Server and method for providing recruitment collaboration services based on a job skills standardization platform

Abstract

This invention provides a server and method for providing recruitment integration services for a job skills standardization platform. [Solution] In the recruitment collaboration service provision system 10 of the job skills standardization platform, the server standardizes job seeker information, including the user's career information and job-related information received from the user terminal, to generate first standardized data including the user's first job-related skills; standardizes job posting information, including recruitment announcements and job descriptions received from the company server, to generate second standardized data; matches the first standardized data and the second standardized data; provides the user terminal with at least one job posting that matches the job seeker information based on the matching result; and provides the company server with at least one job posting that matches the job posting information.

Description

Technical Field

[0001] The present disclosure relates to an employment cooperation service providing server, and more particularly, to a server that standardizes job skills and uses them to provide employment cooperation services.

Background Art

[0002] There is a gap between the resume and job-related skills introduced by job seekers and the job-related skills required by companies seeking employees.

[0003] Due to such a gap, job seekers may not be able to accurately convey their abilities, and companies may fail to secure the necessary human resources.

[0004] In addition, there is a problem that there may be a gap in job skills provided by institutions that provide education to job seekers.

[0005] In addition to this, there is a gap between the skill terms used in educational institutions for job seekers and the skill terms used in companies, and there are many problems in communication.

[0006] Therefore, there is a need for a technology that standardizes the resume and job skills of job seekers and the job-related skills required by companies to improve the employment possibility of job seekers, enables companies to secure human resources suitable for the job, and enables educational institutions to educate the accurate skills necessary for employment, but such technology has not been publicly disclosed at present.

Prior Art Documents

Patent Documents

[0007] Korean Patent Publication No. 10-2019-0118140 (Publication Date: October 16, 2019)

Summary of the Invention

Problems to be Solved by the Invention

[0008] This disclosure is made in view of the above circumstances, and its purpose is to provide a recruitment collaboration service for a job skills standardization platform.

[0009] Furthermore, the purpose of this disclosure is to provide a service that standardizes the skill terminology used in educational institutions for job seekers and the skill terminology used in companies.

[0010] Furthermore, another purpose of this disclosure is to provide a service that matches standardized data of job seekers' job search information with standardized data of companies' job postings.

[0011] Furthermore, another purpose of this disclosure is to standardize terminology used in the job-seeking and education sectors and provide it to educational institutions and companies to offer standardized recruitment collaboration services.

[0012] The issues that this disclosure aims to address are not limited to those mentioned above, and other issues not mentioned can be clearly understood by an average engineer from the following description. [Means for solving the problem]

[0013] A recruitment collaboration service provider server for a job skills standardization platform according to one embodiment of the present disclosure for solving the above-mentioned problems includes a communication module that communicates with a user terminal and a company server, and a processor that performs a job skills standardization process. The processor standardizes job seeker information, including the user's career information and job-related information, received from the user terminal, to generate first standardized data including the user's first job-related skills; standardizes job posting information, including recruitment announcements and job descriptions, received from the company server, to generate second standardized data; matches the first standardized data and the second standardized data; provides the user terminal with at least one job posting that matches the job seeker information based on the matching result; and provides the company server with at least one job seeker that matches the job posting.

[0014] Furthermore, the memory stores a skill library containing multiple job-related skills arranged in a tree structure including at least one lower level, and the processor updates the skill library at pre-set intervals by modifying the second job-related skills required for each job based on new job postings from companies, standardizes the terminology used in job-seeking fields and related educational fields based on the skill library, and can provide the standardized terminology to servers of educational institutions that provide job-seeking related educational services to job seekers and to the company server.

[0015] Furthermore, the processor can check the first item in the job application information that corresponds to the skill library as a first job-related skill possessed by the user, and calculate the first skill level for the checked first job-related skill based on the job application information.

[0016] Furthermore, the processor checks the second item in the job posting information that corresponds to the skill library as a second job-related skill required for the personnel the company is recruiting, calculates a second skill level for the checked second job-related skill based on the job posting information, and can match job postings in which the first skill level corresponds to the second skill level for the same job-related skill with those that correspond to the job seeker information.

[0017] Furthermore, the processor can receive at least one educational curriculum for the education of job seekers from the educational institution's server via the communication module, and generate feedback on the educational curriculum based on a comparison between the third job-related skills set as educational objectives in the curriculum for each job and the second job-related skills required for each job.

[0018] Furthermore, the processor generates relationship information for each of the multiple job-related skills in relation to other job-related skills, and, based on the relationship information, extracts a fourth job-related skill that the user lacks or is deficient in, based on the comparison results between the job-related skills related to the user's desired field of work or specific job at the company the user is applying to and the user's first job-related skills, and can provide the user terminal with information regarding the educational curriculum related to the fourth job-related skill.

[0019] Furthermore, the processor can extract fifth job-related skills for each job, and if there is at least one job among the jobs that is satisfied by the first job-related skills and the first skill level possessed by the user based on the fifth job-related skills for each job, it can set the at least one job as an immediately available job and provide the user terminal with information about the immediately available job.

[0020] Furthermore, the processor generates relational information for each of the multiple job-related skills with other job-related skills, derives multiple sixth job-related skills that are related to multiple first job-related skills possessed by the user, selects at least one sixth job-related skill from the multiple sixth job-related skills based on at least one of the user's job-seeking urgency and job relevance, the job relevance being the range of jobs for which the user seeks recommendations in relation to the first job-related skills, and can provide the user terminal with information regarding the educational curriculum for the selected at least one sixth job-related skill.

[0021] Furthermore, when the job seeking urgency is greater than or equal to a first job seeking urgency that has already been set, the processor selects at least one sixth job-related skill from among the plurality of sixth job-related skills in ascending order of the shortest time required for taking the educational curriculum, calculates, as a numerical value, the degree of relevance to the first job-related skill for each of the plurality of sixth job-related skills, determines a range of jobs that can be recommended to the user based on the degree of job relevance, and can select the at least one sixth job-related skill based on the degree of job relevance, the determined range, and the degree of relevance calculated for each of the plurality of sixth job-related skills.

