Cisco Technology, Inc.

Derek William Engi

Gonzalo A Salgueiro

M David Hanes

Bradley Wise

Md Atiqur Rahman

Julie Allen

Pascale Delaunay

Vivek Kumar Singh

Qihong Shao

Qixu Gong

Vijay Pillai

Jorge Martin Garcia Rangel

Howard Steven Nelson

Ravi Prakash Garg

Goudam Jaganmohan Muralitharan

Rekha Gopikrishnan

Benjamin L Chang

Jaime Madruga Rita

A system and method for an artificial intelligence (AI) confidentiality proxy that can protect a network from the transferal of sensitive AI data sets to outside AI systems. A data contract is established between the proxy and outside AI systems could function as well as user personas for additional protection. This system can also integrate with the network and provide security policy content and inspection rules.

Artificial intelligence (AI) confidentiality proxy to secure AI data sets

A method comprises: receiving a query on a topic from a user associated with user attributes indicative of a user comprehension level on the topic; providing the query to an AI model; receiving from the AI model a response to the query that has a response comprehension level on the topic that is less than the user comprehension level; iteratively adding, to the query, topically-relevant user attributes of the user attributes to produce iterative queries that increase in technical detail on the topic; providing the iterative queries to the AI model; responsive to providing the iterative queries, receiving, from the AI model, iterative responses that increase in technical detail on the topic and have response comprehension levels that increase on the topic; and determining, among the iterative responses, a final response having a response comprehension level that most nearly matches the user comprehension level.

Context injection for improved AI response

Methods are provided for generating hierarchical summaries with actionable recommendations having various granularities. Specifically, the methods involve obtaining notifications related to network issues and generating meta-semantic data that includes a summary of each of the notifications. The methods further involve obtaining inventory data of network devices in a plurality of domains of a network. The inventory data includes configuration information of the network devices. The methods further involve generating a multi-level hierarchical summary specific to the network based on the inventory data and the meta-semantic data. The multi-level hierarchical summary includes a first level specific to one or more affected network devices and a second level specific to a group of network devices. The methods further involve providing the multi-level hierarchical summary for performing one or more actions associated with the network.

Hierarchical auto summary generation with multi-task learning in networking recommendations

A device receives a video stream, where one or more frames of the video stream include embedded metadata that is embedded directly into the one or more frames. The device extracts the embedded metadata from the one or more frames. The device makes an authentication determination regarding the video stream, based on whether the embedded metadata includes a digital signature associated with a sender of the video stream. The device controls, based on the authentication determination, presentation of the video stream to a recipient user.

In-band metadata for authenticity and role-based access in enterprise video streaming services

Techniques described herein relate to automatically generating standard network device configurations. In one example, one or more groups of network device configuration blocks may be obtained. An analysis of the one or more groups of network device configuration blocks may be performed, including identifying respective frequencies associated with respective network device configuration blocks of the one or more groups of network device configuration blocks. Based on the respective frequencies, one or more network device configuration blocks of the one or more groups of network device configuration blocks may be automatically aggregated into a standard network device configuration.

Automated generation of standard network device configurations

This disclosure describes techniques for authenticating a user. For instance, a system may initially generate and then store authentication data for later authenticating the user. The authentication data may include biometrics data (e.g., facial recognition data), credentials data (e.g., a username, password, etc.), and/or environmental data (e.g., object(s) located within an environment). Later, the system may receive image data generated by a user device of the user. In some examples, the system may then analyze the image data using one or more facial recognition techniques in order to identify the user. The system may then use the authentication data, such as the environmental data, to determine that the image data further represents the object(s). Based on determining that the image data further represents the object(s), the system may then verify the user for access to a resource.

Techniques for authenticating a user

In one embodiment, an illustrative method herein comprises: determining, by a process, for each group of policies configured across a plurality of network devices in a computer network, an information set having a list of all policy components used for each group and which policies within each group have which particular policy components of the list of all policy components used for that group; performing, by the process, a comparative analysis of similarity and component variance on policies within each group based on the information set; deriving, by the process, an overall complexity indicator for each group based on the comparative analysis; and providing, from the process to an assessment interface, a ranking of each group as compared to other groups of policies within the computer network based on their respective overall complexity indicator.

Complexity ranking in network device policies

In one embodiment, a device obtains audio data from one or more past conferences. A prediction model that predicts when participants of a conference will speak is generated based on the audio data from the one or more past conferences. The device uses the prediction model to predict a speech distribution for participants of a particular conference. Then, the device proactively optimizes audio parameters of the particular conference based on its predicted speech distribution.

Proactive audio optimization for conferences

In one embodiment, a device maintains a buffer of historical telemetry data of a particular type of telemetry. The device obtains new telemetry data of the particular type of telemetry. The device makes a state evaluation by comparing the new telemetry data to the buffer, to determine whether the new telemetry data is an outlier. The device sends a message indicative of the new telemetry data to a message bus for delivery to a recipient that is not subscribed to receive telemetry data of the particular type of telemetry, when the device determines that the new telemetry data is an outlier.

Message bus subscription management with telemetry inform message

Techniques and architecture for determining compliance of a network with respect to a network design solution. The techniques may include determining a role for each network device of a network that comprises multiple network devices and determining one or more policies related to each network device with respect to other network devices of the network. The techniques may further include based at least in part on the roles for each network device and the one or more policies, determining a level of compliance of a configuration of the network with respect to a network design solution. Based at least in part on the level of compliance, a remedial action may be performed. In configurations, a machine learning model may be used.

Analyzing deployed networks with respect to network solutions

In one example, a logical representation of a first graph is generated. The first graph indicates a configuration of a network device in a network at a first time. The first graph includes a first node representative of a first configuration block of the network device, a second node representative of a second configuration block of the network device, and a first link that indicates, by connecting the first node and the second node, that the first configuration block is associated with the second configuration block. The logical representation of the first graph is compared to a logical representation of a second graph that indicates an actual or planned configuration of the network device at a second time subsequent to the first time. In response, one or more changes in the configuration of the network device from the first time to the second time are identified.

Growing community of inventors

Ferndale, MI, United States of America

Derek William Engi