WO2022157367A1 - Automated systems and methods for identifying, validating, and communicating job matches - Google Patents
Automated systems and methods for identifying, validating, and communicating job matches Download PDFInfo
- Publication number
- WO2022157367A1 WO2022157367A1 PCT/EP2022/051506 EP2022051506W WO2022157367A1 WO 2022157367 A1 WO2022157367 A1 WO 2022157367A1 EP 2022051506 W EP2022051506 W EP 2022051506W WO 2022157367 A1 WO2022157367 A1 WO 2022157367A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- job
- predictors
- information
- match
- candidate
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000010801 machine learning Methods 0.000 claims abstract description 20
- 238000013473 artificial intelligence Methods 0.000 claims description 29
- 238000004891 communication Methods 0.000 claims description 20
- 230000007115 recruitment Effects 0.000 claims description 7
- 230000015654 memory Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 10
- 230000008901 benefit Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000003306 harvesting Methods 0.000 description 4
- 230000000977 initiatory effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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 present disclosure relates to matching job candidates and job positions, and more particularly, to automated systems and methods for gathering job candidates and job positions, matching job candidates with job positions, validating the matches, and communicating with job candidates and/or sources of job positions using machine learning and artificial intelligence systems.
- Job providers and job seekers generally have a common interest in establishing a successful working relationship. Job providers seek persons to successfully complete tasks, and job seekers look for interesting positions that provide stable income. To further this common interest, job providers and job seekers engage in detailed searches and interviews to ensure the common interest in shared. Nevertheless, working relationships do not always turn out to be successful. There is continuing interest in improving the chances that a working relationship will be a successful relationship.
- the present disclosure relates to matching job candidates and job positions.
- a computer-implemented method includes accessing information of a plurality of job candidates and information of a plurality of job positions, applying predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score, and selecting, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
- the predictors of good fit include predictors that a job candidate would fit with a work culture of a job position.
- the predictors of good fit include predictors that a job candidate would develop camaraderie with a company group having a job position.
- the method includes communicating with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
- the method includes communicating with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
- the conversational artificial intelligence system implements a full recruitment lifecycle method.
- the conversational artificial intelligence system is trained to optimize at least one of: communication frequency or channel of communication.
- a system includes one or more processors and one or more memories storing instructions.
- the instructions when executed by the one or more processors, cause the system to access information of a plurality of job candidates and information of a plurality of job positions, apply predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score, and select, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
- the predictors of good fit include predictors that a job candidate would fit with a work culture of a job position.
- the predictors of good fit include predictors that a job candidate would develop camaraderie with a company group having a job position.
- the instructions when executed by the one or more processors, further cause the system to communicate with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
- the instructions when executed by the one or more processors, further cause the system to communicate with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
- the conversational artificial intelligence system implements a full recruitment lifecycle method.
- the conversational artificial intelligence system is trained to optimize at least one of: communication frequency or channel of communication.
- a computer-readable storage medium stores instructions which, when executed by one or more processors of a system, cause the system to access information of a plurality of job candidates and information of a plurality of job positions, apply predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score, and select, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
- the predictors of good fit include predictors that a job candidate would fit with a work culture of a job position.
- the predictors of good fit include predictors that a job candidate would develop camaraderie with a company group having a job position.
- the instructions when executed by the one or more processors, further cause the system to communicate with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
- the instructions when executed by the one or more processors, further cause the system to communicate with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
- the conversational artificial intelligence system implements a full recruitment lifecycle method.
- the conversational artificial intelligence system is trained to optimize at least one of communication frequency or channel of communication.
- FIG. 1 is a block diagram of an exemplary system, in accordance with aspects of the present disclosure
- FIG. 2 is an exemplary display screen for a dashboard for a matching system for matching job candidates and job positions, in accordance with aspects of the present disclosure
- FIG. 3 is an exemplary display screen for viewing or browsing job candidate, in accordance with aspects of the present disclosure
- FIG. 4 is an exemplary display screen of a panel showing the resume for the job candidate, in accordance with aspects of the present disclosure
- FIG. 5 is an exemplary display screen for viewing job positions, in accordance with aspects of the present disclosure
- FIG. 6 is an exemplary display screen for displaying suggested matches of job candidates and job positions, in accordance with aspects of the present disclosure
- FIG. 7 is an exemplary display screen showing a portion of the match report that shows the predictors/features on which the suggested match is based, in accordance with aspects of the present disclosure
- FIG. 8 is an exemplary display screen of a further portion of the match report of FIG. 7, in accordance with aspects of the present disclosure
- FIG. 9 is an exemplary display screen of yet another portion of the match report of FIG. 7, in accordance with aspects of the present disclosure.
- FIG. 10 is an exemplary display screen for accessing e-mails, in accordance with aspects of the present disclosure.
- FIG. 11 is an exemplary display screen for adjusting settings, in accordance with aspects of the present disclosure.
- FIG. 12 is a flow diagram of an exemplary operation, in accordance with aspects of the present disclosure.
- the present disclosure relates to automated systems and methods for gathering job candidates and job positions, matching job candidates with job positions, validating the matches using data, and communicating with job candidates and/or sources of job positions using machine learning and artificial intelligence (“Al”) systems.
- Al machine learning and artificial intelligence
- the machine learning/ Al systems for communicating with job candidates and/or sources of job positions can be implemented to mimic the full recruitment lifecycle method.
- a job candidate may be a person who is seeking a job or a person who does not know he or she has a better job fit and therefore may not be seeking a job change.
- a job position may be a position that has a listed job opening or may be a position that does not have a listed job opening.
- the technology of the present disclosure additionally operates to identify matches between job candidates who may or may not be seeking a job and job positions which may or may not have a listed opening. Accordingly, the technology of the present disclosure can identify matches between job candidates seeking a job and listed job openings.
- the technology of the present disclosure may identify a match between a job candidate who is not seeking a job and a job position that does not have a listed opening. If such a match is identified as a sufficiently good fit, a job candidate presented with such a match may be open to considering a job change, and an employer presented with such a match may be open to creating an opening for the job candidate.
- job candidates and job positions can be matched to each other based on predictors of good fit between a job candidate and a job position, which will be described in more detail later herein.
- job candidates and job positions can be matched to each other based on predictors of job tenure.
- job tenure means an amount of time that a job candidate hired for a job position remains at the job.
- Employers invest time to train new hires and prefer longer job tenures so they can reap the benefits of the time investment.
- Job candidates also generally prefer longer job tenures so they can have income stability.
- An aspect of the present disclosure relates to predictors of longer job tenure. Aspects of the present disclosure relate to a data-driven approach for validating matches between job candidates and job positions.
- the exemplary display screens may be shown on a screen of any electronic device or system, such as a smartphone, a tablet, a laptop, or desktop computer, among other electronic devices or systems.