[0022] Also, a method for providing an employment cooperation service for adopting an occupational skill standardization infrastructure according to an embodiment of the present disclosure for solving the above-described problems is a method performed by a server, and includes: standardizing job seeking information including the user's history information and job-related information received from a user terminal to generate first standardized data including the user's first job-related skill; standardizing job offering information including an employment announcement and a job description received from an enterprise server to generate second standardized data; matching the first standardized data and the second standardized data; providing at least one job offering information matched to the job seeking information to the user terminal based on the matching result; and providing at least one job seeking information matched to the job offering information to the enterprise server based on the matching result.

[0023] In addition, a computer program stored in a computer-readable recording medium for performing a method for embodying the present disclosure can be further provided.

[0024] In addition, a computer-readable recording medium for recording a computer program for executing a method for embodying the present disclosure can be further provided.

Effects of the Invention

[0025] According to the solution to the above-mentioned problems of the present disclosure, it has the effect of providing an employment cooperation service based on job skill standardization.

[0026] Moreover, according to the solution to the above-mentioned problems of the present disclosure, it has the effect of providing a service in which the skill terms used in educational institutions for job seekers and the skill terms used in enterprises are unified.

[0027] Furthermore, according to the solution to the above-mentioned problems of the present disclosure, it has the effect of providing a service that matches the standardized data of job seekers' job hunting information and the standardized data of enterprises' job offers.

[0028] Moreover, according to the solution to the above-mentioned problems of the present disclosure, it has the effect of standardizing the terms used in the job hunting field and the educational field, providing this to educational institutions and enterprises, and providing a standardized employment cooperation service.

[0029] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by ordinary technicians from the following description.

Brief Description of the Drawings

[0030] [Figure 1] It is a schematic diagram of an employment cooperation service providing system according to an embodiment of the present disclosure. [Figure 2] It is a block diagram of an employment cooperation service providing server according to an embodiment of the present disclosure. [Figure 3] It is a diagram showing the process of an employment cooperation service providing system according to an embodiment of the present disclosure. [Figure 4] It is a flowchart of a method for providing an employment cooperation service according to an embodiment of the present disclosure. [Figure 5] It is a diagram showing a skill library configured in a tree structure. [Figure 6] It is a diagram showing a skill library configured in a tree structure. [Figure 7] It is a diagram showing the construction of a library by processing internal data and external data. [Figure 8] This diagram illustrates how to build a library by processing internal and external data. [Figure 9] This diagram shows how to extract skill-related keywords from unstructured data and then match them with a library. [Figure 10] This diagram illustrates the process of extracting keywords from text-formatted input data. [Figure 11] This is a diagram showing the keyword extraction algorithm. [Figure 12] This is a diagram showing the keyword extraction algorithm. [Figure 13] This is an example diagram of an algorithm that calculates the editing cost between two words. [Figure 14] This is an illustrative diagram of an algorithm that calculates a score by considering the editing cost between two words, the length of the words, and any common characters. [Figure 15] This diagram shows the extraction process and the conversion process for standard skill names. [Figure 16] This figure shows the calculation of the Jackard similarity score. [Figure 17] This figure shows the calculation of the Jackard similarity score. [Modes for carrying out the invention]

[0031] Throughout this disclosure, the same reference numerals indicate the same component. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure belongs or content that is redundant in the embodiments is omitted. The terms “parts, modules, components, blocks” as used in this specification may be embodied in software or hardware, and in the embodiments, multiple “parts, modules, components, blocks” may be embodied as a single component, or a single “part, module, component, block” may include multiple components.

[0032] When a part of the specification is described as being "connected" to another part, this includes not only direct connections but also indirect connections, and indirect connections include connections via wireless communication networks.

[0033] Furthermore, when a part is described as "containing" a certain component, unless otherwise specified, this means that it can include other components rather than excluding them.

[0034] Throughout the specification, when a member is described as being "on top of" another member, this includes not only cases where the member is in contact with another member, but also cases where another member exists between the two members.

[0035] Terms such as "first," "second," etc., are used to distinguish one component from another, and do not limit the components to those defined by the aforementioned terms.

[0036] Unless otherwise clearly stated in the context, singular expressions include plural forms.

[0037] Identification codes are used for explanatory purposes at each stage, and do not indicate the order of the stages. Unless the context explicitly states a specific order, the stages may be performed in a different order than that specified.

[0038] The operating principle and embodiments of this disclosure will be described below with reference to the attached drawings.

[0039] In this specification, "Recruitment Collaboration Service Provider Device Related to This Disclosure" includes all kinds of devices that can perform computational processing and provide results to users. For example, the Recruitment Collaboration Service Provider Device Related to This Disclosure may include, or take the form of, a computer, a server device, and a portable terminal.

[0040] Here, the computer may include, for example, a laptop, desktop, or tablet PC equipped with a web browser.

[0041] The server device is a server that communicates with external devices to process information, and may include application servers, computing servers, database servers, file servers, game servers, mail servers, proxy servers, and web servers.

[0042] The aforementioned portable terminal is, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as PCS, GSM, PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access, WCDMA®), WiBro (Wireless Broadband Internet) terminals, and smartphones, as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0043] The artificial intelligence-related functions relating to this disclosure operate using a processor and memory 130. The processor can be configured as one or more processors. In this case, one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. One or more processors are controlled to process input data according to predefined operating rules or artificial intelligence models stored in memory 130. Alternatively, if one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with hardware structures specialized for processing a particular artificial intelligence model.

[0044] The predefined behavioral rules or artificial intelligence models are characterized by being generated through learning. Here, "generated through learning" means that a basic artificial intelligence model is trained using a large amount of training data by a learning algorithm, thereby generating predefined behavioral rules or artificial intelligence models configured to perform desired characteristics (or objectives). Such learning may be performed on the device on which the artificial intelligence relating to this disclosure is performed, or it may be performed via a separate server and / or system. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0045] An artificial intelligence model can consist of multiple neural network layers. Each of these neural network layers has multiple weights, and neural network operations are performed through calculations between the results of calculations in previous layers and these multiple weights. The multiple weights held by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights can be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks can include deep neural networks (DNNs), such as CNNs (Convolutional Neural Networks), DNNs (Deep Neural Networks), RNNs (Recurrent Neural Networks), RBMs (Restricted Boltzmann Machines), DBNs (Deep Belief Networks), BRDNNs (Bidirectional Recurrent Deep Neural Networks), or deep Q-networks, but are not limited to the examples mentioned above.

