Personalized job-related competency enhancement recommendation system

Abstract

A personalized job-related competency enhancement recommendation system is disclosed, comprising: a mobile terminal; and a control server that collects personal competency information from a learner through the mobile terminal, analyzes the personal competency information, and recommends a job training program and a job competency enhancement plan according to the job classification system of the job competency standard.

Description

Technology Field

[0001] The present invention relates to a personalized job-related competency enhancement recommendation system. Background Technology

[0003] Currently, employees in organizations such as general corporations are focusing solely on their assigned duties without consistent goals or direction, aiming to achieve related corporate performance. Furthermore, companies are conducting standardized and formal job-related training in a customary manner based on inaccurate information, resulting in many social and economic side effects.

[0004] This is because current companies lack systems to guide and assist individual employees in setting and designing their own career goals; consequently, the appropriate placement of talent in the right positions is not being achieved. Furthermore, individuals lack learning motivation, ultimately resulting in limited opportunities for performing diverse job functions. Economically, this leads to increased costs due to unnecessary training and exerts a negative impact on national competitiveness.

[0005] In order to address the aforementioned problems, conventional attempts have been made to provide prescriptions for problem-solving and diverse job-related information to individuals with difficulties related to their work through various vocational aptitude tests and interest tests.

[0006] However, the testing methods provided by conventional devices had the problem of being unable to accurately determine the capabilities required to perform all duties of each individual employee being tested, and also failing to provide training information appropriate to the test subject's current situation based on the aforementioned test results. The problem to be solved

[0008] One aspect of the present invention discloses a system that recommends personalized job training and job competency enhancement plans by utilizing job-specific indicator data classified in job competency standards, such as the Korean National Competency Standards (NCS) and the U.S. Workforce Framework for Cybersecurity.

[0009] The technical problems of the present invention are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0011] The system of the present invention includes: a mobile terminal; and a control server that collects personal competency information from a learner through the mobile terminal, analyzes the personal competency information, and recommends a job training program and a job competency enhancement plan according to a job competency standard job classification system.

[0012] Meanwhile, the control server may include: a personal competency information collection unit that collects personal competency information including age, gender, career, workplace, job, and major, and obtains individual survey information including interest keywords and scores for job competency tests for each job according to the personal competency information; a job suitability recommendation unit that analyzes the personal competency information to classify jobs according to the job competency standard job classification system, extracts job competency standard competency units according to the job competency standard job classification, extracts an educational program from an external site for learning the abilities required for the job competency standard competency units, and provides the extracted educational program to the mobile terminal; and a job competency enhancement recommendation unit that includes an artificial intelligence neural network for extracting a job competency standard classification map extending from the personal competency information and individual survey information to the artificial intelligence neural network, inputs the personal competency information and individual survey information into the artificial intelligence neural network, outputs the job competency standard classification map as the output of the artificial intelligence neural network, and provides the output job competency standard classification map to the mobile terminal as an individual job competency enhancement plan.

[0013] Meanwhile, the above-mentioned personal competency information collection unit can calculate individual job diagnosis scores using the following mathematical formula 1, sort all learners by job diagnosis scores according to any one of the same age, career, workplace, job, and major categories, and provide information on the rank of the learner based on the job diagnosis score.

[0014] [Mathematical Formula 1]

[0015]

[0016] (S in mathematical formula 1 J is J's job assessment score, N is the total number of learners, Q n is the number of interest keywords of learner n, Q J represents the number of interest keywords of learner J, and S iis the score for the job competency test. Here, the score for the job competency test is calculated out of 100 points.) Effects of the invention

[0019] According to one aspect of the present invention described above, by recommending a job through a personalized job suitability score and recommending a job competency enhancement plan for a selected job, it is possible to help perform a job corresponding to an individual's ability, attitude, knowledge, etc., and at the same time help strengthen the competencies required for the job. Brief explanation of the drawing

[0021] FIG. 1 is a conceptual diagram of a system according to one embodiment of the present invention. Figure 2 is a conceptual diagram of the control server shown in Figure 1. Specific details for implementing the invention

[0022] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components.

[0023] The terms used herein are for describing the embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used herein, "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components, steps, and actions to the mentioned components, steps, and actions.

[0025] FIG. 1 is a conceptual diagram of a personalized job-related competency enhancement recommendation system according to one embodiment of the present invention.

[0026] Referring to FIG. 1, a system (1) according to one embodiment of the present invention may include a control server (100) and a mobile terminal (200).

[0027] The control server (100) may be an operating server for an education and development site and may provide an education and development recommendation service according to the present invention.

[0028] The control server (100) may be a self-contained server or a cloud server for providing the service according to the present invention, or it may be a peer-to-peer (P2P) set of distributed nodes.

[0029] The control server (100) can perform one or more of the computation, storage, reference, input / output, and control functions of a general computer, and may include an artificial neural network to be described later based on input data.

[0030] The control server (100) may include a processor and memory. The processor may perform maintenance management services according to the present invention and may include devices capable of performing such services. The processor may execute a program or control the control server (100). Program code executed by the processor may be stored in memory. The memory may store relevant information for performing services according to the present invention or a program for implementing a method. The memory may be volatile memory or non-volatile memory.

[0031] The control server (100) can send data to an external device or receive data from an external device using a network.

[0032] The control server (100) can train an artificial intelligence model based on a language model and can also use the artificial intelligence model that has been trained. The processor can train or execute an artificial intelligence model stored in memory, and the memory can store the artificial intelligence model that has been trained. The electronic device that trains the artificial intelligence model and the electronic device that uses it may be the same, but they may also be separate.

