Systems and processes of position fulfillment
Inventors
Grazziotin, Pablo • Boscaini, Lucas • Hoffmann, Leonardo • Kovalski, Filipe
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12271843-B2
Publication Date
2025-04-08
Expiration Date
Abstract
The present disclosure relates generally to systems and processes for position fulfillment and, more particularly, to systems and methods of identifying and matching human resources to an open employment position within an organization. The method includes: obtaining, by a computer system, one or more profiles from one or more data sources; analyzing, by the computer system, the one or more profiles to parse attributes and find similarities and/or recurring occurrences in the parsed attributes; normalizing the parsed attributes based on the at least one similarities and recurring occurrences; and matching the normalized attributes to attributes of an open position.
Core Innovation
The invention relates to HR position-fulfillment systems that obtain a plurality of profiles from at least two data sources, where the profiles are provided in unstructured formats, including free form of different formats and applications. The system uses natural language processing to parse the profiles and identify attributes in the plurality of profiles, and sorts the plurality of profiles into skill categories based on similarities or recurring occurrences in the attributes.
The system normalizes the identified attributes using a neural network by converting the plurality of profiles in the unstructured formats into structured text of a common format. The normalized list of attributes is stored in a database as normalized attributes, and can be used to identify matches by executing a search query in the database using the normalized attributes to match to a set of attributes associated with a user that was in an open position or has certain skill sets desirable for the open position.
The invention supports an iterative and interactive workflow using a graphical user interface displayed on a remote user device. The system displays indications of profiles sorted into skill categories and displays an indication of the normalized attributes that match the set of attributes of the open position responsive to execution of the search query, and automatically updates the indication when a second set of attributes is received and when new profiles are entered into the at least two data sources.
Claims Coverage
The partial document identifies one independent claim (independent claim id clm-00001). The independent claim includes a computer-implemented workflow with natural language processing, neural-network-based normalization into structured text, skill-category sorting, database storage of normalized attributes, and a GUI-driven iterative search and match process with automatic updates and optional filtering, totaling multiple inventive features.
Multi-source profile obtaining and attribute parsing into skill categories
Obtaining a plurality of profiles from at least two data sources provided in unstructured formats, and parsing the plurality of profiles using natural language processing to identify attributes and sorting the plurality of profiles into skill categories based on similarities or recurring occurrences in the attributes.
Neural-network normalization into structured common-format text and database storage
Normalizing a list of attributes using a neural network based on similarities and recurring occurrences, including converting the plurality of profiles in the unstructured formats into structured text of a common format, and storing the normalized list of attributes in a database.
GUI-driven attribute match search and matching display for an open position
Receiving, via the graphical user interface, a selection of a set of attributes associated with a user that was in an open position or has certain skill sets desirable for the open position; executing a search query in the database using the normalized attributes to identify a match of the normalized attributes to the set of attributes of the open position; and displaying, via the graphical user interface, an indication of the normalized attributes that match the set of attributes of the open position.
Automatic updating of matching attributes and subset filtering based on user selection
Receiving a second set of attributes associated with the user; automatically updating the indication of the normalized attributes that match the set of attributes to the open position; displaying the updated indication; receiving a selection of a filter configured to refine the display; determining a subset of the updated indication of the normalized attributes matching the filter; and automatically updating the updated indication to display the subset responsive to the selected filter.
Incremental update of filtered attribute match indications upon ingestion of new profiles from multiple data sources
Responsive to identifying a plurality of new profiles entered into the at least two data sources, updating the subset of the updated indication of the normalized attributes via the graphical user interface, wherein updating comprises automatically updating the subset based on accessing at least a first new profile from a first data source and automatically updating the subset based on accessing at least a second new profile from a second data source.
Independent claim clm-00001 covers end-to-end HR matching of open employment positions to candidate profiles by extracting attributes from unstructured multi-source profiles with natural language processing, sorting into skill categories, normalizing attributes into structured common-format text using a neural network, storing normalized attributes for database search, and providing GUI-driven matching with automatic updates and optional filtering that are refreshed when new profiles are ingested.
Stated Advantages
Enables searching for matches between normalized attributes derived from unstructured profiles and attributes associated with an open position.
Automatically updates the indication of normalized attribute matches responsive to received attributes and responsive to identifying plurality of new profiles entered into at least two data sources.
Allows refining displayed matching results using a selected filter to show a subset of the updated indication of normalized attributes.
Presents match-related information through a graphical user interface displayed on a remote user device.
Documented Applications
Human resources matching for an open employment position by using normalized attributes to identify and display matches for candidate profiles.
Candidate recommendations and job-description generation are described in the provided disclosure summary, including generating a list of attributes based on frequency and using normalized attributes for downstream outputs.
Interested in licensing this patent?