting, for users. While in the meeting, a first user may view video of a second user and determine that the second user is experiencing an emergency event. As such, a user device of the first user may receive an input indicating that the emergency event is occurring with the second user. The system may receive the indication from the user device and verify that the emergency event is occurring. Additionally, the system may then send a notification to emergency personnel that indicates at least that the emergency event is occurring and a location of the second user. Furthermore, the system may send notification(s) to contact(s) associated with the second user that indicate at least that the emergency event is occurring.

Event notifications for online meetings

A network management system tests the availability of a network resource before a user performs a task with the network resource. The system measures network activity of a user performing one or more tasks. The network activity includes communication between a user device of the user and each network resource associated with a corresponding task performed by the user. The system also generates a digital model persona of the user based on the tasks performed by the user, and determines a schedule of the tasks performed the user. Each particular task is associated with a corresponding execution time for the user. The system further configures the digital model persona to test the network resource associated with each corresponding task at a testing time that is a predetermined length of time prior to the execution time for the user.

Predicting future network issues for users with digital model personas

A heterogeneous graph learning system generates and analyzes network implementations. The heterogeneous graph learning system includes obtaining information describing multiple network implementations including heterogeneous nodes. The heterogeneous graph learning system also includes generating a one-hop graph connecting a particular node of the heterogeneous nodes with a set of related nodes. The one-hop graph connects the particular node with the set of related nodes via corresponding edges. The heterogeneous graph learning system further includes transforming the one-hop graph into a weighted graph based on a Dynamic Meta Path Transformation (DMPT). In the DMPT, each of the corresponding edges connecting the particular node to a corresponding related node among the set of related nodes is associated with a corresponding weight.

Heterogeneous graph learning-based unified network representation

Techniques are described to enable selective content sharing in a video conference. In one example, a conferencing system obtains first display content from a first endpoint device in a video conference session. The conferencing system streams the first display content to a second endpoint device in the video conference session and obtains second display content from the second endpoint device. While streaming the first display content to the second endpoint device, the conferencing system streams the second display content to a third endpoint device in the video conference session and prevents streaming of the second display content to the first endpoint device.

Selective content sharing in a video conference

Presented herein are techniques to perform call failure diagnostics. A method includes receiving, at a network device, an indication of calls-of-interest, detecting, at the network device, a failure of one of the calls-of-interest, triggering, in response to the detecting, at the network device, diagnostics data analysis of data associated with the failure of one of the calls-of-interest, determining, based on the diagnostics data analysis, a cause of the failure of the one of the calls-of-interest, and notifying, by the network device, a management system of the cause of the failure of the one of the calls-of-interest and of recent configuration changes on the network device that are related to the cause of the failure of the one of the calls-of-interest.

Distributed diagnostics for network wide route policy analyzer and other use cases

In one embodiment, an issue analysis service obtains telemetry data from a plurality of devices in a network across a plurality of time intervals. The service detects a failure event in which a device in the network is in a failure state. The service clusters the telemetry data obtained prior to the failure event into rounds according to time intervals in which the telemetry data was collected. Each round corresponds to a particular time interval. The service applies a machine learning-based classifier to each one of the rounds of clustered telemetry data to identify one or more common traits appearing in the telemetry data for each round. The service generates a trait change report indicating a change in the one or more common traits appearing in the telemetry data across the rounds leading up to the failure event.

Network issue tracking and resolution system

Techniques are provided herein for remediating storage of sensitive data on a hardware device. In one example, a request to remediate storage of sensitive data on a hardware device is obtained. In response to the request, a database is automatically searched. The database correlates the hardware device with an indication of how to remediate the storage of the sensitive data on the hardware device. Based on the database, the storage of the sensitive data on the hardware device is remediated.

Remediating storage of sensitive data on hardware device

A method is provided that is performed by a computer-implemented user support bot. The method includes obtaining from a user a support request related to software and/or hardware used, or to be used, by the user; obtaining user lifecycle journey information that tracks deployment, adoption and/or use by the user of the software and/or hardware; determining a user intent for the support request based on the user lifecycle journey information when there is ambiguity as to the user intent based solely on the support request; and providing a response to the support request based on the user intent.

User lifecycle journey and asset data based bot skill selection

Growing community of inventors

Durham, NC, United States of America

David C White, Jr