Granted Patent B2

US 12,423,658 · App. 16/380,411 · Granted Sep 23, 2025

Inventors: Rafael Gomes (Porto Alegre, BR); Eduardo Hoefel (Porto Alegre, BR); Andre Mendes (Porto Alegre, BR); Bruna Gouveia (Porto Alegre, BR); Leandro Eidelwein (Porto Alegre, BR); Roberto Dias (Sao Paulo, BR)

Assignee: ADP, Inc.

G06Q10/1053G06N20/00

Abstract

Claims (82)

1. A computer-implemented method, comprising:

receiving, by one or more processors coupled with memory, resume data of a candidate;

embedding, by the one or more processors, the resume data of the candidate into a metadata representation of the candidate within a metadata repository, wherein the metadata repository includes a first plurality of jobs and a first plurality of resume data of candidates successfully hired for the first plurality of jobs;

receiving, by the one or more processors, a notification of a job opening for a new job opportunity with an employer;

executing, by the one or more processors, a machine learning process configured to cluster the first plurality of resume data to generate a second plurality of resume data of candidates successfully hired for jobs similar to the new job opportunity based on a comparison of one or more attributes of each job of the first plurality of jobs to one or more attributes of the new job opportunity;

determining, by the one or more processors using the machine learning process, a target item missing from the metadata representation of the candidate based on a comparison of the metadata representation of the candidate to the second plurality of resume data of candidates successfully hired for jobs similar to the new job opportunity;

engaging, by the one or more processors, responsive to the determination that the target item is missing from the metadata representation of the candidate, the candidate using an artificial intelligence chat bot agent in an automated interview process comprising:

transmitting, by the one or more processors to the candidate, a query generated based on the target item;

receiving, by the one or more processors from the candidate, a response to the query, the response comprising interview audio and image data from the candidate using a microphone and a camera;

extracting, by the one or more processors, audio data from the interview audio, the audio data including words of the response;

assigning, by the one or more processors, a label to one or more of the words of the response, wherein the label indicates that the one or more words of the response are a non-word sound; and

determining, by the one or more processors, a percentage of non-word sounds based on a number of labels assigned to the words of the response;

determining, by the one or more processors, a value for the target item based on a comparison of the percentage of non-word sounds to a threshold value;

generating, by the one or more processors, an updated metadata representation of the candidate based on the metadata representation of the candidate and the value for the target item;

determining, by the one or more processors, that the candidate qualifies for the new job opportunity based on a comparison of the updated metadata representation of the candidate to the second plurality of resume data of candidates successfully hired for jobs similar to the new job opportunity;

providing, by the one or more processors, to a user interface of a device of the employer, an indication that the candidate qualifies for the job opening responsive to determining the candidate qualifies for the new job opportunity;

providing, by the one or more processors, to the user interface of the device of the employer, a one-click process for hiring the candidate for the job opening utilizing the metadata representation of the candidate updated to include the value for the target item determined during the automated interview process, responsive to recommending the candidate to the employer;

executing, by the one or more processors, a hiring process to hire the candidate for the job opening responsive to receiving a selection of the one-click hiring process from the device of the employer; and

notifying, by the one or more processors, the employer the candidate has filled the job opening, responsive to executing the hiring process to hire the candidate.

2. The method of claim 1 , wherein the one or more attributes of each job of the first plurality of jobs and the new job opportunity are selected from the group consisting of job title, requisite employment experience, requisite educational achievements, skills, industry type of the employer, geographic location of job opportunity, temporal context, and employment trends of the industry type of the employer.

3. The method of claim 2 , wherein the machine learning process comprises parallel execution of a plurality of multi-agent machine learning processes in order to cluster the first plurality of resume data to generate a second plurality of resume data.

4. The method of claim 3 , wherein the plurality of multi-agent machine learning processes comprise a dimensional data reduction selected from the group consisting of principal component analysis, T-distributed stochastic neighbor embedding, density-based spatial clustering of applications with noise and ordering points to identify a clustering structure.

5. The method of claim 2 , further comprising:

acquiring, by the one or more processors, resume data from the candidate comprising current and historic employment, job skills and education information;

extracting, by the one or more processors, additional resume data for the candidate from sources identified as relevant to the candidate or to the acquired resume data;

generating, by the one or more processors, confirmed resume data values via disambiguation of the extracted and acquired data; and

embedding, by the one or more processors, the configured resume data values into the metadata representation of the candidate within the repository.

6. The method of claim 5 , wherein the extracted additional resume data is selected from the group consisting of:

changes that are extracted from postings linked to the candidate within a social media service that are selected from the group consisting of marital status, domicile, residence, nationality, visa status, job title, education information and employer information;

text content data that is extracted from a newsfeed, a governmental record, a credit report agency record or an insurance company record;

climate data for residence, work and travel locations of the candidate;

news events extracted from a new media source comprising an employment-related new announcement; and

operating system and current and historic geolocation data extracted from a mobile device of the candidate.