[0046] According to exemplary embodiments of this disclosure, a processor can embody artificial intelligence. Artificial intelligence refers to machine learning methods based on artificial neural networks that enable machines to learn by mimicking human nerve cells (biological neurons). Methodologies for artificial intelligence can be classified into supervised learning, where input and output data are provided as training data depending on the learning method, thus determining the answer (output data) to the problem (input data); unsupervised learning, where only input data is provided without output data, and the answer (output data) to the problem (input data) is not determined; and reinforcement learning, where compensation is given from the external environment each time an action is taken in the current state, and learning progresses in a direction that maximizes such compensation. Furthermore, methodologies for artificial intelligence can also be classified by architecture, which is the structure of the learning model. The architectures of widely used deep learning technologies can be classified into convolutional neural networks, recurrent neural networks, transformers, generative adversarial networks, etc.

[0047] This device may include an artificial intelligence (AI) model. The AI ​​model may be a single AI model or can be embodied in multiple AI models. The AI ​​model may consist of a neural network (or artificial neural network) and may include statistical learning algorithms that mimic biological nerves in machine learning and cognitive science. A neural network can refer to any model in general that possesses problem-solving capabilities by having artificial neurons (nodes) formed by synaptic connections change the strength of these synaptic connections through learning. The neurons in a neural network may include combinations of weights or biases. A neural network may include one or more layers, each consisting of one or more neurons or nodes. Exemplarily, the device may include an input layer, a hidden layer, and an output layer. The neural network constituting the device can infer results from arbitrary inputs by changing the weights of its neurons through learning.

[0048] A processor can generate a neural network, train (or learn) a neural network, perform calculations based on received input data and generate informational signals based on the results, or retrain the neural network. Neural network models can include, but are not limited to, a wide variety of models such as CNNs (like GoogleNet, AlexNet, and VGG Network), R-CNNs, RPNs, RNNs, S-DNNs, S-SDNNs, Deconvolutional Networks, DBNs, RBMs, Fully Convolutional Networks, LSTM Networks, and Classification Networks. A processor can include one or more processors for performing calculations by the neural network model. For example, a neural network can include a deep neural network.

[0049] Neural networks include CNN, RNN, perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Dep Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning Machine), ESN (Echo State Network), and DRN (Deep It is understandable to any engineer that a neural network can include, but is not limited to, any neural network, including, but is not limited to, Residual Networks, Differential Neural Computers (DNCs), Neural Turning Machines (NTMs), Capsule Networks (CNs), Kohonen Networks (KNs), and Attention Networks (ANs).

[0050] According to exemplary embodiments of this disclosure, the processor may include CNNs (Convolutional Neural Networks), R-CNNs (Region with Convolutional Neural Networks), RPNs (Region Proposal Networks), RNNs (Recurrent Neural Networks), S-DNNs (Stacking-based Deep Neural Networks), S-SDNNs (State-Space Dynamic Neural Networks), Deconvolution Networks, DBNs (Deep Belief Networks), RBMs (Restricted Boltzman Machines), Fully Convolutional Networks, LSTMs (Long Short-Term Memory) Networks, Classification Networks, Generative Modeling, eExplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT and SP-BERT for natural language processing, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics, Visual Understanding, Video Synthesis for vision processing, ResNet data intelligence, Anomaly Detection, Prediction, and Time-Series. A variety of artificial intelligence structures and algorithms can be used, but are not limited to, Forecasting, Optimization, Recommendation, and Data Creation. Examples of the present disclosure will be described in detail below with reference to the attached drawings.

[0051] Figure 1 is a schematic diagram of the employment collaboration service provision system according to an embodiment of the present disclosure.

[0052] Referring to Figure 1, the employment collaboration service provision system according to the embodiment of this disclosure includes a server 100, a user terminal, a corporate server 300, and an educational institution server 400.

[0053] Users could include students, job seekers, job-seeking individuals, and company employees.

[0054] Educational institutions may include those that provide educational services related to employment.

[0055] Server 100 can receive user information from user terminals, and this user information includes job-seeking information for job searching.

[0056] Server 100 can receive information from the educational institution server 400, including educational curricula provided by educational institutions, educational objectives for each curriculum, and related job skills.

[0057] Server 100 receives job postings from corporate server 300. These job postings may include corporate recruitment announcements.

[0058] Server 100 standardizes job seeker information received from user terminals, job posting information received from company server 300, and educational curriculum-related information received from educational institution server 400, and performs matching based on these standards.

[0059] Furthermore, the system introduces users to companies and educational curricula that are suitable for their job search, introduces companies to job seekers that are suitable for their job postings, and connects educational institutions with job seekers who need training, as well as proposing educational curricula that align with the latest recruitment information.

[0060] Server 100 can also provide services through service applications. Server 100 can provide services via the web or applications.

[0061] Figure 1 provides an overview of the collaborative service provision system according to an embodiment of this disclosure, and a more detailed explanation will be given below with reference to each drawing.

[0062] Figure 2 is a block diagram of the adoption collaboration service provider server 100 according to an embodiment of the present disclosure.

[0063] Referring to Figure 2, the collaborative service provider server 100 according to the embodiment of this disclosure includes a processor 110, a communication module 120, and memory 130.

[0064] However, in some embodiments, the server 100 may include fewer or more components than those shown in Figure 2.

[0065] The processor 110 can be implemented as a memory 130 that stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of the components within the device, and at least one processor 110 that performs the aforementioned operation using the data stored in the memory 130. In this case, the memory 130 and the processor 110 can be implemented on separate chips. Alternatively, the memory 130 and the processor 110 can be implemented on a single chip.

[0066] Furthermore, the processor 110 can control any one or more of the aforementioned components in combination to implement various embodiments of the present disclosure as described in the following drawings on the device.

[0067] In addition to operations related to the application program, the processor 110 can typically control the overall operation of the device. The processor 110 can provide or process appropriate information or functions to the user by processing signals, data, information, etc. that are input or output by the aforementioned components, or by driving application programs stored in the memory 130.

[0068] Furthermore, the processor 110 can control at least some of the components of the device in order to drive the application program stored in the memory 130. In addition, the processor 110 can operate at least two or more of the components included in the device in combination with each other in order to drive the application program.

