WO2019106437A2 - Mise en correspondance de soumissions de travail avec des offres de travail - Google Patents

Mise en correspondance de soumissions de travail avec des offres de travail Download PDF

Info

Publication number
WO2019106437A2
WO2019106437A2 PCT/IB2018/001531 IB2018001531W WO2019106437A2 WO 2019106437 A2 WO2019106437 A2 WO 2019106437A2 IB 2018001531 W IB2018001531 W IB 2018001531W WO 2019106437 A2 WO2019106437 A2 WO 2019106437A2
Authority
WO
WIPO (PCT)
Prior art keywords
work
bids
offers
job
skills
Prior art date
Application number
PCT/IB2018/001531
Other languages
English (en)
Other versions
WO2019106437A3 (fr
Inventor
Paula D. GUEDES
Eduardo S. LABER
Alexandre R. RENTERIA
Original Assignee
Jobzi Inteligencia De Dados Na Internet, Ltda.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jobzi Inteligencia De Dados Na Internet, Ltda. filed Critical Jobzi Inteligencia De Dados Na Internet, Ltda.
Publication of WO2019106437A2 publication Critical patent/WO2019106437A2/fr
Publication of WO2019106437A3 publication Critical patent/WO2019106437A3/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/105—Human resources
    • G06Q10/1053—Employment or hiring

