Framework for artificial intelligence-based matching of job seekers with open employment positions in an application environment

Abstract

A framework or platform for matching job seekers and open positions of employment is provided in an end-to-end application-based environment that places complete user control of the process of applying for open employment opportunities with the job seekers. The framework or platform enables an acceptance or rejection of a posting for an open position of employment for the purpose of applying for the open position, based on a user's physical interaction, such as swiping, with an interface. The framework or platform includes an artificial intelligence engine that learns job seeker preferences relative to open positions over time through the process of physical interactions such as swiping.

Description

FRAMEWORK FOR ARTIFICIAL INTELLIGENCE-BASED MATCHING OF JOB SEEKERS WITH OPEN EMPLOYMENT POSITIONS IN AN APPLICATION ENVIRONMENT

[0001] This application is an international patent application that claims the benefit of priority and is entitled to the filing date pursuant to U.S. Provisional Patent Application 63 / 708,787, filed October 18, 2024, the content of which is hereby incorporated by reference in its entirety.FIELD

[0002] The present invention relates to the field of employment. Specifically, the present invention relates to an approach for matching job seekers and open positions of employment in an application-based environment.BACKGROUND

[0003] There are many existing software-based tools that enable individuals to search for and seek employment opportunities. For example, LINKEDIN® users are able to search through companies that have profiles on that platform and look for open positions. Similarly, tools such as LINKEDIN® allow companies with open employment positions to seek applicants for such jobs and invite them to apply.

[0004] Such existing tools, however, are not built from the perspective of the job seeker. They do not enable automated and nuanced profile-based matching of job seekers with employment positions and do not provide features that protect such job seekers, for example, from applying for jobs with their own current or past organizations. Existing tools also do not offer sophisticated techniques for (a) matching job seekers with job opportunities in an easy-to-use interface for mobile devices that enables quick selection or rejection of job opportunities or (b) any automated customized application process for opportunities that are selected. Moreover, there is no existing tool that combines any automated matching with built-in resume or curriculum vitae (CV) creation or management features to enhance the matching of applicant skills with open positions.SUMMARY

[0005] The present invention addresses these limitations in the existing art in a software application, known as “twrk”, for matching job seekers and open positions of employment, twrk is the first applicant-oriented tool available that provides an end-to-end platform for job seekers and enables complete user control of the process of selecting and applying for open employmentPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment opportunities, twrk may be embodied within a framework that enables a “true” swipe feature, which enables an acceptance or rejection of an open position of employment for the purpose of applying for the open position, simply based on a user’s interaction with an interface (i.e. , swiping right on a screen to accept or left on a screen to reject). The framework also includes an artificial intelligence-based engine that learns user preferences relative to open positions over time through the process of swiping. The artificial intelligence-based engine also includes a plurality of machine learning techniques, language models, and natural language processing that enable an Al-driven personal recruiter for matching job seekers with open positions of employment, in which the job seeker’s preferences (for example, what they want or do not want in a position, salary preferences, and any other aspects thereof) may be discerned from both the swiping process and from other features of the twrk platform (such as, for example, profile creation and “conversing” with the Al).

[0006] Objectives, embodiments, features, and advantages of the present invention will become apparent from the following description of the embodiments and the accompanying figures, which illustrate, by way of example, the principles of the invention.BRIEF DESCRIPTION OF DRAWINGS

[0007] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate aspects of the disclosed subject matter in at least one of its exemplary embodiments, which are further defined in detail in the following description. Features, elements, and aspects of the disclosure are referenced by numerals with like numerals in different drawings representing the same, equivalent, or similar features, elements, or aspects, in accordance with one or more embodiments. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating the principles herein described and provided by exemplary embodiments of the invention. More generally, those skilled in the art will appreciate that the drawings are schematic in nature and are not to be taken literally or to scale in terms of material configurations, sizes, thicknesses, and other attributes of an apparatus according to aspects of the present invention and its components or features unless specifically set forth herein. In such drawings:

[0008] FIG. 1 A is a flow diagram of a front-end process for profile creation features;

[0009] FIG. 1 B is a continuation of FIG. 1A;

[0010] FIG. 2 is a schematic of a front-end process for resume retrieval and modification features;PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0011] FIG. 3A is a schematic of a front-end process for job matching and auto-apply features;

[0012] FIG. 3B is a continuation of FIG. 3A;

[0013] FIG. 4 is a schematic of a front-end process for past applications and bin features;

[0014] FIG. 5 is a schematic of a front-end process for premium application edit features;

[0015] FIG. 6 is a schematic of a front-end process for referral features;

[0016] FIG. 7 is a schematic of a front-end process for recruiter swiping features;

[0017] FIG. 8 is a schematic of a front-end process for interview-setting features;

[0018] FIG. 9 is a schematic of a back-end process for standard resume creation features;

[0019] FIG. 10 is a schematic of a back-end process for upsell prompt features;

[0020] FIG. 11 is a schematic of a back-end process for right-swipe features; and

[0021] FIG. 12 is a schematic of a back-end process for left-swipe features.DETAILED DESCRIPTION

[0022] In the following description of the present invention, reference is made to the exemplary embodiments illustrating the principles of the present invention and how it is practiced. Other embodiments will be utilized to practice the present invention, and structural and functional changes will be made thereto without departing from the scope of the present invention.

[0023] The present invention is, as noted above, a framework for artificial intelligence-based matching job seekers with postings of open positions of employment in an application-based environment. The framework is embodied in either a desktop or mobile computing application, and it provides job seekers with the ability to either accept or reject a matched posting of an open position of employment. The application allows job seekers to indicate their interest in an open position of employment in this manner, and, if required, apply for such open position within the application-based environment. The framework includes a rich set of features as described further below that provide job seekers with the ability to identify, review, select (for example, using aPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment“swipe” feature left or right on an interface), and apply for appropriate job opportunities, as well as resume and CV guidance.

[0024] The framework of the present invention may be embodied within one or more systems and / or methods that are performed in a plurality of data processing modules and which are components within a computing environment. These data processing modules may be configured to run within external cloud computing environments (and accessed therefrom by the framework), and they also may be configured to run locally on devices hosting the framework, such as on mobile computing devices, “smart” phones, earphones / earbuds, on other wearable internet- enabled devices such watches and eyeglasses, and in automotive platforms. Still further, one or more of the data processing modules may be configured to run within, and executed on, edge computing environments and be responsive to natural language instructions, either verbal, written, or gesture-based. One or more processors may be configured to execute program instructions or routines to perform the elements, modules, components, and functions described herein that together comprise and are embodied within the plurality of data processing modules. The words "module" and “modules” as used herein may referto (and the data processing modules may themselves comprise, at least in part) logic embodied in hardware or firmware, or to a collection of software instructions written in a programming language, such as, for example, Java, Python, C, or assembly. One or more software instructions for such modules may be embedded in firmware. It will be appreciated that the functional data processing modules may include connected logic modules, such as gates and flip-flops, and may include programmable modules, such as programmable gate arrays or processors. The data processing modules described herein may be implemented as either software and / or hardware modules and may be stored in a storage device. It is to be additionally understood that the data processing modules, and the respective components of the present invention that together comprise the specifically configured elements, may interchangeably be referred to as “components,” “modules,” “algorithms” (where appropriate), “engines,” “networks,” and any other similar term that is intended to indicate an element for carrying out a specific data processing function.

[0025] The framework matches job seekers and job listings or postings for open positions of employment within artificial intelligence-driven processes that together scrape relevant postings for job openings for a position (hereafter “job opening”) from a recruiter, employer, hiring manager, job poster or other job aggregator (hereafter together referred to as a “recruiter” or an “employer”) based on input provided either by the job seeker or identified from the job seeker’s skills and experience, and it presents those relevant, matched postings to the job seeker. This input builds a user story for each job seeker. The artificial intelligence-driven processes may be considered as comprising both front-end processes and back-end processes, as described below. It is to bePCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment understood that job seekers may also be referred to herein from time to time as both as a user, a job seeker who is using the twrk platform and job applicant, a job seeker who has applied for a job opening using the twrk platform. It is also to be understood that a job opening may also be referred to herein from time to time as a “job listing” or a “job posting” both of which are considered synonymous terms with a job opening. It is further to be understood that a recruiter may also be referred to as an employer which are to be considered synonymous terms with each and are used interchangeably within the present specification.Front-End Processes

[0026] Front-end processes are shown in the flow diagrams of FIGS. 1-8. As noted above, the framework of the present invention - and the process of twrk’ing or getting matches to job openings - is provided within an application-based environment (referred to as the twrk platform or twrk environment) and one or more interfaces that allow job seekers to build their user stories (or allow such a user story to be built for each job seeker). The application in which the framework is embodied includes a plurality of screens or pages that job seekers are able to interact with via the one or more interfaces.

[0027] In such an application-based environment, some universal principles are provided relative to these pages, such as for example a back button and / or an "undo" button. On every page except when job seekers are in the process of twrk'ing (i.e., getting job matches), users may "start twrk'ing", which brings those users back to the job-matching function page. A profile and / or account page is also provided, within which a “hamburger”-style menu allows users to view their standard or custom resume (and any changes thereto over time), past job applications, and other such pages.

