KR102660170B1 - System for providing life long education service associating with public agency - Google Patents

Abstract

A system for providing lifelong education services linked to public institutions is provided, and includes a user terminal that outputs content of a subscribed curriculum among content according to at least one curriculum, a storage unit that uploads and stores content according to at least one curriculum, and a user When signing up from a terminal, an authentication unit that authenticates the curriculum subscribed to in the user terminal, and a granting unit that verifies the curriculum of the user terminal as a result of authentication and grants access to the content according to the subscribed curriculum to the user terminal. , and includes a lifelong education service providing server including an output unit that outputs the content of the subscribed curriculum from the user terminal.

Description

System for providing lifelong education services linked to public institutions{SYSTEM FOR PROVIDING LIFE LONG EDUCATION SERVICE ASSOCIATING WITH PUBLIC AGENCY}

The present invention relates to a system for providing lifelong education services linked to public institutions. It provides a system that can manage learning and education of various curricula, including statutory compulsory education, job improvement education, and safety and health education, in connection with public institutions.

Low birth rates, aging population, increased leisure due to economic growth, and the Industry 5.0 paradigm call for universal lifelong education that guarantees the right to lifelong learning for all citizens. As interest in lifelong education for adults increases with the development of the industry, it is necessary to reorganize the lifelong learning system into a lifelong learning system that guarantees the right to lifelong learning for all citizens and to prepare a plan to increase the budget according to business expansion. In the case of Korea, the lifelong education voucher project was first introduced in 2018 as part of an education welfare policy as the capabilities of adult learners fell below the OECD average and the educational gap due to economic disparity increased. It was used as a policy tool to expand learners' choices and promote competition in the lifelong learning market by allowing learners to choose lifelong learning services on their own and make purchases. The lifelong education voucher project is being promoted based on Article 16 of the Lifelong Education Act, expense assistance and support, and the Lifelong Education Act was revised in June 2021 to specify that lifelong education vouchers can be issued and used by the national or local government.

At this time, a method of curating statutory mandatory education or recommending job training contents was researched and developed. In this regard, the prior art, Korea Registered Patent No. 10-2520831 (announced on April 13, 2023) and Korea Open Patent No. In No. 2022-0147347 (released on November 3, 2022), information on the corporate status is received from companies in demand for statutory mandatory training, extracts statutory mandatory training that matches the received corporate status, and then curates educational content, Before recommending job training content, a configuration is disclosed that receives the probability of taking job training content for a plurality of classes as input, checks the user's probability of taking the course by class, and then recommends job training content with a high probability of taking the course.

However, in both the former and the latter cases, only a structure that recommends content suitable for companies and users is disclosed, and a method of managing essential or necessary education according to various countries, institutions, companies, and individuals is not disclosed. Lifelong education includes not only legally compulsory education, but also various categories of curricula, such as education that the unemployed or employed must learn or need, disaster safety education for disaster safety, and job competency improvement education to acquire or improve job competency. Accordingly, research and development of an LMS (Learning Management System) platform that can provide content according to various curriculums and manage learning and education in connection with each institution is required.

One embodiment of the present invention provides content according to various training courses in connection with each public institution, and when a user participates in each training course on a user terminal, the user has the right to access the content of the training course according to the certified qualification after authenticating the qualification. It provides an LMS (Learning Management System) platform that can manage learning and education by providing learning support to learners, teaching support to instructors, and various modules and menus for operational support to administrators. A lifelong education service provision system linked to public institutions can be provided. However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention includes a user terminal that outputs content of a subscribed curriculum among content according to at least one curriculum, and content according to at least one curriculum. A storage unit that receives and stores uploads, an authentication unit that authenticates the curriculum subscribed to in the user terminal when signing up from the user terminal, and the user terminal confirms the curriculum of the user terminal as a result of authentication and provides information on content according to the subscribed curriculum. It includes a lifelong education service providing server that includes a granting unit that grants access rights and an output unit that outputs the content of the subscribed curriculum from the user terminal.

According to one of the above-described means of solving the problem of the present invention, content according to various educational courses is provided in connection with each public institution, and when the user participates in each educational course on the user terminal, qualifications are certified, and then education according to the certified qualifications is provided. An LMS (Learning Management System) platform that manages learning and education by granting access to course content, providing learning support to learners, teaching support to instructors, and various modules and menus for operational support to administrators. can be provided.

