US 12,106,250 B2
Skill-gap analysis and recommender system
Gowri Srinivasa, Bengaluru (IN); Chiranth Jawahar, Bengaluru (IN); Diya Chandra, Bangalore (IN); and Namrata Ramesh, Bangalore (IN)
Assigned to PES UNIVERSITY, Bengaluru (IN)
Filed by PES University, Bengaluru (IN)
Filed on Mar. 14, 2022, as Appl. No. 17/693,691.
Claims priority of application No. 202241002228 (IN), filed on Jan. 14, 2022.
Prior Publication US 2023/0230011 A1, Jul. 20, 2023
Int. Cl. G06Q 10/00 (2023.01); G06F 16/903 (2019.01); G06Q 10/0639 (2023.01); G06Q 50/20 (2012.01)
CPC G06Q 10/06393 (2013.01) [G06F 16/90335 (2019.01); G06Q 50/2057 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A computerized system for receiving a real time goal set by a student, performing skill gap analysis and providing a tailored recommendation for said student to fill said skill gap in an educational institution, comprising:
an input/output device serving as an interface for said student;
a controller processing unit and operating system, with transfer of control from said input/output device to a personalized education and skill map generator module;
a database repository of student, university and recruiter information;
said personalized education and skill map generator module, further comprising:
a search engine for receiving a query from said student on a career goal, parsing of said query of said student to extract question words, named entities and discourse markers, and map said extractions to relevant instances in said database, wherein said search engine applies a modified adaptive association pattern mining model for creation of meta categories to capture infrequent patterns or rare opportunities available to the student, and conducts a drill-down for specifics to cater to individual needs of said student, said modified adaptive association pattern mining model performing the processes of:
dynamically forming categories through recording instantiations within a single category as equivalent, and encoding its presence 1 or absence 0, and clustering of related categories through a curated and/or domain-aware hierarchy of categories to determine meaningful frequent itemsets, wherein said itemsets contribute to the generation of association patterns or rules;
automatically drilling down within a sub-set of relevant rows of data to match with a student's profile and elicit the most relevant instantiations of a metacategory to make meaningful specific recommendations to the student;
modeling a trend in historical data in a dataset, and forming new associations through observing changes in the instantiations within a category and thereby adapting to changes in real-time;
a skill gap analyzer module for checking aggregated statistics for a search conducted through said search engine against a skill level of said student, and identifying the skill gap of the student;
recommender module for identifying a temporal factor for every said skill gap to suggest remedial or actionable next steps and for identifying a frequency to suggest actionable next steps or bonus next steps recommendations based on past data; and
goal tracker module for presenting a list of all said recommendations ordered in a decreasing order of their importance and urgency, wherein said goal tracking module provides an assessment of a time-sensitivity of a goal and a mechanism for students to track their progress through prioritizing short and long term goals, and wherein these goals are assessed at regular intervals with reminders at a frequency determined by a user and alerts to any opportunities that would facilitate achieving the goals.