[0028] FIGS. 1A-1B are flow diagrams of one such front-end process 100 within the present invention. Process 100 is a profile creation 102 process, in which a user may provide email addresses and passwords for account setup, and either upload their resume / CV or enable such resume / CV to be accessed from a third-party site, for example, where twrk connects 106 to a user's profile via an application programming interface (API) of a third-party networking site such as LINKEDIN® and creates a resume from the user's profile information on that third-party site. Process 100 for profile creation 102 may also enable several prompts to which a user can respond for the purposes of establishing an account and engaging with a native artificial intelligence (Al) engine (which may be referred to herein as “Twrky”). Twrky, in one embodiment thereof, may include a bot (or chatbot) through which users interact with the Al engine for the purpose of instantiating Twrky for their use of the twrk platform.PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0029] In FIG. 1A, process 100 for profile creation 102, a user first signs into a networking site 104, such as, e.g., LINKEDIN®, and process 100 of the twrk platform connects to the user’s profile 106, via one or more application programming interfaces (API)s. Once connected to the user’s networking site, such as, e.g., LINKEDIN®, process 100 will obtain all data from this profile and store this information on the twrk platform. Process 100 then prompts whether the user wants to create a resume 108 from the profile information collected at step 106. If the user indicates “no” at create a resume 108, process 100 returns to the twrk platform 110, and the user can upload or otherwise provide their own resume 112 to the twrk platform. If the user indicates “yes” at create a resume 108, the user’s stored profiled information 114 is used to create a Standard Resume, and once completed the user is returned 116 to the twrk platform.

[0030] Once a resume is generated or uploaded into the twrk platform, process 100 for profile creation 110 then engages the Twrky artificial intelligence engine to perform various functions 117 using, for example, a language model and one or more agents. Twrky engages with the user by prompting the user for relevant information regarding the job position the user is seeking, the experiences and skills and other relevant work and personal information of use, as well as preferences and dislikes regarding jobs, workplace, location, salary and benefits, etc. in order to refine his or her information for the purpose of semantic matching. As noted above, this may be accomplished via the bot or chatbot interface that Twrky may embody and the user provides this information by responding in any one of a number of ways, for example via speech or voice commands, or via typing onto a type-pad on a user interface, or via some gesture in relation to the device which the job seeker is using. In some embodiments, and referring to FIGS. 1 A & 1 B, Twrky also asks for the user at step 118, what type of job the user is seeking, at step 120 for any quantifiable experience or other information, and at step 122 for desired compensation, at step 124 whether the job seeker wants push notifications, at step 126, any additional benefits or perks that they would like to have in an employment position, at step 128 about user’s desired location, and / or whether the job seeker wants to work on location, or in a remote or hybrid situation, and at step 130 whether there is any criteria that he or she wants (or specifically does not want) in a job.

[0031] At step 132, and referring now to FIG. 1B, Twrky confirms it has enough information to start semantic matching (as described herein) of jobs to the user. Twrky then asks whether the user wants a tour of the twrk platform or to just "start twrk'ing", i.e., to immediately initiate job searching and matching job openings and displaying matches to the user. If the user says no to a tour at step 134, the twrk platform immediately begins semantic matching, or "twrk'ing" 138, and jobs are shown to user in a single screen on the user interface. If the user requests a tour, at stepPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment136 the user is given a tour of basic navigational features within the software application, before the twrk platform begins semantic matching, or "twrk'ing" 138.

[0032] As indicated above, application programming interfaces (APIs) of third parties such as LINKEDIN® may also be utilized, in addition to facilitate semantic matches between job seekers and job openings, for preparing and sending documents such as cover letters as part of job application packages via Twrky’s job application package generator. Such APIs may therefore be used to perform an automatic application process for those job openings which are posted via third-party sites, or directly to a recruiter who provided API credentials via formats such as web forms.

[0033] Regardless, it is to be understood that APIs are just one approach to ingesting input data into the twrk platform and the Twrky artificial intelligence engine. For example, input data for job seekers may be ingested via - and in addition to APIs - via web forms, via documents uploaded or otherwise sent in by job seekers, or via interaction with a Twrky bot as described below. Job openings may be provided to twrk by a recruiter, either via APIs, web crawlers, web forms, or via documents uploaded directly into twrk. It is to be further understood that Twrky may develop and deploy one or more agents (as discussed further herein), in automated workflows, for ingesting input data from one or both of a job seeker and a recruiter.

[0034] The Twrky artificial intelligence engine may include, and in addition to a bot or chatbot interface through which users may interact in their use of the twrk platform, several additional aspects which enable performance of one or more features of both Twrky and the twrk platform. For example, the Twrky artificial intelligence engine enables semantic matching of information in job seeker profiles with job openings for open employment positions. Semantic matching is a process of comparing job seeker information and job openings to holistically match job seekers with job openings based on an overall impression provided by each, rather than simply by matching based on keywords. The present invention ingests user data for job seekers (e.g. authorized LINKEDIN® fields, uploaded resume files, and chatbot transcripts of communications between job seekers and Twrky) and job openings, then applies natural language pre-processing to parse and normalize entities (such as titles, skills, company) against a controlled taxonomy. A feature builder function in the semantic matching process derives structured features (e.g., years- per-skill, recency, location / salary constraints). In parallel, a machine learning-based embedding service converts both job seeker profiles and position descriptions in the job openings into dense vector representations (semantic embeddings).PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0035] These vectors and their metadata are stored in a vector index that supports approximate- nearest-neighbor retrieval with hard metadata filters (location, seniority, legal constraints). At query time, the present encodes the querying entity (candidate or job), performs vector retrieval to generate a candidate set, and then invokes a re-ranking machine learning model (e.g., a crossencoder or equivalent pairwise scorer) to compute joint relevance for each (job seeker, job opening) pair. A policy / scoring engine fuses re-ranker scores with business rules and structured features to output a calibrated match score plus machine-readable evidence keys.

[0036] The Twrky artificial intelligence engine also utilizes language models, such as large or foundational language models, for multiple features within the present invention. In one exemplary implementation of a language model, Twrky automatically creates cover letters to job seekers where they have been matched with an open employment position in a job opening, and adapts resumes of job seekers where necessary. Twrky automatically creates a prompt of the language model that adapts both the content of the cover letter, and any content or format of the job seeker’s resume, to comply with requirements of a job opening and / or any expressed preferences of a recruiter.

[0037] The automatic creation of cover letters, adaptation of resumes of job seekers, and creation of prompts of language models with Twrky may be performed in one or more agents. Agents are steps that define a workflow, and these workflows may be automatically performed to follow a process or procedure or achieve a particular goal or outcome in the twrk platform and / or with Twrky itself. Agents may be developed within Twrky, for example, to conform information provided by a recruiter via a web form for processing within Twrky. Other agents may be developed to complete and compile an automatic job application package. It is to be understood that many workflows may be automated with Twrky and the twrk platform, and therefore that many agents may be developed to perform these workflows.

[0038] Natural language processing (NLP) techniques, and large language models (LLMs), are used in two additional aspects of Twrky’s artificial intelligence-based engine. First, during ingestion, an NLP / LLM extraction step processes user-chat transcripts and resumes to identify preferences and implied skills, in named-entity recognition and / or prompt-constrained LLM extraction. Second, for transparency, an LLM-based explanation generator performs retrieval- augmented generation over stored snippets of identified preferences and implied skills to produce user-facing rationales (e.g. “why this match”), constrained to cite the underlying evidence. The present invention logs explicit and implicit feedback (likes, passes, applies, interview outcomes) and uses these labels to train and fine-tune machine learning models over time (e.g., learning-to- rank for re-ranking and, when sufficient data exists, domain-tuning of the embedding model).PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0039] Operational components in the functions performed by Twrky include one or more of the following components. Ingestion / normalization services; embedding and re-ranking inference endpoints; a vector store; the policy / scoring engine; an explanation service; a feature store; and orchestration / observability for scheduled re-embeddings, drift / quality monitoring, audit logging, and privacy / consent enforcement (scoped access, field-level encryption, revocation, and provenance). It is to be understood that each of these components are not simply to be construed as generic computing components. Instead, each of these components may include combinations of hardware and software elements that together configure the component to perform specific computing functions that enable the present invention to match job seekers with open positions of employment. According, use of the terms in this paragraph, and others that include the words module, element, engine, platform and the like, are not intended to invoke treatment under 35 U.S.C. §1 12(f). Similarly, they are not intended to invoke treatment as elements recited at a high level of generality such that they amount to no more than mere instruction to apply an abstract concept using generic computer components under 35 U.S.C. §101 .

[0040] Twrky may also include, as noted above, as bot or chatbot feature. This bot or chatbot feature may include an avatar that is presented on a consumer-facing interface when a user (job seeker or recruiter) chooses to engage with and communicate with the twrk platform via the bot or chatbot.

[0041] Through Twrky, and regardless of whether an avatar and / or chatbot interface is implemented, users may be prompted to engage with the twrk platform in the following ways. The twrk platform may confirm the type of job that user is looking for; the user may respond and communicate with Twrky via voice commands (analyzed via machine learning techniques capable of natural language processing), via gestures, or typed via a virtual type pad on an interface. Twrky may also ask a user about any quantifiable or measurable experience or information, and, again, the user may respond via voice, gestures, or typed commands as above.

[0042] Twrky may ask the user about their desired compensation. As with the methods of interaction above, the user may respond via voice or typed commands. Twrky may also prompt the user to allow for push notifications. Twrky may ask the user about any additional desired perks or preferences from employment positions, and the user may respond and interact via voice or typed commands.

[0043] Twrky may also prompt the user about their desired employment location and / or whether they want to work on location or whether they prefer a remote or hybrid position. The user mayPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment again respond via voice or typed commands, as above. Twrky may also prompt the user to provide any other information that it should know about with respect to what the user wants (or specifically does not want) in a job, and it enables the user to respond via voice or typed commands, as above.

[0044] Twrky may further confirm that it has what it needs to start matching jobs to the user, and it may prompt the user as to whether they want to take a tour or just "start twrk'ing" to see matches immediately. Twrky may also prompt the user to take a tour of the twrk platform; if so selected by a user, the user is provided with a tour of the basic navigation of the twrk platform. Regardless, at the end of the profile creation process, job matching processes may be initiated immediately. Job matching (or "twrk'ing") therefore begins, and job opportunities are shown to the user in a single screen. (See the Job Matching description below with respect to back-end processes.)