Figure 1 is a diagram for explaining a system for providing lifelong education services linked to public institutions according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a lifelong education service providing server included in the system of FIG. 1.
Figures 3 and 4 are diagrams for explaining an embodiment in which a lifelong education service linked to a public institution is implemented according to an embodiment of the present invention.
Figure 5 is an operation flowchart for explaining a method of providing lifelong education services linked to public institutions according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts unrelated to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this means that it does not exclude other components, but may further include other components, unless specifically stated to the contrary, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms “about,” “substantially,” and the like used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a diagram for explaining a system for providing lifelong education services linked to public institutions according to an embodiment of the present invention. Referring to FIG. 1, the public institution-linked lifelong education service provision system 1 includes at least one user terminal 100, a lifelong education service provision server 300, at least one professor terminal 400, and at least one administrator. It may include a terminal 500. However, since the public institution-linked lifelong education service provision system 1 shown in FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one user terminal 100 may be connected to the lifelong education service providing server 300 through the network 200. In addition, the lifelong education service providing server 300 may be connected to at least one user terminal 100, at least one professor terminal 400, and at least one administrator terminal 500 through the network 200. Additionally, at least one professor terminal 400 may be connected to the lifelong education service providing server 300 through the network 200. In addition, at least one administrator terminal 500 may be connected to at least one user terminal 100, a lifelong education service providing server 300, and at least one professor terminal 400 through the network 200.

Here, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN) and a wide area network (WAN). Wide Area Network, Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), 5G New Radio (NR), 6th Generation of Cellular Networks (6G), and Long Term Evolution (LTE). , WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network) ), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc., but are not limited thereto.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

At least one user terminal 100 authenticates qualifications for completing a curriculum using a web page, app page, program, or application related to a public institution-linked lifelong education service, and provides content of the curriculum according to the certified qualifications. Access rights are granted and printed, after registering for a course, the course history of the content is provided, questions are extracted and printed from the question bank for test evaluation, assignments are uploaded and the results are printed, and curriculum counseling is provided. It may be a user's terminal.

Here, at least one user terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), 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), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

The lifelong education service provision server 300 may be a server that provides a public institution-linked lifelong education service web page, app page, program, or application. In addition, the lifelong education service providing server 300 uploads content according to each curriculum, manages course registration and academic schedule of the user terminal 100, and manages the user terminal 100 and professor at the administrator terminal 500. It may be a server that manages the terminal 400. Here, the lifelong education service providing server 300 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

At least one professor terminal 400 may be a terminal of an instructor who uses a web page, app page, program, or application related to a public institution-linked lifelong education service. The professor terminal 400 may be a terminal that opens a curriculum, manages a classroom, and conducts test evaluations.

Here, at least one professor terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one professor terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one professor terminal 400 is, for example, a wireless communication device that ensures portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), 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), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

At least one administrator terminal 500 manages curriculum and subjects, performs learning operation and course management, and monitors users and instructors using web pages, app pages, programs, or applications related to lifelong education services linked to public institutions. It may be the terminal of the manager who manages it.

Here, at least one manager terminal 500 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one manager terminal 500 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one manager terminal 500 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), 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), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

Figure 2 is a block diagram for explaining the lifelong education service providing server included in the system of Figure 1, and Figures 3 and 4 are an embodiment of a lifelong education service linked to a public institution according to an embodiment of the present invention. This is a drawing to explain.

Referring to FIG. 2, the lifelong education service providing server 300 includes a storage unit 310, an authentication unit 320, an granting unit 330, an output unit 340, a classification unit 350, and an LMS unit 360. ), learning support department (370), teaching support department (380), operation support department (390), and access management department (391).

The lifelong education service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one user terminal 100, at least one professor terminal 400, and at least one administrator When transmitting a public institution-linked lifelong education service application, program, app page, web page, etc. to the terminal 500, at least one user terminal 100, at least one professor terminal 400, and at least one administrator terminal ( 500) can install or open lifelong education service applications, programs, app pages, web pages, etc. linked to public institutions. Additionally, a service program may be run on at least one user terminal 100, at least one professor terminal 400, and at least one administrator terminal 500 using a script executed in a web browser. Here, a web browser is a program that allows the use of web (WWW: World Wide Web) services and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Chrome. , Microsoft Edge, Safari, FireFox, Whale, UC Browser, etc. Additionally, an application refers to an application on a terminal and includes, for example, an app running on a mobile terminal (smartphone).

