KR102231392B1 - Electronic device for providing recommended education content using big data and machine learning model and method for operating thereof - Google Patents

Abstract

According to an embodiment of the present application, a server (100) may be a server which provides an interface for diagnosing various types of characteristics of a learner, and provides customized educational content to the learner based on diagnosed various types of characteristics. The server (100) may provide the interface for diagnosing the learners with an electronic device using the server (100), and may accumulate diagnostic information about the learner received from the electronic device based on the provided interface. In addition, the server (100) may acquire information on various types of educational content provided in a market through an external server (300). Accordingly, it is possible to provide more appropriate educational content to the learner by reconfiguring recommended educational content according to earner′s feedback information.

Description

Electronic device for providing recommended educational content using big data and machine learning model and its operation method {ELECTRONIC DEVICE FOR PROVIDING RECOMMENDED EDUCATION CONTENT USING BIG DATA AND MACHINE LEARNING MODEL AND METHOD FOR OPERATING THEREOF}

The present application is an electronic device for acquiring various diagnostic information about a learner, and providing recommended educational content corresponding to various diagnostic information obtained by using big data and a machine learning model generated based on it to learners, and an operating method thereof It is about.

A questionnaire to test learners' characteristics has been used to diagnose characteristics such as learners' creativity and potential. For example, the diagnostic method includes an intelligence index test (IQ), an emotional index test (EQ), an aptitude test, and a creativity test.

However, all conventional diagnosis methods are performed as a one-time method at the time of diagnosis (e.g., one-time diagnosis using a questionnaire, etc.), and it is difficult to expect to perform in-depth diagnosis on various characteristics of learners from conventional diagnosis methods. . In addition, conventional diagnosis methods are only simple diagnosis and do not perform customized education recommendations for learners based on diagnosis results.

As a theory raised by the social psychologist Jeff Howard in the late '60s is the theory of effort based intelligence. The basic premise of this theory is, "When you try, you get smart." Based on the above theory, it is a technology that creates an educational environment that conducts several diagnoses over a long period of time for various characteristics of learners, and enables learners to make efforts to become smarter education based on the performance of the diagnosis. This is the time when implementation is required.

Korean Patent Application Publication No. 10-2017-0076274 (2017.07.04.) Korean Patent Application Publication No. 10-2018-0038847 (2018.04.17.) Korean Patent Publication No. 10-2128043 (2020.06.29.) Korean Registered Patent Publication No. 10-1905390 (2018.10.08.)

According to an embodiment of the present application, one task is an electronic device that generates a machine learning model for providing recommended educational content, and recommends educational content to learners based on the generated machine learning model and diagnostic information diagnosed for the learner. And to provide a method of operation.

According to an embodiment of the present application, another task is experiential learning more suitable for the second diagnosis based on the data analyzed during the first diagnosis and the period during which the second diagnosis is performed when the learner selects experiential learning for the second diagnosis. It is to provide an electronic device and an operation method that provides an interface for a secondary diagnosis by selecting.

According to an embodiment of the present application, another task is to provide an electronic device and an operating method that provides more appropriate educational content to learners by reconstructing recommended educational content according to the learner's feedback information.

The problem to be solved by the present application is not limited to the above-described problems, and the problems that are not mentioned will be clearly understood by those of ordinary skill in the technical field to which the present application belongs from the present specification and the accompanying drawings. .

According to an embodiment of the present application, a method of operating a server, comprising: receiving a plurality of educational content from an external server, wherein the plurality of educational content is for education sold or distributed by a plurality of companies. Including content, generating a machine learning model by using a plurality of diagnostic information analysis data for a plurality of learners accumulated in the server and a plurality of educational content as training data; Including, the plurality of diagnosis The information analysis data includes values for a plurality of first characteristics, a plurality of second characteristics, and a plurality of third characteristics of the learner, and the machine learning model is at least when diagnostic information analysis data for the learner is input. Identifying a connection of an electronic device associated with a first learner to the server, configured to output one educational content; A first interface for diagnosing the plurality of first characteristics for the first learner is provided to the connected electronic device, and a first value for the plurality of first characteristics is determined based on the provision of the first interface. Acquiring the first diagnostic information analysis data to be included; After the acquisition of the first diagnosis information analysis data, a plurality of second interfaces are provided for diagnosis of the plurality of second characteristics for a first learner, and the plurality of second interfaces are provided based on the provision of the plurality of second interfaces. Acquiring second diagnostic information analysis data including a second value for the second characteristic; Including, each of the plurality of second interfaces is each of a plurality of experiential learning for analyzing the plurality of second characteristics In response to the third diagnostic information analysis data provided to the electronic device and including third values for the plurality of third characteristics based on the first diagnosis information analysis data and the second diagnosis information analysis data, Obtaining; And inputting the first diagnosis information analysis data, the second diagnosis information analysis data, and the third diagnosis information analysis data into the machine learning model, and at least one recommended to the first learner among the plurality of education contents. An operation method including, acquiring educational content and providing the obtained at least one educational content to the electronic device may be provided.