- the display screens may be provided by a server system, such as a cloud server system, and the electronic devices or systems displaying the display screens may request them from the server system.
- the server system can include electronic storage that store information shown in the display screens and/or store related information.
- the devices, computers, and systems described herein may utilize one or more processors that process various information and transform the received information to generate an output.
- the processor may include any type of computing device, computational circuit, or any type of processing circuit capable of executing a series of instructions that are stored in a memory.
- the processor may include multicore central processing units (CPUs) and may include any type of processing device, such as a microprocessor, digital signal processor, microcontroller, programmable logic device (PLD), field programmable gate array (FPGA), or the like.
- the processor may also access a memory or computer-readable storage medium storing data and/or instructions which, when executed by the processor, causes the processor to perform one or more methods, operations, and/or algorithms.
- any of the described methods, programs, algorithms, or codes may be converted to, or expressed in, a programming language or computer program.
- programming language and “computer program,” as used herein, each include any language used to specify instructions to a computer, and include (but is not limited to) the following languages and their derivatives: Assembler, Basic, Batch files, BCPL, C, C+, C++, Delphi, Fortran, HTML, Java, JavaScript, machine code, operating system command languages, Pascal, Perl, PL1, Python, scripting languages, Visual Basic, metalanguages which themselves specify programs, and all first, second, third, fourth, fifth, or further generation computer languages. Also included are database and other data schemas, and any other meta-languages.
- the system includes a database 120 storing job candidate information 122 and job position information 124.
- the information stored in the database 120 can be obtained from various sources, including, without limitation, third party databases 112, webpage harvesting 114, and/or manual entry or upload 116.
- a third party database may be any database which is owned or operated by an entity that is different from the entity which owns or operates the illustrated system. Such third party databases may include information on job candidates or information on job positions.
- the datasets from the various sources can be combined and stored in the illustrated database 120.
- a job candidate is a person who may or may not be seeking a job position, and a job position may or may not have a listed job opening.
- Some of the job candidate information 122 and/or the job position information 124 may be collected by webpage harvesting 114, which persons skilled in the art will understand.
- webpage harvesting includes technology which loads a webpage and extracts information from the webpage in an automated manner without human intervention. Because webpages often publicize information about employee and company details, webpage harvesting may provide a wealth of information about job candidates and job positions.
- job candidate information 122 and/or job position information 124 may be obtained by manual information entry or information upload 116 to the illustrated system.
- the illustrated system may provide an employment marketplace, and job candidates and employers may participate in the employment marketplace by entering or uploading an employee profile or an employer profile. Information entered or uploaded in this manner may also be stored in the database 120.
- the illustrated system includes a good fit matching system 130 which seeks to find good fits between job candidates and job positions. Aspects of the good fit matching will be described later herein in connection with FIGS. 7-9 and 11. For now, it is sufficient to note that the good fit matching system 130 can be implemented in various ways, including using machine learning techniques such as, without limitation, decision trees, support vector machines, and neural networks, among other machine learning techniques. Persons skilled in the art will understand such machine learning techniques and how to implement their training and inference functionality.
- the good fit matching system 130 can provide matches of job candidates and job positions which are predicted to be a good fit for each other. For example, data regarding employers and employees may be used to train various machine learning systems. The data may include the categories, reasons, and/or settings shown in FIGS.
- the machine learning model may be a deep learning neural network that does not require feature engineering.
- the machine learning system may be trained to identify job candidates and job positions whose data shows they may be a good fit. Such and other embodiments are contemplated to be within the scope of the present disclosure.
- the good fit matching system 130 can provide its suggested matches to a conversational machine learning/artificial intelligence (“Al”) system 140, which can be a verbal Al system and/or a written Al system.
- Al machine learning/artificial intelligence
- the conversational Al system 140 can be configured to operate in the same manner as a professional recruiter.
- the conversational Al system 140 can extend invitations to the job candidates 152 and to the employers 154 of the matches to invite them to utilize the illustrated system.
- the conversational Al system 140 can converse with job candidates 152 and job position employers 154, and information obtained by the conversational Al system 140 can be stored in the database 120.
- the conversational Al system 140 can automatically create a profile for a job candidate 152 based on a conversation and can populate profile with information obtained from the job candidate 152 during the conversation.
- the conversational Al system 140 can automatically create a profile for a job position employer 154 based on a conversation and can population the profile with information obtained during the conversation.
- the conversational Al system 140 can be trained to optimize the frequency of communications with job candidates and job position employers, such as having a followup communication a particular number of days (e.g., three days) after a previous conversation.
- the conversational Al system 140 can also be trained to optimize the preferred channel of communications with job candidates and job position employers, such as having a follow-up communication by e-mail, text message, or another channel of communication.
- the illustrated system also includes a graphical user interface (GUI) system 160 for accessing and presenting information from the database 120 to users. Examples of GUI screens are described below in connection with FIGS. 2-11.
- GUI graphical user interface
- FIG. 2 there is shown an exemplary display screen for a dashboard for a matching system for matching job candidates and job positions, in accordance with aspects of the present disclosure.
- the dashboard display screen can be accessed by a “Dashboard” button or link and can display metrics or information relating to job candidates, job positions and matches.
- the illustrated dashboard shows number of job candidates, number of job positions, number of matches of job candidates and job positions, number of approved matches, and number of declined matches.
- the illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, other information can be displayed on a dashboard display screen, and information can be arranged on the dashboard in different ways.
- FIG. 3 is an exemplary display screen for viewing or browsing job candidates, in accordance with aspects of the present disclosure.
- the display screen can be accessed by a “Candidates” button or link and can display job candidates.
- the job candidates are presented in a display card format such that each display card shows a particular job candidate and information about the job candidate, such as name, location, current employer, and current position, among other information.
- the display screen can be scrolled to browse job candidates.
- the search bar near the top of the display screen can be used to search for and display job candidates which match search criteria.
- the illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, job candidates can be presented in various arrangements different from the illustrated display screen, and other information can be displayed for each job candidate.
- a job candidate display card can include a link for accessing and viewing a resume of a job candidate, in accordance with aspects of the present disclosure.
- the display card of a job candidate can include a button or link 310 for opening a resume for the job candidate.
- a panel opens showing the resume for the job candidate, as shown in FIG. 4.
- the resume panel of FIG. 4 can show various information for the job candidate, such as name, contact e-mail, contact number, current employer, current position, education information, work experience information, and skills information, among other resume information.
- the illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, other resume information can be presented, and the resume information can be presented in various formats and arrangements.
- the display card of a job candidate can include a button or link 320 for accessing job position matches for the job candidate.
- the display card can also include a button or link 330 for initiating a telephone call to the job candidate and/or a button or a link 340 for initiating a text message to the job candidate.
- the telephone call and text messaging can be initiated using various technologies, such computer telephony integration, among others.