7. A system, comprising:

a processor;

a computer readable memory in circuit communication with the processor;

a computer readable storage medium in circuit communication with the processor; and

wherein the processor executes program instructions stored on the computer readable storage medium via the computer readable memory and thereby:

receives resume data of a candidate;

embeds the resume data of the candidate into a metadata representation of the candidate within a metadata repository, wherein the metadata repository includes a first plurality of jobs and a first plurality of resume data of candidates successfully hired for the first plurality of jobs;

receives a notification of a job opening for a new job opportunity with an employer;

executes a machine learning process configured to cluster the first plurality of resume data to generate a second plurality of resume data of candidates successfully hired for jobs similar to the new job opportunity based on a comparison of one or more attributes of each job of the first plurality of jobs to one or more attributes of the new job opportunity;

determines, using the machine learning process, a target item missing from the metadata representation of the candidate based on a comparison of the metadata representation of the candidate to the second plurality of resume data of candidates successfully hired for jobs similar to the new job opportunity;

engages, responsive to the determination that the target item is missing from the metadata representation of the candidate, the candidate using an artificial intelligence chat bot agent in an automated interview process comprising:

transmitting, to the candidate, a query generated based on the target item;

receiving, from the candidate, a response to the query, the response comprising interview audio and image data from the candidate using a microphone and a camera;

extracting audio data from the interview audio, the audio data including words of the response;

assigning a label to one or more of the words of the response, wherein the label indicates that the one or more words of the response are a non-word sound; and

determining a percentage of non-word sounds based on a number of labels assigned to the words of the response;

determines a value for the target item based on a comparison of the percentage of non-word sounds to a threshold value;

generates an updated metadata representation of the candidate based on the metadata representation of the candidate and the value for the target item;

determines that the candidate qualifies for the new job opportunity based on a comparison of the updated metadata representation of the candidate to the second plurality of resume data of candidates successfully hired for jobs similar to the new job opportunity;

provides, to a user interface of a device of the employer, an indication that the candidate qualifies for the job opening responsive to determining the candidate qualifies for the new job opportunity;

provides, to the user interface of the device of the employer a one-click process for hiring the candidate for the job opening utilizing the metadata representation of the candidate updated to include the value for the target item determined during the automated interview process, responsive to recommending the candidate to the employer;

executes a hiring process to hire the candidate for the job opening, responsive to receiving a selection of the one-click process from the device of the employer; and

notifies the employer the candidate has filled the job opening, responsive to executing the hiring process to hire the candidate.

8. The system of claim 7 , wherein the one or more attributes of each job of the first plurality of jobs and the new job opportunity are selected from the group consisting of job title, requisite employment experience, requisite educational achievements, skills, industry type of the employer, geographic location of job opportunity, temporal context, and employment trends of the industry type of the employer.

9. The system of claim 8 , wherein the machine learning process comprises parallel execution of a plurality of multi-agent machine learning processes in order to cluster the first plurality of resume data to generate a second plurality of resume data; and

wherein the plurality of multi-agent machine learning processes comprise a dimensional data reduction selected from the group consisting of principal component analysis, T-distributed stochastic neighbor embedding, density-based spatial clustering of applications with noise and ordering points to identify a clustering structure.

10. A computer program product, comprising:

a computer readable storage medium having computer readable program code embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the computer readable program code comprising instructions for execution by a processor that cause the processor to:

receive resume data of a candidate;

embed the resume data of the candidate into a metadata representation of the candidate within a metadata repository, wherein the metadata repository includes a first plurality of jobs and a first plurality of resume data of candidates successfully hired for the first plurality of jobs;

receive a notification of a job opening for a new job opportunity with an employer;

execute a machine learning process configured to cluster the first plurality of resume data to generate a second plurality of resume data of candidates successfully hired for jobs similar to the new job opportunity based on a comparison of one or more attributes of each job of the first plurality of jobs to one or more attributes of the new job opportunity;

determine, using the machine learning process, a target item missing from the metadata representation of the candidate based on a comparison of the metadata representation of the candidate to the second plurality of resume data of candidates successfully hired for jobs similar to the new job opportunity;

engage, responsive to the determination that the target item is missing from the metadata representation of the candidate, the candidate using an artificial intelligence chat bot agent in an automated interview process comprising:

transmitting, to the candidate, a query generated based on the target item;

receiving, from the candidate, a response to the query, the response comprising interview audio and image data from the candidate using a microphone and a camera;

extracting audio data from the interview audio, the audio data including words of the response;

assigning a label to one or more of the words of the response, wherein the label indicates that the one or more words of the response are a non-word sound; and

determining a percentage of non-word sounds based on a number of labels assigned to the words of the response;

determine a value for the target item based on a comparison of the percentage of non-word sounds to a threshold value;

generate an updated metadata representation of the candidate based on the metadata representation of the candidate and the value for the target item;

determine that the candidate qualifies for the new job opportunity based on a comparison of the updated metadata representation of the candidate to the second plurality of resume data of candidates successfully hired for jobs similar to the new job opportunity;

provide to a user interface of a device of the employer, an indication that the candidate qualifies for the job opening responsive to determining the candidate qualifies for the new job opportunity:

provide, to the user interface of the device of the employer, a one-click process for hiring the candidate for the job opening utilizing the metadata representation of the candidate updated to include the value for the target item determined during the automated interview process, responsive to recommending the candidate to the employer;

execute a hiring process to hire the candidate for the job opening responsive to receiving a selection of the one-click hiring process from the device of the employer; and

notify the employer the candidate has filled the job opening, responsive to executing the hiring process to hire the candidate for the job opening.

11. The computer program product of claim 10 , wherein the one or more attributes of each job of the first plurality of jobs and the new job opportunity are selected from the group consisting of job title, requisite employment experience, requisite educational achievements, skills, industry type of the employer, geographic location of job opportunity, temporal context, and employment trends of the industry type of the employer.

12. The computer program product of claim 11 , wherein the machine learning process comprises parallel execution of a plurality of multi-agent machine learning processes in order to cluster the first plurality of resume data to generate a second plurality of resume data; and

wherein the plurality of multi-agent machine learning processes comprise a dimensional data reduction selected from the group consisting of principal component analysis, T-distributed stochastic neighbor embedding, density-based spatial clustering of applications with noise and ordering points to identify a clustering structure.

Assignments (2)

Continuity (1)

References Cited (20)