[0045] Referring now to FIGS. 2, the front-end processes also include a process 200 for editing a resume 202, for example a standard resume generated at step 114 or uploaded at step 112 or a custom resume generated for premium members. In this process 200, a user may retrieve a standard resume and cover letter at step 204, such as, e.g., via a hamburger menu. At this point in process 200, different functions may be available for a user depending on whether he or she has the free / standard or the premium membership with the twrk platform and process 200 may determine whether the user is standard member at step 206. If the user answers "yes”, then the twrk platform prompts the user to upgrade to premium membership at step 208. If the user answers "no” at step 210, then the standard resume is retrieved and the user may edit and save their standard resume directly within the twrk platform at step 212. For example, the user may be presented with a selectable indicia prompting user to save the standard resume, such as, e.g., a radio button or other selectable indicia, at step 212, for example: a box with text such as "Looks good. Save it." After the user has finished editing and saving their standard resume, the user can then exit this page at step 218. Instead of modifying a previously stored standard resume, the twrk platform also allows the user to generate a new standard resume at step 214. For example, the user can prompt twrk to "try again" in creating a standard resume. The process 200 will then generate a new standard resume based on information stored in the twrk platform that was obtained at step 114 from the user’s profile on the networking site, such as, e.g., LINKEDIN®. The user may then edit and save their standard resume directly within and to the twrk platform at step 214. After the user has finished editing their standard resume at step 212 or 214, the user can then exit this page at step 216.

[0046] If the user selects “no” at step 206, and the twrk platform confirms that the user is a premium member at step 218, and if user has a premium membership, then the twrk platform canPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment prompted the user to retrieve their standard or custom resume (e.g., as generated at step 520 and accessed from application bucket 528 of FIG. 5) at step 220. Once retrieved, the user may edit and save their custom resume directly within the twrk platform at step 212. After the user has finished editing their custom resume resume, the user can then exit this page at step 218. Similarly, if the user selects “yes” at step 210, the twrk platform will enable the user to upgrade to a premium membership. Upon completion of this upgrade, the twrk platform will then generate a custom resume based on information stored in the twrk platform that was obtained at step 114 from the user’s profile on the networking site, such as, e.g., LINKEDIN®. The user may then edit and save their custom resume directly within and to the twrk platform at step 222. After the user has finished editing their custom resume at step 220 or 222, the user can then exit this page at step 216.

[0047] As shown in FIGS. 3A & 3B, front-end processes may also include a process 300 for job matching and auto-apply 302 that provide interfaces with the Al-based “Twrky” engine and functions for interacting with matched positions. Referring to FIG. 3A, these functions may include calls to back-end processes at step 310 for the purpose of matching and displaying job openings to the use and refining such job openings based on user’s selection of previous job openings. These back-end processes 310 can pull open job openings from both job openings posed online or otherwise in the public domain as well as job openings uploaded by a recruiter who has obtained a premium membership subscription to the twrk platform. A recruiter member can upload a job opening directly into the twrk platform or use the twrk platform to generate an Al- created job opening. One of the benefits of membership is that job openings from a recruiter member would be prioritized in job searching and matching over job openings from an online or otherwise in the public domain source. An additional feature of premium membership for a recruiter member would be a verification process by the twrk platform that the recruiter member is a real entity or organization, thereby reducing or eliminating ghost job openings. These back- end processes 310 may also include a prefill of a matched "bucket" of job openings that is refined according to the user's swipe patterns on the interface. These functions may include additional calls to back-end processes at step 312 which will enable a full screen display of the first-matched job position for the user.

[0048] Regardless, process 300 for job matching and auto-apply 302 may include a display of a first-matched job opening in a single screen at step 314. Each job match appears in a single screen showing the company name, the job title, the salary, the location (or whether remote or hybrid), an Al-generated summary of the job, the top job requirements, and the percentage of a match that the user is to the job.PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0049] Continuing with FIG. 3A, a user will have the opportunity to swipe right or left at step 320. If the user swipes right using a device, the back-end auto-apply feature 322 is triggered by the twrk platforms. For standard members, this involves auto-submission of the standard job application comprising a standard resume and standard cover letter. For premium members, this involves auto-submission of an Al-generated customized job application comprising a customized resume and customized cover letter tailored to the specific job opening selected (unless the user specifies use of the standard job application). If the selected job opening is from third- party / external source, the twrk platform is no longer involved beyond this point in the application process and the user must engage the recruiter using traditional methods. If the selected job was posted directly within the twrk platform by a premium recruiter with a subscription member, then the twrk platform proceeds to a process 700 as illustrated in FIG. 7. After the first job match is processed, the next job match then appears on the screen at step 324.

[0050] If the user does not swipe right (in other words, swipes left) at 320, then the job opening is rejected and the back end acts to ensure that this particular job opening is not shown again at step 330. The associated back-end process places the position in a bin 450 (See FIG. 4), which stores the rejected resume for a set number of days before removing.

[0051] Process 300 for job matching and auto-apply 302 of the twrk platform may also perform a particular function when a set number of left-swipes happen in a row at step 332. For example, when a user swipes left x times in a row (for example, 5 or 10 swipes), thereby rejecting matched job openings, the twrk platform triggers a back-end process at step 334 whereby the Twrky Al engine prompts the user with a prediction or reason based upon this rejection pattern(s) as to why the user is declining so many job openings. The twrk platform may further prompt the user if this prediction or rationale is correct or not and allow the user provided information to the twrk platform as to why the user is rejecting these job openings. This additional analysis by the twrk platform and confirmation or revision by the user then enables the twrk platform to refine the search and match parameters and conduct further searches ( / .e., twrk'ing) in order to identify job openings more suited to the user’s preferences.

[0052] Not referring to FIG. 3B, the series of front-end processes comprising process 300 of the twrk platform may also include functions that are different for standard versus premium members. For example, if a user is a standard member at step 340 and the user attempts x right-swipe in a single day at step 342, such as, e.g., the user attempts an 1 1thswipe, the user may be prompted to upgrade to a premium membership at step 344. The process 300 then determines if an upgrade has occurred at step 346. If the user declines to upgrade, then the twrk platform invites the user at step 348 to return the next day to prompt the twrk platform to conduct further searching andPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment matching functions for job openings and the user will be allowed to evaluate additional job openings up to the prescribed daily limit. If a user chooses to upgrade to a premium membership, the daily limitation of right-swipe is removed and the twrk platform continues to conduct further searching and matching of job openings for the user and the user may continue evaluating job openings identified by such searches at step 350. The user may therefore continue twrk’ing as a standard member with fewer than X right swipes per day (for example, 10 swipes), the next day as a standard member after 10 right swipes, or immediately as a premium member.

[0053] It is to be understood physical interactions such as “swipes” on an interface are but one type of physical interaction that a job seeker or a recruiter may utilize, and that therefore the present invention is not intended to be limited to any one type of such physical interaction described herein. For example, other types of physical interactions may include a swipe using one or more fingers on a display interface (such as holding one’s fingers on a screen, and moving them in a left direction or a right direction), a movement of a device hosting the twrk platform and on which the interface is being used in a left or right direction, a gesture towards the device hosting the twrk platform and on which the interface is being used (such as waving one’s hand in a left direction or a right direction), or a voice command to move the screen to the left or to the right.

[0054] Referring now to FIG. 4, the twrk platform also includes one or more front-end processes 400 for storage of past job applications 410. These front-end processes 400 allow a user to view past job applications for job openings at step 420 that have already been submitted, for example via a hamburger menu or search past job applications for open positions at step 430 using various search parameters such as, e.g., by recruiter, company, job title, or date submitted. These frontend processes 400 allow a user to select the appropriate past job application at step 440 in order to open the attachment(s) that comprises a job application, such as, e.g. a standard or custom resume and a standard or custom cover letter.

[0055] Still referring to FIG. 4, the front-end processes 400 of the framework of the present invention also includes a “bin” function 450 for the storage of job positions rejected by a user at, e.g., step 330. For example, left-swiped positions at 330 will go into a bin at step 460, which can be accessed again by a user through, e.g., a hamburger menu. A user can access bin at 460 and take jobs out of the bin at step 470 which will place the restored job opening toward the front of the user’s matching queue at 314. For example, a user may mistakenly reject a job opening by left swiping at 314 or reconsider a job opening rejected by the user by left swiping at 314. Job openings in the bin may be stored for up to X days (for instance, 7 days) and then auto-delete thereafter at step 480.PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0056] FIG. 5 illustrates a further front-end process 500, in which premium users may have access to other aspects of the twrk platform that are driven by additional front-end functions. These include a job application generator 510 that creates an Al-generated custom application comprising a custom resume and custom cover letter. For example, in step 520, for every right swipe by a user for a job opening, the twrk platform creates an Al-generated custom application comprising a custom resume and custom cover letter. In step 522, a user selects whether the twrk platform will automatically submit a job application to a recruiter. If the user answers “yes", this feature is turned on in the settings and the twrk platform will auto-submit an Al-generated custom job application to a recruiter for each job opening a user desires to apply for at 524. For example, a premium user can right-swipe at 320 and the twrk platform will auto-submit an Al- generated custom job application to a recruiter for that right-swiped job opening at 524. The default setting will be “yes” for users with premium memberships.

[0057] If a user answers “no”, this feature is turned off in the settings, and the twrk platform will not auto-submit custom job applications for the user. Instead, each custom job application will be placed in an "Application Bucket," at step 526. A user can then access and review the custom job application in Application Bucket prior to submission to a recruiter at step 528, e.g., via a hamburger menu. The user then has an option to approve or edit the job application at step 530. If the user answers “yes”, twrk will submit the user-approved job application to the job poster 550 and user can continue to access, review and edit other job applications or exit the page 560. Typically, the user is prompted to select the "Submit Application Now" radio button at step 570, which will auto-submit the application. If the user answers “no”, the twrk platform will enable the user to edit and modify the custom job application (both custom resume and cover letter) at step 540. Once the job application is revised and saved, the user then approves submission of the job application and twrk will submit the user-approved job application to the job poster 550 and user can continue to access, review and edit other job applications or exit the page 560.