- the illustrated display screen of FIG. 3 is exemplary, and variations are contemplated to be within the scope of the present disclosure.
- FIG. 5 is an exemplary display screen for viewing job positions, in accordance with aspects of the present disclosure.
- the job positions can be accessed by a “Jobs” button or link at the top of the display screen.
- the jobs positions can be arranged in a table format such that each line corresponds to a separate job position.
- Each job position can display information such as company name, job title, job type, city, state, and country, among other job position information.
- the display screen can be scrolled to browse the job positions.
- the search bar near the top of the display screen can be used to search for and display job positions which match search criteria.
- the illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure.
- the job positions can be displayed in various arrangements different from that illustrated in FIG. 5, and various other types of job position information can be displayed.
- a job position can include a button or link 510 which opens more information on the job position, such as a job specification, a button or link 520 which opens an e-mail interface for communicating with the company of the job position via e-mail, and/or a button or link 530 which opens job candidate matches for the job position.
- the illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure.
- the job position can have other buttons or links for accessing other functions or information.
- FIG. 6 is an exemplary display screen for displaying suggested matches of job candidates and job positions, in accordance with aspects of the present disclosure.
- the technology of the present disclosure operates to identify matches between job candidates who may or may not be seeking a job and job positions which may or may not have a listed opening.
- the technology of the present disclosure can identify matches between job candidates seeking a job and listed job openings.
- the technology of the present disclosure may identify a match between a job candidate who is not seeking a job and a job position that does not have a listed opening.
- the suggested matches can be identified based on predictors of increased job tenure. Examples of such predictors will be described in connection with FIGS. 7-9 and 11. For now, it is sufficient to note that the display screen of suggested matches can be accessed and displayed by a “Matches” button or link at the top of the display screen. The suggested matches are displayed using a display card for each suggested match.
- a display card can include various information about the matched job candidate and job position, such as the name of the job candidate, the current employer of the job candidate, the current position of the job candidate, the company of the job position, the title of the job position, and score of the suggested match, among other information.
- the display screen can be scrolled to browse the suggested matches.
- Various buttons or links for interacting with a display card will be described later herein.
- the illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure.
- the suggested matches can be displayed in an arrangement different from that shown in FIG. 6 and other information can be displayed for each suggested match.
- a button or link 610 in a display card of a suggested match can be engaged to open a match report display panel for the suggested match.
- a match report display panel is shown in FIGS. 7-9, and the match report can display information such as current employer of the job candidate, current position of the job candidate, the company of the job position, the title of the job position, and score of the suggested match.
- the suggested matches are identified based on predictors of a good fit between the job candidate and the job position, such as, for example, a good fit for the work culture of a job position, or a good fit for developing camaraderie with the company group which has the job position, among other types of good fit.
- a predictor/feature may be, for example, the job candidate having previously worked at the same place as others in the company group which includes the job position.
- a higher match report total score may indicate that a job candidate would be a good fit for the work culture of a job position and/or would be a good fit for developing camaraderie, such that the good fit may translate to an improved job tenure.
- the predictors of a good fit may coincide with predictors of increased job tenure.
- the predictors of a good fit may be implemented by training a machine learning model using data relating to employers and employees who have had a successful working relationship.
- the machine learning model may be a deep learning neural network, among other things.
- FIG. 7 shows a portion of the match report that shows the predictors/features on which the suggested match is based.
- the terms “predictors” and “features” may be used interchangeably herein.
- the predictors are shown in the match report by both a listing of predictors as well as a pie-chart showing the amount of influence each predictors had in the suggested match.
- the predictors include basic requirements for making the suggested match as well as predictors of good fit which are applicable to the suggested match.
- An example of a basic requirement is that the job candidate and the job position both show the same employment type that is sought, such as full-time employment.
- Another example of a basic requirement is that the skills of the job candidate match the skills requirements of the job position.
- the pie-chart can be interactive such that mousing-over or tapping a slice of the pie-chart will cause more information about the slice to be show displayed.
- Other types of basic requirements are contemplated to be within the scope of the present disclosure.
- FIGS. 8 and 9 show portions of the match report which explain, in more detail, the predictors/features shown in FIG. 7. As shown in FIGS. 7-9, the predictors/features applicable to the illustrated example include:
- Feature 4 Word match - deep overlap between the words describing a describing a candidate and job
- Feature 16 Other candidates with same first name - others from the company have the same first name as this candidate Feature 21 : Other candidates, top bank, same time - others from the company worked at the same top bank as this candidate at same time
- Feature 22 Other candidates, top bank, different time - others from the company worked at the same top bank as this candidate at different time
- the predictors/features are displayed in a table format. Such predictors/features are exemplary and other types of predictors/features not disclosed herein are contemplated to be within the scope of the present disclosure.
- Each predictor/feature is shown with an accompanying value, weight, and score. The score is the product of the value and the weight.
- the table can list the predictors in order of high score to lowest score.
- the sum of the scores of the predictors can be the match report total score. A higher match report total score can indicate a predicted better fit, and lower match report total score can indicate a lesser fit. Accordingly, suggested matches having higher match report total scores would likely be preferable to the job candidate as well as the company having the job position.
- the predictors/features, values, and weights shown in FIGS. 8 and 9 are exemplary and other predictors/features, values, and weights, different from those shown, are contemplated to be within the scope of the present disclosure.
- the values and weights can be predetermined and their numbers can be adjusted to reflect the importance of the predictor in predicting a good fit.
- the illustrated display screens are exemplary, and variations are contemplated to be within the scope of the present disclosure.
- a match report can have various arrangements different from that shown in FIGS. 7-9 and other information can be displayed.
- a match score can be computed in different ways within the scope of the present disclosure.
- the display card can include a button or link 620 for accessing a resume of the job candidate, a button or link 630 for viewing the job specification for the job listing, a button or link 640 for designing a suggested match as a good match, a button or link 650 for designating a suggested match as not a good match, a button or link 660 for initiating a telephone call to the job candidate or the job position, and/or a button or a link 670 for initiating a text message to the job candidate or the job position.
- the illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, buttons or links with other functions may be included in a display card.
- FIG. 10 is an exemplary display screen for accessing e-mails, in accordance with aspects of the present disclosure.
- a listing of e-mails can be shown correspond to received e- mails, sent e-mails, or ready-to-send e-mails. When an e-mail is selected from the listing, the content of the selected e-mail is displayed.
- the illustrated display screen is exemplary and variations are contemplated to be within the scope of the present disclosure. For example, other channels of communication, such as text messages or voice messages, can be used for communications. Such and other communication channels are contemplated to be within the scope of the present disclosure.
- FIG. 11 is an exemplary display screen for adjusting settings, in accordance with aspects of the present disclosure.