Definitions

  • the field relates generally to the processing of bids for work and offers for work, such as matching job seekers with job descriptions.
  • Matching the appropriate combination of functions, knowledge, skills and abilities to produce a given work demand is a challenging effort.
  • human capital for example, the challenge of matching the right bundle of productive functions, knowledge, skills and abilities towards a given work demand is particularly cumbersome.
  • job openings represent a given work demand and job seekers represent a bundle of productive functions, knowledge, skills and abilities.
  • a method comprises obtaining one or more bids for work and one or more offers for work; employing Natural Language Processing techniques to interpret work-specific terminology from one or more of the bids for work and the offers for work; and matching one or more of the bids for work with one or more of the offers for work based on a predefined distance measure between the bids for work and the offers for work.
  • the bids for work comprise job postings for work by one or more of humans and machines and the offers for work comprise resumes.
  • the Natural Language Processing techniques identify one or more characteristics that are implicit in one or more of the bids for work and the offers for work.
  • the matching optionally comprises one or more of: (i) the steps of measuring a relevance of one or more implicit skill requirements for a given job title and identifying one or more additional job titles that demand the one or more implicit skill requirements that satisfy a predefined frequency threshold; and (it) assigning one or more of a weight and a particularity to one or more skills for a given job title.
  • the predefined distance measure between the bids for work and the offers for work comprises a degree of matching between two or more of the bids for work and the offers for work and a degree of quantifiable mismatching between the two or more of the bids for work and the offers for work.
  • illustrative embodiments include, without limitation, apparatus, systems, methods and computer program products comprising processor-readable storage media.
  • FIG. 1 illustrates the work experience and education of a given work seeker over time, according to at least one embodiment of the disclosure
  • FIG. 2 illustrates a matching system 200 for matching bids for work with offers for work, according to one embodiment
  • FIG. 3A illustrates an exemplary job/resume skills intersection process performed by the job and resume skills intersection module of FIG. 2, according to some embodiments of the disclosure
  • FIG. 3B illustrates a skillSetSizeFactor as a function of number of skills, as processed by the job/resume skills intersection process of FIG. 3A, according to an embodiment
  • FIG. 4A illustrates an exemplary mapping from a vesumeEducationLevel and a jobEclucationLevel from a processed user’s resume to find an associated educationF actor, as employed by one or more embodiments of the disclosure
  • FIG. 4B illustrates an exemplary mapping from a metaWorkEducationLevel and an resumeEducationLevel, when a minimum education level requirement is not specified in a job posting, to find an associated educationF actor, as employed by at least one embodiment of the disclosure
  • FIG. 5 illustrates an exemplary job/resume experience match process performed by the job/resume experience match module of FIG. 2, according to some embodiments of the disclosure
  • FIG. 6 illustrates an assignment of a weight to a job/resume skills intersection based on a number of skills identified in a job posting, in one embodiment
  • FIG. 7 illustrates an exemplary processing platform that may be used to implement at least a portion of one or more embodiments of the disclosure comprising a cloud infrastructure
  • FIG. 8 illustrates another exemplary processing platform that may be used to implement at least a portion of one or more embodiments of the disclosure.
  • bids for work and offers for work are processed using Natural Language Processing techniques to interpret work-specific terminology from the bids for work and the offers for work.
  • a bid for work is matched with an offer for work based on a predefined distance measure between the bids for work and the offers for work.
  • the predefined distance measure may be, for example, a degree of quantifiable matching between two or more bids for work and/or offers for work and a degree of quantifiable mismatching between two or more of bids for work and/or offers for work.
  • the bids for work may be, for example, job postings and the offers for work may be, for example, resumes.
  • the bids for work may request the work of humans and/or machines.
  • the bids for work are matched with offers for work by measuring a relevance of implicit skills skill requirements for a given job title and identifying one or more additional job titles that demand the implicit skill requirements skills based on a predefined frequency threshold.
  • a weight and/or a particularity are optionally assigned to skills for a given job title.
  • the Natural Language Processing techniques identify implicit characteristics in the bids for work and/or the offers for work and employ a job ontology of vocabulary terms.
  • a an example would be: in a scenario with a relatively small number of work offerings (e.g., 1 Million jobs) and a relatively small number of relative solutions (e.g., 10 Million resumes), there are 10 trillion possibilities; it is impossible for any human to compare the quality of 10 trillion pairs to find the best fit.
  • a relatively small number of work offerings e.g., 1 Million jobs
  • a relatively small number of relative solutions e.g., 10 Million resumes
  • one or more embodiments of the disclosed methods relate to:
  • NLP Natural Language Processing
  • Jobzi Points quantify a distance between a bundle of work functions, knowledge, skills, and abilities (e.g., as expressed in a resume) and a work requirement (e.g., as expressed in a job description) at any given point in time.
  • the disclosed Jobzi Points distance metric simplifies, accelerates and/or reduces costs of recruitment.
  • the disclosed distance metric greatly improves the matching of the right candidate with a job position. This advantage is particularly relevant for job positions that attract, for example, thousands of candidates and resumes for a given job position.
  • the disclosed Jobzi Points distance metric enables and empowers recruitment to occur in a non-biased manner, without human error.
  • the methods disclosed herein process resumes substantially without bias, and therefore make the hiring process more fair.
  • the disclosed Jobzi Points distance metric allows millions of resumes, for example, to be automatically analyzed in seconds (which ordinarily cannot be achieved with manual or human-based techniques).
