# US 2024/0267308 A1 · Using device behavior knowledge across peers to remove commonalities and reduce telemetry collection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0267308 A1
- Document ID: US20240267308A1
- Status: Published application
- Kind: A1
- Application number: 18/107,258
- Filed: 2023-02-08
- Published: 2024-08-08
- Earliest claimed: 2023-02-08
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Andrea Di Pietro; Sukrit DASGUPTA; Sofia KARYGIANNI
- Web page: https://patentgrep.com/patent/US20240267308A1

## CPC

- H04L 43/062: related to network traffic
- H04L 41/0894: Policy-based network configuration management
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- H04L 41/16: using machine learning or artificial intelligence
- H04L 43/04: Processing captured monitoring data, e.g. for logfile generation
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

In one embodiment, a central agent obtains device inventory data from a plurality of networks regarding endpoint devices in those networks. The central agent receives a request for a behavioral model for a particular type of endpoint device. The central agent selects one or more networks of the plurality of networks to export traffic data associated with endpoint devices of the particular type. The central agent configures one or more export agents at the one or more networks to export the traffic data. The traffic data exported by the one or more export agents is used to train the behavioral model.

## Claims

### Claim 1

A method comprising:
obtaining, by a central agent, device inventory data from a plurality of networks regarding endpoint devices in those networks;
receiving, at the central agent, a request for a behavioral model for a particular type of endpoint device;
selecting, by the central agent, one or more networks of the plurality of networks to export traffic data associated with endpoint devices of the particular type; and
configuring, by the central agent, one or more export agents at the one or more networks to export the traffic data, wherein the traffic data exported by the one or more export agents is used to train the behavioral model.

### Claim 2 (depends on 1)

The method as in claim 1, wherein the device inventory data indicates, for any given endpoint device, its device type and a representation of its observed traffic.

### Claim 3 (depends on 1)

The method as in claim 1, further comprising:
using the traffic data exported by the one or more export agents to train the behavioral model for the particular type of endpoint device.

### Claim 4 (depends on 1)

The method as in claim 1, wherein selecting the one or more networks to export traffic data associated with endpoint devices of the particular type comprises:
determining that at least some of the traffic data has already been collected from the plurality of networks.

### Claim 5 (depends on 1)

The method as in claim 1, wherein selecting the one or more networks to export traffic data associated with endpoint devices of the particular type comprises:
determining that a given network in the plurality of networks exporting the traffic data would violate an export policy associated with that network.

### Claim 6 (depends on 1)

The method as in claim 1, wherein the device inventory data indicates, for any given endpoint device, one or more applications associated with that endpoint device.

### Claim 7 (depends on 6)

The method as in claim 6, wherein selecting the one or more networks to export traffic data associated with endpoint devices of the particular type comprises:
excluding at least one of the plurality of networks from the one or more networks selected to export the traffic data based on its endpoint devices of the particular type having an associated application that is also associated with those endpoint devices in the one or more networks selected to export the traffic data.

### Claim 8 (depends on 1)

The method as in claim 1, wherein the one or more networks are selected based in part on resources available at those one or more networks for exporting traffic data.

### Claim 9 (depends on 1)

The method as in claim 1, further comprising:
configuring an export agent for a network that is not in the plurality of networks to export traffic data for endpoint devices that would add diversity to traffic data previously received by the central agent from the plurality of networks.

### Claim 10 (depends on 1)

The method as in claim 1, wherein the plurality of networks are operated by different entities.

### Claim 11

An apparatus, comprising:
one or more network interfaces;
a processor coupled to the one or more network interfaces and configured to execute one or more processes; and
a memory configured to store a process that is executable by the processor, the process when executed configured to:
obtain device inventory data from a plurality of networks regarding endpoint devices in those networks;
receive a request for a behavioral model for a particular type of endpoint device;
select one or more networks of the plurality of networks to export traffic data associated with endpoint devices of the particular type; and
configure one or more export agents at the one or more networks to export the traffic data, wherein the traffic data exported by the one or more export agents is used to train the behavioral model.

### Claim 12 (depends on 11)

The apparatus as in claim 11, wherein the device inventory data indicates, for any given endpoint device, its device type and a representation of its observed traffic.

### Claim 13 (depends on 11)

The apparatus as in claim 11, wherein the process when executed is further configured to:
use the traffic data exported by the one or more export agents to train the behavioral model for the particular type of endpoint device.

### Claim 14 (depends on 11)

The apparatus as in claim 11, wherein the apparatus selects the one or more networks to export traffic data associated with endpoint devices of the particular type by:
determining that at least some of the traffic data has already been collected from the plurality of networks.

### Claim 15 (depends on 11)

The apparatus as in claim 11, wherein the apparatus selects the one or more networks to export traffic data associated with endpoint devices of the particular type by:
determining that a given network in the plurality of networks exporting the traffic data would violate an export policy associated with that network.

### Claim 16 (depends on 11)

The apparatus as in claim 11, wherein the device inventory data indicates, for any given endpoint device, one or more applications associated with that endpoint device.

### Claim 17 (depends on 16)

The apparatus as in claim 16, wherein the apparatus selects the one or more networks to export traffic data associated with endpoint devices of the particular type by:
excluding at least one of the plurality of networks from the one or more networks selected to export the traffic data based on its endpoint devices of the particular type having an associated application that is also associated with those endpoint devices in the one or more networks selected to export the traffic data.

### Claim 18 (depends on 11)

The apparatus as in claim 11, wherein the apparatus configures the one or more export agents to stop exporting the traffic data when a stopping condition is met.

### Claim 19 (depends on 11)

The apparatus as in claim 11, wherein the process when executed is further configured to:
configure an export agent for a network that is not in the plurality of networks to export traffic data for endpoint devices that would add diversity to traffic data previously received by the apparatus from the plurality of networks.

### Claim 20

A tangible, non-transitory, computer-readable medium storing program instructions that cause a central agent to execute a process comprising:
obtaining, by the central agent, device inventory data from a plurality of networks regarding endpoint devices in those networks;
receiving, at the central agent, a request for a behavioral model for a particular type of endpoint device;
selecting, by the central agent, one or more networks of the plurality of networks to export traffic data associated with endpoint devices of the particular type; and
configuring, by the central agent, one or more export agents at the one or more networks to export the traffic data, wherein the traffic data exported by the one or more export agents is used to train the behavioral model.