- the illustrated settings that can be adjusted are points for the predictors/features applicable to suggested matches, such as the predictors/features shown in FIGS. 8 and 9.
- the points may be assigned in a way that provides better predictions of good fit between a job candidate and a job position and/or better predictions of improved job tenure.
- a predictor/feature may be applicable one or more times to a job candidate and a job position. For example, with regard to the predictor that others from a company worked at same place as the candidate at same time (FIG. 8, feature 7), it has a setting of twenty points.
- the twenty points can be multiplied by five for the five occurrences and can result in one-hundred points for this predictor/feature.
- Other ways of applying the points of a predictor/feature are contemplated.
- the illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure.
- FIG. 12 is a flow diagram of an exemplary operation according to aspects of the present disclosure.
- the operation involves accessing information of a plurality of job candidates and information of a plurality of job positions.
- the operation involves applying predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score.
- the operation involves selecting, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
- the operation involves communicating with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
- the operation involves communicating with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
- phrases “in an embodiment,” “in embodiments,” “in various embodiments,” “in some embodiments,” or “in other embodiments” may each refer to one or more of the same or different embodiments in accordance with the present disclosure.
- a phrase in the form “A or B” means “(A), (B), or (A and B).”
- a phrase in the form “at least one of A, B, or C” means “(A); (B); (C); (A and B); (A and C); (B and C); or (A, B, and C) ”
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
The present disclosure relates to matching job candidates and job positions. In aspects of the present disclosure, a computer-implemented method includes accessing information of job candidates and information of job positions, applying predictors of good fit to the information of the job candidates and the information of the job positions using a machine learning model to provide at least one suggested match having a match score, and selecting, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
Description
AUTOMATED SYSTEMS AND METHODS FOR IDENTIFYING, VALIDATING, AND COMMUNICATING JOB MATCHES
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] The present application claims the benefit of, and priority to, U.S. Provisional Application No. 63/140,418, filed January 22, 2021, the entire contents of which are hereby incorporated by reference herein in its entirety.
FIELD
[0002] The present disclosure relates to matching job candidates and job positions, and more particularly, to automated systems and methods for gathering job candidates and job positions, matching job candidates with job positions, validating the matches, and communicating with job candidates and/or sources of job positions using machine learning and artificial intelligence systems.
BACKGROUND
[0003] Job providers and job seekers generally have a common interest in establishing a successful working relationship. Job providers seek persons to successfully complete tasks, and job seekers look for interesting positions that provide stable income. To further this common interest, job providers and job seekers engage in detailed searches and interviews to ensure the common interest in shared. Nevertheless, working relationships do not always turn out to be successful. There is continuing interest in improving the chances that a working relationship will be a successful relationship.
SUMMARY
[0004] The present disclosure relates to matching job candidates and job positions.
[0005] In accordance with aspects of the present disclosure, a computer-implemented method includes accessing information of a plurality of job candidates and information of a plurality of job positions, applying predictors of good fit to the information of the plurality of
job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score, and selecting, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
[0006] In various embodiments of the computer-implemented method, the predictors of good fit include predictors that a job candidate would fit with a work culture of a job position. [0007] In various embodiments of the computer-implemented method, the predictors of good fit include predictors that a job candidate would develop camaraderie with a company group having a job position.
[0008] In various embodiments of the computer-implemented method, the method includes communicating with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
[0009] In various embodiments of the computer-implemented method, the method includes communicating with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
[0010] In various embodiments of the computer-implemented method, the conversational artificial intelligence system implements a full recruitment lifecycle method.
[0011] In various embodiments of the computer-implemented method, the conversational artificial intelligence system is trained to optimize at least one of: communication frequency or channel of communication.
[0012] In accordance with aspects of the present disclosure, a system includes one or more processors and one or more memories storing instructions. The instructions, when executed by the one or more processors, cause the system to access information of a plurality of job candidates and information of a plurality of job positions, apply predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job
positions, using a machine learning model, to provide at least one suggested match having a match score, and select, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
[0013] In various embodiments of the system, the predictors of good fit include predictors that a job candidate would fit with a work culture of a job position.
[0014] In various embodiments of the system, the predictors of good fit include predictors that a job candidate would develop camaraderie with a company group having a job position.
[0015] In various embodiments of the system, the instructions, when executed by the one or more processors, further cause the system to communicate with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
[0016] In various embodiments of the system, the instructions, when executed by the one or more processors, further cause the system to communicate with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
[0017] In various embodiments of the system, the conversational artificial intelligence system implements a full recruitment lifecycle method.
[0018] In various embodiments of the system, the conversational artificial intelligence system is trained to optimize at least one of: communication frequency or channel of communication.
[0019] In accordance with aspects of the present disclosure, a computer-readable storage medium stores instructions which, when executed by one or more processors of a system, cause the system to access information of a plurality of job candidates and information of a plurality of job positions, apply predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score, and select, from among
the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
[0020] In various embodiments of the computer-readable storage medium, the predictors of good fit include predictors that a job candidate would fit with a work culture of a job position.
[0021] In various embodiments of the computer-readable storage medium, the predictors of good fit include predictors that a job candidate would develop camaraderie with a company group having a job position.
[0022] In various embodiments of the computer-readable storage medium, the instructions, when executed by the one or more processors, further cause the system to communicate with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
[0023] In various embodiments of the computer-readable storage medium, the instructions, when executed by the one or more processors, further cause the system to communicate with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
[0024] In various embodiments of the computer-readable storage medium, the conversational artificial intelligence system implements a full recruitment lifecycle method.
[0025] In various embodiments of the computer-readable storage medium, the conversational artificial intelligence system is trained to optimize at least one of communication frequency or channel of communication.
[0026] The details of one or more embodiments of the disclosure are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the techniques described in this disclosure will be apparent from the description and drawings, and from the claims.
BRIEF DESCRIPTION OF THE DRAWINGS
[0027] A detailed description of embodiments of the disclosure will be made with reference to the accompanying drawings, wherein like numerals designate corresponding parts in the figures.
[0028] FIG. 1 is a block diagram of an exemplary system, in accordance with aspects of the present disclosure;
[0029] FIG. 2 is an exemplary display screen for a dashboard for a matching system for matching job candidates and job positions, in accordance with aspects of the present disclosure;
[0030] FIG. 3 is an exemplary display screen for viewing or browsing job candidate, in accordance with aspects of the present disclosure;
[0031] FIG. 4 is an exemplary display screen of a panel showing the resume for the job candidate, in accordance with aspects of the present disclosure;
[0032] FIG. 5 is an exemplary display screen for viewing job positions, in accordance with aspects of the present disclosure;
[0033] FIG. 6 is an exemplary display screen for displaying suggested matches of job candidates and job positions, in accordance with aspects of the present disclosure;
[0034] FIG. 7 is an exemplary display screen showing a portion of the match report that shows the predictors/features on which the suggested match is based, in accordance with aspects of the present disclosure;
[0035] FIG. 8 is an exemplary display screen of a further portion of the match report of FIG. 7, in accordance with aspects of the present disclosure;
[0036] FIG. 9 is an exemplary display screen of yet another portion of the match report of FIG. 7, in accordance with aspects of the present disclosure;
[0037] FIG. 10 is an exemplary display screen for accessing e-mails, in accordance with aspects of the present disclosure;
[0038] FIG. 11 is an exemplary display screen for adjusting settings, in accordance with aspects of the present disclosure; and
[0039] FIG. 12 is a flow diagram of an exemplary operation, in accordance with aspects of the present disclosure.