[0058] FIG. 6 illustrates yet another front-end process 600, in which a user may forward a job opening to another person 610. In some embodiments, a user selects ajob opening and a contact, e.g., by clicking on a "Friends" icon, that the user desires to send the job opening to 620. The twrk platform then prompts a user at step 630 to send the job opening to that contact, e.g. , by text or email. An option may also be included to send ajob opening to a contact within the twrk platform itself. Once a posting is sent to a contact (or not sent), a user is able to then keep twrk'ing or move to another page at step 640.

[0059] The twrk platform may further include one or more recruiter-specific swiping front-end functions as illustrated in the process 700 of FIG. 7. Such recruiter-specific swiping front-endPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment functions in process 700 provide additional features within the twrk platform that enable a recruiter to also swipe left or right relative to job seekers who have swiped right to apply for, or express interest in, a job opening. Such a front-end process 700 is initiated when a job seeker swipes right on an open job opening at step 702; the job seeker (and / or the job seeker’s job application) is placed in and appears in the recruiter’s "candidate bucket", an inbox listing all of potential candidates that could be a match for an open job opening at step 704. The twrk platform then sends a notification to a recruiter that there is at least one job candidate in the recruiter’s candidate bucket for the relevant job opening at step 706.

[0060] The twrk platform enables a recruiter to open or otherwise access the candidate bucket at step 708 to view the list of candidates who have swiped right relative to a particular job opening. A recruiter then selects, at step 710, any of the job seekers / candidates in the candidate bucket to start viewing the candidates. Each candidate's job application includes the resume and cover letter, summary of the candidate's qualifications including strengths, most relevant experience, and other indica selected by the recruiter, and percentage of matching to the job opening appear to the recruiter at step 712 in a single screen.

[0061] The twrk platform enables a recruiter to also physically interact with an interface, for example by swiping right or left, to initiate additional functions within the Twrky Al-based engine. If a recruiter swipes left (or clicks on left / reject button) 714, the candidate is rejected and will not re-appear to the recruiter for the particular job opening at 716. The twrk platform then sends a notification to the rejected job candidate at 718 that the recruiter has passed on that candidate for the particular job opening. On the recruiter’s screen, the next job seeker in the candidate bucket appears at 720 unless / until there are no more potential candidates.

[0062] If a recruiter does not swipe (or otherwise physically interact) left, the recruiter may instead select and save a candidate for later or future consideration 722, for example using the hamburger-style menu. If a recruiter chooses to save a candidate, the candidate is placed back in the candidate bucket for the relevant job position at 724. The next job seeker in the candidate bucket then appears on the screen, unless or until there are no more potential candidates 720. The candidate may be automatically notified at 726 that their application has been reviewed and is pending.

[0063] A recruiter may instead choose to swipe right at 728, indicating that the recruiter interest in this job seeker for this particular open position. Swiping right causes the twrk platform to initiate a notification that is sent to the job seeker that they have a potential match with the recruiter for the relevant position at 730. The job seeker may be prompted to arrange an interview, for example by connecting his or her calendaring system with the recruiter’s calendaring system, or simplyPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment linking with the recruiter’s calendaring system to select a date and time for the interview. This may also be accomplished automatically by an agent as noted below, particularly where both parties’ calendars are linked within the twrk platform. Regardless, the next job seeker in the candidate bucket appears on the screen, unless or until there are no more potential candidates at 720.

[0064] This recruiter-side functionality therefore provides notification to a job seeker of what happened when the job seeker submitted a job application for a job opening. It also addresses one of the major issues that job seekers have with existing applications used for searching for job openings: that the job seekers are not provided any notification regarding job openings that the job seekers have expressed interest in, the status of the job application, and whether any decision has been made by a recruiter.

[0065] FIG. 8 illustrates one or more additional functions in a further front-end process 800 that may be implemented in the framework of the present invention. The front-end process 800 of FIG. 8 enables interview-specific functions that allow both a job seeker and a recruiter to quickly schedule and conduct an interview. In FIG. 8, a job seeker has received a notification that there is a potential match with an employer for a particular open position, e.g., at 730 in FIG. 7, the twrk platform initiates an interview setting process 810. For example, this can occur after a job seeker has swiped right on an open position and a recruiter has also swiped right on that particular candidate.

[0066] In the interview setting process 810 of FIG. 8, the twrk platform asked a job seeker if the job seeker is still interested in the job opening 820, If the job seeker answers “yes”, then the twrk platform opens a notification, which enables the job seeker to open the recruiter’s calendar and schedule job seeker’s own interview on the recruiter’s calendar 830. The recruiter is then sent a notification that the job seeker has requested an interview on the recruiter’s calendar, and the recruiter is able to see and accept the interview on recruiter’s own calendar 840. When the interview has been set, the job seeker is taken back within the application to their notifications page 850.

[0067] If a job seeker is no longer interested in a job opening for which both the job seeker and the employer have swiped right, the job seeker answers “no” at 820. The twrk platform then prompts the job seeker to provide reasons for declining the job at 860, such as, e.g., the job seeker’s situation has changed or that the job seeker is no longer interested / available for the job opening. In this case, the recruiter is sent a notification that the job seeker is no longer available for the job opening at 870. The job seeker is then taken back to their notifications page 850.Back-End ProcessesPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0068] Back-end processes are shown FIGS. 9-12. The twrk platform in which the framework is embodied includes a plurality of such back-end processes, as discussed further below; these back-end processes govern how twrk’ing — or getting job matches — occurs.

[0069] As shown in FIG. 9, one back-end process 900 involves standard resume or CV and cover letter creation 910. This is from (a) the resume that the user uploaded, (b) one that is auto-created by utilizing information from a third-party site, such as, for example, the user's LINKEDIN® Profile, or by other methods such as (c) one created using voice or typed information from the user directly, or (d) any combination of these, at step 920. For users who are premium members, they may be shown a toggle 930 by which they can opt to only send the standard resume and cover letter with each right-swipe instead of their custom resume and cover letter; the default will be for this toggle to be off.

[0070] This back-end process(es) 900 for resume creation may also allow for a highlight and "always include" and / or a highlight and "never include" at step 940. This is for all users, whether standard or premium members to view and / or edit the standard resume 950. If the twrk platform creates the standard resume from a profile from a third-party site, then the user can review and delete this resume and cover letter and prompt the twrk platform to generate a new standard resume and cover letter for review by the user.

[0071] As also shown in FIG. 9, another aspect of this back-end process 900 involves determining membership status, including prompts to encourage users to upgrade from standard memberships to premium memberships at 960. A user may upgrade without being prompted, via settings that are typically available via the hamburger-style menu at 970. The twrk platform indicates at 980, the benefits of a premium membership, as noted herein, and can list such benefits which at least includes unlimited swiping, auto-generation of curated resumes and cover letters per right-swipe, and auto-submission of curated resumes and cover letters per right swipe as indicated at 980.

[0072] FIG. 10 illustrates a further back-end process 1000, where a user may be prompted to upgrade membership through an “upsell prompt” 1010 in which a recommendation is provided at 1020 (for example, via a pop-up window) to upgrade one’s membership. Ifthis is selected at 1030, the back-end process 1000 may generate an additional screen or pop-up window with pricing and tier information at 1040 that displays upgrade options. If this is further selected, it triggers a payment process 1050 in which payment information may be provided by the job seeker. Once completed, the job seeker is returned to the original page at 1060. Alternatively, if thePCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment recommendation at 1020 is not taken, a user may simply select a radio button (or other indicia) stating "Continue Without Upgrade" or the like at 1070, and the user may continue twrk’ing or return to the original page at 1060.

[0073] FIGS. 11 & 12 illustrate still other back-end processes 1100 and 1200 respectively that govern what happens within the framework when users interact by swiping right or swiping left using their screens. In process 1100 of FIG. 11 , upon a first right-swipe by users with standard membership at 1110, they may be prompted to upgrade at 1120. If the user chooses to upgrade at 1130, back-end functions for enabling "Right-Swipe Premium" features are engaged at 1140. If not, users may auto-submit their standard resume at 1150 to the related job post, at a maximum of x per calendar day (for example, 10). Upon the 1 1th right-swipe, the user is again prompted to upgrade to a premium membership level at 1160. If the user upgrades at 1170, they may access the "Right-Swipe Premium" features at 1140; if not, they return to the auto-submit of the standard resume at 1150.

[0074] Referring to FIG. 11 , a premium member who right-swipe 1180 on their screen has access to features such as auto-generated PDFs, curated resumes and cover letters 1182, and are able to have a custom job application comprising these elements auto-submitted on their behalf for the related job opening at 1184. Each application will be searchable on the "Past Applications" page at 1186, which maintains all submitted applications for x days (for example, 30 days).

[0075] Referring to the back end process 1200 of FIG. 12, a left-swipe 1210 rejects a job opening for all users, standard or premium. Rejected positions are sent to the bin at 1220 and are not shown again to the user, unless the user takes it out of the bin within x days (for example, 7 days). X left-swipes in a row (for instance, 5) at 1230 may trigger a prompt for the user to allow the Twrky Al engine to learn more about the user’s preferences at 1240. For example, the user may be prompted with “You've swiped left several times. Is there something we need to take into consideration to send you better matches?" The user may then provide new information, e.g., by speaking or typing, to the twrk platform at 1250, which then uses the information to re-configure job matches, if needed or appropriate at 1260.Features List and Description

[0076] The framework of the present invention provides a rich set of features within the twrk platform to enable matching of job seekers with postings of open positions of employment. One such set of features is provided around the profile creation process, typically when a user first creates an account and registers with the twrk platform. It is to be noted however that users mayPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment amend or revise their profile at any time. Users may therefore go back to the profile creation questions and sections that are discussed below, whenever they want to update their information and / or preferences.

