US 12,033,416 B2
Devices, systems and methods for assessing a match between job descriptions and resumes
Javier Ponce Suarez, Brooklyn, NY (US); Oscar Vergé Arderiu, Brooklyn, NY (US); Mandar Naik, Mumbai Maharashtra (IN); and Ruben Robledo Velazquez, Valladolid (ES)
Assigned to ATOS France, Bezons (FR)
Filed by Atos IT Solutions and Services, Inc., New Castle, DE (US)
Filed on Jan. 4, 2021, as Appl. No. 17/140,317.
Prior Publication US 2022/0215196 A1, Jul. 7, 2022
Int. Cl. G06V 30/418 (2022.01); G06F 18/21 (2023.01); G06F 18/214 (2023.01); G06F 18/2411 (2023.01); G06N 20/00 (2019.01); G06Q 10/1053 (2023.01); G06V 30/19 (2022.01); G06V 30/414 (2022.01)
CPC G06V 30/418 (2022.01) [G06F 18/214 (2023.01); G06F 18/2178 (2023.01); G06F 18/2411 (2023.01); G06N 20/00 (2019.01); G06Q 10/1053 (2013.01); G06V 30/414 (2022.01)] 14 Claims
OG exemplary drawing
 
1. A device configured for assessing a match between job descriptions and resumes, the device comprising:
a memory that stores
a first database comprising one or more job description documents, each job description document of the one or more job description documents defining a description of a job, and
a second database comprising one or more resume documents, each resume document of the one or more resume documents defining a resume for applying to a job description,
a receiver configured to receive a matching request from a user, wherein the matching request comprises at least one document provided by the user,
a first machine learning engine configured to determine a correlation between the matching request and a keyword-based data structure, the keyword-based data structure defining, for said each job description document of the first database and for said each resume document of the second database, one or more predefined keywords that have been found in the each job description document and the each resume document, the first machine learning engine implementing a classification algorithm,
at least one processor configured to generate a matching score based on a strength of the correlation,
a second machine learning engine configured to extract one or more keywords from the each job description document and the each resume document, the second machine learning engine implementing a supervised learning algorithm and having been trained to determine whether said one or more predefined keywords are found in a given document, and
wherein the at least one processor is further configured to use the one or more predefined keywords as the matching request.