DETAILED DESCRIPTION
[0040] The present disclosure relates to automated systems and methods for gathering job candidates and job positions, matching job candidates with job positions, validating the matches using data, and communicating with job candidates and/or sources of job positions using machine learning and artificial intelligence (“Al”) systems. As explained in more detail below, the machine learning/ Al systems for communicating with job candidates and/or sources of job positions can be implemented to mimic the full recruitment lifecycle method.
[0041] Aspects of the present disclosure provide computerized processes for gathering job candidates and job positions without human intervention. A job candidate may be a person who is seeking a job or a person who does not know he or she has a better job fit and therefore may not be seeking a job change. A job position may be a position that has a listed job opening or may be a position that does not have a listed job opening. Broadly, the technology of the present disclosure additionally operates to identify matches between job candidates who may or may not be seeking a job and job positions which may or may not have a listed opening. Accordingly, the technology of the present disclosure can identify matches between job candidates seeking a job and listed job openings. Additionally, the technology of the present disclosure may identify a match between a job candidate who is not seeking a job and a job position that does not have a listed opening. If such a match is identified as a sufficiently good fit, a job candidate presented with such a match may be open
to considering a job change, and an employer presented with such a match may be open to creating an opening for the job candidate.
[0042] In aspects of the present disclosure, job candidates and job positions can be matched to each other based on predictors of good fit between a job candidate and a job position, which will be described in more detail later herein. In aspects of the present disclosure job candidates and job positions can be matched to each other based on predictors of job tenure. As used herein, the term “job tenure” means an amount of time that a job candidate hired for a job position remains at the job. Employers invest time to train new hires and prefer longer job tenures so they can reap the benefits of the time investment. Job candidates also generally prefer longer job tenures so they can have income stability. An aspect of the present disclosure relates to predictors of longer job tenure. Aspects of the present disclosure relate to a data-driven approach for validating matches between job candidates and job positions.
[0043] A better understanding of the features and advantages of the disclosed technology will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the technology are utilized, and to the accompanying drawings, which show exemplary display screens of aspects of the present disclosure. The exemplary display screens may be shown on a screen of any electronic device or system, such as a smartphone, a tablet, a laptop, or desktop computer, among other electronic devices or systems. The display screens may be provided by a server system, such as a cloud server system, and the electronic devices or systems displaying the display screens may request them from the server system. The server system can include electronic storage that store information shown in the display screens and/or store related information.
[0044] The devices, computers, and systems described herein may utilize one or more processors that process various information and transform the received information to
generate an output. The processor may include any type of computing device, computational circuit, or any type of processing circuit capable of executing a series of instructions that are stored in a memory. The processor may include multicore central processing units (CPUs) and may include any type of processing device, such as a microprocessor, digital signal processor, microcontroller, programmable logic device (PLD), field programmable gate array (FPGA), or the like. The processor may also access a memory or computer-readable storage medium storing data and/or instructions which, when executed by the processor, causes the processor to perform one or more methods, operations, and/or algorithms.
[0045] Any of the described methods, programs, algorithms, or codes may be converted to, or expressed in, a programming language or computer program. The terms “programming language” and “computer program,” as used herein, each include any language used to specify instructions to a computer, and include (but is not limited to) the following languages and their derivatives: Assembler, Basic, Batch files, BCPL, C, C+, C++, Delphi, Fortran, HTML, Java, JavaScript, machine code, operating system command languages, Pascal, Perl, PL1, Python, scripting languages, Visual Basic, metalanguages which themselves specify programs, and all first, second, third, fourth, fifth, or further generation computer languages. Also included are database and other data schemas, and any other meta-languages. No distinction is made between languages which are interpreted, compiled, or use both compiled and interpreted approaches. No distinction is made between compiled and source versions of a program. Thus, reference to a program, where the programming language could exist in more than one state (such as source, compiled, object, or linked) is a reference to any and all such states. Reference to a program may encompass the actual instructions and/or the intent of those instructions.
[0046] Referring now to FIG. 1, there is shown a block diagram of an exemplary system according to aspects of the present disclosure. The system includes a database 120 storing job
candidate information 122 and job position information 124. The information stored in the database 120 can be obtained from various sources, including, without limitation, third party databases 112, webpage harvesting 114, and/or manual entry or upload 116. A third party database may be any database which is owned or operated by an entity that is different from the entity which owns or operates the illustrated system. Such third party databases may include information on job candidates or information on job positions. The datasets from the various sources can be combined and stored in the illustrated database 120.
[0047] As mentioned above, a job candidate is a person who may or may not be seeking a job position, and a job position may or may not have a listed job opening. Some of the job candidate information 122 and/or the job position information 124 may be collected by webpage harvesting 114, which persons skilled in the art will understand. One example of webpage harvesting includes technology which loads a webpage and extracts information from the webpage in an automated manner without human intervention. Because webpages often publicize information about employee and company details, webpage harvesting may provide a wealth of information about job candidates and job positions.
[0048] As mentioned above, job candidate information 122 and/or job position information 124 may be obtained by manual information entry or information upload 116 to the illustrated system. For example, the illustrated system may provide an employment marketplace, and job candidates and employers may participate in the employment marketplace by entering or uploading an employee profile or an employer profile. Information entered or uploaded in this manner may also be stored in the database 120.
[0049] The illustrated system includes a good fit matching system 130 which seeks to find good fits between job candidates and job positions. Aspects of the good fit matching will be described later herein in connection with FIGS. 7-9 and 11. For now, it is sufficient to note that the good fit matching system 130 can be implemented in various ways, including using
machine learning techniques such as, without limitation, decision trees, support vector machines, and neural networks, among other machine learning techniques. Persons skilled in the art will understand such machine learning techniques and how to implement their training and inference functionality. The good fit matching system 130 can provide matches of job candidates and job positions which are predicted to be a good fit for each other. For example, data regarding employers and employees may be used to train various machine learning systems. The data may include the categories, reasons, and/or settings shown in FIGS. 7-9 and 11, among other data. In various embodiments, the machine learning model may be a deep learning neural network that does not require feature engineering. In various embodiments, the machine learning system may be trained to identify job candidates and job positions whose data shows they may be a good fit. Such and other embodiments are contemplated to be within the scope of the present disclosure.