[0069] The processor 110 can be embodied in one or more units. In the following, even if the processor 110 is expressed singly, it can be considered as multiple units. The processor 110 can control the configuration of the collaborative service provider device. The processor 110 may mean a data processing device built into hardware that has a physically structured circuit for performing functions expressed by code or instructions contained in a program. Thus, the processor 110 is an example of a data processing device built into hardware and can encompass processing devices such as microprocessors, central processing units (CPUs), processor cores, multiprocessors, ASICs (application-specific integrated circuits), and FPGAs (field programmable gate arrays), but the scope of the present invention is not limited thereto. The processor 110 may separately include a learning processor 110 for performing artificial intelligence calculations, or it may include a learning processor 110 itself.

[0070] In various embodiments, the processor 110 may include one or more of a Central Processing Unit (CPU), an Application Processor (AP), or a Communication Processor (CP). At least a portion of the processor 110 is hardware that can access the memory 130 and perform functions relating to the instruction words stored in the memory 130.

[0071] The communication module 120 may include one or more modules that connect the adoption collaboration service provider device to one or more networks.

[0072] The communication module 120 may include one or more components that enable communication with external devices, for example, at least one of a broadcast receiving module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0073] Wired communication modules can include a variety of wired communication modules such as Local Area Network (LAN) modules, Wide Area Network (WAN) modules, or Value Added Network (VAN) modules, as well as a variety of cable communication modules such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), DVI (Digital Visual Interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).

[0074] Wireless communication modules can include not only Wi-Fi modules and Wireless broadband modules, but also modules that support a variety of wireless communication methods such as GSM (Global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G.

[0075] The wireless communication module may include a wireless communication interface that includes an antenna and a transmitter for transmitting communication signals. The wireless communication module may further include a signal conversion module that, under the control of the processor 110, modulates the digital control signals output from the processor 110 via the wireless communication interface into analog wireless signals.

[0076] The short-range communication module is for short-range communication and uses Bluetooth® (registered trademark). TM It can support short-range communication using at least one of the following technologies: RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee (registered trademark), NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus).

[0077] The communication module 120 may also use the name of the communication interface.

[0078] A communication interface can configure communication between an electronic device and an external device. For example, the communication interface can communicate with the external device via wireless communication (e.g., Wi-Fi (Wireless Fidelity), Bluetooth (registered trademark), NFC (Near Field Communication), MST (magnetic stripe transmission), etc.) or wired communication.

[0079] Memory 130 can store data that supports the various functions of this device. Memory 130 can store numerous application programs (applications) driven by this device, data for the operation of this device, and instruction words. At least some of these application programs may exist for the basic functions of this device. On the other hand, application programs can be stored in memory 130, installed in the device, and driven by the processor 110 to perform their operations (or functions).

[0080] Memory 130 can store data that supports the various functions of this device, programs for the operation of the processor 110, input / output data (e.g., music files, still images, videos, etc.), and numerous application programs (applications) driven by this device, data for the operation of this device, and instruction words. At least some of these application programs can be downloaded from an external server 100 via wireless communication.

[0081] Such memory 130 may include at least one type of storage medium from among flash memory type, hard disk type, SSD type (Solid State Disk type), SDD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Furthermore, memory 130 can also function as a database, separate from the device but connected via wired or wireless means.

[0082] The memory 130 can be electrically connected to the processor 110 and can store at least one code executed by the processor 110. The memory 130 can refer to various forms of storage devices. The memory 130 can store information necessary for performing calculations using artificial intelligence, machine learning, and artificial neural networks.

[0083] Memory 130 can store a variety of learning models. Learning models stored in memory 130 can infer result values ​​for new input data that is not training data, and the inferred values ​​can be used as the basis for decisions to take some action. Learning models stored in memory 130 can be trained based on label information, and various backpropagation algorithms can be applied to improve the accuracy of training so that the loss function has a target value.

[0084] Furthermore, the memory 130 can include multiple processes for the adoption collaboration service provision device.

[0085] Figure 3 shows the process of the employment collaboration service provision system 30 according to an embodiment of the present disclosure.

[0086] The processor 110 requests the user terminal to generate a user profile. (S310)

[0087] At this time, users can input their personal information, educational background, and skills-related information via their device in order to generate their profile.

[0088] The user information entered for such a user profile may include personal information, educational background, work history, and job-related information, as well as job-seeking information.

[0089] The processor 110 performs skill standardization based on user information received from the user terminal. (S320)

[0090] The processor 110 can analyze user information using a skill extraction algorithm and update the user information by matching it with standard skill names in the skill library based on the analysis results.

[0091] Next, the processor 110 stores and manages the user's skills in memory 130. (S330)

[0092] The processor 110 can recommend personalized learning based on the user's skills stored in memory 130. (S340)

[0093] The processor 110 can recommend customized recruitment information based on the user's skills stored in memory 130. (S350)

[0094] Through this process, recruitment and matching take place between job seekers and companies seeking to hire. (S360)

[0095] Through System 30, users can evaluate their own skill level and identify areas that need improvement.

[0096] The processor 110 can match the user's skills with the user's job interests and provide a customized learning roadmap as needed. In this case, the learning roadmap can include things like the educational curriculum required in the field the user wishes to work in, and the educational curriculum required for career advancement and self-improvement.

[0097] Furthermore, the processor 110 can automatically recommend job postings to the user's terminal if there are any that match the user's skills, or if new job postings are updated.

[0098] The processor 110 extracts the skills required for each job as standardized data based on the company's job postings, and then matches the job seekers needed for each job based on this data.

[0099] In one embodiment, server 100 can receive information from corporate server 300 regarding corporate recruitment announcements, job descriptions, and skills required for each job.

[0100] For example, when a user applies for a specific job or company, the processor 110 can provide a matching result between the skills required for the applied field and the skills the user possesses. In this case, the skills being matched refer to skills that have been standardized through the processor 110.

[0101] Furthermore, companies can evaluate whether or not to hire users (job seekers) based on their standardized skill information, propose employment to users, and provide feedback.

[0102] The processor 110 can receive educational programs, curricula, and other information provided by educational institutions from the educational institution server 400, and can also receive information such as educational objectives and related job skills for each educational program and curriculum.

[0103] Furthermore, the processor 110 can propose curriculum adjustments to educational institutions based on market demand and provide diverse information such as the skill distribution of students and graduates, and student learning data.

[0104] Educational institutions can provide users with customized educational programs and curricula, as well as support for career development after completing the relevant education, information on additional education, and job placement services.

[0105] Companies can provide educational institutions with information on the skills and job requirements needed in the workplace.