  • the disclosed techniques also simplify and accelerate the job search process. Rather than having to read through multiple job descriptions to identify those that are most compatible with their resume (e.g., capturing a bundle of work functions, knowledge, skills, and abilities), one or more embodiments of the present disclosure allow jobseekers to focus strictly on the jobs for which they have the highest Jobzi Points (for example, the top N or top specified percentage of all job postings). In this manner, Jobzi Points signal work opportunities compatible with the resumes of jobseekers that they may not have been aware of or searching for, as the exemplary Jobzi Points match resumes with substantially all potential work positions in the market.
  • Jobzi Points signal work opportunities compatible with the resumes of jobseekers that they may not have been aware of or searching for, as the exemplary Jobzi Points match resumes with substantially all potential work positions in the market.
  • Jobzi Points Quantifying the distance between a bundle of work functions, knowledge, skills, and abilities (e.g., as expressed in a resume) and a work requirement (e.g., as expressed in a job description) at any given point in time can be done via Jobzi Points, disclosed herein.
  • Jobzi Points understand the attributes that a job seeker does not possess, described in his or her resume, and that are required by the work demand described in a job description. It is important that the number of Jobzi Points reflect the importance of the attribute; in other words, the lack of an important attribute.
  • the present disclosure provides a unit of measurement that quantifies a degree of matching between job openings and job seekers, and in doing so also quantifies a degree of mismatching between job openings and job seekers.
  • the disclosed techniques capture whether two items are a good match, and how distant they are from being a good match.
  • a point-based distance system is provided that automatically matches a bid for work and an offer for work.
  • a bid for work demand is described in a job description document, which includes features, such as a title, a description of activities, required knowledge and recommended skills, experience level as well as education and training.
  • a bid for work usually includes an indication of salary and benefits (such as a price paid per monthly service).
  • a job posting for a coffee barista may be filled by a qualified person or an automated coffee machine with the appropriate capabilities, as described, for example, in a functional specification.
  • methods and apparatus are provided for determining and updating tacit knowledge behind job offerings.
  • a job seeker's productive abilities are typically described by a resume, which usually contains his or her contact information, professional experiences, academic history, certifications and skills that she considers relevant.
  • a resume usually contains his or her contact information, professional experiences, academic history, certifications and skills that she considers relevant.
  • there are a number of information items that are often implied by the resume such as which skills a job seeker knows as a consequence of her education, the level of experience acquired over the time she's spent in previous positions or the skills acquired during her professional experience.
  • methods and apparatus are provided for calculating and inferring tacit information from candidate information (e.g., a CV (Curriculum Vitae)) and from job offerings.
  • candidate information e.g., a CV (Curriculum Vitae)
  • methods and apparatus are provided for the identification and inference of additional tacit requirements that relate to the profile of individual hiring institutions or persons (e.g., Company A only hires 30% of its engineers from a given pool of educational institutions).
  • additional tacit requirements relate to the profile of individual hiring institutions or persons (e.g., Company A only hires 30% of its engineers from a given pool of educational institutions).
  • a method is required in one or more embodiments to evaluate the similarity between two professional titles, or two skills. It is also important that this similarity measurement is on a scale, and not binary. To that end, skills, educational levels, courses and experience in a metaWork are considered as a space of attributes (e.g., as a vector of attributes). Similarity between metaWorks can be calculated as attribute vectors, where 0 - 1 is a scale. Skills are mapped using this same methodology. Two titles or skills that are considered synonyms to a human have a similarity of 1 while two titles or skills that are not similar are considered a 0 (e.g., psychologist and stevedore). A similarity score of 0.9 indicates the titles or skills are closely similar but not synonyms (e.g., Java programmer and C# programmer).
  • this distance captures the evolution of knowledge, skills, training, experience, understood in a given work demand and compares them with a given work supply at any specific point in time.
  • the unit of scale is a range of 0 to 100, where the closer the distance between the work demand and the work supply are to each other, the closer to 100 the Jobzi Points will be. Meanwhile, if the work demand and the work supply are very far from each other, the distance measure will be closer to 0.
  • FIG. 1 provides a graphical illustration 100 indicating the work experience and education of a given work seeker over time.
  • the distance of the work seeker relative to four different job postings are also shown.
  • the distance between a resume of the given work seeker that evolves as time progresses is influenced by different factors.
  • the distance of the work seeker from the four different work demands (jobs 1 through 4) is high.
  • the distance to work demand 1 (associated with job 1) is the one that is closest.
  • Job 1 is a job for a work seeker with no professional experience, but with a particular educational requirement.
  • the work seeker and Job 1 are a "market-clearing match!," 120-1 as they are within clearing distance upon the work seeker's course completion.
  • Job 2 For Job 2, the course requirement is important and that can be observed through the reduced distance upon course completion. Job 2, however, does require professional experience. For that reason, the distance between Job 2 and the job seeker is high even upon his completion of the course requirement. As that candidate begins to acquire professional experience through Job 1, his distance to Job 2 is reduced over time. As such, the given work seeker gets closer to Job 2 until the given work seeker is close enough for there to be a second market-clearing match 120-2.
  • Job 3 it is not enough for the work seeker to have the academic requirement and professional experiences up to the beginning of Work Experience 2. Once the work seeker started a new course (educationion 2), the distance of the given work seeker to Job 3 is reduced. Upon course completion, a third market-clearing match 120-3 is realized.
  • Job 4 is similar to Job 3 but requires more experience and professional seniority. This can be observed as the scores get better throughout the seeker's time at Work Experience 3, until the fourth match 120-4 occurs.