According to an embodiment of the present application, there is provided a server, comprising: a database storing a plurality of diagnostic information analysis data for a plurality of learners; Communication circuit; And at least one processor; wherein the at least one processor: receives a plurality of educational content from an external server using the communication circuit, and the plurality of educational content is sold or distributed by a plurality of companies. Includes content for education, and generates a machine learning model by using a plurality of diagnostic information analysis data for the plurality of learners and a plurality of education content as training data, and the plurality of diagnostic information analysis data are provided to the learner. Values for a plurality of first characteristics, a plurality of second characteristics, and a plurality of third characteristics are included, and the machine learning model outputs at least one educational content when diagnostic information analysis data for the learner is input. And identifying a connection of an electronic device associated with a first learner to the server, and for diagnosing the plurality of first characteristics for the first learner with the connected electronic device using the communication circuit 1 interface is provided, and first diagnostic information analysis data including first values for the plurality of first characteristics is obtained based on the provision of the first interface, and the first diagnostic information is obtained by using the communication circuit. After acquisition of the analysis data, a plurality of second interfaces for diagnosing the plurality of second characteristics for a first learner are provided, and a second interface for the plurality of second characteristics is provided based on the provision of the plurality of second interfaces. Obtaining second diagnostic information analysis data including 2 values, each of the plurality of second interfaces is provided to the electronic device corresponding to each of a plurality of experiential learning for analyzing the plurality of second characteristics, Acquiring third diagnostic information analysis data including third values for the plurality of third characteristics, based on the first diagnosis information analysis data and the second diagnosis information analysis data, and the first diagnosis information analysis data , The second diagnosis information analysis data, and the third diagnosis information analysis data By inputting into the machine learning model, obtaining at least one educational content recommended to the first learner from among the plurality of educational contents, and providing the at least one educational content obtained using the communication circuit to the electronic device A server, configured to be configured, may be provided.

The solution means of the problem is not limited to the above-described solution means, and solutions that are not mentioned will be clearly understood by those of ordinary skill in the art from the present specification and the accompanying drawings. .

According to an embodiment of the present application, an electronic device and a method of operation generate a machine learning model for providing recommended educational content, and recommend educational content to learners based on the generated machine learning model and diagnostic information diagnosed for the learner. I can.

According to an exemplary embodiment of the present application, the electronic device and the operation method further perform the second diagnosis based on the data analyzed during the first diagnosis and the period during which the second diagnosis is performed when the learner selects experiential learning for the second diagnosis. An electronic device and an operation method that provide an interface for secondary diagnosis by selecting an appropriate experiential learning may be provided.

According to the exemplary embodiment of the present application, the electronic device and the operation method may provide an electronic device and an operation method that provides more appropriate education content to a learner by reconstructing recommended education content according to a learner's feedback information.

According to various embodiments, effects are not limited to the above-described effects, and effects not mentioned will be clearly understood by those of ordinary skill in the art from the present specification and the accompanying drawings. .

1 is a diagram illustrating an example of devices included in a smart education system according to an embodiment of the present application.
2 is a block diagram illustrating an example of a server and an electronic device according to an embodiment of the present application.
3 is a diagram illustrating an example of an operation of generating a machine-learning model for providing recommended educational content of a server according to an embodiment of the present application.
4 is a diagram illustrating an example of a generated machine learning model according to an embodiment of the present application.
5 is a flowchart illustrating an example of an operation of a smart education system according to an embodiment of the present application.
6 is a diagram for explaining an example of an operation of acquiring primary diagnosis information of a server and analyzing primary diagnosis information according to an embodiment of the present application.
7 is a diagram for describing an example of an operation of acquiring secondary diagnosis information of a server and analyzing secondary diagnosis information according to an embodiment of the present application.
8 is a diagram for explaining an example of an operation of analyzing tertiary diagnosis information of a server according to an embodiment of the present application.
9 is a diagram for describing an example of an operation of providing information on recommended educational content to an electronic device of a server according to an embodiment of the present application.
10 is a flowchart illustrating another example of the operation of the smart education system according to an embodiment of the present application.
11 is a diagram for explaining an example of an operation of selecting an experience activity for secondary diagnosis of a server according to an embodiment of the present application.
12 is a view for explaining an example of an operation of combining experience activities when selecting an experience activity for secondary diagnosis by a server according to an embodiment of the present application.
13 is a flowchart illustrating another example of the operation of the smart education system according to an embodiment of the present application.
14 is a diagram for explaining an example of an operation of re-recommending educational content of a smart education system according to an embodiment of the present application.

According to an embodiment of the present application, a method of operating a server, comprising: receiving a plurality of educational content from an external server, wherein the plurality of educational content is for education sold or distributed by a plurality of companies. Including content, generating a machine learning model by using a plurality of diagnostic information analysis data for a plurality of learners accumulated in the server and a plurality of educational content as training data; Including, the plurality of diagnosis The information analysis data includes values for a plurality of first characteristics, a plurality of second characteristics, and a plurality of third characteristics of the learner, and the machine learning model is at least when diagnostic information analysis data for the learner is input. Identifying a connection of an electronic device associated with a first learner to the server, configured to output one educational content; A first interface for diagnosing the plurality of first characteristics for the first learner is provided to the connected electronic device, and a first value for the plurality of first characteristics is determined based on the provision of the first interface. Acquiring the first diagnostic information analysis data to be included; After the acquisition of the first diagnosis information analysis data, a plurality of second interfaces are provided for diagnosis of the plurality of second characteristics for a first learner, and the plurality of second interfaces are provided based on the provision of the plurality of second interfaces. Acquiring second diagnostic information analysis data including a second value for the second characteristic; Including, each of the plurality of second interfaces is each of a plurality of experiential learning for analyzing the plurality of second characteristics In response to the third diagnostic information analysis data provided to the electronic device and including third values for the plurality of third characteristics based on the first diagnosis information analysis data and the second diagnosis information analysis data, Obtaining; And inputting the first diagnosis information analysis data, the second diagnosis information analysis data, and the third diagnosis information analysis data into the machine learning model, and at least one recommended to the first learner among the plurality of education contents. An operation method including, acquiring educational content and providing the obtained at least one educational content to the electronic device may be provided.

