Patent search ap:("AT&T Intellectual Property I Page L.P.") AND inv:"Jelena Mirkovic"

1.

发明授权
Prediction of network events via rule set representations of machine learning models 有权

公开(公告)号：US11669751B2

公开(公告)日：2023-06-06

申请号：US17105971

申请日：2020-11-27

Applicant: AT&T Intellectual Property I, L.P. , University of Southern California , President and Fellows of Harvard College

Inventor： Yaron Kanza , Balachander Krishnamurthy , Sivaramakrishnan Ramanathan , Minian Yu , Jelena Mirkovic

IPC: G06F15/16 , G06N5/025 , H04L43/0876 , H04L43/067 , H04L41/16 , H04L41/08

CPC classification number: G06N5/025 , H04L41/16 , H04L43/067 , H04L43/0876 , H04L41/0876

Abstract: A processing system including at least one processor may obtain a time series of measurement values from a communication network and train a prediction model in accordance with the time series of measurement values to predict future instances of an event of interest, where the time series of measurement values is labeled with one or more indicators of instances of the event of interest. The processing system may then generate a deterministic finite automaton based upon the prediction model, convert the deterministic finite automaton into a rule set, and deploy the rule set to at least one network component of the communication network.

2.

发明申请
PREDICTION OF NETWORK EVENTS VIA RULE SET REPRESENTATIONS OF MACHINE LEARNING MODELS 有权

公开(公告)号：US20220172076A1

公开(公告)日：2022-06-02

申请号：US17105971

申请日：2020-11-27

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Yaron Kanza , Balachander Krishnamurthy , Sivaramakrishnan Ramanathan , Minlan Yu , Jelena Mirkovic

IPC: G06N5/02 , G06N3/04 , H04L12/26

Abstract: A processing system including at least one processor may obtain a time series of measurement values from a communication network and train a prediction model in accordance with the time series of measurement values to predict future instances of an event of interest, where the time series of measurement values is labeled with one or more indicators of instances of the event of interest. The processing system may then generate a deterministic finite automaton based upon the prediction model, convert the deterministic finite automaton into a rule set, and deploy the rule set to at least one network component of the communication network.

Patent Agency Ranking