  • Job 1 requires a seeker that has a zero-to-no work experience, thus, as this seeker continually gains professional experience, the work seeker is increasingly distant from Job 1.
  • Matching skills demanded by work e.g., by a job
  • skills supplied e.g., by a resume
  • Matching skills demanded by work e.g., by a job
  • skills supplied e.g., by a resume
  • the metaWork is important towards knowing these skills, educations and experience levels that are explicitly required and/or implicitly required.
  • the objective of a metaWork is to learn and inteipret the different relationships between requirements in layers that are hidden to any human reader. As an example, through data, it is learned that the AutoCADTM computer-aided design tool is required by a very high percentage of electrical designers; therefore, if a work demand for an electrical designer does not include this skill in the description, there is still a very high likelihood that the work demand still requires the skill.
  • a methodology is therefore provided that enables a real-time, scalable, calculation of matches ⁇ job, resume ⁇ between a pair of work demand description (e.g., by a job) and work supply description (e.g., by a resume).
  • FIG. 2 illustrates a matching system 200 for matching bids for work with offers for work, according to one embodiment of the disclosure.
  • the exemplary matching system 200 receives a raw job posting 205 that is processed according to a job ontology 210, as discussed further below in the section entitled "Jobzi Ontology,” to generate a processed job posting 225.
  • the processed job posting 225 is also processed by a metaWork module 215, as discussed further below in a section entitled “Metawork,” that determines the abilities and/or additional credentials required for this type of profession.
  • the exemplary matching system 200 also receives a raw user resume 220 that is also processed according to the Jobzi ontology 210 to generate a processed resume 230.
  • An Absolute Adherence module 235 processes the skills from a processed resume 230 and a metaWork 215 to calculate the absolute adherence between the processed resume 230 and the metaWork 215, as described further below in a section entitled “Absolute Adherence Module 235.”
  • An Experience Over Time with Time Lapse module 240 processes the work experience from the processed resume 230; the title from the processed job 225; and the education level from the metaWork 215 to calculate the experience over time for the processed resume 230 while accounting for time lapse, as described below in a section entitled“Experience Over Time with Time Lapse Module 240.”
  • a course experience adherence module 255 processes a metaWork maximum course weight computed by module metaWorkComseMaxWeight 245 and the experience over time value computed by the Experience Over Time with Time Lapse module 240 to calculate a courseExperienceAdherence value between a processed resume 230 and a metaWork 215, as discussed further below in the section entitled“Course Experience Adherence Module 255.”
  • a job and resume skills intersection module 260 processes the skills from the processed job 225, and the skills and work experience from the processed resume 230, and computes a job and resume skills intersection, as discussed further below in the section entitled“Job and Resume Skills Intersection Module 260.”
  • a weighted adherence module 265 computes a weighted adherence between a processed resume 230 and a metaWork 215, using a simple weighted adherence module 250, as discussed further below in the section entitled“Weighted Adherence Module 265.”
  • a job/resume education level match module 270 processes the education levels from the metaWork 215, processed job 225 and processed resume 230 to compute a job/resume education level match between a minimum education level requirement associated with a processed job posting 225 and the user’s resume education level, as discussed further below in the section entitled“Job/Resume Education Level Match Module 270.”
  • a job/resume experience match factor module 275 processes the experience requirement and title from the processed job 225 and the work experience from the processed resume 230 to compute a job/resume experience match factor between a job experience requirement and the experiences from the processed user resume 230, as discussed further below in the section entitled“Job/Resume Experience Match Factor Module 275.”
  • a combined skills intersection and adherence module 280 combines the weighted adherence and the job and resume skill intersection, calculated by modules 265 and 260, respectively, as discussed further below in the section entitled “Combined Skills Intersection and Adherence Module 280.”
  • sub-contexts Some of these contexts are further compartmentalized into sub-contexts, which allows for a greater understanding of further complexities.
  • An example of a sub-context is language skills, which is a sub-context of the skills context.
  • the disclosed methodology generates vocabulary terms that are contextualized, placed within a hierarchy, synonym-enriched and relationship-oriented. Relationships between terms may take a variety of forms, such as “is a synonym to,”“is a part of,”“is a,” etc. As an example,“english”“is a” language skill.
  • a similar process to identifying work terms in work demand documents is applied to work supply documents (e.g., resumes).
  • work supply documents e.g., resumes.
  • a metaWork 215 is the combination of information aggregated by title, that is, the knowledge, skills, courses and professional requirements including experience and salaries, related to that profession.
  • metaWork 215 can be compared in different ways. As an example, it is possible to measure the relevance of a certain skill for a given metaWork 215 and then find out in which other metaWork 215 it is also demanded with a high frequency. Understanding the difference between the frequency (weight) of a given skill and its particularity is important. While the weight measures the importance of a given skill, particularity measures the skill demand between all metaWorks 215. In this manner, whether a skill is specific to a profession (high particularity in a specific metaWork 215) or if it is a cross-sectional skill (low particularity against all metaWorks 215) can be understood.
  • metaWork 215 Another important characteristic of a metaWork 215 is that it enables access to characteristics that are implicitly important in a work description or in the resume description. In that way, it is possible to understand which characteristics are relevant for a given work demand, whether or not it is explicitly required in the description.
  • the Absolute Adherence between a resume 220 and a metaWork 215 is calculated, as follows:
  • the metaWork 215 provides a list of skills with a combined weight and particularity.
  • the product of the weight and particularity is computed because the substantially most relevant skills are those that have high weight and high particularity.