Referring to FIG. 2, the storage unit 310 can upload and store content according to at least one curriculum. Content according to an embodiment of the present invention may include, for example, a tomorrow learning course, a voucher course, and a general course as shown in Figure 4a, and as shown in Figure 4g, the general course includes a mixed training course, a legally mandatory training course, and a job. It can be divided into improvement education courses, etc. In addition, content can be classified into various categories. Accordingly, categories may be subdivided, deleted, added, or changed depending on the embodiment, so they are not limited to those listed and are not excluded for reasons not listed.

The authentication unit 320 may authenticate the curriculum subscribed to in the user terminal 100 when signing up in the user terminal 100 . For example, the Tomorrow Learning course and the voucher course have different support organizations and different application qualifications, as shown in Figures 4c to 4f. Accordingly, when applying for the Tomorrow Learning course or voucher course on the user terminal 100, it is necessary to apply in advance to each public institution, apply, and then prove that you have been selected or selected. At this time, since it is necessary to pay for the Tomorrow Learning course or voucher course with a Tomorrow Learning card or voucher card, information on whether payment can be made with each card and, if so, what kind of curriculum can be taken must be mapped. For example, it can be mapped as [curriculum-educational content]. Of course, when registering for a course, you can only take the subjects you have registered for, so it can be mapped and stored as [curriculum - educational content - course registration subject], and only access rights to it can be granted.

The granting unit 330 may confirm the curriculum of the user terminal 100 as a result of authentication and grant access to the user terminal 100 for content according to the subscribed curriculum.

The output unit 340 can output the content of the curriculum subscribed to in the user terminal 100. The user terminal 100 may output content of a subscribed curriculum among content according to at least one curriculum.

The classification unit 350 is a tomorrow's learning course to improve workers' job skills, a voucher course taken with a lifelong education voucher, a job improvement course that provides content necessary for the job course, and a court that provides content on matters stipulated by law. Categories of compulsory education courses can be provided. Of course, as described above, the classification is not limited to this, and categories may be changed, added, or deleted depending on the embodiment.

The LMS unit 360 provides learning support to the user terminal 100, professor support to the terminal of the professor in charge of lectures according to the curriculum, and operational support to support operation according to the curriculum through LMS (Learning Management System). can do. At this time, learning support can be provided as shown in Figures 3b and 3c, teaching support as shown in Figure 3d, and operational support as shown in Figure 3e.

The learning support unit 370 may provide a curriculum learning module, a test evaluation module, a task evaluation module, and a curriculum counseling module to support learning of the user terminal 100. To summarize, it can be as shown in Table 1 below.

Learning support Curriculum learning module -Check subject learning process contents
-View list of learning courses, detailed information on subjects, and preview courses
-Course registration course selection and attendance
-Take classes by accessing cyber classrooms and actual learning content
-Check class attendance history for each user Test evaluation module -Performance of tests presented in the question bank system Assignment evaluation module - Determine student level through task performance
-After completing the assignment, check the professor's correction guidance on the results Subject counseling module - Accumulated in the form of a bulletin board to answer questions related to students’ course learning contents
-Provide notification function for responses to inquiries through bulletin board or email

At this time, an intelligent learning analysis platform can be provided. The intelligent learning analysis platform collects the learner's learning activity data and analyzes and predicts the learner's level, providing instructors and learners with analysis information on learning progress and optimal customized prescription data. It is an intelligent learning system that ultimately leads to improved academic achievement of learners. At this time, an additional intelligent tutoring agent platform can be provided, with the goal of utilizing an agent that can manage and evolve the ecosystem of learners and intellectuals for the learning space. For this purpose, it can be broadly divided into a core agent and an assistant agent. The core agent is a component part of the agent for user-learning-intellectuals, including User Experience Agent (UXA), User Profile Agent (UPA), Smart Study Agent (STA), and Smart Tutor Agent. It can be classified as (Smart Tutor Agent, STA). And it can be designed as a Tag Analysis Agent (TAA) and a Knowledge Map Agent (KMA) to cooperate with smart learning agents.

