US 11,880,806 B2
Systems and methods for automatic candidate assessments
Achim Preuss, Hamburg (DE); Richard Justenhoven, Hamburg (DE); Niels Kruse, Hamburg (DE); and Nicholas Martin, Austin, TX (US)
Assigned to Cut-E Assessment Global Holdings Limited, Loughrea (IE)
Filed by Cut-E Assessment Global Holdings Limited, Loughrea (IE)
Filed on Jul. 7, 2021, as Appl. No. 17/369,121.
Application 17/369,121 is a continuation of application No. 17/160,131, filed on Jan. 27, 2021, granted, now 11,093,901.
Claims priority of provisional application 62/967,443, filed on Jan. 29, 2020.
Prior Publication US 2022/0172172 A1, Jun. 2, 2022
Int. Cl. G06Q 10/10 (2023.01); G06Q 10/1053 (2023.01); G06F 40/242 (2020.01); G10L 15/08 (2006.01); G10L 15/26 (2006.01)
CPC G06Q 10/1053 (2013.01) [G06F 40/242 (2020.01); G10L 15/08 (2013.01); G10L 15/083 (2013.01); G10L 15/26 (2013.01); G10L 2015/088 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A system comprising:
processing circuitry;
a non-transitory data repository to store
a plurality of competency categories,
a plurality of interview questions,
a set of associations between given questions of the plurality of interview questions and given competencies of the plurality of competency categories, and
a natural language classifier personality model trained to identify, from words and phrases present in an interview transcript, personality aspect identifiers that each map to one or more of the plurality of competency categories,
wherein the set of associations comprises a plurality of enabler attributes, wherein the plurality of enabler attributes comprises sets of standardized attributes that provide a translation mechanism for translating competencies into personality aspects that the natural language classifier personality model is trained to automatically identify from an interview transcript; and
a non-transitory computer readable memory coupled to the processing circuitry, the memory storing machine-executable instructions, wherein the machine-executable instructions, when executed on the processing circuitry, cause the processing circuitry to
send, for display to a remote user of the system, one or more interactive screens to accept input from the user defining elements of a candidate interview program, the one or more interactive screens allowing the user to select, as elements of the candidate interview program,
one or more selected competencies from the plurality of competency categories, and
one or more selected interview questions from the plurality of interview questions, based on the selected competencies and the set of associations,
receive, from a remote computing device of a first party via a network, a candidate video and/or audio submission associated with the candidate interview program,
wherein the candidate video and/or audio submission includes a plurality of question responses captured as video or audio responses, and
wherein each question response of the plurality of question responses responds to a respective interview question of the selected interview questions,
for each question response of the plurality of question responses,
generate a transcript of the respective question response, wherein generating the transcript includes applying a speech-to-text algorithm to an audio portion of the respective question response, and
apply the natural language classifier personality model to the transcript to locate personality aspect identifiers within the transcript,
calculate, based on the personality aspect identifiers located within each of the plurality of question responses, a candidate score for each of the selected competencies, and
send, for presentation within a user interface screen of a second remote computing device of a second party responsive to receiving a request to view candidate interview results, one or more of the candidate scores for each of the selected competencies.