US 11,924,151 B2
Methods and systems for analysis and/or classification of electronic information based on objects present in the electronic information
Simon David Ryan, Glen Waverly (AU)
Assigned to Firstwave Technology Pty Ltd, North Sydney (AU)
Filed by Firstwave Technology Pty Ltd, North Sydney (AU)
Filed on Jul. 2, 2020, as Appl. No. 16/919,985.
Application 16/919,985 is a continuation of application No. 15/424,469, filed on Feb. 3, 2017, granted, now 10,742,579.
Application 15/424,469 is a continuation of application No. 13/810,389, granted, now 9,813,367, issued on Apr. 9, 2015, previously published as PCT/AU2011/000896, filed on Jul. 15, 2011.
Claims priority of provisional application 61/344,407, filed on Jul. 16, 2010.
Prior Publication US 2021/0029067 A1, Jan. 28, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 51/212 (2022.01); G06N 5/047 (2023.01); G06N 5/048 (2023.01); G06Q 10/107 (2023.01); G06Q 30/02 (2023.01)
CPC H04L 51/212 (2022.05) [G06N 5/047 (2013.01); G06N 5/048 (2013.01); G06Q 10/107 (2013.01); G06Q 30/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of classifying electronic information comprising:
receiving an electronic message from a live stream source in substantially real time;
breaking down the electronic message received into component parts;
extracting at least one selected object and at least one flow indicator from the component parts;
assigning a signature value to the at least one selected object;
storing the signature value and the at least one flow indicator for at least a predefined period of time;
combining the at least one flow indicator with flow indicators observed in other electronic messages in order to identify at least one flow pattern;
comparing the signature value to at least one database of signature values assigned to objects observed in other electronic messages;
algorithmically predicting a classification for the electronic message based, at leat in part, on the at least one selected object or the at least one flow pattern meeting at least one predefined classification threshold;
monitoring the at least one predicted classification threshold for the at least one selected object or the at least one flow pattern over a predefined period of time; and
updating the predicted classification based, at least in part, on a greater statistical weight of observations that modifies the initial prediction.