[0050] In accordance with aspects of the present disclosure, the good fit matching system 130 can provide its suggested matches to a conversational machine learning/artificial intelligence (“Al”) system 140, which can be a verbal Al system and/or a written Al system. Persons skilled in the art will understand how to implemental verbal and written conversational Al systems. In aspects of the present disclosure, the conversational Al system 140 can be configured to operate in the same manner as a professional recruiter. For example, the conversational Al system 140 can extend invitations to the job candidates 152 and to the employers 154 of the matches to invite them to utilize the illustrated system. The conversational Al system 140 can converse with job candidates 152 and job position employers 154, and information obtained by the conversational Al system 140 can be stored in the database 120. For example, the conversational Al system 140 can automatically create a profile for a job candidate 152 based on a conversation and can populate profile with information obtained from the job candidate 152 during the conversation. Similarly, the
conversational Al system 140 can automatically create a profile for a job position employer 154 based on a conversation and can population the profile with information obtained during the conversation. The conversational Al system 140 can be trained to optimize the frequency of communications with job candidates and job position employers, such as having a followup communication a particular number of days (e.g., three days) after a previous conversation. The conversational Al system 140 can also be trained to optimize the preferred channel of communications with job candidates and job position employers, such as having a follow-up communication by e-mail, text message, or another channel of communication.
[0051] The illustrated system also includes a graphical user interface (GUI) system 160 for accessing and presenting information from the database 120 to users. Examples of GUI screens are described below in connection with FIGS. 2-11.
[0052] Referring now to FIG. 2, there is shown an exemplary display screen for a dashboard for a matching system for matching job candidates and job positions, in accordance with aspects of the present disclosure. The dashboard display screen can be accessed by a “Dashboard” button or link and can display metrics or information relating to job candidates, job positions and matches. For example, the illustrated dashboard shows number of job candidates, number of job positions, number of matches of job candidates and job positions, number of approved matches, and number of declined matches. The illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, other information can be displayed on a dashboard display screen, and information can be arranged on the dashboard in different ways.
[0053] FIG. 3 is an exemplary display screen for viewing or browsing job candidates, in accordance with aspects of the present disclosure. The display screen can be accessed by a “Candidates” button or link and can display job candidates. The job candidates are presented in a display card format such that each display card shows a particular job candidate and
information about the job candidate, such as name, location, current employer, and current position, among other information. The display screen can be scrolled to browse job candidates. The search bar near the top of the display screen can be used to search for and display job candidates which match search criteria. The illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, job candidates can be presented in various arrangements different from the illustrated display screen, and other information can be displayed for each job candidate.
[0054] A job candidate display card can include a link for accessing and viewing a resume of a job candidate, in accordance with aspects of the present disclosure. As shown in FIG. 3, the display card of a job candidate can include a button or link 310 for opening a resume for the job candidate. When the button or link 310 is engaged, a panel opens showing the resume for the job candidate, as shown in FIG. 4. The resume panel of FIG. 4 can show various information for the job candidate, such as name, contact e-mail, contact number, current employer, current position, education information, work experience information, and skills information, among other resume information. The illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, other resume information can be presented, and the resume information can be presented in various formats and arrangements.
[0055] Referring again to FIG. 3, the display card of a job candidate can include a button or link 320 for accessing job position matches for the job candidate. The display card can also include a button or link 330 for initiating a telephone call to the job candidate and/or a button or a link 340 for initiating a text message to the job candidate. The telephone call and text messaging can be initiated using various technologies, such computer telephony integration, among others. The illustrated display screen of FIG. 3 is exemplary, and variations are contemplated to be within the scope of the present disclosure.
[0056] FIG. 5 is an exemplary display screen for viewing job positions, in accordance with aspects of the present disclosure. The job positions can be accessed by a “Jobs” button or link at the top of the display screen. The jobs positions can be arranged in a table format such that each line corresponds to a separate job position. Each job position can display information such as company name, job title, job type, city, state, and country, among other job position information. The display screen can be scrolled to browse the job positions. The search bar near the top of the display screen can be used to search for and display job positions which match search criteria. The illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, the job positions can be displayed in various arrangements different from that illustrated in FIG. 5, and various other types of job position information can be displayed.
[0057] With continuing reference to FIG. 5, a job position can include a button or link 510 which opens more information on the job position, such as a job specification, a button or link 520 which opens an e-mail interface for communicating with the company of the job position via e-mail, and/or a button or link 530 which opens job candidate matches for the job position. The illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, the job position can have other buttons or links for accessing other functions or information.
[0058] FIG. 6 is an exemplary display screen for displaying suggested matches of job candidates and job positions, in accordance with aspects of the present disclosure. As mentioned above herein, the technology of the present disclosure operates to identify matches between job candidates who may or may not be seeking a job and job positions which may or may not have a listed opening. The technology of the present disclosure can identify matches between job candidates seeking a job and listed job openings. Also, the technology of the present disclosure may identify a match between a job candidate who is not seeking a job and
a job position that does not have a listed opening. If such a match is identified as a sufficiently good fit, a job candidate presented with such a match may be open to considering a job change, and an employer presented with such a match may be open to creating an opening for the job candidate. In aspects of the present disclosure, the suggested matches can be identified based on predictors of increased job tenure. Examples of such predictors will be described in connection with FIGS. 7-9 and 11. For now, it is sufficient to note that the display screen of suggested matches can be accessed and displayed by a “Matches” button or link at the top of the display screen. The suggested matches are displayed using a display card for each suggested match. A display card can include various information about the matched job candidate and job position, such as the name of the job candidate, the current employer of the job candidate, the current position of the job candidate, the company of the job position, the title of the job position, and score of the suggested match, among other information. The display screen can be scrolled to browse the suggested matches. Various buttons or links for interacting with a display card will be described later herein. The illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, the suggested matches can be displayed in an arrangement different from that shown in FIG. 6 and other information can be displayed for each suggested match.
[0059] As shown in FIG. 6, a button or link 610 in a display card of a suggested match can be engaged to open a match report display panel for the suggested match. Such a match report display panel is shown in FIGS. 7-9, and the match report can display information such as current employer of the job candidate, current position of the job candidate, the company of the job position, the title of the job position, and score of the suggested match.
[0060] As mentioned above herein, the suggested matches are identified based on predictors of a good fit between the job candidate and the job position, such as, for example, a good fit for the work culture of a job position, or a good fit for developing camaraderie with
the company group which has the job position, among other types of good fit. Such a predictor/feature may be, for example, the job candidate having previously worked at the same place as others in the company group which includes the job position. Thus, a higher match report total score may indicate that a job candidate would be a good fit for the work culture of a job position and/or would be a good fit for developing camaraderie, such that the good fit may translate to an improved job tenure. Thus, in various aspects, the predictors of a good fit may coincide with predictors of increased job tenure. In various embodiments, the predictors of a good fit may be implemented by training a machine learning model using data relating to employers and employees who have had a successful working relationship. The machine learning model may be a deep learning neural network, among other things.