According to an embodiment of the present application, the information based on the diagnosis of the first characteristic includes information on creativity for each area, information on language ability, and information on creative thinking ability, and information on creativity for each area Includes information on fluency, flexibility, sophistication, originality, and imagination, and the information on creative thinking ability includes information on attention/observation, associative/shaping, categorization ability, analogy/reasoning ability, and integrated thinking ability. In addition, the information based on the diagnosis of the second characteristic includes information on a strength area/security area and information on a creative problem-solving ability and self-esteem, and an operation method may be provided.

According to an embodiment of the present application, the first interface includes an interface for receiving a questionnaire and an answer for diagnosis of the first characteristic, and the plurality of second interfaces are to be filled out of the plurality of experience activities. An operation method including at least one of information on checklists or information on questionnaires may be provided.

According to an embodiment of the present application, pre-storing a plurality of first experience activities for diagnosis of the second characteristic; Identifying values representing the first characteristics from the first diagnostic information analysis data, and identifying a specified number of characteristics from a highest value in descending order based on the identification; Selecting a plurality of experiential activities of the specified number corresponding to the identified characteristics of the specified number of the plurality of first experiential activities; And generating and providing the second interface including at least one of information on checklists to be filled out of the selected plurality of experience activities or information on questionnaires; further comprising, an operation method to be provided. I can.

According to an embodiment of the present application, the steps of obtaining personal information on the first learner and setting a period in which the second diagnosis will be performed based on the obtained personal information; And identifying the specified number based on the set period of the plurality of pre-stored first experiential activities, and sequentially selecting a plurality of experiential activities as many as the specified number; including, an operation method to be provided. I can.

According to an embodiment of the present application, the step of identifying the specified number based on the set period among the plurality of pre-stored first experience activities, and sequentially selecting a plurality of experience activities as many as the specified number includes: Selecting a first experience activity having a highest priority; When the first experiential activity is selected, identifying a first rest period associated with the first experiential activity based on a duration or difficulty of the first experiential activity; Selecting a second experience activity to be performed after the first pause period, and identifying a second pause period associated with the second experience activity based on a required period or difficulty level of the second experience activity; An operation method may be provided, further comprising: stopping the operation of selecting the plurality of experience activities when the period in which the experience activity can be performed based on the second pause period is less than a preset threshold period.

According to an embodiment of the present application, the threshold period is set based on the personal information of the first learner, and the threshold period is set to decrease as the age of the first learner increases, and an operation method may be provided. have.

According to an exemplary embodiment of the present application, the method includes: identifying a degree of similarity between the selected plurality of experiential activities; And combining at least two or more experiential activities having a similarity greater than or equal to a preset value among the selected plurality of experiential activities.

According to an embodiment of the present application, the method includes: receiving feedback information on the provided at least one educational data from the electronic device; And reconstructing the at least one educational data based on the feedback information.

According to an embodiment of the present application, there is provided a server, comprising: a database storing a plurality of diagnostic information analysis data for a plurality of learners; Communication circuit; And at least one processor; wherein the at least one processor: receives a plurality of educational content from an external server using the communication circuit, and the plurality of educational content is sold or distributed by a plurality of companies. Includes content for education, and generates a machine learning model by using a plurality of diagnostic information analysis data for the plurality of learners and a plurality of education content as training data, and the plurality of diagnostic information analysis data are provided to the learner. Values for a plurality of first characteristics, a plurality of second characteristics, and a plurality of third characteristics are included, and the machine learning model outputs at least one educational content when diagnostic information analysis data for the learner is input. And identifying a connection of an electronic device associated with a first learner to the server, and for diagnosing the plurality of first characteristics for the first learner with the connected electronic device using the communication circuit 1 interface is provided, and first diagnostic information analysis data including first values for the plurality of first characteristics is obtained based on the provision of the first interface, and the first diagnostic information is obtained by using the communication circuit. After acquisition of the analysis data, a plurality of second interfaces for diagnosing the plurality of second characteristics for a first learner are provided, and a second interface for the plurality of second characteristics is provided based on the provision of the plurality of second interfaces. Obtaining second diagnostic information analysis data including 2 values, each of the plurality of second interfaces is provided to the electronic device corresponding to each of a plurality of experiential learning for analyzing the plurality of second characteristics, Acquiring third diagnostic information analysis data including third values for the plurality of third characteristics, based on the first diagnosis information analysis data and the second diagnosis information analysis data, and the first diagnosis information analysis data , The second diagnosis information analysis data, and the third diagnosis information analysis data By inputting into the machine learning model, obtaining at least one educational content recommended to the first learner from among the plurality of educational contents, and providing the at least one educational content obtained using the communication circuit to the electronic device A server, configured to be configured, may be provided.

The embodiments described in this specification are for clarifying the idea according to various embodiments to those of ordinary skill in the technical field to which the present application belongs, and thus the present application is limited by the embodiments described in the present specification. No, according to various embodiments, the scope should be construed as including modifications or variations without departing from the spirit according to various embodiments.

The terms used in this specification have been selected as general terms that are currently widely used in consideration of functions in the present application, but this varies depending on the intention, custom, or the emergence of new technologies of those with ordinary knowledge in the technical field to which the present application belongs. I can. However, if a specific term is defined and used in an arbitrary meaning unlike this, the meaning of the term will be separately described. Therefore, the terms used in the present specification should be interpreted based on the actual meaning of the term and the entire contents of the present specification, not a simple name of the term.

