Invention Grant
- Patent Title: Active learning for interactive labeling of new device types based on limited feedback
-
Application No.: US16194442Application Date: 2018-11-19
-
Publication No.: US11100364B2Publication Date: 2021-08-24
- Inventor: Grégory Mermoud , Pierre-André Savalle , Jean-Philippe Vasseur , David Tedaldi
- Applicant: Cisco Technology, Inc.
- Applicant Address: US CA San Jose
- Assignee: Cisco Technology, Inc.
- Current Assignee: Cisco Technology, Inc.
- Current Assignee Address: US CA San Jose
- Agency: Behmke Innovation Group LLC
- Agent Kenneth J. Heywood; Jonathon P. Western
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06N20/00 ; H04L12/26

Abstract:
In one embodiment, a device clusters traffic feature vectors for a plurality of endpoints in a network into a set of clusters. Each traffic feature vector comprises traffic telemetry data captured for one of the endpoints. The device selects one of the clusters for labeling, based in part on contextual data associated with the clusters that was not used to form the clusters. The device obtains a device type label for the selected cluster by providing data regarding the selected cluster and the contextual data associated with that cluster to a user interface. The device provides the device type label and the traffic feature vectors associated with the selected cluster for training a machine learning-based device type classifier.
Public/Granted literature
- US20200160100A1 ACTIVE LEARNING FOR INTERACTIVE LABELING OF NEW DEVICE TYPES BASED ON LIMITED FEEDBACK Public/Granted day:2020-05-21
Information query