[0033] Artificial intelligence is a computer system that partially implements the functions of the human brain and is capable of learning, speculating, and making judgments on its own. As learning progresses, the probability of extracting the correct answer can increase. Artificial intelligence can be composed of learning and component technologies that utilize it. The learning aspect of AI is an algorithmic technology that classifies and learns features based on input data, while the component technologies may be techniques that utilize these learning algorithms to partially implement the functions of the human brain.

[0034] Artificial intelligence is a technology that facilitates the approach to problems where multiple probabilistic answers are possible, enabling it to logically and probabilistically infer optimal cycles, methods, and plans based on input data. AI inference techniques can include evaluating input data, optimization prediction, knowledge and probability-based reasoning, and preference-based planning.

[0035] Artificial neural networks are learning algorithms in the field of machine learning that programmatically implement the connections between neurons and synapses in the brain. By creating a neural network structure through programming and then training it, artificial neural networks can acquire desired functions. Although errors may exist, they can learn from massive datasets to produce appropriate output data from input data. They have the advantage of being able to obtain output data that has yielded statistically good results and are similar to human reasoning.

[0036] The network is a high-speed backbone network of a large-scale communication network capable of high-capacity, long-distance voice and data services, and may be a next-generation wired and wireless network for providing the Internet or high-speed multimedia services.

[0037] If the network is a mobile communication network, it may be a synchronous mobile communication network or an asynchronous mobile communication network. As an example of an asynchronous mobile communication network, a WCDMA (Wideband Code Division Multiple Access) network may be cited. In this case, although not shown in the drawing, the network may include an RNC (Radio Network Controller). Meanwhile, although a WCDMA network was given as an example, it may be a 3G LTE network, a 4G network, a next-generation communication network such as 5G, or other IP-based IP networks.

[0038] The mobile terminal (200) can include any terminal capable of exchanging data over a network, such as a desktop computer, laptop, tablet, or smartphone.

[0039] A mobile terminal (200) may include one or more of the computation function, storage function, reference function, input / output function, and control function of a computer to perform a service according to the present invention.

[0040] A mobile terminal (200) may access a website or install an application to receive a service according to the present invention. The mobile terminal (200) may exchange data through the website or the application.

[0041] The mobile terminal (200) may be a terminal possessed by a job training and job development learner.

[0042] The mobile terminal (200) can access a site provided by the control server (100) to input personal status information and output personalized job training and development plans provided by the control server (100).

[0043] A system (1) according to one embodiment of the present invention can help effectively develop an individual's abilities and knowledge and strengthen the abilities and knowledge required for the job by recommending personalized job training and job competency enhancement plans.

[0045] Figure 2 is a conceptual diagram of the control server shown in Figure 1.

[0046] Referring to FIG. 2, a control server (100) according to one embodiment of the present invention may include a personal competency information collection unit (110), a job suitability recommendation unit (120), and a job competency enhancement plan recommendation unit (130).

[0047] The personal competency information collection unit (110) can collect personal competency information from the learner through a mobile terminal (200).

[0048] Personal competency information may include age, gender, work experience, workplace, job function, major, etc. Additionally, personal competency information may include documents describing the educational content completed or knowledge possessed by the learner, work results produced using possessed skills, resumes, and portfolios.

[0049] Specifically, documentary materials containing detailed information regarding various educational courses, programs, seminars, and workshops previously completed by the learner may be collected. These documents may include the scope of key knowledge acquired by the learner, major concepts and theories learned during the course, and a list of learning materials utilized. Examples include certificates of completion for professional training courses, academic transcripts, seminar attendance certificates, and learning summary reports. Through such materials, the learner's level of knowledge and understanding can be assessed, and they serve as a basis for grasping that knowledge.

[0050] Furthermore, the actual work results and detailed records of tasks performed by learners in relation to their duties can be collected. These serve as data to evaluate the learners' actual work performance capabilities and primarily include outputs created using the tools, technologies, or skills employed by the learners. For example, this includes code or programs written by a learner with programming skills, design drawings for a design engineer, analysis reports or visualizations for a data analyst, and marketing strategy reports written by a marketing professional. Through these work results, the learners' actual technical proficiency and problem-solving abilities can be specifically identified.

[0051] In addition, resumes written by learners and portfolios summarizing job-related achievements can be collected and utilized to evaluate their careers, work performance attitudes, and learning outcomes. Resumes may include the learner's career history, job history, certifications, and related activities, while portfolios consist of materials that systematically present projects or work performance results performed in the past. For example, a resume describes roles and achievements related to past job history, while a portfolio may include materials specifically detailing project-specific information, applied skills, results, and contributions. Through this, the learner's consistent learning attitude and diligence in job performance can be assessed.

[0052] The personal competency information collection unit (110) can receive survey responses for education and development recommendations from learners through a mobile terminal (200) and store them as individual survey information.

[0053] For example, individual survey information may include interest keywords, scores on job competency tests based on individual competency information, etc.

[0054] The job suitability recommendation unit (120) can identify individual competency information, classify jobs for each learner in correspondence with the job competency standard job classification system, identify job competency standard competency units corresponding to the jobs classified for each learner, identify the learner's job suitability in its current state in comparison with the abilities required for the job competency standard competency units, and recommend jobs with high suitability and corresponding job education programs by comparing them with the abilities required for other job competency standard competency units.

[0055] Job competency standards refer to the competencies (knowledge, skills, attitudes, etc.) required to perform job duties in the industrial field, standardized at the national level, and represent a competency unit or a set of competency units.

[0056] In this embodiment, a job classification system based on the NCS defined in Korea is applied to classify jobs for each learner, and a job training program can be recommended to evaluate and learn the competencies required for the jobs classified for each learner.