[0077] During profile creation, users may be presented with a notification to inform the user of the upcoming process; for example, they may be provided with a pop-up or other window stating “Let’s create your profile! This will only take a couple minutes. We want to give you the best user experience possible.” The profile creation process may be gamified, for example by presenting a visual “percentage completed” indicator throughout the process.

[0078] The profile creation process includes enabling data input by the user, for example for the purpose of constructing a resume. This may occur by gathering data from the user’s LINKEDIN® profile upon the user’s sign-in (permissions included) or by uploading an existing resume document (such as a PDF, a Word document, a Google document, or any other format).

[0079] Users may also utilize voice commands as a method of data entry in the profile creation process. Voice commands, as noted above, may be analyzed using one or more machine learning algorithms and language models that perform natural language processing techniques to understand the user’s voice-based data entry. Regardless, for users that speak their prior experience for the purpose of resume creation, the Twrky Al engine (or, through the Twrky bot) asks (via either an automated voice played through the device’s speaker, or via words presented on a screen) recruiter- like questions that are meant to clarify certain factors.

[0080] For example, this may include iterative questions such as “From the information you provided, it looks like you are interested in a position as a / an . Is this right?” If yes, the: “Great! Let’s talk about your biggest strengths.” If no, then: “What type of positions are you looking for?” and “Which part of your past experience do you feel best equips you to work as a / an ?”

[0081] Twrky may also ask the user “Do you have any measurable experience? For example, have you done anything that earned a certain amount of money for a company, increased a percentage of customers or revenue, or did anything that can be reflected with numbers or percentages?” Twrky may also ask “Is there anything in particular that you want your next job to have or avoid? For instance, do you want to have a 401 (k), or do you want to avoid working on the weekends?” All of this is designed to help build a profile for the user and may also be used to build content for a resume for the user, without the user having to type any information at all into the application. It is to be understood that any format of such questions is possible, and thereforePCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment the present specification is not to be limited to any specific content or words of any such questions mentioned herein; indeed, the tTwrky Al engine may itself learn from user responses and selfgenerate customized questions to help tailor a user’s resume accordingly.

[0082] The user input(s) from above may also be used to auto-create a resume, as noted above. Regardless, the resume created by twrk is viewable by the user by navigating to that page after profile creation is finished (see description of the Resume Management section below). The resume - whether created by twrk or uploaded by the user - is accessible via a hamburger menu (or other intuitive indicia on the screen). A pop-up may also notify the user where they can locate their resume after they are finished creating their profile. This resume will be referred to as the user’s standard resume.

[0083] A further screen is presented during profile creation for selected preferences for salary or wages. This screen may have a slider for minimum-sought hourly wage / salary and, check-mark box options for part-time, full-time, other type (contract, gig, freelancer, contractor), or temporary work. These indicia may be placed anywhere on the screen; for example, the slider may appear at the top-half, and the check-mark boxes may appear at the bottom half.

[0084] The user may also be prompted during the profile creation process to allow for push notifications. This may occur, for example, immediately after the salary input section, and the prompt may be presented at the bottom of the wage / salary page. Such a prompt may be designed to obtain a higher number of users opting in to receive push notifications.

[0085] Another screen that users may see during the profile creation process may relate to location. In this conversational screen, Twrky may ask the user questions such as “Where would you like to work? Feel free to let me know all of the locations that you’re interested in, whether you’re wanting a 100% remote position, or if you’re looking for a hybrid opportunity.” If Twrky needs more information, it may prompt the user to explain the information it needs to retrieve the best matches.

[0086] During profile creation, users may be asked if they want a “tour” of how things work and where to find items within twrk. If they say or indicate yes, a brief tutorial is provided; if they want to skip the tutorial, the job-matching function simply launches right away so that users can begin twrk’ing — job matching.

[0087] A radio button or other indicia may be presented for Job-Matching Launch. This starts the job-matching process (twrk’ing). It is to be noted that the user is able to get to the job-matchPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment function from any page within the twrk platform. The twrk platform displays the first-matched job position on a full screen, including company logo, job title, wage / salary, location, and an Al- generated summary of the job description, including the responsibilities and the qualifications.

[0088] The twrk platform provides continuance for users, with seamless job matching to provide users with a pleasant job-searching experience. In a further embodiment of the application, the “qualifications” appearing at the bottom of each job suggestion are quantified by a percentage. Regardless, this pleasant job-searching experience also includes, as noted throughout, the ability to auto-apply to job openings with the standard resume (for standard members) or customized resumes and cover letters for premium members.

[0089] The full job description may be viewed by, for example, swiping up on the screen. Alternatively, this may occur by swiping down. Regardless, this will show the company’s actual job description, rather than the Al-generated summary of the job description.

[0090] Another set of features is provided around the process of inviting friends to use the twrk platform. Users may, for example, send a job opening to a friend or contact. A radio button or other indicia may be presented on the screen (for example, in the bottom-left corner). Options may be presented to the user to send the job opening via email, text, third-party social media account, or within the application itself.

[0091] For job openings sent to a friend or contact outside of twrk, the application may autopopulate an invitation to view and connect via twrk. For example, such an invitation may include text such as “I saw this job on twrk and thought it might interest you: [link].” When the friend clicks on the link, it would open twrk (if that friend is already a member) or prompt the friend to download twrk (if that friend does not already have it downloaded).

[0092] For members, twrk provides an approach for sending job opening recommendations to connected friends within the application. The twrk platform may therefore include additional features and processes (front end and back end) that enable users to connect or engage natively through the application, such as messaging, uploading other items such as images or pictures, blocking certain users, etc. Regardless, it is important to note that safety and security features and processes are also present so that users are comfortable in knowing that an employer cannot simply download the twrk platform and then search for their employees who may be using twrk to find other positions.PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0093] If users send a job opening to a friend or contact, one efficient way to promote usage is if that friend is also a twrk user. This creates network effect for the twrk platform. In such a case, the recipient of the recommended job opening should be notified, and there may be a “bucket” where all recommended postings can be seen. The notification of the shared job opening may include which connection sent the recommendation. That friend may then be able to swipe as if they were in the job-matching portion of the application.

[0094] Yet another set of features is provided around universal navigation within the twrk platform. One such feature is quick access to the job-matching function from any page. Also, by default, twrk should never match a user to positions listed by their current employer or organization, or any jobs of their former employers or organizations. If there are similarly spelled names, twrk should ask, “is X the same employer as Y on your resume?” twrk’s Al engine recognizes similar-sounding, similarly-spelled, or similarly-formatted names and, by default, never sends those recommendations to the user. If twrk is confused and needs more information, it asks the user and learns from the user’s voice or typed responses.

[0095] For all voice / conversational screens, a typepad icon is available (for example, in the lower right-hand corner) to provide users with the option to type in case they are in a quiet space or otherwise cannot speak (or the application is for some reason having trouble understanding the user’s voice-based data entry).

[0096] A further set of features is provided around resume management. In a resume retrieval feature, users can view and edit their standard resume, for example via a hamburger menu. They may also be able to edit a resume; such a feature includes the ability to edit and save the standard resume directly within the twrk platform. This is the resume that will be sent with every right-swipe for users with standard memberships.

[0097] Several buttons and toggles are provided to enable resume management features. For example, for users with standard memberships, a button (or other indicia) that is by default turned on, indicates that the twrk-generated standard resume is what will be sent when the user swipes right to apply for an open position. An option may be provided to “use my own resume” where users can upload their own resumes in PDF format (or other file type) or by connecting to a Google Drive Doc. Additional buttons may indicate which resume is going to be sent as part of the application process upon a right swipe.

[0098] For users with premium memberships, a toggle that is by default turned on indicates “Submit twrk’s auto-generated customized resumes for me with each right-swipe.” If the userPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment toggles that off, then they need to select which resume they want to send: their standard resume that twrk auto-generated upon profile creation, or one that the user specifically uploaded to the platform. Alternatively, the user may edit these in their “Application Bucket” if they do not want the auto-generated version to be automatically sent. Users may also be able to store or share the resume(s) that are auto-generated for them outside of the twrk platform, for example on their mobile devices.

[0099] Other features are provided around job matching and job applications within the twrk platform. As noted above, for rejection of a suggested job opening, users swipe left; rejected job openings are not shown again. Left-swiped job openings go in a “trash bin” and are stored there for no more than x days. Users may take a rejected job out of the bin; all of the trash bin items that are “put back” into the queue should then jump the line and be the first ones for the user to swipe on when they “start twrk’ing” again. Those job openings may also be sent to a friend.

[0100] If the user swipes to the right, this starts the auto-apply process. All applications made upon a right swipe (whether under the standard membership plan or the premium membership plan) are accessible and stored in a separate page, for at least 30 days. A search function, with a corresponding window, is also provided so that users can search by employer or title (or other information).

[0101] Users are able to send the application to themselves (for example, via email). An “undo” button should linger for a set amount of time after any given swipe.

[0102] Standard membership users, as noted above, get (for example) 10 right-swipes (applications sent) per day. After that, they are prompted to upgrade to premium and shown all of the added bonuses that come with a premium membership. Standard membership users only have their standard resume sent as part of the automatic application process.

[0103] Premium membership users, as also noted above, get unlimited swipes and unlimited job applications. Premium memberships users do not have their standard resume sent, unless they specifically indicate that they only want their standard resume sent; instead, they have an Al- generated custom resume and custom cover letter sent as part of their application process. The custom resume may include an Al-generated “Summary Section” at the top of each such resume.

[0104] The twrk platform defaults to the free or standard version. The default is therefore that the twrk platform either submits the resume that the user uploaded, or the resume that twrk created from their LINKEDIN® (or other third-party) profile. Some users who want their “standard resume”PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment by using their LINKEDIN® profile will nonetheless want some further customization. The twrk platform may ask the user if they want to customize, and this will generate a prompt of the user to upgrade their membership.