  • the idea is: if the user’s processed resume 230 has the two most important skills (defined by the product of its weight and particularity) for the metaWork meaning a perfect match in terms of skills.
  • step (2) with only the resume’s skills declared by the user (as explained in (2), the skills formally declared by the user as his abilities)
  • This education level is an integer from 1 to N. The higher this number, the higher is the education level required by the metaWork title.
  • MaxSim the maximum adjusted similarity from above.
  • ° calculate the adjusted work experience duration: using the similarity between the work experience title and the job posting title, and combining with the time lapse, adjust the work experience duration.
  • a job posting is asking for a“bus driver” and there are two candidates, the first one has worked 5 years as a“truck driver” but 10 years ago and the second is working for the last 5 years as a“tractor driver”.
  • the work experience of the first candidate is adjusted two times: his work experience is adjusted because he has worked 10 years ago and is also adjusted because he has worked in a similar job.
  • the work experience of second candidate is only penalized once because he has worked in a similar job, but there’s no adjustment from time lapse since he’s still working as a “tractor driver”.
  • the courseExperienceAdherence between a processed resume 230 and a metaWork 215 is calculated, as follows:
  • some jobs posting ask for specific educational course and, in some cases, the educational course is mandatory.
  • the educational course is mandatory.
  • to fulfill the requirements of a lawyer job posting it is mandatory to have studied in a law school.
  • salesman job posting doesn’t have a specific educational course requirement.
  • metaWorkCourseMuxWeight the course with the highest weight
  • the law course has a very high weight.
  • step (3) Given the most important course for the metaWork 215 in step (1) and the most important course for the metaWork 215 found in the user’s resume in step (2): calculate the education course match between a user’s processed resume 230 and a metaWork 215:
  • the courseAdherence is equal to 1. This is the case of someone with a degree from a law school applying to a lawyer job.
  • Job and Resume Skills Intersection is calculated, follows:
  • FIG. 3A illustrates an exemplary job/resume skills intersection process 300 performed by the job and resume skills intersection module 260 of FIG. 2, according to some embodiments of the disclosure.
  • FIG. 3B illustrates a skillSetSizeF actor as a function of number of skills, as processed by the job/resume skills intersection process 300, according to an embodiment.
  • an exemplary job/resume skills intersection process 300 proceeds as follows:
  • skillSetSizeFactor (see graphical representation 380 of skillSetSizeFactor as a function of number of skills in FIG. 3 B), as follows:
  • resumeSkillValue jobSkillValue .
  • the weighted adherence between a processed resume 230 and a metaWork 215, is computed, as follows:
  • a simpleWeightedAdlierence 250 is defined, as follows:
  • step (2) Given the simpleWeightedAdherence in step (1), the courseExperienceAdherence and its weight from step (2):
  • Job/Resume Education Level Match Module 270 Job/Resume Education Level Match Module 270:
  • the job/resume education level match is computed, as follows:
  • a job/resume education level match factor (a number between 0 and 1) is computed between a job’s minimum education level requirement and the user’s resume education level, as follows:
  • meta Work EducationLevel • From the associated metaWork, get the most frequent education level requirement: meta Work EducationLevel.
  • mapping respects the following rules:
  • Job/Re sume Experience Match Module 275 • if no minimum education level requirement was found in the job posting, use the metaWorkEducationLevel and the respective resumeeducationionLevel and the metaWorkEducationLevel and educationF actor mapping to resumeeducationionLevel, using the exemplary mapping 450 shown in FIG. 4B.
  • Job/Re sume Experience Match Module 275
  • a job/resume experience match factor 560 (a number between 0 and 1) between a job experience requirement and the experiences (not only the last one) from the processed user resume 230 is computed, as follows.
  • FIG. 5 illustrates an exemplary job/resume experience match process 500 performed by the job/resume experience match module of FIG. 2, according to some embodiments of the disclosure. As shown in FIG. 5, the exemplary job/resume experience match process 500 proceeds in the following manner:
  • Jobzi ontology 210 • process the raw job title and description using Jobzi ontology 210 to obtain a metaWork title and also vocabulary terms associated with job experience requirements found in the title and description (examples: junior, senior, etc.);
  • JER job experience requirement
  • a lower level of experience requirement like a“junior” position, should have a high experience match with someone that just got out of school/university, even if he doesn’t have any professional experience. So, if 2 people are applying for a“junior” position, if the first one has no professional experience and the second one has 3 months of professional experience, the match factor 560 of the second one should be higher than the first one, but both match factors 560 should be high because this job position is not requiring a very experienced professional. In this case, not 100% of the job/resume experience match factor 560 comes from "k".
  • step (3) Given the job posting in step (1) and the resume’s work experiences ranked by their similarities from step (3):
  • ° calculate the adjusted resume’s work experience duration using the similarity between the work experience title and the job posting title and using a proprietary formula, adjust (usually penalize) the work experience duration.
  • the idea is: if the user has worked for two years in a job with the exact title that the job posting is requiring, i.e., with similarity of 1, consider the full two years of experience. But if he has worked in a similar job, e.g., with similarity less than 1, instead of considering that he has no experience, penalize the experience and count it with less than two years.
  • Resume Skill Intersection have been calculated by modules 265 and 260, respectively, the values are combined by the combined skills intersection and adherence module 280 before determining a final Jobzi Points computation.
  • FIG. 6 illustrates an assignment 600 of a weight, w, to a job/resume skills intersection based on a number of skills identified in a job posting, in one embodiment of the disclosure.
  • the more that skills are identified from the job posting the more that weight is given to the Job and Resume Skill Intersection (e.g., for more skills in the job posting, the more that weight assigned to the job's skills)