[0057] The job suitability recommendation unit (120) can analyze the information collected by the personal competency information collection unit (110) to classify jobs according to the individual NCS job classification system and extract NCS competency units. The NCS competency unit is a competency unit assigned according to the NCS job classification system. For example, in the job classification system of Business Management (Major Classification) > Business Management (Medium Classification) > Project Management (Minor Classification) > Official Development Assistance Project Management (Detailed Classification), the competency unit for establishing Official Development Assistance project development strategies can be extracted.

[0058] For example, the job suitability recommendation unit (120) may include an artificial intelligence model for extracting individual NCS competency units from individual competency information.

[0059] The job suitability recommendation unit (120) may include a number of AI models that have been pre-trained for the execution of an AI algorithm. The AI ​​models may output output data based on input data and learn on their own using the results, thereby improving their data processing capabilities.

[0060] Artificial intelligence models can output result data by extracting features and inferring patterns based on input data, and as this process accumulates, the reliability of the result data increases.

[0061] In this embodiment, the artificial intelligence model can infer the best output data by using big data as input data as is, or by using it as input data after undergoing a processing process to clean up unnecessary data.

[0062] In this embodiment, the artificial neural network may be an algorithm that outputs NCS competency units for personal competency information including age, gender, career, workplace, job, major, etc. The artificial neural network can infer the best output data by using big data as input data as is, or by using it as input data after undergoing a processing step to clean up unnecessary data.

[0063] Artificial intelligence learning models are classified according to the type of learning into supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. In addition, machine learning algorithms include Decision Tree, K-Nearest Neighbor, Artificial Neural Network, Support Vector Machine, Ensemble Learning, Gradient Descent, and Na Bayes Classifier, Hidden Markov Model, K-Means Clustering, etc. can be used.

[0064] Language models and artificial neural networks can be pre-trained on various input values ​​that may be included in the input data.

[0065] Language models can use supervised learning to perform additional fine-tuning for specific tasks after completing pre-training; for example, when performing sentiment analysis, they learn by labeling sentences contained in a given text as positive or negative.

[0066] Language models can perform unsupervised learning by utilizing large-scale text data in prior training to predict the next word; for example, BERT-family language models can be trained by deleting some words from a sentence and then predicting those words.

[0067] Language models can be semi-supervised by being trained with a large amount of unlabeled text data during the pre-training phase and then fine-tuned with a small amount of labeled data. For example, training can be performed using 100 pieces of labeled text data and 1,000 pieces of unlabeled text data.

[0068] Language models can learn to improve the quality of their answers based on human feedback during the learning phase.

[0069] The job suitability recommendation unit (120) inputs personal competency information into such an artificial intelligence model and can obtain NCS competency unit information as the output of the artificial intelligence model.

[0070] The job suitability recommendation unit (120) can extract an educational program for learning the competencies required for the NCS competency unit from an external site and provide the extracted educational program to a mobile terminal (200).

[0071] In addition, the job suitability recommendation unit (120) identifies personal competency information based on personal competency information, classifies jobs for each learner in correspondence with the job competency standard job classification system, identifies job competency standard competency units corresponding to the jobs classified for each learner, identifies the learner's job suitability in its current state in comparison with the abilities required for the job competency standard competency units, and can provide jobs with high suitability to the mobile terminal (200) by comparing them with the abilities required for other job competency standard competency units.

[0072] The job competency enhancement recommendation unit (130) can analyze the personal competency information and individual survey information collected by the personal competency information collection unit (110) and recommend an NCS classification map based on individual abilities, knowledge, or interests as an individual job competency enhancement plan.

[0073] For example, the job competency enhancement recommendation unit (130) may include an artificial intelligence model for extracting an NCS classification map from at least one of personal competency information and individual survey information. The NCS classification map is structured from major classification to medium classification to minor classification to detailed classification to competency unit, and job development can be performed along this NCS classification map.

[0074] The job competency enhancement recommendation unit (130) may include a number of artificial intelligence models that have been pre-trained to perform machine learning algorithms. It may output output data based on input data through machine learning and learn on its own using the results, thereby improving its data processing ability on its own.

[0075] Artificial intelligence models can output result data by extracting features and inferring patterns based on input data, and as this process accumulates, the reliability of the result data increases.

[0076] In this embodiment, the algorithm model may be an algorithm that outputs an NCS classification map based on at least one of personal competency information including age, gender, career, workplace, job, major, etc., interest keywords, and personal survey information including scores for job competency tests by job according to personal competency information. The artificial intelligence model can infer the best output data by using big data as input data as is, or by using it as input data after undergoing a processing step to clean up unnecessary data.

[0077] Artificial intelligence models are classified into Supervisory Learning, Unsupervisory Learning, Semi-supervised Learning, and Reinforcement Learning, depending on the type of learning.

[0078] The language models on which artificial intelligence models are based can consist of GPT family models such as GPT-4, BERT family models such as RoBERTa and CodeBERT, T5 family models such as mT5 and ByT5, and UniLM family models such as UniLMv2 and UniLM++.

[0079] An artificial intelligence model can be constructed by interconnecting multiple language models. The AI ​​model may be pre-trained on various input values ​​that may be included in the input data. The AI ​​model can output data by inferring vulnerabilities based on the data input by the user.

[0080] And machine learning algorithms include Decision Tree, K-Nearest Neighbor, Artificial Neural Network, Support Vector Machine, Ensemble Learning, Gradient Descent, Na Bayes Classifier, Hidden Markov Model, K-Means Clustering, etc. can be used.

[0081] Artificial neural networks can stack and connect numerous artificial neurons in several layers. Artificial neural networks may be pre-trained on various input values ​​that may be included in the input data. Artificial neural networks can infer vulnerabilities based on the data input by the user and output data.

