Granted Patent B2

US 12,507,156 · App. 18/061,986 · Granted Dec 23, 2025

Inventors: Matthew A. Silverman (Shaker Heights, OH); Michael B. Delong (Macedonia, OH); Ashish Pasha Sheikh (Akron, OH); Federico Lovison (Fontanelle, IT)

Assignee: Cisco Technology, Inc.

H04W48/08G01S5/02521H04W24/08

Abstract

Claims (60)

1 . A method, comprising:

receiving data describing radio frequency characteristics of a wireless network transmission environment;

presenting the data for display on a graphical user interface (GUI) associated with a network device in the wireless network;

receiving input from the GUI identifying one or more portions of the data; and

training a machine learning (ML) model to classify an interferer in the wireless network transmission environment using the identified one or more portions of the data;

classifying an additional one or more portions of the data as relating to the interferer, using the ML model;

presenting the classified additional one or more portions of the data for display on the GUI;

receiving a second input from the GUI reflecting accuracy of the classification of the additional one or more portions of the data as relating to the interferer; and

further training the ML model using the second input.

2 . The method of claim 1 ,

wherein the data describing the wireless network transmission environment is captured at a wireless access point (AP), and

wherein the GUI is associated with at least one of: (i) the AP or (ii) a controller in the network environment.

3 . The method of claim 2 , further comprising:

transmitting the trained ML model to the AP, wherein the AP is configured to classify the interferer using the trained ML model.

4 . The method of claim 1 , wherein receiving input from the GUI identifying one or more portions of the data comprises receiving input identifying one or more portions of the data reflecting the interferer.

5 . The method of claim 1 ,

wherein the data describing radio frequency characteristics of the wireless network transmission environment comprises spectrogram data describing radio frequency and time characteristics of the wireless network transmission environment, and

wherein receiving the input from the GUI identifying one or more portions of the data comprises receiving identification of one or more portions of the spectrogram data.

6 . The method of claim 1 , further comprising:

identifying one or more known signals in the received data based on using one or more previously generated classifiers with the received data; and

displaying one or more unknown signals in the data on the GUI, based on the identified one or more known signals.

7 . The method of claim 1 , further comprising:

determining that the ML model is sufficiently trained based on the received second input from the GUI.

8 . The method of claim 1 ,

wherein the wireless network transmission environment comprises a WiFi network supporting a 6 GHz band, and

wherein the interferer in the wireless network transmission environment operates using at least a portion of the 6 GHz band.

9 . The method of claim 1 , further comprising:

configuring one or more parameters for the wireless network based on classifying the interferer using the trained ML model.

10 . A system, comprising:

a processor; and

a memory having instructions stored thereon which, when executed on the processor, performs operations comprising:

receiving data describing radio frequency characteristics of a wireless network transmission environment;

presenting the data for display on a graphical user interface (GUI) associated with a network device in the wireless network;

receiving input from the GUI identifying one or more portions of the data;

training a machine learning (ML) model to classify an interferer in the wireless network transmission environment using the identified one or more portions of the data;

classifying an additional one or more portions of the data as relating to the interferer, using the ML model;

presenting the classified additional one or more portions of the data for display on the GUI;

receiving a second input from the GUI reflecting accuracy of the classification of the additional one or more portions of the data as relating to the interferer; and

further training the ML model using the second input.

11 . The system of claim 10 ,

wherein the data describing the wireless network transmission environment is captured at a wireless access point (AP), and

wherein the GUI is associated with at least one of: (i) the AP or (ii) a controller in the network environment.

12 . The system of claim 11 , the operations further comprising:

transmitting the trained ML model to the AP, wherein the AP is configured to classify the interferer using the trained ML model.

13 . The system of claim 10 , wherein receiving input from the GUI identifying one or more portions of the data comprises receiving input identifying one or more portions of the data reflecting the interferer.

14 . A non-transitory computer-readable medium having instructions stored thereon which, when executed by a processor, performs operations comprising:

receiving data describing radio frequency characteristics of a wireless network transmission environment;

presenting the data for display on a graphical user interface (GUI) associated with a network device in the wireless network;

receiving input from the GUI identifying one or more portions of the data;

training a machine learning (ML) model to classify an interferer in the wireless network transmission environment using the identified one or more portions of the data;

classifying an additional one or more portions of the data as relating to the interferer, using the ML model;

presenting the classified additional one or more portions of the data for display on the GUI;

receiving a second input from the GUI reflecting accuracy of the classification of the additional one or more portions of the data as relating to the interferer; and

further training the ML model using the second input.

15 . The non-transitory computer-readable medium of claim 14 ,

wherein the data describing the wireless network transmission environment is captured at a wireless access point (AP), and

wherein the GUI is associated with at least one of: (i) the AP or (ii) a controller in the network environment.

16 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:

transmitting the trained ML model to the AP, wherein the AP is configured to classify the interferer using the trained ML model.

17 . The non-transitory computer-readable medium of claim 14 , wherein receiving input from the GUI identifying one or more portions of the data comprises receiving input identifying one or more portions of the data reflecting the interferer.

Assignments (1)

Continuity (1)

References Cited (16)