The drawings attached to the present specification are for easy explanation of the present application, and the shapes shown in the drawings may be exaggerated and displayed as necessary to aid understanding, according to various embodiments, so that the present application is limited by the drawings. It is not.

In the present specification, when it is determined that a detailed description of a well-known configuration or function related to the present application may obscure the subject matter according to various embodiments, a detailed description thereof will be omitted as necessary.

1. Smart education system based on big data and machine learning models

Hereinafter, a smart education system according to an embodiment of the present application will be described.

In the present specification, the smart education system may be defined as a system that provides educational content based on big data and machine learning models accumulated according to diagnosis over a long period of time for learners.

In this specification, the smart education system diagnoses various characteristics of learners (eg, children) (eg, creativity by area, language creativity, strength area, complementary area, etc.) over a long period of time several times, and evaluates the diagnosis result. Can provide. The smart education system accumulates information on various types of educational content provided on the market. Based on the accumulated diagnostic data on learners and information on educational content, a machine learning model for recommending educational content may be generated. When diagnostic data for a new learner is acquired, the smart education system may recommend educational content for a new learner using a machine learning model.

Hereinafter, the smart education system will be described in more detail.

2. Composition of Smart Education System

1 is a diagram illustrating an example of devices included in a smart education system according to an embodiment of the present application.

Referring to FIG. 1, the smart education system may include a server 100, an electronic device 200, and an external server 300.

According to an embodiment of the present application, the server 100 provides an interface for diagnosing various types of characteristics (eg, creativity by area, language creativity, strength area, complementary area, etc.) of learners (eg, children). And, it may be a server that provides customized educational content to learners based on the diagnosed various types of characteristics. The server 100 provides an interface (eg, a screen including a questionnaire) for diagnosing learners with an electronic device (eg, 200) using the server 100, and based on the provided interface (eg, conducting a questionnaire), Diagnosis information (eg, questionnaire answers) on learners received from the device (eg, 200) may be accumulated. In addition, the server 100 may obtain information on educational content of various types (eg, textbooks, experiences, videos, teaching aids, etc.) provided on the market (or sold/distributed) through the external server 300. have. As a result, the server 100 may generate a machine learning model for recommending educational content using information on the acquired educational content and accumulated diagnostic information. The server 100 may provide recommended educational content corresponding to diagnosis information of a specific learner based on the generated machine learning model. A specific learner may use the provided recommended education content through the server 100 or request the server 100 to pay for the recommended education content and receive the recommended education content. In addition, the server 100 may provide accumulated data (eg, diagnostic information on learners, information on educational content, machine learning model) to another server for collaboration.

According to an embodiment of the present application, the electronic device 200 is capable of communicating with the server 100, and various types of electronic devices available to a user (for example, a learner (for example, children) or an educator (for example, a teacher)) (201, 202, 203) may be included. The electronic device may include personal terminals (eg, smart phone 201, etc.), electronic devices provided in a fixed location (eg, PC 202, etc.), and a movable personal notebook 203. . For example, the electronic device 200 may be an electronic device used by a learner or an educator to conduct a questionnaire on a learner. The electronic device 200 may authenticate with the server 100 information associated with the electronic device 200 (or user data associated with the user of the electronic device 200) when accessing the server 100. have. The electronic device 200 may access the server 100 under the control of the user, and provide an interface for a questionnaire provided from the server 100 to the user (eg, displayed on a display). A user (eg, a learner or educator) may fill in an answer to a questionnaire on the interface, and the answer to the entered questionnaire may be transmitted to the server 100.

According to the exemplary embodiment of the present application, the external server 300 may provide information on various types of educational content to the server 100. For example, the external server 300 may be a server operated by a third-party that conducts an education-related business. The educational content may include textbooks, experiences, videos, teaching aids, etc. provided, distributed, and/or sold by various companies.

Meanwhile, the advertisement system is not limited to the devices included in the smart education system illustrated in FIG. 1, and the advertisement system may be implemented to include more devices or fewer devices.

2.1. An example of configurations of the server 100 and the electronic device 200

Hereinafter, an example of configurations for performing the operation of the server 100 and the electronic device 200 will be described. In the case of the configuration of the external server 300, since it may be implemented as the configuration of the server 100 or the electronic device 200, a redundant description will be omitted.

2 is a block diagram illustrating an example of the server 100 and the electronic device 200 according to an embodiment of the present application. Meanwhile, the present invention is not limited to that shown in FIG. 2, and the server 100 and the electronic device 200 may include fewer or more components than the illustrated components. For example, the electronic device 200 further includes at least one component (eg, an interface providing module 121) included in the server 100 to be described later, and provides an interface based on information provided from the server 100. It may be implemented to perform an operation of configuring. Hereinafter, FIG. 2 will be further described with reference to FIGS. 3 to 4.

3 is a diagram for explaining an example of an operation of generating a machine-learning model for providing recommended educational content of the server 100 according to an embodiment of the present application. 4 is a diagram illustrating an example of a generated machine learning model according to an embodiment of the present application.

On the other hand, modules included in the first control circuit 120 of the server 100 described below (for example, the interface providing module 121, etc.), the first control circuit 120 performs an operation associated with the module. Can be controlled to do. In other words, the modules are implemented with a program for controlling to perform an operation associated with the module, computer-readable code, or instructions, and the modules are executed by the first control circuit 120 , It is possible to control the control circuit 120 to perform an operation related to the module.

2.1.1 An example of the configuration of the server 100

First, an example of the configuration of the server 100 will be described below.

2, according to an embodiment, the server 100 includes a first communication circuit 110, an interface providing module 121, an information acquisition module 122, an information analysis module 123, and an educational content recommendation module. A first control circuit 120 including 124 and a database 125 may be included.

