公开(公告)号：US20220036202A1

公开(公告)日：2022-02-03

申请号：US17387979

申请日：2021-07-28

Applicant: Parallel Wireless, Inc.

Inventor： Murli Sivashanmugam ,  Babu Rajagopal ,  Seshashayi Thalluri

IPC: G06N5/02 ,  H04W24/08

Abstract: Systems, methods and computer software are disclosed for providing intelligent traffic classification at a mobile edge using Artificial Intelligence (AI). In one embodiment, a method is disclosed, comprising: receiving a packet; performing Prediction Function (PF) feature extraction on the packet; performing, using a light weight AI model, traffic type classification for the packet based on the feature extraction; performing Learning Function (LF) feature extraction on the packet; determining, using a heavy weight AI model, features and predictions for the packet; classifying the packet by the heavy weight AI model; and sending a determined traffic class to the light weight AI model.

公开(公告)号：US20220309243A1

公开(公告)日：2022-09-29

申请号：US17703411

申请日：2022-03-24

Applicant: Parallel Wireless, Inc.

Inventor： Murli Sivashanmugam ,  Amod Mishra

IPC: G06F40/274 ,  H04L41/0803 ,  G06F3/0481 ,  G06F40/284

Abstract: Systems, computer readable media and methods are disclosed for providing Artificial Intelligence (AI) based AutoComplete for network node configuration. In one embodiment a method includes predicting a configuration to use based on a model, wherein predicting a configuration comprises: accepting user inputs; converting, by a tokenizer, the user inputs into word tokens; taking, by the model, the word tokens as input sequences and using transfer learning methods calculating parameters of occurrences of next words; and ranking the word tokens according to values of their parameters wherein word tokens with a highest value are suggested to a user for auto completion of the network node configuration.