In one embodiment of the present invention, it can be designed to provide a next-generation e-learning environment that enables collective intelligence-based learners and intellectuals to communicate socially based on a platform and supports the role of an intelligent tutor for learners. This applies the Scenario-Based Design technique to analyze the learning patterns of group learners, pheromones that follow the traces of other fellow learners, and a study caravan defined according to the characteristics specified by the learner. ), can include the concept of an explicitly formed study team (Team), breaking away from anonymity. UPA stores and manages user input or learning pattern processes through a learning process recognition module, and can cooperate with SSA using algorithms such as statistics, data mining, and analysis. In addition, STAs act as tutors by analyzing learners' activities, participation, sharing, and communication, or provide knowledge information as team leaders. When individuals cooperate or compete with each other in groups, and when intelligence or behaviors that did not exist suddenly appear, the power of collective intelligence becomes even greater. Therefore, through analysis of various user data extracted from UPA, user learning patterns are distinguished in the learning process recognition module, and natural pheromones are formed. For example, from the user's perspective, even if there is a strategy I want to learn, or in a situation where I do not know anything at all, the agent can not only provide information about fellow users who have the most similar learning pattern, learning purpose, and learning direction, but also provide new knowledge. Learning, participation, and sharing become possible in real time.

By using an intelligent user interface based on user experience, learners can share learning knowledge information between their own learning environment and fellow learners and utilize it dynamically. Learners can check detailed analysis of what path other learners are learning through or what content they are using, and check pheromones and caravans related to learning. Through this agent concept, it is possible to provide a platform to share, open, and participate in knowledge between intellectuals and learners, and to provide a structure to create, manage, and distribute new knowledge, and to provide data generated from users. and information can be automatically analyzed and designed to intelligently respond to learning situations. Additionally, a cooperative learning ecosystem can be formed between tutors and tutees within the platform ecosystem.

<False registration detected>

In the case of taking a course just for completion, most people use bots to remove pop-ups that appear in the middle and provide the same effect as listening in person to make it look like the course has been completed. To prevent this, if any bots or macros are running, block them and operate the front camera of the user terminal 100 to take pictures to determine whether the user is present when content is played at a preset period or randomly. You can. If the photos are taken at a pre-set interval but the user does not meet the pre-set percentage, this can be viewed as illegal course attendance and no certificate of completion can be set to be issued. If the user blocks the front camera for security reasons, it is determined whether the location of the user terminal 100, such as a smartphone, in addition to the user terminal 100, such as a laptop where educational content is currently played, is close to the laptop. Thus, it is possible to determine whether the user is in the vicinity where educational content is currently being played. Even at this time, the user may lie down on the bed and use the smartphone or sleep with the laptop running. Therefore, if no keystrokes, such as hitting the keyboard or activating KakaoTalk, occur on the laptop, it is determined that the user is not present. And it can be treated as an illegal course.

The professor support department 380 can provide a course creation module, a classroom management module, and an exam evaluation module to support professors on professor terminals. This can be summarized as Table 2 below.

Professor support Course opening module - Establishment of course operation plan: Course classification registration management
- Establishment of lecture plan: Registration of course syllabus, progress information, etc.
- Establishment of evaluation plan: Establishment of evaluation criteria for offered courses Classroom management module - Check the learning status of the subject in charge: Provide curriculum, course opening, and bulletin board status
-Learning material management: Provides video content upload interface, registers learning materials Test evaluation module -Student management: Provide status inquiry screen for each student, student progress management, activity inquiry
-Assignment management: Assignment assignment, inquiry and score of submitted assignments, assignment feedback
-Test management: test submission, grade inquiry, evaluation result feedback
- Curriculum counseling: Responding to curriculum counseling inquiries from students in charge

At this time, similar questions are often posted repeatedly on professor bulletin boards or inquiry bulletin boards. There are many cases where students are unable to find the same answer because they have trouble finding the posted bulletin board posts or because students have different focuses. In these cases, to prevent repeated questions and answers, a search engine that expands the query language is provided, or the same question is expressed differently. In this case, an answer can be provided through natural language processing and natural language interpretation to provide the same answer. For this purpose, generative GPT may be used or a large language model may be used.

<Query extension>

Query word expansion can expand nouns and noun phrases into similar words/synonyms using the word embedding model. Since problems with word expansion accuracy occur when using a limited amount of training dataset, additional training can be performed on the pre-training model. Additional learning performs preprocessing tasks such as removing special characters from the learning corpus, and extracts nouns and noun phrases using the OKT morpheme analyzer that supports noun phrase extraction. At this time, all results of the extracted noun phrases are learned. Noun phrases are learned by connecting each word with a separator to recognize it as a single word in the word embedding model. Using the model learned in this way, expansion is performed on the nouns and noun phrases separated from the user query. The extended query word multiplies this by Cartesian to create a query and perform a search. Dataset search results can return a list of datasets and a dataset similarity score. Next, ranking is required. Data sets are ranked to provide highly relevant data first. For this purpose, a log learning model can be created using the dataset logs selected for the queries searched by headhunters. This is used because previously selected datasets have a higher probability of being reselected than other datasets. Therefore, the similarity score from the keyword search result and the score provided by the log learning model are used to assign a ranking and sort them in descending order. The log learning model learns based on logs for the dataset clicked on among the query results. To create the model, the input query and the clicked data set are embedded using the document embedding model, and a negative sampling technique is used to embed N random data sets among the non-clicked data sets in the same way and convert them to 1 and 0. Label and learn the stored data. The result of this model refers to the click probability of the data set. Of course, the query language can be expanded in a variety of ways other than those described above, and even if the user, a headhunter, is in a specialized field and does not know various synonyms or synonyms, the query language can be expanded automatically using the headhunting domain-specific library or dictionary described above. And you can get accurate search results even if you do not enter the exact keyword.