The first communication circuit 120 may communicate with an external device. For example, the first communication circuit 120 is connected to a network through wireless communication or wired communication to establish communication with an external device (for example, the electronic device 200), and communicates with the electronic device 200 through the set communication. It is possible to receive related information (eg, user data and additional information) and transmit an interface for diagnosing characteristics of learners. The wireless communication is, for example, LTE, LTE-A (LTE Advance), CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), or GSM ( Global System for Mobile Communications) and the like may include cellular communication using at least one of. According to an embodiment, wireless communication is, for example, WiFi (wireless fidelity), Bluetooth, Bluetooth low power (BLE), Zigbee, near field communication (NFC), magnetic secure transmission, radio It may include at least one of a frequency (RF) and a body area network (BAN). According to one embodiment, wireless communication may include GNSS. The GNSS may be, for example, a Global Positioning System (GPS), a Global Navigation Satellite System (Glonass), a Beidou Navigation Satellite System (hereinafter "Beidou"), or Galileo, the European global satellite-based navigation system. Hereinafter, in this document, "GPS" may be used interchangeably with "GNSS". Wired communication may include at least one of, for example, universal serial bus (USB), high definition multimedia interface (HDMI), recommended standard 232 (RS-232), power line communication, or plain old telephone service (POTS). have. The network 162 may include at least one of a telecommunication network, for example, a computer network (eg, LAN or WAN), the Internet, or a telephone network.

The first control circuit 120 may control the overall operation of the server 100. To this end, the first control circuit 120 may perform calculation and processing of various types of information and control the operation of components of the server 100 (eg, the first communication circuit 110). The first control circuit 120 may be implemented as a computer or a similar device according to hardware, software, or a combination thereof. In terms of hardware, the first control circuit 120 may be provided in the form of an electronic circuit (eg, a CPU, etc.) that performs a control function by processing an electrical signal, and in software, the first control circuit ( 120) may be provided in the form of a program that drives. Meanwhile, in the following description, if there is no special mention, the operation of the server 100 may be interpreted as being performed by the control of the first control circuit 120.

The first control circuit 120 includes an interface providing module 121, and the interface providing module 121 is electronic devices (for example, 200) that are connected to the server 110. An interface for diagnosing various characteristics can be provided. The interface provided by the interface providing module 121 may include areas in which information for diagnosing characteristics of a learner can be written. The interface providing module 121 may provide various types of interfaces for each step of diagnosing a learner, which will be described later in detail with reference to FIGS. 6 to 7.

The first control circuit 101 includes an information acquisition module 122, and the information acquisition module 122 receives various types of information from the external server 300 and the electronic device 200 and receives a database ( 125) can be accumulated. For example, the information acquisition module 122 may acquire information on various types of educational content from the external server 300 and accumulate it in the database 125. In addition, the information acquisition module 122 may receive information such as an answer to a questionnaire through an interface provided to the electronic device 200 and allow the received information to be analyzed by the information acquisition module 123. The information acquisition module 122 may process (eg, pre-process) the collected information into a form for analysis.

The first control circuit 101 includes an information analysis module 123, and the information analysis module 123 is raw data for generating a machine learning model, which is obtained by the information acquisition module 122. Analyzing information about learners (e.g., diagnostic information) to obtain diagnostic information analysis data representing values for various types of characteristics (e.g. creativity by domain, linguistic creativity, creative thinking ability, strength areas, complementary areas, etc.) I can. As described above, the information analysis module 123 may acquire and analyze various types of diagnosis information based on various types of interfaces provided for each diagnosis step of a learner. When the diagnostic information obtained based on each of the different types of interfaces is analyzed, the analyzed diagnostic information data (eg, first diagnostic information analysis data and secondary diagnostic information analysis data) is the characteristics of different areas for the learner. Can represent a value for. This will be described in detail later in FIGS. 6 to 7. The information analysis module 123 may accumulate the analyzed diagnostic information data in the database 125.

The first control circuit 101 includes an educational content recommendation module 124, and the educational content recommendation module 124 is based on the accumulated educational content data and the accumulated diagnostic information analysis data as shown in FIG. A machine learning model 330 may be generated. The generated machine learning model 330 returns recommended training data in response to input of diagnostic information analysis data (eg, primary diagnosis information analysis data, secondary diagnosis information analysis data, and third diagnosis information analysis data). Can be implemented to As shown in FIG. 3, the educational content recommendation module 114 uses the educational content data accumulated in the database 125 from the information acquisition module 113 and the accumulated diagnostic information data as a training data set for machine learning model learning. It can be obtained with (training data set). The educational content recommendation module 114 uses each of the accumulated diagnostic information data as input data 301, 302, 303, and 304 to provide educational contents (first education content 311, second education content) corresponding to each. A machine learning model may be generated by performing training in a manner that weights the content 312. For example, the educational content recommendation module 124 extracts a value representing a first characteristic of a learner (eg, fluency among creativity) from the diagnostic analysis data, and the extracted first characteristic and first education data (eg: A weight for the first education data may be set based on a recommended value according to the degree of association by comparing the degree of relevance of Company A's A fairy tale book). For example, if the degree of correlation between the fluency and company A's storybook A is high, and the value of fluency extracted from the diagnostic analysis data is high, the weight for the storybook A of company A is set high, and the fluency extracted from the diagnostic analysis data is set higher. If the value for is low, the weight can be set low. The degree of association may be analyzed by various types of data analysis algorithms (eg, Nearest neighbor algorithm, etc.). For another example, the educational content recommendation module 124 extracts a value representing a second characteristic (eg, language creativity) for a learner from the diagnostic analysis data, and extracts the extracted second characteristic and the second education data (eg B A weight for the second education data may be set based on a recommended value according to the association degree by comparing the association degree of the company's soccer activity). For example, if the correlation between the language creativity and the soccer activity of Company B is low, and the value of the language creativity extracted from the diagnostic analysis data is high, the weight for the soccer activity of Company B is set low, and the extracted from the diagnostic analysis data If the value for language creativity is low, the weight can be set high. The operation of setting the weight higher or lower is only an example, and may be performed in reverse. According to the above-described learning operation, the generated machine learning model 330 includes characteristics diagnosed for the learner as shown in FIG. 4 (e.g., area-specific creativity, language creativity, creative thinking ability strength area, complementary area). Etc.) may include information on weights for educational contents. The machine learning model 330 generated accordingly is, as shown in FIG. 3, when the analyzed diagnostic information data (eg, first diagnostic information analysis data and secondary diagnostic information analysis data) is input (Input), In response to values for various types of characteristics included in the analyzed diagnostic information data (e.g., primary diagnostic information analysis data and secondary diagnostic information analysis data), weights are assigned to each educational content, and the educational content having the highest weight is selected. It can be recommended by outputting. Alternatively, it is not limited to what is described, and the machine learning model 330 may output a preset number of educational contents in descending order from the highest weight.

