US 11,943,122 B2
Management data analytics
Yizhi Yao, Chandler, AZ (US); and Joey Chou, Scottsdale, AZ (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Oct. 2, 2020, as Appl. No. 17/062,006.
Claims priority of provisional application 62/910,053, filed on Oct. 3, 2019.
Prior Publication US 2021/0021494 A1, Jan. 21, 2021
Int. Cl. H04L 43/06 (2022.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); H04L 41/0631 (2022.01); H04L 41/147 (2022.01); H04L 41/16 (2022.01); H04L 41/5009 (2022.01); H04L 41/5067 (2022.01); H04L 43/04 (2022.01)
CPC H04L 43/06 (2013.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01); H04L 41/0631 (2013.01); H04L 41/147 (2013.01); H04L 41/5009 (2013.01); H04L 43/04 (2013.01); H04L 41/16 (2013.01); H04L 41/5067 (2013.01)] 16 Claims
OG exemplary drawing
 
1. An apparatus to be employed as a Management Data Analytics Service (MDAS) producer, the apparatus comprising:
network interface circuitry (NIC) configurable to:
obtain input data related to one or more managed networks and services from one or more data sources,
provide an analytics report to an MDAS consumer for root cause analysis of ongoing issues, prevention of potential issues, and prediction of network or service demands, and
obtain, from the MDAS consumer, at least one execution report describing actions taken by the MDAS consumer based on the analytics report, wherein the at least one execution report is based on past actions taken by the MDAS consumer; and
processor circuitry communicatively coupled with the NIC, the processor circuitry configurable to:
prepare and process the input data,
operate a machine learning (ML) model to analyze the prepared and processed input data, wherein the analysis includes classification of the input data, correlation of the input data with historical data and the at least one execution report provided by the MDAS consumer, learning or recognition of one or more data patterns based on the correlation, and derivation of inferences, insights, and predictions based on the learning or recognition,
generate the analytics report based on the analysis,
evaluate results of the actions taken by the MDAS consumer, and
tune the ML model based on the evaluated results of the actions taken by the MDAS consumer.