<Automatic grading of assignments>

Even if artificial intelligence (AI) is introduced, in areas such as road driving, aircraft piloting, medical care, and law enforcement, where the role of humans (experts) is difficult to completely exclude, collaboration between humans and machines or human capabilities by machines was early on. System development research based on the premise of collaboration with machines has been actively conducted using augmentation as a basic model. The area of academic discourse that deals with this is cognitive engineering. Cognitive engineering is based on the research results of cognitive science and engineering design approaches, and is designed to design systems to assist human decision-making and methods of interaction between humans and machines. This is the field of applied research that we want to design. The design process of an automatic system according to this cognitive engineering design approach is generally: first, to identify the cognitive load factors experienced by practitioners in the relevant field while performing tasks, and second, to design a system that can assist based on this and quickly. After implementation, it can be summarized as a series of processes to improve the system through repeated verification.

Accordingly, in one embodiment of the present invention, it is a step to design an argumentative writing grading performance model based on a collaborative grading situation between human graders such as instructors, lecturers, and teachers who grade assignments, and machine graders. Assuming a collaborative grading situation between machine graders, it is possible to propose a tentative plan for a collaborative grading performance model, including what role the machine grader should play in order to reduce the cognitive load of teacher graders in the grading process. The second step is to verify this. Accordingly, based on the model, we use deep learning-based natural language processing techniques to implement an automatic scoring function and develop an automatic scoring program. In the third step, the effectiveness of the scoring program can be verified by analyzing the results of the collaborative evaluation.

The operation support unit 390 may provide a curriculum management module, a learning operation module, a course management module, and a user management module to support the operation of the administrator terminal.

Operational support Curriculum management module -Course management: Classification and registration management by course area, registration of basic information
-Subject management: Information registration management for detailed subjects, content and textbook management Classroom management module -Learning information management: Advance information and registration management for learning
-Learner information management: status inquiry, course approval/change/cancellation
-Course progress management: View and manage course progress
-Statistics and report management: Grades, statistics management
-Mail management; Sending learner encouragement emails
-Bulletin board management: Notices, data room, 1:1 inquiry management User management module
-Professor management: Professor basic information and authority management
-Student management: View and manage student personal information
-Operator management: Operator basic information and rating management

In addition to the above-mentioned functions, in order to increase the effectiveness of education and training even in non-face-to-face situations, content should be developed similar to actual situations and learning activities should be designed to achieve learning goals. Additionally, excellence in the quality of the education and training system that supports various learning activities is required. Accordingly, it is possible to set an LMS evaluation index that supports non-face-to-face education by considering the key elements of non-face-to-face education, evaluate the LMS according to an embodiment of the present invention according to the set LMS evaluation index, and use the above-mentioned functions or menus. In addition, additional functions or menus to be added can be recommended. Also, the LMS can be an open source-based LMS, a service-type LMS, or a commercial LMS. Here, the open source-based LMS may use, for example, Moodle, which has an active development community and provides Korean language translation and customization services. A conversion module linking databases between information systems is supported, as well as learner tracking, chat, dialog, forum, glossary, journal, and quiz. Supports survey and report functions. Although it is an open source-based LMS that has a larger user base overseas than domestically, it is evaluated as excellent for supporting Korean and being easy to install. In Korea, many elementary, middle, high, and lifelong education institutions have adopted and used it. You can also use Google Classroom, a service-based LMS, or edwith operated by Naver, NHN. edwith (www.edwith.org) is a MOOC platform developed with the purpose of providing a new educational model and platform to lead educational innovation, and provides free courses by famous domestic professors focusing on the software field. Employees at schools and educational institutions can open courses and operate learning content directly within the platform, and can also access it through the edwith mobile app. It fully includes LMS functions such as student management, learning material management, various evaluations and grading, and live broadcasting. Of course, it is obvious that in addition to the above-described program, the LMS according to an embodiment of the present invention can be used or developed and installed directly.