[0106] This allows educational institutions to develop and update their programs and curricula to align with corporate requirements and recommend graduates to companies. Companies can then evaluate the effectiveness of these programs and curricula and provide feedback to ensure they are successfully developing the talent they need.

[0107] In the system 30 according to the embodiment of this disclosure, by using standardized skills and skill names, unlike conventional methods, it not only facilitates communication between job seekers, educational institutions, and companies, but also maximizes the mutually complementary capabilities of each party.

[0108] 1. Needs Identification System 30 can grasp the skill demand in the labor market in real time by accessing company recruitment announcements, job-related information, etc., whenever pre-set conditions are met. In this case, the pre-set conditions can be a pre-set time, a condition in which company recruitment announcements are updated, and a variety of other conditions can be applied.

[0109] 2. Value Alignment System 30 can accurately match the educational curriculum required by the user (job seeker) with the skills required by the market (companies).

[0110] 3. Learning Impact System 30 enables individuals to systematically develop skills by providing a clear learning path.

[0111] 4. Outcome Verification System 30 aims to demonstrate a clear ROI through collaboration between educational institutions and companies, thereby achieving substantial skill improvement.

[0112] The main advantages that System 30 offers by using the same terminology in relation to skills in the education and labor markets are numerous. System 30 maximizes efficiency and effectiveness in skills management and development, providing concrete and clear benefits to educational institutions, businesses, and individuals.

[0113] Firstly, system 30 provides improved interaction and communication.

[0114] System 30 facilitates communication between the education and labor markets by ensuring that they use the same terminology in relation to skills. This allows educational institutions to develop curricula that better meet industry demands, and enables companies to more clearly communicate their requirements for the personnel they need. As a result, users (job seekers) can acquire the skills required in the market and enter the job market more effectively.

[0115] Secondly, System 30 reduces skill disparities and performs accurate skill matching.

[0116] Bridging the gap between education and actual job requirements is one of System 30's key goals. By using the same terminology, educational programs can be designed to more accurately match market demands, ensuring that users (job seekers) possess the skills actually needed when entering the job market. As a result, this improves individuals' employability and allows companies to more easily and accurately secure suitable talent.

[0117] Thirdly, System 30 will ensure the efficient use of educational resources.

[0118] System 30 enables educational institutions to utilize resources more efficiently. By using the same skills terminology, overlapping content in educational programs is reduced, allowing them to focus on more essential areas. As a result, the quality of education improves, and learners experience a more valuable education, as they acquire the skills needed for the job market with redundant instruction eliminated.

[0119] Fourth, System 30 enhances the practicality of the curriculum.

[0120] System 30 can accurately reflect the current and future skill demands of the market. Based on this information, educational institutions can adjust their curricula to meet market needs. As a result, it significantly contributes to improving the practicality of educational programs and increasing the job placement success rate of users (job seekers).

[0121] Fifth, System 30 supports comprehensive career development.

[0122] System 30 provides comprehensive support for individual career development. Using consistent skill terminology allows individuals to more clearly define their learning paths and career goals. This enables individuals to systematically plan their career paths and strategically develop the necessary skills.

[0123] Sixth, System 30 addresses the skills gap among employees.

[0124] System 30 uses analytical tools to assess employees' current skill levels and identify necessary skills training. This allows System 30 to effectively address employee skill gaps and improve overall work performance.

[0125] System 30, through these advantages, increases the efficiency of the education and labor markets and makes a substantial contribution to individual growth and career development. System 30 can strengthen the coordination between the two markets and more effectively support skills-based education and job hunting.

[0126] Figure 4 is a flowchart of the method for providing the employment collaboration service according to the embodiment of this disclosure.

[0127] Referring to Figure 4, the adopted collaborative service provision system, apparatus, server 100, and method according to the embodiment of this disclosure will be described.

[0128] The processor 110 standardizes the job application information and generates the first standardized data. (S410)

[0129] The processor 110 standardizes the user information received from the user terminal to generate first standardized data, which includes the user's first job-related skills.

[0130] In this case, user information includes at least one of the following: user's personal information, educational background, work history, or job-related information.

[0131] Processor 110 standardizes the job information and generates second-order standardized data. (S420)

[0132] The processor 110 standardizes the job information, including the recruitment announcement and job description received from the corporate server 300, to generate second-order standardized data.

[0133] The processor 110 can standardize job information received from the corporate server 300, including job postings, job-related skills, and job descriptions (job introductions), and generate second-order standardized data, including second-order job-related skills required for each job posting.

[0134] Figures 5 and 6 show a skill library structured in a tree format.

[0135] Referring to Figures 5 and 6, the server 100 includes a skills library 500 containing multiple job-related skills arranged in a tree structure including at least one sub-level, and such a library 500 may be stored in memory 130.

[0136] Referring to Figure 5, the highest-level major category is information and communications 510, and its sub-levels include broadcasting technology 520, communication technology 530, and information technology 540. Sub-levels of information technology 540 include information technology management 550, digital twin 560, information technology operation 570, and information technology strategy and planning 580.

[0137] Referring to Figure 6, Table 600 is shown for major, medium, minor, and detailed classifications. Major classifications are based on major industrial sectors, medium classifications are based on sub-industries that make up major industrial sectors, minor classifications are based on occupational groups, which are sets of similar occupations, and minor classifications can be used to classify the size of an occupation by the set of job skills in which the given tasks and duties have a high degree of similarity.

[0138] The processor 110 matches the first standardized data and the second standardized data. (S430)

[0139] The processor 110 provides job information that matches the job seeker information based on the matching result in S430. (S440)

[0140] The processor 110 can provide the user terminal with at least one job posting (e.g., a recruitment notice) that matches the job seeker information based on the matching results.

[0141] The processor 110 provides job seeker information that matches the job postings based on the matching results in S430. (S450)

[0142] The processor 110 can provide the company server 300 with at least one job seeker information (job seeker information) that matches the job posting based on the matching results.

[0143] As one embodiment, the processor 110 can update the skill library by modifying the second job-related skills required for each job based on new recruitment announcements from companies, revised recruitment announcements, and job-related skill information required for each job, at pre-set intervals.

[0144] The processor 110 can standardize terminology used in job-seeking fields and related educational fields based on a skills library, and provide the standardized terminology to the servers 100 of educational institutions and the enterprise servers 300 that provide recruitment-related educational services to job seekers.

[0145] The processor 110 can check the first item in the job application information that corresponds to the skills library as the first job-related skill possessed by the user.