[0061] FIG. 7 shows a portion of the match report that shows the predictors/features on which the suggested match is based. The terms “predictors” and “features” may be used interchangeably herein. The predictors are shown in the match report by both a listing of predictors as well as a pie-chart showing the amount of influence each predictors had in the suggested match. The predictors include basic requirements for making the suggested match as well as predictors of good fit which are applicable to the suggested match. An example of a basic requirement is that the job candidate and the job position both show the same employment type that is sought, such as full-time employment. Another example of a basic requirement is that the skills of the job candidate match the skills requirements of the job position. In various embodiments, the pie-chart can be interactive such that mousing-over or tapping a slice of the pie-chart will cause more information about the slice to be show displayed. Other types of basic requirements are contemplated to be within the scope of the present disclosure.
[0062] FIGS. 8 and 9 show portions of the match report which explain, in more detail, the predictors/features shown in FIG. 7. As shown in FIGS. 7-9, the predictors/features applicable to the illustrated example include:
Feature 1 : Job title - overlap between candidate’s job title and job’s title
Feature 2: Candidate match - overlap between candidate’s skills and job’s skills
Feature 3: Employment type - candidate and job have same employment type
Feature 4: Word match - deep overlap between the words describing a describing a candidate and job
Feature 5: Prior companies - other candidates who have worked at this company share prior employers
Feature 7: Other candidates, same company, same time - others from the company worked at same place as this candidate at same time
Feature 8: Other candidates, same company, different time - others from the company worked at same place as this candidate at different time
Feature 9: Other candidates, similar tenure - others from the company have similar average job tenures to this candidate
Feature 11 : Other candidates, different subject same university - others from the company studied a different subject at the same university as this candidate
Feature 12: Other candidates, same subject different university - others from the company studied the same subject as this candidate at a different university
Feature 16: Other candidates with same first name - others from the company have the same first name as this candidate
Feature 21 : Other candidates, top bank, same time - others from the company worked at the same top bank as this candidate at same time
Feature 22: Other candidates, top bank, different time - others from the company worked at the same top bank as this candidate at different time
Feature 25: Other candidates from the same town (not large) - others from the company live in the same town (not including world’s largest cities) as this candidate
Feature 26: Other candidates from the same zip - others from the company live in the same zip code as this candidate
Feature 27: Other candidates from the same area code - others from the company live in the same area code as this candidate
[0063] In FIGS. 8 and 9, the predictors/features are displayed in a table format. Such predictors/features are exemplary and other types of predictors/features not disclosed herein are contemplated to be within the scope of the present disclosure. Each predictor/feature is shown with an accompanying value, weight, and score. The score is the product of the value and the weight. The table can list the predictors in order of high score to lowest score. The sum of the scores of the predictors can be the match report total score. A higher match report total score can indicate a predicted better fit, and lower match report total score can indicate a lesser fit. Accordingly, suggested matches having higher match report total scores would likely be preferable to the job candidate as well as the company having the job position.
[0064] The predictors/features, values, and weights shown in FIGS. 8 and 9 are exemplary and other predictors/features, values, and weights, different from those shown, are contemplated to be within the scope of the present disclosure. In aspects of the present disclosure, the values and weights can be predetermined and their numbers can be adjusted to reflect the importance of the predictor in predicting a good fit. The illustrated display screens
are exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, a match report can have various arrangements different from that shown in FIGS. 7-9 and other information can be displayed. Additionally, a match score can be computed in different ways within the scope of the present disclosure.
[0065] Referring again to FIG. 6, the display card can include a button or link 620 for accessing a resume of the job candidate, a button or link 630 for viewing the job specification for the job listing, a button or link 640 for designing a suggested match as a good match, a button or link 650 for designating a suggested match as not a good match, a button or link 660 for initiating a telephone call to the job candidate or the job position, and/or a button or a link 670 for initiating a text message to the job candidate or the job position. The illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure. For example, buttons or links with other functions may be included in a display card.
[0066] FIG. 10 is an exemplary display screen for accessing e-mails, in accordance with aspects of the present disclosure. A listing of e-mails can be shown correspond to received e- mails, sent e-mails, or ready-to-send e-mails. When an e-mail is selected from the listing, the content of the selected e-mail is displayed. The illustrated display screen is exemplary and variations are contemplated to be within the scope of the present disclosure. For example, other channels of communication, such as text messages or voice messages, can be used for communications. Such and other communication channels are contemplated to be within the scope of the present disclosure.
[0067] FIG. 11 is an exemplary display screen for adjusting settings, in accordance with aspects of the present disclosure. The illustrated settings that can be adjusted are points for the predictors/features applicable to suggested matches, such as the predictors/features shown in FIGS. 8 and 9. In aspects of the present disclosure, the points may be assigned in a way
that provides better predictions of good fit between a job candidate and a job position and/or better predictions of improved job tenure. A predictor/feature may be applicable one or more times to a job candidate and a job position. For example, with regard to the predictor that others from a company worked at same place as the candidate at same time (FIG. 8, feature 7), it has a setting of twenty points. If five others from a company worked at same place as the job candidate at the same time, the twenty points can be multiplied by five for the five occurrences and can result in one-hundred points for this predictor/feature. Other ways of applying the points of a predictor/feature are contemplated. The illustrated display screen is exemplary, and variations are contemplated to be within the scope of the present disclosure.
[0068] FIG. 12 is a flow diagram of an exemplary operation according to aspects of the present disclosure. At block 1210, the operation involves accessing information of a plurality of job candidates and information of a plurality of job positions. At block 1220, the operation involves applying predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score. At block 1230, the operation involves selecting, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position. At block 1240, the operation involves communicating with a job candidate of the at least one suggested match using a conversational artificial intelligence system. At block 1250, the operation involves communicating with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
[0069] The embodiments disclosed herein are examples of the disclosure and may be embodied in various forms. For instance, although certain embodiments herein are described as separate embodiments, each of the embodiments herein may be combined with one or more of the other embodiments herein. Specific structural and functional details disclosed
herein are not to be interpreted as limiting, but as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present disclosure in virtually any appropriately detailed structure. Like reference numerals may refer to similar or identical elements throughout the description of the figures.
