US 11,854,537 B2
Systems and methods for parsing and correlating solicitation video content
Arran Stewart, Austin, TX (US); and Steve O'Brien, Raleigh, NC (US)
Assigned to MY JOB MATCHER, INC., Austin, TX (US)
Filed by MY JOB MATCHER, INC., Austin, TX (US)
Filed on Jan. 31, 2023, as Appl. No. 18/103,713.
Application 18/103,713 is a continuation of application No. 17/487,157, filed on Sep. 28, 2021, granted, now 11,574,629, issued on Feb. 7, 2023.
Prior Publication US 2023/0178073 A1, Jun. 8, 2023
Int. Cl. G10L 15/18 (2013.01); G06V 20/40 (2022.01); G10L 25/57 (2013.01); G06V 10/94 (2022.01)
CPC G10L 15/18 (2013.01) [G06V 20/41 (2022.01); G06V 10/95 (2022.01); G10L 25/57 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A system for parsing and correlating solicitation video content, the system comprising a computing device configured to:
receive a solicitation video related to a subject, wherein the solicitation video comprises:
at least an image component, wherein the at least an image component comprises non-verbal content; and
at least an audio component, wherein the at least an audio component comprises audible verbal content related to at least an attribute of the subject;
transcribe at least a keyword as a function of the at least an audio component using an automatic speech recognition process, wherein the automatic speech recognition process comprises performing voice recognition on the audio component in order to identify a speaker and further comprises a speaker dependent automatic speech recognition process which is a type of automatic speech recognition process that uses training that is specific to the speaker;
classify, using a machine vision process comprising a classifier, the non-verbal content to at least a feature,
associate the subject with at least a job description as a function of the at least a keyword and the at least a feature; and
calculate a ranking of the subject out of a plurality of candidates, wherein the ranking is based on a description-centric ranking factor.