[0146] The processor 110 can then calculate the first skill level for the first job-related skills that have been checked based on the job application information.

[0147] For example, the processor 110 can calculate the first skill level for the first job-related skill by considering the job seeker information, including the user's introduction related to the first job-related skill, the user's educational status, completion certificates, qualifications, work history, and at least one of the following from the work history: information about the company the user worked for, information about the job the user performed, and years of work experience.

[0148] Processor 110 can check the second item in the job posting that corresponds to the skills library as the second job-related skill required for the person the company is hiring.

[0149] The processor 110 can then calculate a second skill level for the checked second job-related skills based on the job information.

[0150] For example, processor 110 can calculate the second skill level for a second job-related skill by considering information such as the required proficiency level, years of experience, whether or not training has been completed, and qualification certificates from the job information.

[0151] In one embodiment, the processor 110 receives information about at least one educational curriculum for the education of job seekers from the educational institution's server 100 via the communication module 120.

[0152] The processor 110 can then generate feedback for the educational curriculum based on a comparison between the third job-related skills, which are set as educational objectives in the curriculum for each job, and the second job-related skills, which are required for each job.

[0153] In one embodiment, the processor 110 can generate relationship information between each of several job-related skills and other job-related skills.

[0154] Then, the processor 110 can extract fourth job-related skills that the user lacks or is missing, based on a comparison of job-related skills related to the user's desired field of study or specific job at the company they are applying to, using relevant information as a reference.

[0155] The processor 110 can provide the user terminal with information regarding the educational curriculum related to the fourth job-related skills.

[0156] Specifically, the processor 110 can extract recommended sections, chapters, or playback times from the educational curriculum, taking relevant information into consideration. By providing this extracted information to the user terminal, the system can skip sections that the user already knows or has completed, allowing them to learn only the parts they need.

[0157] Processor 110 can extract fifth-job-related skills from each job posting included in the current recruitment advertisement.

[0158] The processor 110 can compare each job with the first job-related skills possessed by the user based on the fifth job-related skills. Specifically, the processor 110 can check if there is at least one job among the fifth job-related skills of each job that is satisfied by the first job-related skills possessed by the user, and if there is such a job, it can also check if the skill level is also satisfied.

[0159] Then, if the processor 110 finds that at least one job exists that is met by the user's first job-related skills and first skill level, it can set that job as an immediately available job and provide the user terminal with information about the immediately available job.

[0160] Through this functionality, server 100 can provide information about job postings that the user was unaware of but that match the job-related skills the user possesses.

[0161] In one embodiment, the processor 110 can generate relationship information between each of several job-related skills and other job-related skills.

[0162] The processor 110 can derive multiple sixth job-related skills that are related to the first job-related skills possessed by the user.

[0163] The processor 110 can then select at least one of the user's job-seeking urgency and job relevance from among a plurality of sixth job-related skills, and provide the user terminal with information regarding the educational curriculum for the selected at least one sixth job-related skill.

[0164] In this context, job relevance refers to the range of jobs for which the user seeks recommendations in relation to their primary job-related skills.

[0165] For example, if a user only desires employment in job fields related to their primary job-related skills, the degree of job relevance is close to 0, meaning they are only interested in learning job-related skills that are very closely related to their primary job-related skills.

[0166] For example, if a user desires employment in diverse fields even if those fields are not directly related to their primary job-related skills, their job-relatedness score will be close to 100, meaning they are interested in learning job-related skills even if their relevance to those skills is somewhat low.

[0167] In a further embodiment, if the user's job-seeking urgency is equal to or greater than the already set first job-seeking urgency, the processor 110 selects at least one of the sixth job-related skills from among several sixth job-related skills in order of the shortest time required to complete the educational curriculum.

[0168] The processor 110 can calculate the degree of relevance between each of the multiple sixth job-related skills and the first job-related skills as a numerical value, and determine the range of jobs that can be recommended to the user based on the job relevance.

[0169] The processor 110 can then select at least one of the sixth job-related skills based on the job relevance, the determined range, and the relevance calculated for each of the plurality of sixth job-related skills.

[0170] The following describes an example of how processor 110 extracts skills and builds a skills library.

[0171] Figures 7 and 8 illustrate the process of building a library by processing internal and external data.

[0172] Figure 7 shows the process 700 for building a skills library, and Figure 8 shows the process 800 for building a skills library with added data management functionality.

[0173] Processor 110 standardizes and systematically stores diverse skills required in the education and labor markets, thereby standardizing skill terminology among stakeholders.

[0174] In this context, the labor market refers to the job market (employee / job seeker market).

[0175] Processor 110 collects skills-related data from diverse sources, including job postings in the labor market and educational curricula from educational institutions. This data serves as important foundational information for understanding job-specific skill requirements.

[0176] Furthermore, the processor 110 can generate and manage metatables for keywords that contain detailed information such as job title and major.

[0177] Referring to Figures 7 and 8, the processor 110 can collect user information, lecture information, company information, skill information, job information, and major information based on a data source 730 that includes internal data 710, 810 and external data 720, 820.740 Then, the processor 110 processes the collected information by performing morphological separation, data standardization, data preprocessing, synonym processing, data structuring, and data modeling processes, respectively,750, 830 and finally constructs a skill library 840.760

[0178] Furthermore, as shown in Figure 8, the processor 110 can manage error data and perform a process to review changes.

[0179] In one embodiment, the processor 110 stores the collected skills in a skill library after a systematic classification process, and the library is stored in a skill list table containing skill information. Such a skill list library is divided into major categories (e.g., skills, job specialization), medium categories (e.g., programming languages, frameworks), and minor categories (e.g., Python, JavaScript), so that each skill is clearly distinguished, and each skill includes synonyms and similar skill information along with a standard skill name, so that diverse expressions of skill names can be managed in one standard form.

[0180] Furthermore, processor 110 can calculate the similarity between skills using natural language processing techniques such as Word2Vec from unstructured text data. The similarity includes information about how the skills are related to each other and can be used to represent this graphically.

[0181] The processor 110 can derive standard skill names based on the skills most frequently mentioned in the database and perform synonym processing through similarity analysis. Through this process, the server 100 can manage skills more accurately and consistently.

[0182] Furthermore, the processor 110 can register each skill stored in the skill library in the proper noun dictionary of the morphological analyzer. This solves the problem of having to accurately recognize skill names during the text analysis process.