[0105] The default for premium membership is that twrk will automatically send a custom cover letter and custom resume with each right swipe. Upon the user first signing up for a premium membership, the twrk platform lets them know that this is the default and, if they want to turn this off and edit each application before it is sent, they need to specifically make this selection within the settings section. If the user wants to be able to review or edit their applications before they are auto-submitted, then the users are directed to a “review” page (akin to a shopping cart). The users may then be asked to confirm proceeding with submission of the application (the cover letter plus resume).

[0106] A resume summary section has, for the standard resume, a heading that is the title of their most recent job (the user can edit this if they want to); and a short following paragraph or bullet points highlighting the best elements of that resume. For the premium (or custom) resumes, an Al-generated summary heading matches the nature of the title of the position to which the user is applying. A following summary paragraph highlights the top (one or several) items within the user's resume that would best fit what the job position is seeking.

[0107] Al-prompted feedback is triggered, as noted above, after x (for example, 5) left-swipes in a row to prompt the user to improve job matching. This Al-prompted feedback inquires as to what is wrong with the suggested job openings being presented, and why they are swiping left so many times in a row. The Twrky Al engine may be able to predict the reason for this based upon swiping patterns. The voice-prompt feature may also pop up, allowing the user to converse with Twrky and explain why they kept swiping left. The typed alternative should be available to the user for this Al-prompted feedback. Users may also have the ability to skip this Al-prompted feedback feature (for example, where consecutive left-swipes could be because of random reasons not based on a specific pattern).

[0108] Users may also access a search feature to search for, view, and retrieve past applications, and search results may be displayed on a dedicated page. Users may type search terms into a search bar and search by employer name, job title, etc. Users are able to view whatever twrk submitted as the application packet for that position - whether they have a standard or premium membership. Users can export, download, and email these items to themselves.PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0109] Twrky also includes a feature that provides recruiter- like suggestions. For instance, if users are not getting too many matches, or if the matches are too low of a matching percentage, Twrky interjects and makes suggestions, such as, for example “Your skills are also suitable for a director of operations role and an insurance management role”... or suggesting an increase in radius (for location) for jobs.

[0110] The application also includes features around membership levels. In addition to the features that attach at each membership level, the twrk platform enables a special student rate when they create a profile with a “.edu” email address. Additionally, beta testers who signed up via a waitlist may get a premium membership at a discounted rate (which should not be visible to the other Beta users. Regardless, all paid memberships auto-renew for the same time period and at the same rate until canceled. Canceled memberships end the day after their most recent paid period. Premium memberships may also be available for a specific x-day free trial.

[0111] Additional features may include a heightened level of user verification to prevent fake applicants or bots from inundating hiring managers with fake applications to their job openings. Features may also be added to ensure that the job openings themselves are real, to avoid presenting fake postings to twrk users. Users may also be able to upload additional supporting documents, such as letters of recommendation and work or writing samples.Other Artificial Intelligence and Machine Learning Implementations

[0112] As noted above, the present invention may include implementation of one or more artificial intelligence-based algorithms, in applications of machine learning techniques for matching job seekers with open positions of employment.

[0113] Artificial intelligence-based algorithms in the present invention may include many types of machine learning techniques. These may include, but are not limited to, k-nearest neighbor (KNN), logistic regression, support vector machines or networks (SVM), and one or more neural networks.

[0114] Neural networks may be applied in the present invention to identify and model appropriate relationships between data points to provide a more accurate understanding of various data points associated with matching a user’s skills and experience with available postings for open employment opportunities. For example, neural networks may be applied to develop more accurate understandings of jobs a job seeker has been previously involved with; this may include discerning quantifiable metrics, such as whether the job seeker increased a percentage ofPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment customers or revenue, and seeking characteristics in job openings that would produce a more suitable metrics-oriented match. This may occur, for example, where a job opening is seeking candidates that have very specific skills or achieved significant results associated with specific projects.

[0115] Regardless, there are many types of neural networks, which are computing systems that "learn" to perform tasks in a supervised manner without being programmed with task-specific rules, based on examples. Neural networks are generally comprised of nodes, which are computational units having one or more biased input / output connections. Such biased connections act as transfer (or activation) functions that combine inputs and outputs in some way. Neural networks are based on arrays of connected, aggregated nodes (or, “neurons”) that transmit signals to each other in the multiple layers over the biased input / output connections. Connections, as noted above, are activation or transfer functions which “fire” these nodes and combine inputs according to mathematical equations or formulas. Different types of neural networks generally have different configurations of these layers of connected, aggregated nodes, but they can generally be described as an input layer, a middle or ‘hidden’ layer, and an output layer. These layers perform different transformations on their various inputs, using different mathematical calculations or functions. Signals travel between layers, from the input layer to the output layer via the middle layer, and may traverse layers, and nodes, multiple times.

[0116] Signals are transmitted between nodes over connections, and the output of each node is calculated in a non-linear function that sums all of the inputs to that node. Weight matrices and biases are typically applied to each node, and each connection, and these weights and biases are adjusted as the neural network processes inputs and transmits them across the nodes and connections. These weights represent increases or decreases in the strength of a signal at a particular connection. Additionally, nodes may have a threshold, such that a signal is sent only if the aggregated output at that node crosses that threshold. Weights generally represent how long an activation function takes, while biases represent when, in time, such a function starts; together, they help gradients minimize over time. At least in the case of weights, they can be initialized and change (i.e. , decay) over time, as a system learns what weights should be, and how they should be adjusted. In other words, neural networks evolve as they learn, and the mathematical formulas and functions that comprise a neural network can change over time as a system improves itself.

[0117] The foregoing descriptions of embodiments of the present invention have been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise forms disclosed. Accordingly, many alterations, modifications, and variations are possible in light of the above teachings, and may be made by those having ordinaryPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment skill in the art without departing from the spirit and scope of the invention. For example, the application of the present invention may enable users to interact with the Twrky Al-based engine via gestures (for example, a long press on a particular radio button, or simply shaking or moving a device on which they are interacting with the application in a particular manner) in addition to voice or typed commands. Still further, users may interact with other types of physical interactions other than left or right swipes, movements or commands. Instead, up or down physical interactions with an interface may also be implemented. It is therefore intended that the scope of the invention be limited not by this detailed description. For example, notwithstanding the fact that the elements of a claim are set forth below in a certain combination, it must be expressly understood that the invention includes other combinations of fewer, more, or different elements, which are disclosed above even when not initially claimed in such combinations.

[0118] In closing, foregoing descriptions of embodiments of the present invention have been presented for the purposes of illustration and description. It is to be understood that, although aspects of the present invention are highlighted by referring to specific embodiments, one skilled in the art will readily appreciate that these described embodiments are only illustrative of the principles comprising the present invention and such examples are not limiting thereto. As such, the specific embodiments are not intended to be exhaustive or to limit the invention to the precise forms disclosed. The use of any and all examples or exemplary language (e.g., “such as”) provided herein is intended merely to better illuminate the present invention and does not pose a limitation on the scope of the invention otherwise claimed. No language in the present specification should be construed as indicating any non-claimed element essential to the practice of the invention.

[0119] In addition, groupings of alternative embodiments, elements, steps and / or limitations of the present invention are not to be construed as limitations. Each such grouping may be referred to and claimed individually or in any combination with other groupings disclosed herein. It is anticipated that one or more alternative embodiments, elements, steps and / or limitations of a grouping may be included in, or deleted from, the grouping for reasons of convenience and / or patentability. When any such inclusion or deletion occurs, the specification is deemed to contain the grouping as modified, thus fulfilling the written description of all Markush groups used in the appended claims. In addition, all methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. Therefore, it should be understood that embodiments of the disclosed subject matter are in no way limited to a particular element, compound, composition, component, article, apparatus, methodology, use, protocol, step, and / or limitation described herein, unless expressly stated as such.PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0120] While aspects of the inventive subject matter have been described with reference to at least one exemplary embodiment, it is to be clearly understood by those skilled in the art that the inventive subject matter is not limited thereto. For example, although each embodiment represents a single combination of inventive elements, the inventive subject matter is considered to include all possible combinations of the disclosed elements. Thus, if one embodiment comprises elements A, B, and C, and a second embodiment comprises elements B and D, then the inventive subject matter is also considered to include other remaining combinations of A, B, C, or D, even if not explicitly disclosed. Furthermore, those of ordinary skill in the art will recognize that certain changes, modifications, permutations, alterations, additions, subtractions, and subcombinations thereof can be made in accordance with the teachings herein without departing from the spirit of the present inventive subject matter. Thus, while the inventive subject matter is susceptible of various modifications and alternative embodiments, certain illustrated embodiments thereof are shown in the drawings and will be described below in detail. It should be understood, however, that there is no intention to limit the inventive subject matter to any specific form disclosed, but on the contrary, the inventive subject matter is to cover all modifications, alternative embodiments, and equivalents falling within the scope of the claims. It is intended that the following appended claims and claims hereafter introduced are interpreted to include all such changes, modifications, permutations, alterations, additions, subtractions, and sub-combinations as are within their true spirit and scope. Accordingly, the scope of the present inventive subject matter is not to be limited to that precisely as shown and described by this specification. Rather, the scope of the inventive subject matter is to be interpreted only in conjunction with the appended claims and it is made clear, here, that the inventor(s) believe that the claimed subject matter is the inventive subject matter.

[0121] Certain embodiments of the present inventive subject matter are described herein, including the best mode known to the inventors for conducting the inventive subject matter. Of course, variations on these described embodiments will become apparent to those of ordinary skill in the art upon reading the foregoing description. The inventor expects skilled artisans to employ such variations as appropriate, and the inventors intend for the present inventive subject matter to be practiced otherwise than specifically described herein. Accordingly, this inventive subject matter includes all modifications and equivalents of the subject matter recited in the claims appended hereto as permitted by applicable law. Moreover, any combination of the abovedescribed embodiments in all possible variations thereof is encompassed by the inventive subject matter unless otherwise indicated herein or otherwise clearly contradicted by context.