  • the less that skills are identified from the job posting the more that weight is given to the weighted Adherence (e.g., for less skills in job posting, the more that weight is assigned to the metaWork skills).
  • the combinedSkillsIntersectionAndAdherence is defined as a convex combination of weightedAdherence and J ob&ResumeSkillslntersection as follows: where w is defined by a mapping function that respect the rule of more skills, then more weight to J ob&ResumeSkillsInter section as shown in FIG. 6.
  • module 280 Once a combined measure of skill intersection and adherence is obtained from module 280 between an user's resume, a job posting and its associated metaWork, it is combined with the experience and education factors from modules 270 and 275.
  • the combinedSkillsIntersectionAndAdherence is adjusted by the educationFactor and experienceFactor giving the Jobzi's Points, as follows:
  • One or more embodiments of the disclosure provide methods and apparatus for matching task descriptions to capability descriptions.
  • the foregoing applications and associated embodiments should be considered as illustrative only, and numerous other embodiments can be configured using the techniques disclosed herein, in a wide variety of different applications.
  • Jobzi Points quantify the distance between a bundle of work functions, knowledge, skills, and abilities (e.g., as expressed in a resume) and a work requirement (e.g., as expressed in a job description) at any given point in time.
  • the disclosed Jobzi Points distance metric simplifies, accelerates and/or reduces costs of recruitment for employers.
  • the disclosed distance metric greatly improves the matching of the right candidate with a job position. This advantage is particularly relevant for job positions that attract, for example, thousands of candidates and resumes for a given job position.
  • the disclosed Jobzi Points distance metric enables and empowers recruitment to occur in a non-biased manner, without human error.
  • the methods disclosed herein process resumes substantially without bias, and therefore make the hiring process more fair.
  • the disclosed Jobzi Points distance metric allows millions of resumes, for example, to be automatically analyzed in seconds (which ordinarily cannot be achieved with manual or human-based techniques).
  • the disclosed techniques also simplify and accelerate the job search process. Rather than having to read through multiple job descriptions to identify those that are most compatible with their resume (e.g., capturing a bundle of work functions, knowledge, skills, and abilities), one or more embodiments of the present disclosure allow jobseekers to focus strictly on the jobs for which they have the highest Jobzi Points (for example, the top N or top specified percentage of all job postings). In this manner, Jobzi Points signal work opportunities compatible with the resumes of jobseekers that they may not have been aware of or searching for, as the exemplary Jobzi Points match resumes with substantially all potential work positions in the market.
  • Jobzi Points signal work opportunities compatible with the resumes of jobseekers that they may not have been aware of or searching for, as the exemplary Jobzi Points match resumes with substantially all potential work positions in the market.
  • the disclosed task matching techniques may be implemented using one or more processing platforms.
  • One or more of the processing modules or other components may therefore each run on a computer, storage device or other processing platform element.
  • a given such element may be viewed as an example of what is more generally referred to herein as a“processing device.”
  • illustrative embodiments disclosed herein can provide a number of significant advantages relative to conventional arrangements. It is to be appreciated that the particular advantages described above and elsewhere herein are associated with particular illustrative embodiments and need not be present in other embodiments. Also, the particular types of information processing system features and functionality as illustrated and described herein are exemplary only, and numerous other arrangements may be used in other embodiments. In these and other embodiments, compute services can be offered to cloud infrastructure tenants or other system users as a Platform as a Service (PaaS) offering, although numerous alternative arrangements are possible.
  • PaaS Platform as a Service
  • the cloud infrastructure further comprises sets of applications running on respective ones of the virtual machines under the control of the hypervisor. It is also possible to use multiple hypervisors each providing a set of virtual machines using at least one underlying physical machine. Different sets of virtual machines provided by one or more hypervisors may be utilized in configuring multiple instances of various components of the system.
  • cloud infrastructure can be used to provide what is also referred to herein as a multi-tenant environment.
  • One or more system components such as matching system 200, or portions thereof, are illustratively implemented for use by tenants of such a multi-tenant environment.
  • Cloud infrastructure as disclosed herein can include cloud-based systems such as Amazon Web Services (AWS), Google Cloud Platform (GCP) and Microsoft Azure.
  • Virtual machines provided in such systems can be used to implement at least portions of a task matching platform in illustrative embodiments.
  • the cloud-based systems can include object stores such as Amazon S3, GCP Cloud Storage, and Microsoft Azure Blob Storage.
  • the cloud infrastructure additionally or alternatively comprises a plurality of containers implemented using container host devices.
  • a given container of cloud infrastructure illustratively comprises a Docker container or other type of Linux container (LXC).
  • LXC Linux container
  • the containers may run on virtual machines in a multi-tenant environment, although other arrangements are possible.
  • the containers may be utilized to implement a variety of different types of functionality within the matching system 200.
  • containers can be used to implement respective processing devices providing compute services of a cloud-based system.
  • containers may be used in combination with other virtualization infrastructure such as virtual machines implemented using a hypervisor.
  • processing platforms will now be described in greater detail with reference to FIGS. 7 and 8. These platforms may also be used to implement at least portions of other information processing systems in other embodiments.
  • the cloud infrastructure 700 in this exemplary processing platform comprises virtual machines (VMs) and/or container sets 702-1, 702-2, . . . 702 -L implemented using a virtualization infrastructure 704.
  • the operating system level virtualization infrastructure illustratively comprises kernel control groups of a Linux operating system or other type of operating system.
  • the virtualization infrastructure 704 runs on physical infrastructure 705 and illustratively comprises one or more hypervisors and/or operating system level virtualization infrastructure.