[0183] The processor 110 can set appropriate cost values ​​for skill names so that they can be given priority consideration during the analysis process, thereby improving the accuracy of the analysis.

[0184] Furthermore, through the specific configuration described above, Server 100 eliminates the skill-based disparity between educational institutions and the labor market, enabling individuals and organizations to develop and manage skills more effectively.

[0185] Figure 9 illustrates the process of extracting skill-related keywords from unstructured data and matching them in conjunction with a library.

[0186] Figure 10 shows the process of extracting keywords from text-formatted input data.

[0187] Figure 9 shows process 900, in which input data 910 is processed and extracted using model 930, matched with skill library 920, and finally output data 940 is obtained. Figure 10 shows process 1000, in which keywords 1020, including skill keywords, occupational keywords, and major keywords, are extracted from user information 1010.

[0188] Referring to Figures 9 and 10, user information is shown as input data 910. Skill-related keywords are extracted from the unstructured input data 910 using natural language processing (NLP) technology, and these are then linked with the skill library 920 to perform specific matching.

[0189] Processor 110 receives student information or text-based data collected through member registration, lecture attendance, etc., as input, extracts keywords indicating competence, and returns them in list form. At this time, the returned keywords are matched with the data collected during the data collection stage and classified according to the hierarchical information to which they belong. The tokenizer can use MeCab, a Korean morphological analyzer.

[0190] As one example, the processor 110 can consolidate English words into lowercase for keyword matching and remove unnecessary words. The processor 110 can also automatically remove emails, URLs, HTML tags, etc., based on regular expressions.

[0191] Processor 110 uses MeCab, a Korean morphological analyzer, to tokenize words and separate them into nouns and foreign words. When constructing the skill library, all skills were registered as proper nouns, so they are classified as nouns in this process. The extracted keywords are then matched with data stored in the pre-constructed skill library and returned as a hierarchical structure of terms in standard language.

[0192] Figures 11 and 12 show the keyword extraction algorithms, respectively.

[0193] The keyword extraction algorithm 1100 will be explained with reference to Figure 11.

[0194] The processor 110 performs a primary extraction of keywords stored in the skill library 1110 using an edit distance algorithm (1120, Levenshtein Algorithm) to obtain tokens that have been pre-processed by morphological analysis. Then, the processor 110 performs a scoring 1130 to filter out meaningful keywords from the primary extracted keywords and returns a list of keywords that meet the already set criteria.

[0195] Next, the processor 110 uses the Jaro Distance Algorithm 1140 to search the skill library 1110 for the term with the highest string similarity to the keywords in the list and performs a secondary extraction process 1150.

[0196] At this point, the processor 110 applies n-grams to adjacent words because meaningful keywords extracted in the first step can combine to form a single keyword. Then, the processor 110 matches the words extracted in the second step against the standard language and returns them to a list along with the hierarchical structure.

[0197] The bottom row of Figure 11 shows the final processed Output 1160.

[0198] The keyword extraction algorithm 1200 shown in Figure 12 will be explained.

[0199] Processor 110 uses the edit distance algorithm (Levenshtein Algorithm) to extract keywords stored in the skill library from tokens that have been pre-processed using the input text.

[0200] The processor 110 assigns scores to the initially extracted keywords to filter them for meaningful keywords, and returns a list of keywords that meet certain criteria.

[0201] Processor 110 uses the Jaro Distance Algorithm to search the skill library for the term with the highest string similarity to the keywords in the list.

[0202] The processor 110 applies n-grams to adjacent words because, when the meaningful keywords extracted in the first stage are combined, they can form a single keyword.

[0203] Processor 110 matches the second-stage extracted words against the standard language and returns them to a list along with their hierarchical structure.

[0204] Figure 13 is an example diagram of an algorithm that calculates the editing cost between two words.

[0205] Referring to Figure 13, the edit distance algorithm (Levenshtein Algorithm, 1300) is shown.

[0206] The edit distance algorithm (Levenshtein Algorithm, 1300) is an algorithm that calculates the edit cost between two words, where the edit cost is the number of deletions, additions, and substitutions required to transform word1 into word2. A drawback of this algorithm is that the cost increases with increasing word length.

[0207] Figure 14 is an example diagram of an algorithm that calculates a score by considering the editing cost between two words, the length of the words, and the common characters.

[0208] Referring to Figure 14, the Jaro distance Algorithm 1400 is shown.

[0209] The Jaro distance algorithm 1400 calculates a score by considering not only the editing cost between two words, but also the length of the words and the number of common characters. It calculates the editing cost and only considers the number of character position swaps. A weighted value can be assigned depending on the number of common characters.

[0210] The recruitment collaboration service provider server 100 for the job skills standardization platform according to the embodiment of this disclosure has the effect of using both of these algorithms together to complement the shortcomings of each algorithm.

[0211] Figure 15 shows the extraction process and the conversion process for standard skill names.

[0212] Referring to Figure 15, the processor 110 performs a primary extraction on the example data 1510 and obtains the primary extraction result 1520.

[0213] Next, the processor 110 performs a secondary extraction on the primary extraction result 1520 to obtain the secondary extraction result 1530, which is then converted into a standard skill name to obtain the final result 1540.

[0214] Figures 16 and 17 show the calculation of Jackard similarity.

[0215] Referring to Figure 16, the Jackard similarity calculation algorithm 1600 is shown.

[0216] Referring to the Jackard similarity calculation algorithm 1600 in Figure 16 and the example shown in Figure 17, the processor 110 can recommend suitable lectures (educational curricula) for jobs where data is insufficient by calculating Jackard similarity. In this case, the comparison list may be a list of job competencies desired by the student (user, job seeker) and the job competencies that the student lacks. The processor 110 calculates by subtracting the competencies that the student already possesses from the job competencies.

[0217] As a further example, the processor can utilize Neural Matrix Factorization (NMF). NMF is a powerful collaborative filtering technique that represents interaction data between students and lectures as a matrix and decomposes it into low-dimensional latent factors for learning. By calculating the inner product between individual students and latent factors, it can predict individual lecture interests and areas of interest, and recommend suitable lectures.

[0218] The processor can recommend courses based on whether students belong to a group (major, desired job, etc.) that shares common interests or preferred courses. It can recommend courses that have been taken most frequently within the group, or apply an NMF model based on the preferences and interests of students within the group.