[0082] An artificial neural network can be one that is trained according to reinforcement learning, which is a learning method. Reinforcement learning is a method that gradually increases the probability of obtaining the correct result by setting rewards and constraints.

[0083] Artificial neural networks can also be modeled based on Convectional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs).

[0084] The job competency enhancement recommendation unit (130) inputs personal competency information and individual survey information into such an artificial intelligence model and can output an NCS classification map as the output of the artificial intelligence neural network.

[0085] The job competency enhancement recommendation section (130) can provide the NCS classification map as an individual job competency enhancement plan to a mobile terminal (200).

[0086] Meanwhile, the personal competency information collection unit (110) can calculate individual job suitability scores using the following mathematical formula 1, sort all learners by job suitability score, and provide information on the rank of the learner according to the job suitability score.

[0087] [Mathematical Formula 1]

[0088]

[0089] S in mathematical formula 1 J is J's job assessment score, N is the total number of learners, Q n is the number of interest keywords of learner n, Q J is the number of interest keywords of learner J, S i represents the score for the job competency test. Here, the score for the job competency test refers to the overall suitability score derived through the job knowledge suitability score, skill suitability score, attitude and education suitability score.

[0090] The score for the job competency test refers to the comprehensive suitability score calculated based on job knowledge suitability, skills suitability, and attitude and education suitability. Each score is derived through individual evaluation and is calculated as the final score of the job competency test by reflecting weights.

[0091] The knowledge suitability score is a score that evaluates how well a learner fits the theoretical knowledge and concepts required for the relevant job, and it is calculated based on the details of educational programs completed by the learner, qualification exam scores, and knowledge assessment results. For example, in the case of a job related to a specific programming language, the learner's theoretical knowledge achievement may be evaluated as 85 out of 100 points by assessing the educational completion records and relevant exam scores submitted by the learner. In this case, the knowledge suitability score is assigned as 85 points.

[0092] The technical suitability score is a score that evaluates how proficiently a learner can use the skills required to perform the relevant job in the workplace, and it is evaluated based on the work results, portfolios, and practical assignments submitted by the learner. For example, if the source code and project completeness submitted by a learner applying for a development position are evaluated to verify practical skills and the degree of code optimization, and the result is calculated as 90 out of 100 points, the technical suitability score is assigned as 90 points.

[0093] The attitude and education suitability score is a score that evaluates a learner's sincerity, learning attitude, willingness to continue learning, and status of education completion, and is evaluated based on the resume and work experience submitted by the learner, as well as records of completing educational programs. For example, if the result of an evaluation based on the number of educational courses completed by the learner, job-related project experience, and project performance is calculated as 80 out of 100 points, the attitude and education suitability score is assigned as 80 points.

[0094] The knowledge suitability score, skill suitability score, and attitude and education suitability score derived in this manner are calculated as a comprehensive suitability score by applying their respective weights. For example, if the weight for the knowledge suitability score is assigned as 0.3, the weight for the skill suitability score as 0.4, and the weight for the attitude and education suitability score as 0.3, the score for the job competency test is derived as Comprehensive Suitability Score = (Knowledge Suitability Score × 0.3) + (Skill Suitability Score × 0.4) + (Attitude and Education Suitability Score × 0.3). In the example, the Comprehensive Suitability Score is calculated as 85 × 0.3 + 90 × 0.4 + 80 × 0.3 = 85.5, and the final score for the job competency test is 85.5 points.

[0095] According to mathematical formula 1, by comparing the average number of interest keywords of all learners with the number of interest keywords entered by the learner, a high job diagnostic score is calculated according to the learner's level of interest, and furthermore, the job diagnostic score is calculated by reflecting the job competency test score.

[0096] For example, the score on the job competency test is 80 points, and the total number of learners is 100, =1000, if the number of learner interest keywords is 5, the job diagnosis score can be calculated as 40 points.

[0097] The personal competency information collection unit (110) can help to objectively determine the level of interest or job ability by sorting all learners by job diagnosis score according to one of the same age, career, workplace, job and major categories and presenting the rank of the learner according to the job diagnosis score.

[0098] Meanwhile, the job suitability recommendation unit (120) can check whether each learner has taken job training and calculate an achievement score based on taking job training.

[0099] [Mathematical Formula 2]

[0100]

[0101] S in mathematical equation 2 E is the achievement score, s is the number of required competencies corresponding to the NCS competency unit, N is the number of job training programs, n is the number of job training programs taken, L is the level assigned to the NCS competency unit, P n can be defined as 0 if the nth job training program has been passed, and 1 otherwise.

[0102] According to mathematical formula 2, a high achievement score is calculated based on the number of required competencies assigned to the NCS competency unit, the level, and whether or not a job training program is taken, and a square root value is applied to reflect this so as not to have too large a range of change.

[0103] For example, the number of job training programs is 5, the number of job training programs taken is 3, the level is 7, and the number of required competencies is 15, and If =2, the achievement score can be calculated as 1.81.

[0104] If the job suitability recommendation unit (120) calculates the achievement score to be below a predetermined score, it considers the learner's NCS competency unit to be inappropriate, re-extracts an NCS competency unit corresponding to a classification number that differs from the classification number of the extracted NCS competency unit by one or more, extracts an educational program for learning the competency required for the re-extracted NCS competency unit from an external site, and provides the extracted educational program to a mobile terminal (200).

[0105] Meanwhile, the job competency enhancement recommendation unit (130) can calculate a map evaluation score by evaluating the extracted NCS classification map.