The database 125 may store various types of information (eg, educational content, diagnostic information analysis data, machine learning model, etc.). The database can store data temporarily or semi-permanently. For example, in the database 125 of the server 100, an operating program (OS: Operating System) for driving the server 100, data or programs or applications (eg, web applications) for hosting a web site Data related to, and the like may be stored. Examples of the database 125 include a hard disk (HDD), a solid state drive (SSD), a flash memory, a read-only memory (ROM), and a random access memory (RAM). There may be a back. Such a database may be provided as a built-in type or a detachable type.

2.1.2 An example of the configuration of the electronic device 200

Hereinafter, an example of the configuration of the electronic device 200 will be described.

Referring to FIG. 2, according to an embodiment, the electronic device 200 may include a second communication circuit 220, a second control circuit 210, an input device 230, and a display 240. .

The second communication circuit 210 may establish communication with external devices (eg, the server 100). The second communication circuit 220 establishes and connects with the server 100, receives information about the interface from the server 100, and sends the server 100 to learners (e.g., children) based on the interface. ) Can be transmitted. Since the second communication circuit 220 may be implemented like the first communication circuit 110 of the server 100 described above, a redundant description will be omitted.

The second control circuit 220 may control the overall operation of the electronic device 200. Since the second control circuit 220 may be implemented like the first control circuit 120 of the electronic device 200, redundant descriptions will be omitted.

The input device 230 may receive information (eg, diagnostic information in an information input window displayed on an interface) from a user. The input device 230 may be various interfaces or connection ports that receive user input or output information to the user. The input device 230 may be divided into an input module and an output module, and the input module receives a user input from a user. User input may be in various forms, including key input, touch input, and voice input. Examples of input modules that can receive such user input include a traditional keypad, keyboard, and mouse, as well as a touch sensor that detects a user's touch, a microphone that receives a voice signal, a camera that recognizes gestures through image recognition, Proximity sensor consisting of an illuminance sensor or infrared sensor that detects the user's approach, a motion sensor that recognizes the user's motion through an acceleration sensor or a gyro sensor, and various types of input means that detect or receive various types of user input It is a comprehensive concept that includes all of. Here, the touch sensor may be implemented as a piezoelectric or capacitive touch sensor that senses a touch through a touch panel or a touch film attached to the display panel, an optical touch sensor that senses a touch by an optical method, or the like. In this case, the input device 230 may be implemented in the display 240 to be described later to receive a user's touch input. In other words, the display 240 may include a touch screen as the input device 230, and receive, for example, a touch, gesture, proximity, or hovering input using an electronic pen or a part of the user's body. I can. In addition, the input device 230 may be implemented in the form of an input interface (USB port, PS/2 port, etc.) that connects an external input device that receives a user input instead of a device that detects a user input by itself.

The display 240 may include a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a microelectromechanical system (MEMS) display, or an electronic paper display. . The display 240 may display an interface including a window (eg, a questionnaire window) for receiving information from a user, an interface visually configuring recommended educational content, and the like.

3. Operation of the smart education system

Hereinafter, various examples of operations of devices (eg, the server 100, the electronic device 200, and the advertisement server 300) constituting the smart education system will be described.

3.1. First Embodiment <Operation of Providing Recommended Educational Content Based on Diagnosis for Each Stage>

According to an embodiment, when the electronic device 200 is connected to the server 100, the server 100 provides diagnostic information on characteristics of learners (eg, children) from the electronic device 200. Interface can be provided. In this case, the server 100 may provide different interfaces to the electronic device 200 for each stage (eg, primary or secondary) in which diagnosis is performed, and receive various types of diagnosis information based on this. The server 100 acquires values representing various types of characteristics associated with the learner from the received various types of diagnostic information, inputs the values into the machine learning model 330 to identify recommended educational content, and uses the electronic device 200. ) To be used by learners.

5 is a flowchart illustrating an example of an operation of a smart education system according to an embodiment of the present application. According to various embodiments, the operation of the smart education system is not limited to the order of operations illustrated in FIG. 5, and may be performed in a different order from the illustrated order. Further, according to various embodiments, more operations may be performed, or at least one operation less than that of the smart education system illustrated in FIG. 5 may be performed. Hereinafter, FIG. 5 will be described with reference to FIGS. 6 to 9.