  • the operating system level virtualization infrastructure illustratively comprises kernel control groups of a Linux operating system or other type of operating system.
  • the cloud infrastructure 700 further comprises sets of applications 710-1, 710-2, .
  • the VMs/container sets 802 may comprise respective VMs, respective sets of one or more containers, or respective sets of one or more containers running in VMs.
  • the cloud infrastructure 700 may encompass the entire given system or only portions of that given system, such as one or more of client, servers, controllers, or computing devices in the system.
  • the system may of course include multiple virtualization infrastructures each providing a set of virtual machines using at least one underlying physical machine. Different sets of virtual machines provided by one or more virtualization infrastructures may be utilized in configuring multiple instances of various components of the system.
  • the cloud infrastructure additionally or alternatively comprises a plurality of containers implemented using container host devices.
  • a given container of cloud infrastructure illustratively comprises a Docker container or other type of LXC.
  • the containers may be associated with respective tenants of a multi-tenant environment of the system, although in other embodiments a given tenant can have multiple containers.
  • the containers may be utilized to implement a variety of different types of functionality within the system.
  • containers can be used to implement respective compute nodes or cloud storage nodes of a cloud computing and storage system.
  • the compute nodes or storage nodes may be associated with respective cloud tenants of a multi-tenant environment of system.
  • Containers may be used in combination with other virtualization infrastructure such as virtual machines implemented using a virtualization infrastructure.
  • one or more of the processing modules or other components of the disclosed matching system 200 may each run on a computer, server, storage device or other processing platform element.
  • a given such element may be viewed as an example of what is more generally referred to herein as a“processing device.”
  • the cloud infrastructure 700 shown in FIG. 7 may represent at least a portion of one processing platform.
  • the processing platform 800 in this embodiment comprises at least a portion of the given system and includes a plurality of processing devices, denoted 802-1, 802-2, 802-3, . . . 802 -K, which communicate with one another over a network 804.
  • the network 804 may comprise any type of network, such as a wireless area network (WAN), a local area network (LAN), a satellite network, a telephone or cable network, a cellular network, a wireless network such as WiFi or WiMAX, or various portions or combinations of these and other types of networks.
  • the processing device 802-1 in the processing platform 800 comprises a processor 810 coupled to a memory 812.
  • the processor 810 may comprise a microprocessor, a microcontroller, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other type of processing circuitry, as well as portions or combinations of such circuitry elements, and the memory 812, which may be viewed as an example of a “processor-readable storage media” storing executable program code of one or more software programs.
  • Articles of manufacture comprising such processor-readable storage media are considered illustrative embodiments.
  • a given such article of manufacture may comprise, for example, a storage array, a storage disk or an integrated circuit containing RAM, ROM or other electronic memory, or any of a wide variety of other types of computer program products.
  • the term “article of manufacture” as used herein should be understood to exclude transitory, propagating signals. Numerous other types of computer program products comprising processor-readable storage media can be used.
  • network interface circuitry 814 which is used to interface the processing device with the network 804 and other system components, and may comprise conventional transceivers.
  • the other processing devices 802 of the processing platform 800 are assumed to be configured in a manner similar to that shown for processing device 802- 1 in the figure.
  • processing platform 800 shown in the figure is presented by way of example only, and the given system may include additional or alternative processing platforms, as well as numerous distinct processing platforms in any combination, with each such platform comprising one or more computers, storage devices or other processing devices.
  • matching system 200 may be collectively implemented on a common processing platform of the type shown in FIGS. 7 or 8, or each such element may be implemented on a separate processing platform.
  • processing platforms used to implement illustrative embodiments can comprise different types of virtualization infrastructure, in place of or in addition to virtualization infrastructure comprising virtual machines.
  • virtualization infrastructure illustratively includes container-based virtualization infrastructure configured to provide Docker containers or other types of LXCs.
  • components of an information processing system as disclosed herein can be implemented at least in part in the form of one or more software programs stored in memory and executed by a processor of a processing device.
  • a processor of a processing device For example, at least portions of the functionality of the flow charts and/or pseudo code shown in various figures are illustratively implemented in the form of software running on one or more processing devices.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention concerne des techniques permettant de mettre en correspondance des soumissions de travail avec des offres de travail. Un procédé donné à titre d'exemple consiste à : obtenir des soumissions de travail et des offres de travail ; utiliser des techniques de traitement de langage naturel pour interpréter une terminologie spécifique à un travail provenant des soumissions de travail et/ou des offres de travail ; et mettre en correspondance les soumissions de travail avec les offres de travail d'après une mesure de distance prédéfinie entre les soumissions de travail et les offres de travail. Les soumissions de travail comprennent, par exemple, des offres d'emplois et les offres de travail comprennent des curriculum vitae. La mesure de distance prédéfinie entre les soumissions de travail et les offres de travail comprend, par exemple, un degré de correspondance entre au moins deux soumissions de travail et offres de travail ainsi qu'un degré de discordance quantifiable entre les au moins deux soumissions de travail et offres de travail.
PCT/IB2018/001531 2017-11-30 2018-11-29 Mise en correspondance de soumissions de travail avec des offres de travail WO2019106437A2 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201762592559P 2017-11-30 2017-11-30
US62/592,559 2017-11-30

