US 12,321,704 B2
Composite extraction systems and methods for artificial intelligence platform
Paul O'Hagan, Brooklin (CA); Isidre Royo Bonnin, Terrassa (ES); Robert Kapitan, Lachine (CA); Ravinder Reddy Yeddla, Hyderabad (IN); and Renaud Levert, Montreal (CA)
Filed by OPEN TEXT CORPORATION, Waterloo (CA)
Filed on Oct. 31, 2022, as Appl. No. 17/977,432.
Application 17/977,432 is a continuation of application No. 17/508,820, filed on Oct. 22, 2021, granted, now 12,141,528.
Prior Publication US 2023/0127562 A1, Apr. 27, 2023
Int. Cl. G06F 40/295 (2020.01); G06F 16/33 (2019.01); G06F 16/334 (2025.01); G06F 16/34 (2019.01); G06F 16/38 (2019.01); G06F 40/30 (2020.01)
CPC G06F 40/295 (2020.01) [G06F 16/3344 (2019.01); G06F 16/34 (2019.01); G06F 16/38 (2019.01); G06F 40/30 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method for content analysis, comprising:
receiving content on a server, the server executing a composite module engine, wherein the composite module engine utilizes a plurality of modules for assessing the content;
executing a composite of the plurality of modules, by the composite module engine, said executing comprising:
defining a plurality of meta-data fields corresponding to content-of-interest within the content, each meta-data field associated with an assessment level;
defining a plurality of meta-data rules, a least a portion of the meta-data rules associated with patterns in the content;
defining a plurality of meta-data field context rules to analyze a context for each meta-data field;
generating a plurality of meta-data field instances within the content, each meta-data field instance associated with one of the meta-data fields, said generating based at least in part on the plurality of meta-data rules; and
for each meta-data field instance, generating a meta-data field context based at least in part on the meta-data field context rules;
generating, by the composite module engine, an assessment for each meta-data field instance based on the meta-data field context for the meta-data field instance and the assessment level of the associated meta-data field; and
generating, by the composite module engine, a classification meta-data field for the content by applying a meta-data rule to each assessment of the respective meta-data field instances.