[0070] The phrases “in an embodiment,” “in embodiments,” “in various embodiments,” “in some embodiments,” or “in other embodiments” may each refer to one or more of the same or different embodiments in accordance with the present disclosure. A phrase in the form “A or B” means “(A), (B), or (A and B).” A phrase in the form “at least one of A, B, or C” means “(A); (B); (C); (A and B); (A and C); (B and C); or (A, B, and C) ”
[0071] It should be understood that the foregoing description is only illustrative of the present disclosure. Various alternatives and modifications can be devised by those skilled in the art without departing from the disclosure. Accordingly, the present disclosure is intended to embrace all such alternatives, modifications, and variances. The embodiments described with reference to the attached drawing figures are presented only to demonstrate certain examples of the disclosure. Other elements, steps, methods, and techniques that are insubstantially different from those described above and/or in the appended claims are also intended to be within the scope of the disclosure.
Claims
1. A computer-implemented method comprising: accessing information of a plurality of job candidates and information of a plurality of job positions; applying predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score; and selecting, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
2. The computer-implemented method of claim 1, wherein the predictors of good fit include predictors that a job candidate would fit with a work culture of a job position.
3. The computer-implemented method of claim 1, wherein the predictors of good fit include predictors that a job candidate would develop camaraderie with a company group having a job position.
4. The computer-implemented method of claim 1, further comprising communicating with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
5. The computer-implemented method of claim 4, further comprising communicating with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
6. The computer-implemented method of claim 4, wherein the conversational artificial intelligence system implements a full recruitment lifecycle method.
7. The computer-implemented method of claim 6, wherein the conversational artificial intelligence system is trained to optimize at least one of: communication frequency or channel of communication.
8. A system comprising: one or more processors; and one or more memories storing instructions which, when executed by the one or more processors, cause the system to: access information of a plurality of job candidates and information of a plurality of job positions; apply predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score; and select, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
9. The system of claim 8, wherein the predictors of good fit include predictors that a job candidate would fit with a work culture of a job position.
10. The system of claim 8, wherein the predictors of good fit include predictors that a job candidate would develop camaraderie with a company group having a job position.
11. The system of claim 8, wherein the instructions, when executed by the one or more processors, further cause the system to: communicate with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
12. The system of claim 11, wherein the instructions, when executed by the one or more processors, further cause the system to: communicate with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
13. The system of claim 11, wherein the conversational artificial intelligence system implements a full recruitment lifecycle method.
14. The system of claim 13, wherein the conversational artificial intelligence system is trained to optimize at least one of: communication frequency or channel of communication.
15. A computer-readable storage medium storing instructions which, when executed by one or more processors of a system, cause the system to: access information of a plurality of job candidates and information of a plurality of job positions; apply predictors of good fit to the information of the plurality of job candidates and the information of the plurality of job positions, using a machine learning model, to provide at least one suggested match having a match score; and select, from among the at least one suggested match, at least one match score indicating a good fit between a job candidate and a job position.
16. The computer-readable storage medium of claim 15, wherein the predictors of good fit include predictors that a job candidate would fit with a work culture of a job position.
17. The computer-readable storage medium of claim 15, wherein the predictors of good fit include predictors that a job candidate would develop camaraderie with a company group having a job position.
18. The computer-readable storage medium of claim 15, wherein the instructions, when executed by the one or more processors, further cause the system to: communicate with a job candidate of the at least one suggested match using a conversational artificial intelligence system.
19. The computer-readable storage medium of claim 18, wherein the instructions, when executed by the one or more processors, further cause the system to: communicate with a source of a job position of the at least one suggested match using a conversational artificial intelligence system.
20. The computer-readable storage medium of claim 18, wherein the conversational artificial intelligence system implements a full recruitment lifecycle method.
21. The computer-readable storage medium of claim 20, wherein the conversational artificial intelligence system is trained to optimize at least one of: communication frequency or channel of communication.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US202163140418P | 2021-01-22 | 2021-01-22 | |
US63/140,418 | 2021-01-22 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022157367A1 true WO2022157367A1 (en) | 2022-07-28 |
Family
ID=81307572
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2022/051506 WO2022157367A1 (en) | 2021-01-22 | 2022-01-24 | Automated systems and methods for identifying, validating, and communicating job matches |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2022157367A1 (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140122355A1 (en) * | 2012-10-26 | 2014-05-01 | Bright Media Corporation | Identifying candidates for job openings using a scoring function based on features in resumes and job descriptions |
US20190019159A1 (en) * | 2017-07-17 | 2019-01-17 | ExpertHiring, LLC | Method and system for managing, matching, and sourcing employment candidates in a recruitment campaign |
-
2022
- 2022-01-24 WO PCT/EP2022/051506 patent/WO2022157367A1/en active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140122355A1 (en) * | 2012-10-26 | 2014-05-01 | Bright Media Corporation | Identifying candidates for job openings using a scoring function based on features in resumes and job descriptions |
US20190019159A1 (en) * | 2017-07-17 | 2019-01-17 | ExpertHiring, LLC | Method and system for managing, matching, and sourcing employment candidates in a recruitment campaign |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220006761A1 (en) | Systems and processes for operating and training a text-based chatbot | |
George et al. | A review of ChatGPT AI's impact on several business sectors | |
Griol et al. | An automatic dialog simulation technique to develop and evaluate interactive conversational agents | |
US10970794B1 (en) | Dynamic pagination of tax return questions during preparation of electronic tax return | |
US20200193382A1 (en) | Employment resource system, method and apparatus | |
US8566699B2 (en) | Intent-based information processing and updates | |
US7672908B2 (en) | Intent-based information processing and updates in association with a service agent | |
US11861562B2 (en) | Real-time candidate matching based on a system-wide taxonomy | |
US11580180B2 (en) | Job prospect and applicant information processing | |
JP7329159B1 (en) | Information processing system, information processing method and program | |
US20240028909A1 (en) | Deep learning model based data generation | |
CN113112282A (en) | Method, device, equipment and medium for processing consult problem based on client portrait | |
US11803861B2 (en) | System and method for matching a customer and a customer service assistant | |
JP7311899B2 (en) | Question answering system, question receiving and answering system, primary answer system, and question answering method using them | |
US11874865B2 (en) | Intelligent digital assistant that provides end-user with information from firm databases to assist end-user in performing job functions | |
WO2022157367A1 (en) | Automated systems and methods for identifying, validating, and communicating job matches | |
KR102374530B1 (en) | Optimized question and answer system and method thereof | |
CN113870998A (en) | Interrogation method, device, electronic equipment and storage medium | |
JP2022075642A (en) | Debater system for collaborative discussion based on explainable prediction | |
JP7490905B1 (en) | Job search support system, job search support method and program | |
JP7385077B1 (en) | Search support system, search support method and program | |
JP7482335B1 (en) | Search support system, search support method and program | |
JP7475529B1 (en) | Information management system, information management method and program | |
JP7474378B1 (en) | Text creation support system, information processing method and program | |
JP7474377B1 (en) | Text creation support system, information processing method and program |
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: 22704870 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 22704870 Country of ref document: EP Kind code of ref document: A1 |