[0106] [Mathematical Formula 3]

[0107]

[0108] S in mathematical equation 3 M is the NCS Roadmap evaluation score, Lm is the average of the levels assigned to the NCS competency units included in the NCS Roadmap, m is the number of NCS competency units included in the NCS Roadmap, and s m is the basic roadmap evaluation score, k n is the number of job-related keywords included in the nth NCS competency unit, p n represents the number of keywords corresponding to the keywords of interest entered by the learner among the job-related keywords included in the nth NCS competency unit.

[0109] According to mathematical formula 3, the roadmap evaluation score was calculated to be high by reflecting the level assigned to the NCS competency unit, the number of NCS competency units, and whether the user's input interest keywords were included.

[0110] For example, the basic roadmap evaluation score is 5, the average of the level assigned to the NCS competency units is 5, and the number of NCS competency units is 10, and If =10, the NCS roadmap evaluation score can be calculated as 15.8.

[0111] The job competency enhancement recommendation unit (130) can present the NCS roadmap and the NCS roadmap evaluation score together to the mobile terminal (200), and at this time, the higher the NCS roadmap evaluation score, the more likely it is that an NCS roadmap suitable for the user's interest has been extracted.

[0113] Meanwhile, the control server (100) may include an engine server.

[0114] An engine server according to one embodiment of the present invention may include an alpha extraction unit, a beta extraction unit, a database, an indicator analysis unit, and a learning suggestion unit.

[0115] The alpha extraction unit can receive the problem content that the user is learning through the user terminal (500) and extract alpha, which is an indicator necessary to solve the problem content.

[0116] The beta extraction unit receives the solution process of the problem content being studied by the user through the user terminal (500) and can extract beta, which is an indicator of the user's basic skills, memorization ability, application ability, cognitive ability, and learning ability.

[0117] In addition, the beta extraction unit can extract beta from the solution process based on the solution steps and solution configuration.

[0118] The database can convert the problem content received from the alpha extraction unit into problem source code and the solution process received from the beta extraction unit into solution source code, and classify and cumulatively store the converted problem source code and solution source code by user.

[0119] The indicator analysis unit can analyze each user's overall learning indicators based on problem source code and solution source code accumulated and stored in the database classified by user, alpha indicators extracted by the alpha extraction unit, and beta indicators extracted by the beta extraction unit.

[0120] In addition, the indicator analysis unit can analyze the user's overall learning indicators based on the similarity between the indicators required to solve the problem content extracted by the alpha extraction unit and the indicators possessed by the user extracted by the beta extraction unit.

[0121] Meanwhile, the indicator analysis unit can determine the similarity between the indicator required to solve the problem and the indicator possessed by the user based on the value calculated using [Mathematical Formula 4] below, based on the basic skill indicator required to solve the problem content extracted from the alpha extraction unit, the memorization skill indicator required to solve the problem content extracted from the alpha extraction unit, the application skill indicator required to solve the problem content extracted from the alpha extraction unit, the cognitive skill indicator required to solve the problem content extracted from the alpha extraction unit, the learning skill indicator required to solve the problem content extracted from the alpha extraction unit, the basic skill indicator possessed by the user based on the solution steps and solution composition extracted from the beta extraction unit, the memorization skill indicator possessed by the user based on the solution steps and solution composition extracted from the beta extraction unit, the application skill indicator possessed by the user based on the solution steps and solution composition extracted from the beta extraction unit, the cognitive skill indicator possessed by the user based on the solution steps and solution composition extracted from the beta extraction unit, and the learning skill indicator possessed by the user based on the solution steps and solution composition extracted from the beta extraction unit.

[0122] [Mathematical Formula 4]

[0123]

[0124] Here, may refer to the basic skill indicator required to solve the corresponding problem content extracted from the alpha extraction unit, and may refer to the memorization ability indicator required to solve the corresponding problem content extracted from the alpha extraction unit, and may refer to an application ability indicator required to solve the corresponding problem content extracted from the alpha extraction unit, and may refer to the cognitive ability indicator required to solve the corresponding problem content extracted from the alpha extraction unit, and may refer to the learning ability indicator required to solve the corresponding problem content extracted by the alpha extraction unit, and may refer to an indicator of the user's basic skills based on the solution steps and solution structure extracted from the beta extraction unit, and may refer to the memorization ability indicator possessed by the user based on the solution steps and solution configuration extracted from the beta extraction unit, and may refer to an application capability indicator possessed by the user based on the solution steps and solution configuration extracted from the beta extraction unit, and may refer to an indicator of cognitive ability possessed by the user based on the solution steps and solution configuration extracted from the beta extraction unit, and may refer to an indicator of the user's learning ability based on the solution steps and solution configuration extracted from the beta extraction unit, and It may refer to a value that serves as a criterion for judging the similarity between the indicators required to solve the problem and the indicators possessed by the user, based on the calculated value.

[0125] Each of the aforementioned indicators , , , and class , , , and This can mean that each indicator is represented as a numerical value.

[0126] in other words, , , , and Each indicator required to solve the problem can be assigned '1' when it is at its lowest, and '10' when it is at its highest, and , , , and If each metric held by the user is the lowest, it can be assigned '1', and if each metric is the highest, it can be assigned '10'.

[0127] In other words, the case where the basic skill indicator required to solve the problem content extracted by the alpha extraction unit must be the highest. can be substituted as 10, and in the case where the user's basic skill index is the lowest based on the solution steps and solution structure extracted from the beta extraction unit can be substituted as '1'.

[0128] for example, is 10, is 7, is 8, is 7, is 9, is 5, is 3, is 2, is 3, In the case of 4, It can be calculated as 7.34, and is 8, is 6, is 5, is 5, is 4, is 8, is 5, is 5, is 4, In the case of 4, It can be calculated as 24.3.