Additionally, in order to find search results for announcements more quickly and easily, the search engine is provided as ElasticSearch and additional customization services can be provided. For example, the educational institution portal site according to an embodiment of the present invention is a website where notices for members within the lifelong education center are uploaded, for example, work notices, student notices, academic notices, and completion notices. There are various bulletin boards for notices, entrance exam notices, etc., and faculty and staff select the appropriate bulletin board and write notices in the form of posts. The educational institution portal provides a search engine for postings. For example, when users, including students, find a posting they are looking for, they can use the search function to find the posting without having to manually search for the desired posting on the bulletin board. .

Educational institution portal posts have characteristics that differentiate them from the target documents of general search engines, and these characteristics make it difficult for search engines to provide users with the results they want in response to their queries. Main characteristics include that there are almost no hyperlinks between posts, many posts contain only images such as posters without text, and there are many notices about repeated events or academic calendars. Additionally, it uses formal vocabulary that users do not use on a daily basis. Accordingly, one embodiment of the present invention can provide customization that customizes Elasticsearch according to the characteristics of educational institution portal posts to design a search engine specialized for educational institution portal posts.

Looking at the search process of a general search engine, a search engine consists of ① Document Collecting, ② Text Processing, ③ Indexing, ④ Query Processing, ⑤ Searching, ⑥ Ranking is carried out in six stages. A web crawler is used in the document collection stage. This is the process where a search engine collects documents that will be returned as results for a query and stores them in a database. In the text processing stage, tokenization, normalization, and stopword elimination are performed. Plain text text is normalized through morpheme analysis (Stemming) and transformed into a list of tokens. For example, the sentence [Create a list of graduates] is a list such as [Complete-noun], [Of-Particle], [List-Noun], [Eul-Particle], [Write-Verb] It is transformed. Additionally, tokens that do not affect the content of the text are removed through stopword removal. In the index creation stage, an index is created so that documents can be accessed quickly and documents are stored based on this index. The most commonly used technique is Inverted Index. Through an inverted index, the search engine creates a mapping from a word to a document containing the word and stores it. By creating an index, the search engine can quickly find documents containing the word you are looking for, so it can quickly process queries sent by users.

Users using search engines send queries to the search engine through the user interface provided by the search engine. The most popular user interface is the web-based graphic user interface. Portal sites such as Google and Naver are examples. In the query processing stage, the query sent by the user is processed so that it is easy to use in the search stage. Similar to document processing in the text processing stage, tokenization and normalization are performed through morphological analysis. Additionally, synonym analysis is performed to process synonyms. For example, if a search engine knows that the synonym for the word [job competency] is [job skill], the search engine will query not only documents containing the word [job competency] but also the word [job skill]. The query is processed to also find documents containing .

In the search step, documents related to a given query are searched from the index. When using inverted indexing technology, you can easily find documents containing the tokens included in the query because the list of documents containing the word is already mapped for each word. If the query includes multiple tokens, several strategies can be considered for selecting documents. The simplest way is to select only documents that contain all tokens. In this case, the likelihood of not including documents related to the query (relevant) in the search results increases, lowering reliability (recall), but the likelihood of including irrelevant documents decreases, thereby increasing precision. Conversely, there are also strategies that include documents in search results even if they contain only one token. In this case, it is advantageous for reliability but disadvantageous for accuracy. Generally, a strategy is used that compromises the two strategies and selects documents containing a certain percentage of tokens or more.

In the ranking stage, the documents found in the finding stage are sorted in order of high relevance to the query. When there are many documents related to a query, showing the most relevant documents first has a great impact on user experience, so the ranking step is important in creating a high-quality search engine. Algorithms used to determine rankings can be broadly divided into two types. The first is Link Analysis, which analyzes the number and importance of hyperlinks between documents. More important documents are ranked based on the assumption that they will receive more hyperlinks from other important documents. For example, the PageRank algorithm can be used. The second is text analysis, which analyzes the number and location of words included in the text. For example, TF-IDF (word frequency-inverse document frequency) can be used.