6 is a view for explaining an example of an operation of acquiring primary diagnosis information of the server 100 and analyzing primary diagnosis information according to an embodiment of the present application. 7 is a diagram for explaining an example of an operation of acquiring secondary diagnosis information of the server 100 and analyzing secondary diagnosis information according to an embodiment of the present application. 8 is a diagram for explaining an example of an operation of analyzing tertiary diagnosis information of the server 100 according to an embodiment of the present application. 9 is a diagram illustrating an example of an operation of providing information on recommended educational content to the electronic device 200 of the server 100 according to an embodiment of the present application.

According to an embodiment, when the electronic device 200 is connected in operation 501, the server 100 may authenticate the electronic device 200 and perform a pre-test. For example, the electronic device 200 may access the server 100 with an address (eg, a web address) using a web application or a web program. The server 100 identifies the access of the electronic device 200, requests the provided electronic device 200 to provide authentication information (eg, ID and password), and receives information for authentication. By doing this, you can authenticate. The server 100 checks information on the authenticated electronic device 200, checks information on a diagnosis history performed by a learner (eg, children) associated with the electronic device 200, and performs a current diagnosis step of the learner. I can confirm. On the other hand, the server 100 determines whether to store the pre-test result data associated with the connected electronic device 200, and if it is not stored, a guardian and/or personality type test (MBTI), which is a neighbor of the learner, and a parenting and disposition test. By performing, it is possible to acquire and store pre-test data including personality type test result data and parenting and disposition test result data. The above personality type test is performed to compare the personality type of a neighbor (e.g., a parent or educator) with a learner's disposition to suggest a proper parenting method.Based on CGJung's psychological typology, Katharine Cook Briggs and Isabel Briggs Myers It is a test that is performed based on the self-report personality type index devised by For example, the type test asks for questions that ask about one's usual appearance (eg, "I like to speak, so I often make mistakes") and scores for it. In addition, the parenting and disposition test is a test to check the degree of understanding of learners' dispositions by neighbors (e.g., parents or educators), learning characteristics, motivation characteristics, creativity characteristics, leadership characteristics, communication characteristics, spatial and abstract thinking characteristics. It is a test that analyzes based on the total score by presenting 5 questions for each field and asking for a score for each problem, divided by adaptive ability. The pre-tests may be performed through the electronic device 100 connected to the server 200 or may be performed in writing and written to the server 200.

According to an embodiment, the electronic device 200 may transmit primary diagnosis information in operation 502. In other words, the server 100 may receive primary diagnosis information from the electronic device 200. For example, the server 100 (for example, the interface providing module 121) is an electronic device 200 connected to the server 100 as shown in FIG. An interface 610 for obtaining may be provided. The interface providing module 610 is information for diagnosing characteristics corresponding to the diagnosis step of "primary" based on the identification that the diagnosis step for the learner associated with the currently connected electronic device 200 is "primary" An interface 610 composed of items that can be inputted may be provided to the electronic device 200. The characteristics corresponding to the “primary” diagnosis stage are domain-specific (eg fluency, flexibility, sophistication, originality, imagination) creativity, language ability, and creative thinking ability (eg, attention/observation ability, association/imagination, categorization ability). , Analogy/reasoning skills, integrated thinking skills, etc.). The creativity test for each area is a test that measures creative factors such as fluency, flexibility, sophistication, originality, and imagination in a specific situation. Fluency is the ability to apply one's thoughts about a specific situation in various ways, and sophistication is It is the ability to make one's thoughts concrete and refine them to make new ones, originality is the ability to generate one's own thoughts novelly and novelly, and imagination is the ability to create new thoughts or ideas based on one's own thoughts. The linguistic ability test measures language comprehension ability including factual comprehension ability and reasoning comprehension ability, logical expression ability, and creative language expression. The creative thinking ability test measures the tendency to enable creative thinking ability such as attention/observation ability, association/shaping ability, categorization ability, analogy/reasoning ability, and integrated thinking ability based on the functions of the left and right brains. This is a measure of what kind of thinking skills a learner enjoys using in a specific situation, and the level of thinking is high in the order of attention/observation->association/shaping->categorization ability->inference/reasoning ability->integrative thinking ability (right) The higher the level, the higher).

According to various embodiments, the electronic device 200 may receive input from a user (eg, a learner) for questionnaires included in a provided interface and transmit response information to the questionnaires to the server 100. Alternatively, a user of the electronic device 200 (eg, an educator) outputs the interface provided to the electronic device 200 in a written form (eg, outputs to a printer), and provides the printed interface to the learners. Answer information to questionnaires may be transmitted to the server 100 by inputting handwritten information from a learner into the electronic device 200. The questionnaires included in the interface are questions such as pictures and/or text arrangements, and questions to be answered within the time limit for the question subject (eg, "What is the picture in the view?", "Tell me what comes to mind" , "Tell me why", etc.). The learner may write an answer to the questions included in the questionnaires, and the answer information may be provided to the server 100 through the electronic device 200. In addition, information on items (eg, checklists) that the educator has evaluated for the learner through the electronic device 200 is also transmitted to the server 100 together with the answer information to the questionnaire included in the primary diagnosis interface. I can.

According to an embodiment, the server 100 may process primary diagnostic information and perform data analysis in operation 503. According to an embodiment, the information acquisition module 122 of the server 100 may process response information to a received questionnaire into a form capable of analysis as shown in FIG. 6. The processing is pre-processing, conversion into data in a form that can be analyzed (e.g., converting text data into values), or converting an array of data for analysis (e.g., allocating processing into two-dimensional data). ) Can be included. Answer information to the processed questionnaire is defined as primary diagnosis information, and may be raw data for generating primary diagnosis information analysis data to be described later. Hereinafter, an analysis operation on the processed data of the server 100 will be described.