[0129] The output The larger the value of , the higher the similarity between the indicators needed to solve the problem and the indicators possessed by the user can be judged.

[0130] Conversely, the produced The smaller the calculated value of , the lower the similarity between the indicators required to solve the problem and the indicators possessed by the user may be judged to be.

[0131] Here, since the content of the proposed learning methods or improvement directions may differ depending on the metrics the user possesses, it must be possible to determine the level of similarity between the metrics required to solve the problem and the metrics possessed by the user.

[0132] Among the two examples described above, since the first example yields a smaller value than the second example, it is determined that the similarity between the indicators required to solve the problem and the indicators possessed by the user is low; therefore, the user's learning method or direction for improvement can be provided as one capable of improving all of 'basic skills, memorization ability, application ability, cognitive ability, and learning ability.'

[0133] Conversely, since the second example yields a larger value than the first example, it is determined that the similarity between the indicators required to solve the problem and the indicators possessed by the user is high, so it is possible to suggest ways to maintain the user's 'basic skills, memorization ability, application ability, cognitive ability, and learning ability'.

[0134] Meanwhile, the content of the suggestions, such as enabling users to propose or maintain learning methods or directions for improvement regarding 'basic skills, memorization ability, application ability, cognitive ability, and learning ability,' is It may vary depending on the standard of the value, and The standard for the value of can be set by the engine server administrator.

[0135] For example, regarding the proposed content If the standard for the value is set to '10', If the calculated value is greater than '10', it can suggest to the user that they maintain their current overall learning metrics.

[0136] The engine server is for the proposed content pre-configured by the administrator When the standard value of is set to '10' according to the example, in the case of the first example among the two examples described above, the engine server can suggest learning methods or improvement directions such as 'basic skills, memorization skills, application skills, cognitive skills, and learning skills'.

[0137] Conversely, the engine server [regarding] the proposed content pre-configured by the administrator When the standard value of is set to '10' according to the example, in the case of the second example among the two examples described above, the engine server can suggest to the user that the user can maintain the current state.

[0138] However, regarding determining the content of suggesting learning methods and improvement directions to users registered on the engine server Setting the standard value to '10' is just one example, and the standard can be changed by the engine server administrator.

[0139] However, the content of the learning method or improvement direction may change depending on the difficulty and type of the problem, and the content of the learning method or improvement direction may also change based on the problem source code and solution source code accumulated and stored in the database.

[0140] In other words, this is because if the difficulty level of the problem is 'low,' even if it is determined that there is a high similarity between the indicators required to solve the problem—such as learning methods or improvements—and the indicators possessed by the user, it does not mean that the absolute numerical value of the user's learning indicators is high.

[0141] Accordingly, when the difficulty level is 'low' and there is a high similarity between the indicators required to solve the problem and the indicators possessed by the user, it may be suggested to maintain the current status since the user satisfies all indicators of 'basic skills, memorization ability, application ability, cognitive ability, and learning ability'; however, when the difficulty level is 'high' and there is a low similarity between the indicators required to solve the problem and the indicators possessed by the user, it may be suggested to the user to build basic skills and then solve a number of memorization and application problems, as all indicators of 'basic skills, memorization ability, application ability, cognitive ability, and learning ability' are low.

[0142] In other words, the engine server and the user cannot determine the user's overall learning indicators regarding learning methods or directions for improvement based on a single problem; however, the engine server will be able to determine the user's overall learning indicators based on multiple problem contents and solutions to provide guidance on learning methods or directions for improvement.

[0143] Meanwhile, the indicator analysis department can analyze the indicators that the user needs to improve based on the user's basic skills based on the user's solution structure, the user's memorization ability based on the user's solution structure, the user's application ability based on the user's solution structure, the user's cognitive ability based on the user's solution structure, and the user's learning ability based on the user's solution structure using the following [Mathematical Formula 5].

[0144] [Mathematical Formula 5]

[0145]

[0146] Here, can refer to the user's basic skills based on the user's solution structure, and can refer to the user's memorization ability based on the user's solution configuration, and can refer to the user's application ability based on the user's solution configuration, and can refer to the user's cognitive ability based on the user's solution construction, and can refer to the user's learning ability based on the user's solution configuration, and Depending on the calculated value, it may refer to a reference value for analyzing the indicators that the user needs to raise.

[0147] step, , , , and can represent each user's metric as a numerical value, and if each metric is the lowest, it can be assigned '1', and if each metric is the highest, it can be assigned '10'.

[0148] for example, is 10, is 9, is 8, is 8, In the case where it is 7, It can be calculated as 11.81, and is 5, is 4, is 3, is 5, In the case of 5, It can be calculated as 6.84.

[0149] The output The higher the calculated value of , the more content regarding learning methods and improvement directions that can raise indicators of the user's application ability can be provided to the user, and the calculated The smaller the value of , the more information regarding learning methods and improvement directions that can raise the indicator of the user's basic skills can be provided to the user.

[0150] Among the two examples described above, since the first example yields a larger value than the second example, it is possible to provide the user with information on learning methods and improvement directions that can raise the indicators of the user's application ability.

[0151] Meanwhile, regarding providing users with content on learning methods and improvement directions that can raise indicators of their application ability, memorization skills, or basic proficiency, clarity The standard for the value of can be set by the engine server administrator.

[0152] For example, regarding providing users with content on learning methods and improvement directions that can raise indicators of their application ability. Regarding setting the standard for the value to '11 or higher' and providing users with learning methods and improvement directions that can boost their memorization ability metrics Regarding setting the standard value to '6-10' and providing users with learning methods and improvement directions to raise indicators of their basic skills The threshold for the value of can be set to 'less than 5'.