<Educational institution portal search engine>

In one embodiment of the present invention, the search engine's post processing, query processing, and ranking can be customized by reflecting the characteristics of educational institution portal posts. In the post processing stage, the essential content of the post is not only tokenized and normalized, but also the letters of the image included in the post are extracted using a letter recognition library. Through this process, the search engine can correctly process cases where key words are not included in the text but only in the image. The morpheme analyzer for tokenization and normalization can be used because Elasticsearch provides English and Korean analyzers by default, and other open source Korean analyzers can be used as needed. In addition, since educational institution portal posts have metadata such as author, creation date, and number of views, these metadata are also extracted.

In the query processing stage, synonym processing is performed. Elasticsearch automatically processes the query when a list of synonyms is provided, so that not only documents containing tokens included in the original query but also documents containing synonyms are included in the search results. However, because educational institution portal posts use words that are different from general Korean synonyms, there are limitations in using the existing Korean synonym database. Therefore, it is necessary to create a synonym list suitable for educational institution portal posts. To create a synonym list, you need to analyze users' behavioral trends. For example, if a user searches for the word A and then searches again for the word B without selecting any search results, it can be assumed that A and B are likely to have a synonymous relationship. If you collect a lot of data like this, you can automatically create a list of synonyms for educational institution portal posts.

In the ranking stage, you can basically use the TF-IDF algorithm provided by Elasticsearch, and in addition, you can improve the ranking results by using metadata extracted during the article processing process. For example, the more views it has and the more recent the creation date, the higher the ranking. A high number of views means that the post is wanted by many users, so there is a high probability that users will be satisfied when it is provided as a search result. In addition, the fact that the creation date is recent means that it is a notice about a recent event among repetitive events, so it is highly likely that the post is what the user wants. This allows you to customize the search engine. At this time, if spacing is applied, the spacing can be adjusted so that it is not recognized as a different word, and in the case of information individually scattered across multiple sites, classification can be performed by collecting and integrating all posts from each site. In addition, as a result of the user's navigation, for example, when looking for class information, if it cannot be found on the main page and must go through several steps, the search box on the main page will be opened to reduce the path length until the user finds the desired information. You can set it so that you can immediately find the page with the desired results. Of course, it is obvious that various search engines can be used in addition to the above-mentioned search engines. In addition, it is obvious that the above-mentioned search engine can be set to be used in various search windows other than announcements.

The access management unit 391 stores content according to at least one curriculum in the cloud platform, and when authentication is performed on the user terminal 100, determines and stores accessible content in the cloud platform according to the authentication result, Access rights to content accessible from the user terminal 100 may be granted.

Figures 3a to 3f show the structure of an LMS according to an embodiment of the present invention, which is currently implemented as shown in Figures 4a to 4n. Since the web pages of FIGS. 4A to 4N are under development, they are not limited to these menus, structures, site maps, etc.

Matters that are not explained about the method of providing lifelong education services linked to public institutions in Figures 2 to 4 are the same as those explained in relation to the method of providing lifelong education services linked to public institutions through Figure 1, or can be easily explained from the explained contents. Since inference is possible, the description below will be omitted.

Figure 5 is a diagram showing a process in which data is transmitted and received between each component included in the public institution-linked lifelong education service provision system of Figure 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described with reference to FIG. 5, but the present application is not limited to this embodiment, and the process shown in FIG. 5 according to the various embodiments described above It is obvious to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to FIG. 5, the lifelong education service providing server uploads and stores content according to at least one curriculum (S5100), and authenticates the curriculum subscribed to by the user terminal when signing up at the user terminal (S5200).

In addition, the lifelong education service providing server confirms the curriculum of the user terminal as a result of authentication, grants access to the user terminal for content according to the subscribed curriculum (S5300), and provides access to the curriculum subscribed to the user terminal. The contents of are output (S5400).

The sequence between the above-described steps (S5100 to S5400) is only an example and is not limited thereto. That is, the order between the above-described steps (S5100 to S5400) may change, and some of the steps may be executed simultaneously or deleted.

Matters that are not explained about the method of providing lifelong education services linked to public institutions in Figure 5 are the same as or can be easily explained from the contents explained about the method of providing lifelong education services linked to public institutions through Figures 1 to 4. Since inference is possible, the description below will be omitted.