[0219] The method according to one embodiment of the present disclosure described above can be embodied in a program (or application) and stored on a medium for execution in conjunction with a hardware server.

[0220] The aforementioned program may include code encoded in a computer language such as C, C++, Java®, or machine language, which is read by the computer's processor (CPU) via the computer's device interface, in order for the computer to read the program and execute the method embodied by the program. Such code may include functional code related to functions that define the functions necessary to execute the method, and may include execution procedure-related control code necessary for the computer's processor to execute the functions in a predetermined order. Furthermore, such code may further include memory reference-related code indicating where (address) in the computer's internal or external memory should be referenced for additional information or media necessary for the computer's processor to execute the functions. In addition, if the computer's processor needs to communicate with any other computer or server located remotely in order to execute the functions, the code may further include communication-related code indicating how to communicate with any other computer or server located remotely using the computer's communication module, and what information or media should be sent and received during communication.

[0221] The aforementioned storage medium refers not to a medium that stores data for a short time, such as a register, cache, or memory, but rather to a medium that stores data semi-permanently and is readable by a device. Specifically, examples of the storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. That is, the program can be stored on various recording media on various servers to which the computer can connect, or on various recording media on the user's computer. Furthermore, the medium can be distributed across computer systems connected via a network, and code that can be read by computers in a distributed manner can be stored on it.

[0222] Steps of the methods or algorithms described in relation to embodiments of the present invention can be embodied directly in hardware, in software modules executed by hardware, or in combination thereof. The software modules can always reside on RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, hard disk, removable disk, CD-ROM, or any form of computer-readable recording medium known in the art to which the present invention belongs.

[0223] While embodiments of this disclosure have been described above with reference to the attached drawings, a person ordinary in the art to which this disclosure belongs should be able to understand that this disclosure can be implemented in other specific forms without altering its technical idea or essential features. Accordingly, the embodiments described above should be understood in all respects as illustrative and not limiting.

Claims

1. A communication module that communicates with user terminals and corporate servers, A memory containing at least one process for standardizing job skills, Includes a processor that performs the operation according to the process described above, The aforementioned processor, The job-seeking information, including the user's career history and job-related information received from the user terminal, is standardized to generate first standardized data, including the user's first job-related skills. The recruitment information, including the job posting and job description received from the aforementioned company server, is standardized to generate second standardized data. The first standardized data and the second standardized data are matched, A server that provides the user terminal with at least one job posting that matches the job seeker information based on the matching results, and provides the company server with at least one job seeker information that matches the job posting.

2. The aforementioned memory is A skills library is stored containing multiple job-related skills arranged in a tree structure that includes at least one sub-level. The aforementioned processor, At pre-set intervals, the skills library is updated by modifying the second job-related skills required for each position based on the company's new recruitment announcements. The server according to claim 1, characterized in that it standardizes terminology used in job-seeking fields and related educational fields based on the skills library, and provides the standardized terminology to the servers of educational institutions that provide recruitment-related educational services to job seekers and to the corporate servers.

3. The aforementioned processor, In the job information, the first item corresponding to the skill library is checked as the first job-related skill possessed by the user. The server according to claim 2, characterized in that it calculates a first skill level for the first job-related skills that have been checked based on the job application information.

4. The aforementioned processor, In the aforementioned job posting, the second item corresponding to the aforementioned skills library is checked as the second job-related skill required for the personnel the company is recruiting. Based on the aforementioned job information, calculate the second skill level for the second job-related skills that were checked. The server according to claim 3, characterized in that it matches job postings in which the first skill level corresponds to the second skill level for the same job-related skills with job seeker information that corresponds to the job seeker information.

5. The aforementioned processor, The communication module receives at least one educational curriculum for the education of job seekers from the server of an educational institution. The server according to claim 2, characterized in that it generates feedback for the educational curriculum based on the results of a comparison between the third job-related skills set as educational objectives in the educational curriculum for each job and the second job-related skills required for each job.

6. The aforementioned processor, For each of the aforementioned job-related skills, relationship information with other job-related skills is generated. Based on the aforementioned relevance information and the comparison results between the user's job-related skills related to the specific job of the company they are applying to and the user's first job-related skills, a fourth job-related skill that the user lacks or is deficient in is extracted. The server according to claim 5, characterized in that it provides the user terminal with information regarding the educational curriculum related to the fourth job-related skills.

7. The aforementioned processor, Extract the fifth job-related skills by job function, Based on the aforementioned job-specific fifth job-related skills, if there is at least one job among the aforementioned jobs that is satisfied by the first job-related skills and the first skill level possessed by the user, The aforementioned at least one position is designated as a position for which immediate applications are accepted, The server according to claim 3, characterized in that it provides the user terminal with information regarding the immediately available job applications.

8. The aforementioned processor, For each of the aforementioned job-related skills, relationship information with other job-related skills is generated. Derive multiple sixth job-related skills that are related to multiple first job-related skills possessed by the user, Based on at least one of the user's job-seeking urgency and job relevance, at least one sixth job-related skill is selected from the plurality of sixth job-related skills. The aforementioned job relevance means the range of jobs for which the user seeks recommendations in relation to the first job-related skills, The server according to claim 5, characterized in that it provides the user terminal with information regarding the educational curriculum for the selected sixth job-related skill.

9. The aforementioned processor, If the job-seeking urgency is equal to or greater than the already established first job-seeking urgency, then at least one of the sixth job-related skills is selected from the plurality of sixth job-related skills in order of the shortest time required to complete the educational curriculum. For each of the aforementioned sixth job-related skills, the degree of correlation with the first job-related skill is calculated as a numerical value. Based on the aforementioned job relevance, the range of jobs that can be recommended to the user is determined. The server according to claim 8, characterized in that it selects at least one sixth job-related skill based on the job relevance, the determined range, and the relevance calculated for each of the plurality of sixth job-related skills.

10. The server is used for testing, The process includes standardizing job-seeking information, including the user's career history and job-related information, received from the user terminal, to generate first standardized data, which includes the user's first job-related skills. The process involves standardizing job postings, including recruitment announcements and job descriptions, received from a company server to generate second-level standardized data. The step of matching the first standardized data and the second standardized data, The steps include providing the user terminal with at least one job posting that matches the job seeker information based on the matching results, The steps include providing the company server with at least one job seeker information that matches the job information based on the matching results, A method that includes this.

Images