[0122] The words, language, and terminology used in this specification is for the purpose of describing particular embodiments, elements, steps and / or limitations only and is not intended toPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment limit the scope of the present inventive subject matter, which is defined solely by the claims. In addition, such words, language, and terminology are to be understood not only in the sense of their commonly defined meanings, but to include by special definition in this specification structure, material or acts beyond the scope of the commonly defined meanings. Thus, if an element, step or limitation can be understood in the context of this specification as including more than one meaning, then its use in a claim must be understood as being generic to all possible meanings supported by the specification and by the word itself.

[0123] The definitions and meanings of the elements, steps or limitations recited in a claim set forth below are, therefore, defined in this specification to include not only the combination of elements, steps or limitations which are literally set forth, but all equivalent structure, material or acts for performing substantially the same function in substantially the same way to obtain substantially the same result. In this sense it is therefore contemplated that an equivalent substitution of two or more elements, steps and / or limitations may be made for any one of the elements, steps or limitations in a claim set forth below or that a single element, step, or limitation may be substituted for two or more elements, steps and / or limitations in such a claim. Although elements, steps or limitations may be described above as acting in certain combinations and even initially claimed as such, it is to be expressly understood that one or more elements, steps and / or limitations from a claimed combination can in some cases be excised from the combination and that the claimed combination may be directed to a sub-combination or variation of a subcombination. As such, notwithstanding the fact that the elements, steps and / or limitations of a claim are set forth below in a certain combination, it must be expressly understood that the inventive subject matter includes other combinations of fewer, more, or different elements, steps and / or limitations, which are disclosed in above combination even when not initially claimed in such combinations. Furthermore, insubstantial changes from the claimed subject matter as viewed by a person with ordinary skill in the art, now known or later devised, are expressly contemplated as being equivalently within the scope of the claims. Therefore, obvious substitutions now or later known to one with ordinary skill in the art are defined to be within the scope of the defined elements. Accordingly, the claims are thus to be understood to include what is specifically illustrated and described above, what is conceptually equivalent, what can be obviously substituted and also what essentially incorporates the essential idea of the inventive subject matter.

[0124] Unless otherwise indicated, all numbers expressing a characteristic, item, quantity, parameter, property, term, and so forth used in the present specification and claims are to be understood as being modified in all instances by the term “about.” As used herein, the term “about” means that the characteristic, item, quantity, parameter, property, or term so qualifiedPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment encompasses a range of plus or minus ten percent above and below the value of the stated characteristic, item, quantity, parameter, property, or term. Similarly, as used herein, unless indicated to the contrary, the term “substantially” is a term of degree intended to indicate an approximation of the characteristic, item, quantity, parameter, property, or term so qualified, encompassing a range that can be understood and construed by those of ordinary skill in the art. Accordingly, unless indicated to the contrary, the numerical parameters set forth in the specification and attached claims are approximations that may vary. At the very least, and not as an attempt to limit the application of the doctrine of equivalents to the scope of the claims, each numerical indication should at least be construed in light of the number of reported significant digits and by applying ordinary rounding techniques.

[0125] Notwithstanding that the numerical ranges and values setting forth the broad scope of the inventive subject matter are approximations, the numerical ranges and values set forth in the specific examples are reported as precisely as possible. Any numerical range or value, however, inherently contains certain errors necessarily resulting from the standard deviation found in their respective testing measurements. Unless the context dictates the contrary, all ranges set forth herein should be interpreted as being inclusive of their endpoints and open-ended ranges should be interpreted to include only commercially practical values. Recitation of numerical ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate numerical value falling within the range. Unless otherwise indicated herein, each individual value of a numerical range is incorporated into the present specification as if it were individually recited herein. Similarly, all lists of values should be considered as inclusive of intermediate values unless the context indicates the contrary.

[0126] Use of the terms “may” or “can” in reference to an embodiment or aspect of an embodiment also carries with it the alternative meaning of “may not” or “cannot.” As such, if the present specification discloses that an embodiment or an aspect of an embodiment may be or can be included as part of the inventive subject matter, then the negative limitation or exclusionary proviso is also explicitly meant, meaning that an embodiment or an aspect of an embodiment may not be or cannot be included as part of the inventive subject matter. In a comparable manner, use of the term “optionally” in reference to an embodiment or aspect of an embodiment means that such embodiment or aspect of the embodiment may be included as part of the inventive subject matter or may not be included as part of the inventive subject matter. Whether such a negative limitation or exclusionary proviso applies will be based on whether the negative limitation or exclusionary proviso is recited in the claimed subject matter.PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment

[0127] The terms “a,” “an,” “the” and similar references used in the context of describing the present inventive subject matter (especially in the context of the following claims) are to be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. Further, ordinal indicators - such as, e.g., “first,” “second,” “third,” etc. - for identified elements are used to distinguish between the elements, and do not indicate or imply a required or limited number of such elements, and do not indicate a particular position or order of such elements unless otherwise specifically stated.

[0128] When used in the claims, whether as filed or added per amendment, the open-ended transitional term “comprising”, variations thereof such as, e.g., “comprise” and “comprises”, and equivalent open-ended transitional phrases thereof like “including”, “containing” and “having”, encompass all the expressly recited elements, limitations, steps, integers, and / or features alone or in combination with unrecited subject matter; the named elements, limitations, steps, integers, and / or features are essential, but other unnamed elements, limitations, steps, integers, and / or features may be added and still form a construct within the scope of the claim. Specific embodiments disclosed herein may be further limited in the claims using the closed-ended transitional phrases “consisting of’ or “consisting essentially of’ (or variations thereof such as, e.g., “consist of’, “consists of’, “consist essentially of’, and “consists essentially of’) in lieu of or as an amendment for “comprising.” When used in the claims, whether as filed or added per amendment, the closed-ended transitional phrase “consisting of’ excludes any element, limitation, step, integer, or feature not expressly recited in the claims. The closed-ended transitional phrase “consisting essentially of” limits the scope of a claim to the expressly recited elements, limitations, steps, integers, and / or features and any other elements, limitations, steps, integers, and / or features that do not materially affect the basic and novel characteristic(s) of the claimed subject matter. Thus, the meaning of the open-ended transitional phrase “comprising” is being defined as encompassing all the specifically recited elements, limitations, steps and / or features as well as any optional, additional unspecified ones. The meaning of the closed-ended transitional phrase “consisting of’ is being defined as only including those elements, limitations, steps, integers, and / or features specifically recited in the claim, whereas the meaning of the closed- ended transitional phrase “consisting essentially of’ is being defined as only including those elements, limitations, steps, integers, and / or features specifically recited in the claim and those elements, limitations, steps, integers, and / or features that do not materially affect the basic and novel characteristic(s) of the claimed subject matter. Therefore, the open-ended transitional phrase “comprising” (and equivalent open-ended transitional phrases thereof) includes within its meaning, as a limiting case, claimed subject matter specified by the closed-ended transitional phrases “consisting of’ or “consisting essentially of.” As such, the embodiments described hereinPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment or so claimed with the phrase “comprising” expressly and unambiguously provide description, enablement, and support for the phrases “consisting essentially of’ and “consisting of.”

[0129] It should be apparent to those skilled in the art that many more modifications besides those already described are possible without departing from the inventive concepts herein. The inventive subject matter, therefore, is not to be restricted except in the spirit of the appended claims. Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms “comprises” and “comprising” should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, components, or steps that are not expressly referenced. Where the specification and claims refer to at least one of something selected from the group consisting of A, B, C .... and N, the text should be interpreted as requiring only one of each element from the group, not A plus N, or B plus N, etc.

[0130] Any claims intended to be treated under 35 U.S.C. §112(f) will begin with the words “means for,” but use of the term “for” in any other context is not intended to invoke treatment under 35 U.S.C. §1 12(f). Accordingly, Applicant reserves the right to pursue additional claims after filing this application, in either this application or in a continuing application.

[0131] It should be understood that the methods and the order in which the respective elements of each method are performed are purely exemplary. Depending on the implementation, they may be performed in any order or in parallel, unless indicated otherwise in the present disclosure.

[0132] Finally, all patents, patent publications, and other references cited and identified in the present specification are individually and expressly incorporated herein by reference in their entirety to the same extent as if each individual publication or patent application were specifically and individually indicated to be incorporated by reference. These publications are provided solely for their disclosure prior to the filing date of the present application. The reference to any prior art in this specification is not, and should not be taken as, an acknowledgement or any form of suggestion that the prior art forms part of the common general knowledge from any country. In addition, where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies and the definition of that term in the reference does not apply. Lastly, nothing in this regard is or should be construed as an admission that the inventors are not entitled to antedate such disclosure by virtue of prior invention or for any other reason. All statements as to the date or representation as to the contents of these documents are based on the information available toPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment the applicant and do not constitute any admission as to the correctness of the dates or contents of these documents.