The method of providing lifelong education services linked to public institutions according to an embodiment described in Figure 5 can also be implemented in the form of a recording medium containing instructions executable by a computer, such as an application or program module executed by a computer. there is. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The method of providing lifelong education services linked to public institutions according to an embodiment of the present invention described above can be executed by an application installed by default on a terminal (this may include programs included in a platform or operating system, etc., installed by default on the terminal). It may be executed by an application (i.e., a program) that the user installs directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method of providing lifelong education services linked to public institutions according to an embodiment of the present invention described above is implemented as an application (i.e., program) installed by default in the terminal or directly installed by the user and readable by a computer such as in the terminal. It can be recorded on any recording medium that can be recorded.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as single may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (7)

A user terminal that outputs content of a subscribed curriculum among content according to at least one curriculum; and
A storage unit for uploading and storing content according to at least one curriculum, an authentication unit for authenticating the curriculum subscribed to by the user terminal when signing up from the user terminal, and confirming the curriculum of the user terminal as a result of the authentication. and a lifelong education service providing server including a granting unit that grants access rights to the user terminal to content according to the subscribed curriculum, and an output unit that outputs the content of the subscribed curriculum from the user terminal;
The lifelong education service provision server is,
Provides categories of tomorrow's learning courses to improve workers' job skills, voucher courses taken with lifelong education vouchers, job improvement courses that provide content necessary for job courses, and statutory mandatory training courses that provide content on matters stipulated by law. a classification unit that does;
An LMS unit that provides learning support as the user terminal, professor support as the professor's terminal in charge of lectures according to the curriculum, and operational support to support operation according to the curriculum through an LMS (Learning Management System);
In order to support learning on the user terminal, the learner's learning activity data is collected using the curriculum learning module, test evaluation module, task evaluation module, and curriculum consultation module, and the learner's level is analyzed and predicted to provide instructor and learner analysis of the learning progress. A learning support department that provides an intelligent learning analysis platform that provides information and customized prescription materials and an intelligent tutoring agent platform that utilizes agents to manage learners and intellectuals for the learning space;
A professor support department that provides a course creation module, a classroom management module, and an exam evaluation module to support professors using the professor terminal;
To support the operation of the administrator terminal, an operation support department that provides a curriculum management module, learning operation module, course management module, and user management module;
Store content according to the at least one curriculum on a cloud platform, and when authentication is performed on the user terminal, determine and store accessible content within the cloud platform according to the authentication result, and content accessible on the user terminal. It further includes an access management unit that grants access rights to,
The faculty support department said,
Query language expansion that provides answers through natural language processing and natural language interpretation to provide the same answer when the same question is expressed differently on the inquiry bulletin board for consulting subjects by expanding nouns and noun phrases into similar words/synonyms using a word embedding model. , perform a preprocessing task to remove special characters from the learning corpus, and use the OKT morpheme analyzer that supports noun phrase extraction to connect each word with a separator to recognize it as a single word in the noun and word embedding model to create the learned noun phrase. Extract, learn further, and Cartesian multiply the expanded query to create and search queries, and rank the dataset to provide highly relevant data first in the dataset search results that return the dataset list and dataset similarity score. In order to assign a ranking, a log learning model is created using the dataset log selected for the queries searched by headhunters, and a ranking is assigned using the similarity score from the keyword search result and the score provided by the log learning model to sort in descending order. , In order to create a log learning model based on the log of the clicked dataset among the query results, the input query and the clicked dataset are embedded using a document embedding model, and a negative sampling technique is used to embed the unclicked data. Among the three, N random numbers are embedded in the same way, labeled as 1 and 0, and the saved data is learned. The result value is set as the click probability of the relevant dataset, and the query is expanded on the query board.
The operation support department said,
A conversion module that sets LMS evaluation indicators that support non-face-to-face education, evaluates the LMS according to the set LMS evaluation indicators, and provides a search engine as ElasticSearch to link databases between information systems. Supports learner tracking, chat, dialog, forum, glossary, journal, and quizzes. It provides survey and report functions, and search results for announcements, but Elasticsearch uses ① document collecting through a web crawler, ② tokenization, and plain text text. Normalize each morpheme through morphological analysis (Stemming), and stopword elimination to remove tokens that do not affect the content of the text. Text processing step; ③ Create an index on the documents ④ Query processing step where tokenization and normalization are performed through morphological analysis and synonyms are analyzed for synonym processing; ⑤ Finding documents related to the query from the index ( Searching stage, ⑥ Analyze the number and importance of hyperlinks between documents through link analysis of the documents found in the finding stage, and use the TF-IDF algorithm provided by Elasticsearch, but at the text processing stage. By using the extracted metadata to improve the ranking results and proceed through six stages of ranking to sort the query in order of relevance, customization is provided according to the characteristics of the educational institution portal posts. A public institution-linked lifelong education service provision system characterized by the following.

delete delete delete delete delete delete

Images