METHOD AND RELATIVE IMPLEMENTATION THROUGH AN ELECTRONIC DEVICE FOR THE ANALYSIS OF THE FLOW OF DATA PRESENT WITHIN AN IOT SYSTEM FOR A PRECISE DOMAIN OF INTEREST FOR PROBABILISTIC EVENT IDENTIFICATION

(19)

(11)

EP 4 086 794 A8

(12)	CORRECTED EUROPEAN PATENT APPLICATION
	Note: Bibliography reflects the latest situation

(15)	Correction information:
	Corrected version no 1 (W1 A1)

(48)	Corrigendum issued on:
	04.01.2023 Bulletin 2023/01

(43)	Date of publication:
	09.11.2022 Bulletin 2022/45

(21)	Application number: 22168635.5

(22)	Date of filing: 15.04.2022

(51)

International Patent Classification (IPC):

G06F 21/55^(2013.01)

H04L 9/40^(2022.01)

(52)	Cooperative Patent Classification (CPC):
	G06F 21/554; H04L 63/1425; H04L 63/1441

(84)	Designated Contracting States:
	AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
	Designated Extension States:
	BA ME
	Designated Validation States:
	KH MA MD TN

(30)

Priority:

15.04.2021 IT 202100009548

(71)	Applicant: Minervas S.r.l.
	84084 Fisciano (SA) (IT)

(72)	Inventors:
	PASCALE, Francesco 84025 EBOLI (SA) (IT) ADINOLFI, Ennio, Andrea 84013 CAVA DE' TIRRENI (SA) (IT) COPPOLA, Simone 84091 BATTIPAGLIA (SA) (IT) SANTONICOLA, Emanuele 84014 NOCERA INFERIORE (SA) (IT)

(74)	Representative: Marchioro, Paolo
	Studio Bonini S.r.l. Corso Fogazzaro, 8 36100 Vicenza 36100 Vicenza (IT)

(54)	METHOD AND RELATIVE IMPLEMENTATION THROUGH AN ELECTRONIC DEVICE FOR THE ANALYSIS OF THE FLOW OF DATA PRESENT WITHIN AN IOT SYSTEM FOR A PRECISE DOMAIN OF INTEREST FOR PROBABILISTIC EVENT IDENTIFICATION

(57) A method (1) implemented by electronic computer for analysing data traffic within a computer network of an loT system in a precise domain of interest, in order to identify the occurrence of one or more events in that domain. The method envisages acquiring a plurality of data packages (6) of the data traffic coming from the computer network, calculating the mean square value (RMS) of each of the acquired parameters, comparing the calculated mean square values (RMS) so as to identify the most probable scenario, placing the mean square values (RMS) as input to a Bayesian network (9) pre-constituted and suitably trained by means of the values relative to the parameters of the specific scenario identified, where this Bayesian network (9) provides as output a probability index of the occurrence of an event.