Claims

PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application EnvironmentCLAIMS1 . A method for matching job seekers with open employment positions, comprising: creating a profile for a job seeker in a software application-based computing environment comprised of at least one software application for matching job seekers with job openings for open employment positions, wherein the profile includes information about the job seeker; ingesting the job openings, by scraping third-party job-posting sites for the job openings for the open employment positions, and accepting additional job openings for the open employment positions that are provided directly by employers into the at least one software application, wherein the job openings and the additional job openings together comprise a plurality of job openings, and wherein the at least one software application extracts data that defines the open employment positions from the plurality of job openings; semantically matching the profile of the job seeker to the open employment positions, by comparing information in the profile with the data that defines the open employment positions extracted from the plurality of job openings, in an artificial intelligence engine configured to enable the at least one software application to learn job seeker preferences relative to the plurality of job openings overtime, from the both the information in the job seeker’s profile and from the job seeker’s physical interaction with the at least one software application using a plurality of navigation features, and create matches between the job seekers and the plurality of job openings; and providing the plurality of navigation features via a user interface for the physical interaction with the at least one software application, the plurality of navigation features allowing the job seekers to review, select, or reject matched job openings, and the navigation features including a left physical interaction with the user interface to reject a particular matched job opening and a right physical interaction with the user interface to select the particular matched job opening, wherein a job application package for the particular matched job opening is automatically prepared for the job seeker upon a selection of the particular matched job opening via a right physical interaction with the user interface, and wherein the matching and the automatic generation of the job application package in the at least one software application is controlled by the information about the job seeker and thePCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment job seeker’s physical interactions with the at least one software application using the plurality of navigation features.

2. The method of claim 1 , wherein the job application package is transmitted to the employer when the employer also selects the job seeker for the particular job opening, and wherein the job application package includes links to one or both of the job seeker’s calendar and a calendar of a recruiter designated by the employer.

3. The method of claim 2, wherein a video call is initiated at a time selected by one or both of the job seeker and employer, the video call for conducting an interview between the job seeker and the employer.

4. The method of claim 3, wherein the video call is hosted within the software application-based computing environment.

5. The method of any one of claims 1-4, wherein the plurality of job openings are obtained through one or more of web crawlers, application programming interfaces (APIs), or web forms.

6. The method of any one of claims 1-5, wherein the information about the job seeker and is obtained from one or more of an upload of an existing resume by the job seeker, a link to a third-party site where one or more of the job seeker’s skills, experience, education, and training are provided, a web form, or the job seeker’s interaction with a chatbot within the software application-based computing environment.

7. The method of any one of claims 1-6, wherein the artificial intelligence engine includes a bot that is configured to provide additional navigation features for the job seeker’s physical interactions with the at least one software application that enable communication between the job seeker and the at least one software application, wherein the bot enables the at least one software application to further learn the job seeker preferences relative to the job openings over tie, and identify additional semantic matches between the job seekers and the plurality of job openings from the additional navigation features.

8. The method of claim 7, further comprising integrating one or both of the job seeker’s physical interactions with the at least one software application and the chatbot with a language model, by developing prompts that generate one or both of cover letters and updated resumes for application packages in response to the job openings.PCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment9. The method of any one of claims 1-8, wherein the left physical interaction and the right physical interaction may be one or more of a swipe using one or more fingers on the user interface, a touch of the user interface, a movement of the device hosting the application, a gesture towards the device hosting the application, or a voice command.

10. A method for matching job seekers with open employment positions, comprising: obtaining input data, in a software application-based computing environment that includes at least one software application, that represents both a plurality of job seekers and a plurality of job openings for open employment positions, the input data that represents the plurality of job openings obtained by one or both of scraping third-party job-posting sites for the open employment positions, or enabling an employer to provide a job opening directly into the at least one software application; analyzing the input data within the at least one software application to match the plurality of job seekers with appropriate job openings among the plurality of job openings for the open employment positions, by: creating a profile for each job seeker in the plurality of job seekers, wherein the profile includes information about each job seeker; semantically matching the profile of each job seeker to the plurality of job openings, by comparing information in the profile of each job seeker with data extracted from each job opening, based on preferences of the plurality of job seekers learned over time, the preferences learned within an artificial intelligence engine that analyzes each job seeker’s physical interactions with the at least one software application using navigation features, and from the information in the job seeker’s profile, and create matches between the job seekers and the plurality of job seekers; providing the navigation features to allow the plurality of job seekers to review, select, or reject the plurality of job openings in the at least one software application, via a user interface for accessing and physically interacting with the at least one software application, the navigation features including a left physical interaction with the user interface to reject a particular matched job opening and a right physical interaction with the user interface to select the particular matched job opening; andPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment automatically creating a job application package for the particular job opening for a particular job seeker upon a selection of the particular job opening via a right physical interaction with the user interface, wherein the matching and the automatic generation of the job application package in the at least one software application is controlled by the information about the job seeker and the job seeker’s physical interactions with the at least one software application using the navigation features, and wherein the job application package informs the employer that has provided the particular job opening that the particular matched job opening has been selected by the job seeker from the right physical interaction the user interface.1 1 . The method of claim 10, wherein the job application package is transmitted to the employer when the employer also selects the job seeker for the particular job opening, and wherein the job application package includes links to one or both of the job seeker’s calendar and a calendar of a recruiter designated by the employer.

12. The method of claim 11 , wherein a video call is initiated at a time selected by one or both of the job seeker and employer, the video call for conducting an interview between the job seeker and the employer.

13. The method of claim 12, wherein the video call is hosted within the software application-based computing environment.

14. The method of any one of claims 10-13, wherein the plurality of job openings are obtained through one or more of web crawlers, application programming interfaces (APIs), or web forms.

15. The method of any one of claims 10-14, wherein the information about the job seeker and is obtained from one or more of an upload of an existing resume by the job seeker, a link to a third-party site where one or more of the job seeker’s skills, experience, education, and training are provided, a web form, or the job seeker’s interaction with a chatbot within the software application-based computing environment.

16. The method of any one of claims 10-15, wherein the artificial intelligence engine includes a bot that is configured to provide additional navigation features for the job seeker’s physicalPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment interactions with the at least one software application that enable communication between the job seeker and the at least one software application, wherein the bot enables the at least one software application to further learn the job seeker preferences relative to the job openings over tie, and identify additional semantic matches between the job seekers and the plurality of job openings from the additional navigation features.

17. The method of claim 16, further comprising integrating one or both of the job seeker’s physical interactions with the at least one software application and the chatbot with a language model, by developing prompts that generate one or both of cover letters and updated resumes for application packages in response to the job openings.

18. The method of any one of claims 10-17, wherein the left physical interaction and the right physical interaction may be one or more of a swipe using one or more fingers on the user interface, a touch of the user interface, a movement of the device hosting the application, a gesture towards the device hosting the application, or a voice command.

19. A system for matching job seekers with open employment positions, comprising: a data ingestion service configured to obtain input data, in a software application-based computing environment that includes at least one software application, that represents both a plurality of job seekers and a plurality of job openings for open employment positions, the input data that represents the plurality of job openings obtained by one or both of scraping third-party job-posting sites for the open employment positions, or enabling an employer to provide a job opening directly into the at least one software application; an artificial intelligence engine that analyzes the input data within the at least one software application to match the plurality of job seekers with appropriate job openings among the plurality of job openings for the open employment positions, the artificial intelligence engine configured to: create a profile for each job seeker in the plurality of job seekers, wherein the profile includes information about each job seeker; semantically match the profile of each job seeker to the plurality of job openings, by comparing information in the profile of each job seeker with data extracted from each job opening, based on preferences of the plurality of job seekers learned over time; andPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment a plurality of navigation features within the at least one software application that enable the artificial intelligence engine to learn the preferences of the plurality of job seekers over time, wherein the artificial intelligence engine analyzing each job seeker’s physical interactions with the at least one software application using the plurality of navigation features, and from the information in the job seeker’s profile, to create matches between the job seekers and the plurality of job seekers, wherein the plurality of navigation features to allow the plurality of job seekers to review, select, or reject the plurality of job openings in the at least one software application, via a user interface for accessing and physically interacting with the at least one software application, the plurality of navigation features including a left physical interaction with the user interface to reject a particular matched job opening and a right physical interaction with the user interface to select the particular matched job opening; and a job application package generator, configured to automatically create a job application package for the particular job opening for a particular job seeker upon a selection of the particular job opening via a right swipe of the user interface, wherein the matching and the automatic generation of the job application package in the at least one software application is controlled by the information about the job seeker and the job seeker’s physical interactions with the at least one software application using the plurality of navigation features, and wherein the job application package informs the employer that has provided the particular job opening that the particular matched job opening has been selected by the job seeker from the right physical interaction with the user interface.

20. The system of claim 19, wherein the job application package is transmitted to the employer when the employer also selects the job seeker for the particular job opening, and wherein the job application package includes links to one or both of the job seeker’s calendar and a calendar of a recruiter designated by the employer.21 . The system of claim 20, wherein a video call is initiated at a time selected by one or both of the job seeker and employer, the video call for conducting an interview between the job seeker and the employer.

22. The system of claim 21 , wherein the video call is hosted within the software application-basedPCT Patent Application UETWK1-0008WCZaylia, Framework for Artificial Intelligence-Based Matching of Job Seekers with Open Employment Positions in an Application Environment computing environment.

23. The system of any one of claims 19-22, wherein the plurality of job openings are obtained through one or more of web crawlers, application programming interfaces (APIs), or web forms.

24. The system of any one of claims 19-23, wherein the information about the job seeker and is obtained from one or more of an upload of an existing resume by the job seeker, a link to a third-party site where one or more of the job seeker’s skills, experience, education, and training are provided, a web form, or the job seeker’s interaction with a chatbot within the software application-based computing environment.

25. The system of any one of claims 19-24, wherein the artificial intelligence engine includes a bot that is configured to provide additional navigation features for the job seeker’s physical interactions with the at least one software application that enable communication between the job seeker and the at least one software application, wherein the bot enables the at least one software application to further learn the job seeker preferences relative to the job openings over tie, and identify additional semantic matches between the job seekers and the plurality of job openings from the additional navigation features.

26. The system of claim 25, further comprising integrating one or both of the job seeker’s physical interactions with the at least one software application and the chatbot with a language model, by developing prompts that generate one or both of cover letters and updated resumes for application packages in response to the job openings.

27. The system of any one of claims 19-26, wherein the left physical interaction and the right physical interaction may be one or more of a swipe using one or more fingers on the user interface, a touch of the user interface, a movement of the device hosting the application, a gesture towards the device hosting the application, or a voice command.

Images