AI-based network troubleshooting with expert feedback
AssigneeCisco Technology, Inc.
InventorsJean-Philippe Vasseur, Grégory Mermoud, Pierre-André Savalle, Eduard Schornig
Life of this patent
Estimating the term…
Abstract
In one implementation, a device uses a large language model-based agent to identify a task to correct an issue in a network. The device makes a determination that the large language model-based agent cannot complete the task. The device identifies, based on the determination, a subject matter expert to help complete the task. The device sends a request to the subject matter expert to complete the task.
Claims20
A method comprising:
- using, by a device, a large language model-based agent to identify a task to correct an issue in a network, wherein the large language model-based agent interfaces with a network controller to cause execution of actions performed on the network to troubleshoot the issue;
- making, by the device, a determination that the large language model-based agent cannot complete the task;
- identifying, by the device and based on the determination, a subject matter expert to help complete the task;
- and
- sending, by the device, a request, including the actions, to the subject matter expert to complete the task.
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:
- use a large language model-based agent to identify a task to correct an issue in a network, wherein the large language model-based agent interfaces with a network controller to cause execution of actions performed on the network to troubleshoot the issue;
- make a determination that the large language model-based agent cannot complete the task;
- identify, based on the determination, a subject matter expert to help complete the task;
- and
- send a request, including the actions, to the subject matter expert to complete the task.
A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:
- using, by the device, a large language model-based agent to identify a task to correct an issue in a network, wherein the large language model-based agent interfaces with a network controller to cause execution of actions performed on the network to troubleshoot the issue;
- making, by the device, a determination that the large language model-based agent cannot complete the task;
- identifying, by the device and based on the determination, a subject matter expert to help complete the task;
- and
- sending, by the device, a request, including the actions, to the subject matter expert to complete the task.
Dependencies are inferred from the claim text.