Publications (2)

Publication Number Publication Date
WO2019106437A2 true WO2019106437A2 (fr) 2019-06-06
WO2019106437A3 WO2019106437A3 (fr) 2019-08-08

Family

ID=66663832

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2018/001531 WO2019106437A2 (fr) 2017-11-30 2018-11-29 Mise en correspondance de soumissions de travail avec des offres de travail

Country Status (1)

Country Link
WO (1) WO2019106437A2 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021089129A1 (fr) 2019-11-05 2021-05-14 Nalantis Nv Analyse et comparaison de données numériques codées en caractères, en particulier pour la mise en correspondance d'emplois
CN117094540A (zh) * 2023-10-20 2023-11-21 一智科技(成都)有限公司 一种智能派工方法、系统和存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050080657A1 (en) * 2003-10-10 2005-04-14 Unicru, Inc. Matching job candidate information
US20050144065A1 (en) * 2003-12-19 2005-06-30 Palo Alto Research Center Incorporated Keyword advertisement management with coordinated bidding among advertisers
US7720791B2 (en) * 2005-05-23 2010-05-18 Yahoo! Inc. Intelligent job matching system and method including preference ranking
US20070273909A1 (en) * 2006-05-25 2007-11-29 Yahoo! Inc. Method and system for providing job listing affinity utilizing jobseeker selection patterns
US20090276415A1 (en) * 2008-05-01 2009-11-05 Myperfectgig System and method for automatically processing candidate resumes and job specifications expressed in natural language into a common, normalized, validated form

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021089129A1 (fr) 2019-11-05 2021-05-14 Nalantis Nv Analyse et comparaison de données numériques codées en caractères, en particulier pour la mise en correspondance d'emplois
BE1027696A1 (nl) 2019-11-05 2021-05-17 Nalantis Nv Analyse en vergelijking van tekengecodeerde digitale gegevens, met name voor job matching
CN117094540A (zh) * 2023-10-20 2023-11-21 一智科技(成都)有限公司 一种智能派工方法、系统和存储介质
CN117094540B (zh) * 2023-10-20 2024-03-29 一智科技(成都)有限公司 一种智能派工方法、系统和存储介质

Also Published As

Publication number Publication date
WO2019106437A3 (fr) 2019-08-08

Similar Documents

Publication Publication Date Title
US20230342608A1 (en) Systems and processes for bias removal in a predictive performance model
Roszkowska et al. Application of fuzzy TOPSIS to scoring the negotiation offers in ill-structured negotiation problems
Rashid et al. ELECTRE-based outranking method for multi-criteria decision making using hesitant intuitionistic fuzzy linguistic term sets
US8032469B2 (en) Recommending similar content identified with a neural network
RU2637883C1 (ru) Способ создания обучающего объекта для обучения алгоритма машинного обучения
US11282005B2 (en) Selecting a plurality of individuals and AI agents to accomplish a task
CA2959340A1 (fr) Modeles d'apprentissage machine pouvant etre personnalises
US10983786B2 (en) Automatically evaluating software project requirements
US11238410B1 (en) Methods and systems for merging outputs of candidate and job-matching artificial intelligence engines executing machine learning-based models
US20190286978A1 (en) Using natural language processing and deep learning for mapping any schema data to a hierarchical standard data model (xdm)
US11195135B2 (en) Systems and methods for ranking entities
US20220180323A1 (en) System and method for generating job recommendations for one or more candidates
Nguyen et al. A linguistic multi-criteria decision-aiding system to support university career services
WO2019106437A2 (fr) Mise en correspondance de soumissions de travail avec des offres de travail
US11836633B2 (en) Generating realistic counterfactuals with residual generative adversarial nets
Shekapure et al. Enhanced e-Learning experience using case based reasoning methodology
Hossain et al. Development of an Intelligent Job Recommender System for Freelancers using Client's Feedback Classification and Association Rule Mining Techniques.
Suthaharan et al. Supervised learning algorithms
CN110262906B (zh) 接口标签推荐方法、装置、存储介质和电子设备
Ureña et al. On incomplete fuzzy and multiplicative preference relations in multi-person decision making
Danielson et al. Using surrogate weights for handling preference strength in multi-criteria decisions
CN112925913B (zh) 用于匹配数据的方法、装置、设备和计算机可读存储介质
CN111316259A (zh) 用于反馈和裁定的语义属性的动态合成和瞬时聚簇的系统和方法
Mandis Reducing racial and gender bias in machine learning and natural language processing tasks using a GAN approach
Kuznietsova et al. Business intelligence techniques for missing data imputation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18884829

Country of ref document: EP

Kind code of ref document: A2

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18884829

Country of ref document: EP

Kind code of ref document: A2

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 13/11/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18884829

Country of ref document: EP

Kind code of ref document: A2