[0153] When the criteria for analyzing the metrics that the user needs to improve are set to provide content regarding learning methods and improvement directions to enhance application ability, memorization skills, and basic skills according to each section, the resulting Depending on the range in which the value of is included, the engine server can provide the user with information on learning methods and improvement directions to enhance application ability, memorization ability, and basic skills.

[0154] As described above, the calculated Based on the fact that the learning methods and improvement directions provided by the engine server to the user are applied differently for each section according to the value of , in the case of the first example described above, the engine server can provide the user with learning methods and improvement directions that can raise the indicators of the user's application ability.

[0155] In addition, in the case of the second example, the engine server can provide the user with information on learning methods and improvement directions that can boost the user's memorization ability metrics.

[0156] However, regarding providing users with content on learning methods and improvement directions that can raise indicators of their application capabilities Setting the standard for the value of each interval is just one example, and the standard can be changed by the engine server administrator.

[0157] The Learning Suggestion Department can suggest learning methods or directions for improvement based on the user's indicators analyzed by the Indicator Analysis Department, as well as the user's interests or future aspirations.

[0158] In addition, the learning suggestion unit can generate a learning model from problem source code and solution source code accumulated and stored in the database to perform deep learning, and based on the content learned through deep learning, it can analyze the solution steps and solution structure required to solve the problem source code input by the user, and if the solution steps and solution structure required to solve the problem content are insufficient based on the solution steps and solution structure from the solution process input by the user, it can suggest a learning method or direction for improvement to raise the relevant indicator by presenting the insufficient solution steps and solution structure to the user as a basis.

[0159] In addition, the Learning Suggestion Department may suggest learning methods or directions for improvement to raise indicators that are low among the user's overall learning indicators analyzed by the Indicator Analysis Department, but need to be raised for the user's interests or future aspirations.

[0160] Meanwhile, the learning suggestion department can extract the solution steps and solution configurations that are lacking for the user by using [Mathematical Formula 6] below, based on the solution steps required to solve the problem, the number of solution configurations required to solve the problem, the solution steps written by the user to solve the problem, and the number of solution configurations written by the user to solve the problem.

[0161] [Mathematical Formula 6]

[0162]

[0163] Here, can refer to the solution steps required to solve the problem, and can mean the number of solution configurations required to solve the problem, and may refer to the solution steps written by the user to solve the problem, and may mean the number of solution configurations written by the user to solve the problem, and may refer to a criterion value for extracting the solution steps and solution configurations that are lacking for the user.

[0164] step, and can be assigned a non-zero value and ' and ' If ' is 0 or 1, the corresponding mathematical expression is not calculated, and the user's solution steps and solution structure can be determined to be appropriate.

[0165] Also, the solution step It can be verified and quantified at each step based on the number of equal signs; for example, if the number of equal signs used in the solution to the problem is 5 can be substituted with 5.

[0166] for example, is 3, is 5, is 2, In the case of 4, It can be calculated as -0.39, and is 7, is 10, is 8, In the case where it is 13, It can be calculated as 0.317.

[0167] The output The larger the value of , the more the user's solution steps and solution configuration are judged to have been used more than the steps and configuration required to solve the problem, so the probability of extracting the solution steps and solution configurations lacking for that user may decrease.

[0168] Conversely, the produced The smaller the value of is calculated, the more likely it is that the user's solution steps and solution configurations are used less than the steps and configurations required to solve the problem, and thus the probability of extracting the insufficient solution steps and solution configurations for that user may increase.

[0169] Here, extracting the solution steps and solution structures that are lacking for the user may be an act of extraction intended to be added to content that provides the user with learning methods and directions for improvement.

[0170] Among the two examples described above, since the first example yields a smaller value than the second example, the probability of extracting solution steps and solution configurations that are lacking for the user may increase.

[0171] Conversely, as the second example yields a larger value than the first example, the probability of extracting solution steps and solution configurations that are lacking for that user may decrease.

[0172] Meanwhile, regarding the engine server extracting the missing solution steps and solution configurations for the user, a clear The standard for the value of can be set by the engine server administrator.

[0173] For example, regarding extracting the missing solution steps and solution configurations for the corresponding user registered on the engine server If the standard for the value is set to '0', If this value is greater than '0', the insufficient solution steps and solution configurations for that user may not be extracted.

[0174] Regarding extracting insufficient solution steps and solution configurations from the user registered on the server According to the example where the value standard is set to '0', in the case of the first example among the two examples described above, the solution steps and solution configuration that are lacking for the user can be extracted.

[0175] Conversely, regarding extracting the missing solution steps and solution configurations for the corresponding user registered on the server According to the example where the value standard is set to '0', in the case of the second example among the two examples described above, the solution steps and solution configurations that are insufficient for the user may not be extracted.

[0176] However, regarding extracting insufficient solution steps and solution configurations for the corresponding user registered on the server Setting the standard value to '0' is just one example, and the standard can be changed by the engine server administrator.

