US 12,287,761 B2
Systems and methods for machine learning-based classification of digital computer files using file metadata
Steve Woodward, Canton, MI (US); Alexis Johnson, Canton, MI (US); Stefan Larson, Dexter, MI (US); and Shaun Becker, Canton, MI (US)
Assigned to DryvIQ, Inc., Ann Arbor, MI (US)
Filed by DryvIQ, Inc., Ann Arbor, MI (US)
Filed on Feb. 6, 2023, as Appl. No. 18/106,270.
Claims priority of provisional application 63/328,711, filed on Apr. 7, 2022.
Claims priority of provisional application 63/307,978, filed on Feb. 8, 2022.
Prior Publication US 2023/0251999 A1, Aug. 10, 2023
Int. Cl. G06F 16/16 (2019.01); G06F 16/11 (2019.01)
CPC G06F 16/164 (2019.01) [G06F 16/119 (2019.01)] 10 Claims
OG exemplary drawing
 
1. A machine learning-based method for accelerated content classification and routing of digital files in a data handling and data governance service, the method comprising:
identifying a digital computer file associated with a subscriber to the data handling and data governance service;
sequentially routing the digital computer file to one or more machine learning-based content classification models of a plurality of distinct machine learning-based content classification models based on a service-defined model instantiation and execution sequence, wherein:
(i) the service-defined model instantiation and execution sequence defines a model instantiation and execution order for the plurality of distinct machine learning-based content classification models that enables a fast content classification of the digital computer file while minimizing a computation time or runtime of the one or more machine learning-based content classification models; and
(ii) the one or more machine learning-based content classification models include a machine learning-based filename classification model;
computing, via the machine learning-based filename classification model, a content classification inference based on extracted filename feature data of the digital computer file; and
executing one or more computer-executable instructions based on the content classification inference, wherein executing the one or more computer-executable instructions includes one of:
(a) a routing of the digital computer file to a subsequent machine learning-based content classification model based on the service-defined model instantiation and execution sequence when a content confidence value associated with the content classification inference fails to satisfy a minimum content classification threshold; and
(b) a migration of the digital computer file to a target data storage repository when the content confidence value satisfies the minimum content classification threshold.