[0178] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without changing its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. Explanation of the symbols

[0180] 1: Personalized Job-Related Competency Enhancement Recommendation System 100: Control Server 200: Mobile terminal

Claims

Claim 1 A mobile terminal; and a control server that collects personal competency information from a learner through the mobile terminal, analyzes the personal competency information, and recommends job training programs and job competency enhancement plans according to the job classification system of the job competency standards; wherein the control server includes: a personal competency information collection unit that collects personal competency information including age, gender, career, workplace, job, and major, and obtains individual survey information including interest keywords and scores for job competency tests by job according to the personal competency information; and a job suitability recommendation unit that analyzes the personal competency information, classifies jobs according to the job classification system of the job competency standards, extracts competency units of the job competency standards according to the job classification of the job competency standards, extracts educational programs for learning the competencies required for the competency units of the job competency standards from an external site, and provides the extracted educational programs to the mobile terminal. ...and includes an artificial intelligence neural network for extracting a classification map of job competency standards extending from major categories to medium categories to minor categories to detailed categories to competency units from individual competency information and individual survey information, inputs individual competency information and individual survey information into the artificial intelligence neural network, outputs a classification map of job competency standards as the output of the artificial intelligence neural network, and provides the output classification map of job competency standards to the mobile terminal as an individual job competency enhancement plan; wherein the individual competency information collection unit calculates an individual job diagnosis score using the following mathematical formula 1, sorts all learners by job diagnosis score according to any one of the same age, career, workplace, job, and major categories, and provides the rank at which the learner is located according to the job diagnosis score, [Mathematical Formula 1] (S in mathematical formula 1 J is J's job assessment score, N is the total number of learners, Q n is the number of interest keywords of learner n, Q J represents the number of interest keywords of learner J, and S i is the score for the job competency test. Here, the score for the job competency test is calculated out of 100 points.) The above job suitability recommendation unit verifies whether each learner has taken job training, calculates an achievement score based on the completion of job training, and [Mathematical Formula 2] (S in mathematical formula 2 E is the achievement score, s is the number of required competencies corresponding to the NCS competency unit, N is the number of job training programs, n is the number of job training programs taken, L is the level assigned to the NCS competency unit, P n (It is calculated as 0 if the n-th job training program is passed, and 1 otherwise.) The above job competency enhancement recommendation unit calculates a map evaluation score by evaluating the extracted NCS classification map, and [Equation 3]* (S in mathematical formula 3 M is the NCS Roadmap evaluation score, Lm is the average of the levels assigned to the NCS competency units included in the NCS Roadmap, m is the number of NCS competency units included in the NCS Roadmap, and s m is the basic roadmap evaluation score, k n is the number of job-related keywords included in the nth NCS competency unit, p n ... refers to the number of keywords corresponding to the keywords of interest entered by the learner among the job-related keywords included in the n-th NCS competency unit.) The above control server includes an engine server, and the above engine server includes an alpha extraction unit, a beta extraction unit, a database, an indicator analysis unit, and a learning suggestion unit; the above alpha extraction unit receives the problem content being studied by the user through a user terminal and extracts alpha, which is an indicator necessary to solve the problem content; the above beta extraction unit receives the solution process in which the user solved the problem content being studied through the user terminal and extracts beta, which is an indicator of the user's basic skills, memorization ability, application ability, cognitive ability, and learning ability; the above beta extraction unit extracts beta based on the solution steps and solution structure from the solution process; the above database converts the problem content received from the above alpha extraction unit into problem source code and the solution process received from the above beta extraction unit into solution source code, classifies and cumulatively stores the converted problem source code and solution source code by each user; and the above indicator analysis unit [retrieves] the problem source code and solution cumulatively stored in the above database classified by user Based on the source code, the alpha indicator extracted by the alpha extraction unit, and the beta indicator extracted by the beta extraction unit, the overall learning indicator of each user is analyzed; the indicator analysis unit analyzes the overall learning indicator of the user according to the similarity between the indicator required to solve the problem content extracted by the alpha extraction unit and the indicator possessed by the user extracted by the beta extraction unit; the indicator analysis unit includes the basic skill indicator required to solve the relevant problem content extracted by the alpha extraction unit, the memorization ability indicator required to solve the relevant problem content extracted by the alpha extraction unit, the application ability indicator required to solve the relevant problem content extracted by the alpha extraction unit, the cognitive ability indicator required to solve the relevant problem content extracted by the alpha extraction unit, and the learning ability indicator required to solve the relevant problem content extracted by the alpha extraction unit.A personalized job-related competency enhancement recommendation system that determines the similarity between the indicators required to solve the relevant problem and the indicators possessed by the user based on the values ​​calculated using [Mathematical Formula 4] below, based on the basic skill indicators possessed by the user based on the solution steps and solution configurations extracted by the beta extraction unit, the memorization ability indicators possessed by the user based on the solution steps and solution configurations extracted by the beta extraction unit, the application ability indicators possessed by the user based on the solution steps and solution configurations extracted by the beta extraction unit, the cognitive ability indicators possessed by the user based on the solution steps and solution configurations extracted by the beta extraction unit, and the learning ability indicators possessed by the user based on the solution steps and solution configurations extracted by the beta extraction unit. [Mathematical Formula 4] (from mathematical formula 4 represents the basic skill indicator required to solve the corresponding problem content extracted by the alpha extraction unit, and represents the memorization ability index required to solve the corresponding problem content extracted by the alpha extraction unit, and represents the application ability indicator required to solve the corresponding problem content extracted by the alpha extraction unit, and represents the cognitive ability indicator required to solve the corresponding problem content extracted by the alpha extraction unit, and represents the learning ability indicator required to solve the corresponding problem content extracted by the alpha extraction unit, and represents the basic skill indicator possessed by the user based on the solution steps and solution composition extracted from the beta extraction unit, and represents the memorization ability index possessed by the user based on the solution steps and solution configuration extracted from the beta extraction unit, and represents an application capability indicator possessed by the user based on the solution steps and solution configuration extracted from the beta extraction unit, and represents an indicator of the user's cognitive ability based on the solution steps and solution configuration extracted from the beta extraction unit, and represents the learning ability indicator possessed by the user based on the solution steps and solution configuration extracted from the beta extraction unit, and refers to a value that serves as a criterion for judging the similarity between the indicators required to solve the problem and the indicators possessed by the user, based on the calculated value. Claim 2 delete Claim 3 delete

Images