According to an embodiment, the information analysis module 123 of the server 100 analyzes various characteristics based on the processed primary diagnosis information received from the information acquisition module 122 as shown in FIG. 6. Creativity analysis by domain, language creativity analysis, and creative thinking utilization analysis) can be performed. As described above, the server 100 extracts information on the answer to the questionnaire from the primary diagnosis information, and based on the information for scoring previously stored, the server 100 Creativity, imagination) Can calculate multiple values representing creativity, language ability, and creative thinking ability (e.g. attention/observation ability, association/imagination, categorization ability, analogy/reasoning ability, integrated thinking ability, etc.). The information for scoring may include information on a correct answer for each question and a score assigned to a specific characteristic when the correct answer is answered. For example, the server 100 is based on the information for scoring that the answer to the first question is the first answer and the first score is assigned to a specific characteristic (eg, fluency), the server 100 is determined from the received primary diagnosis information. When extracting the first answer to 1 question, a first score can be given to the learner. In addition, the server 100 may proceed with scoring by subtracting a penalty score for the time limit. As a result, the server 100 may perform scoring based on the answers to each questionnaire extracted from the primary diagnosis information, and assign a score for each characteristic to identify values. In addition, the server 100 may generate comprehensive analysis information on learners based on the identified values. Information including values of scores for each characteristic and comprehensive analysis information on learners may be defined as primary diagnosis information analysis data. The server 100 may create an interface by visualizing the primary diagnosis information analysis data in a form that can be displayed on the electronic device 200 (eg, graphing scores), and an interface in which the first diagnosis information analysis data is visualized. May be provided to the electronic device 200.

According to an embodiment, the electronic device 200 may transmit secondary diagnosis information in operation 504. In other words, the server 100 may receive secondary diagnosis information from the electronic device 200. For example, after the server 100 generates primary diagnostic information analysis data and provides it to the electronic device 200, various characteristics (eg, strength area/security area, and creative problem-solving ability and self-esteem) for the learner. ), you can perform a secondary diagnosis to diagnose. The strength area and the security area are divided into 8 intelligence and 1 false area, as shown in Table 1 below, and the degree of development (eg, moderate, poor, excellent) and participation level (eg, active, conditional, and excellent) as a result of the test. Passive, intrusive) is evaluated. The creative problem-solving ability is a test that observes four areas: the ability to understand and interpret a problem, the ingenious ability to generate an idea for a problem, the ability to directly put it into action, and the degree of participation in the task. Evaluation of the areas is performed through actual observation. The self-esteem test is a comprehensive assessment of body image (consciousness of one's body, an important factor in ego formation), self-image (attitude toward me), empathy ability (emotional communication ability), communication ability, inner immersion, self-confidence, and human affinity. The self-esteem index evaluated by is tested.

According to an embodiment, the server 100 may designate a period and period in which the secondary diagnosis is performed for diagnosis of the various characteristics (eg, strength area/security area, and creative problem solving ability and self-esteem). In addition, the server 100 is a field-specific (language, mathematics, science, art, etc.)experience activity (e.g., drawing, theater, physical education) at a specified period (e.g., monthly) for the specified period (e.g., 3 months). , Molding/sculpture, etc.) can be selected. The selection of the experience activities may be selected based on information for each characteristic included in the first diagnosis information analysis data. This will be described later in the embodiments of FIGS. 10 to 12. The interface providing module 610 is information for diagnosing characteristics corresponding to the diagnosis step of "secondary" based on the identification that the diagnosis step for the learner associated with the currently connected electronic device 200 is "secondary" An interface 610 composed of items that can be inputted may be provided to the electronic device 200. For example, the interface providing module 121 of the server 100 may provide an interface including a checklist or a questionnaire for evaluating the various characteristics within the experience activity performed for each specified period, as shown in FIG. 6. Can provide. The interface including the checklist or questionnaire is automatically provided to the electronic device 100 of a user (eg, an educator) whenever an experience activity is performed on a periodic basis, and answer information is written on the interface during the experience activity, and the server 200 Can be provided as. Alternatively, the interface including the checklist, workbook, or questionnaire is printed in a written form by a user (e.g., an educator) and used for experience activities, and after the experience activity, the user organizes and answers through the electronic device 200 Information may be uploaded to the server 100. The questionnaires may be composed of questions for evaluating each characteristic within the experiential activity. For example, questionnaires may be composed of questions for identifying characteristics to be analyzed during the above-described secondary diagnosis, such as "present a lot of novel and unique ideas" and "perform in-depth thinking about things". Accordingly, the answer information may be transmitted to the server 200 whenever the experience activity is performed for each specified period during the specified period.

According to an embodiment, the server 100 may process secondary diagnostic information and analyze data in operation 505. According to an embodiment, the server 100 may process the answer information received from the secondary diagnosis into a form that can be analyzed, as shown in FIG. 7 as in the first diagnosis information. I can. The processed information may be defined as secondary diagnosis information. A redundant description of this will be omitted. Hereinafter, according to an embodiment, an analysis operation of the server 100 on secondary diagnosis information will be described.

According to an embodiment, the information analysis module 122 may analyze characteristics of the received secondary diagnosis information (strength/complementary area analysis, creative problem-solving ability and self-esteem analysis) as shown in FIG. 7. have. As described above, the information analysis module 122 extracts a checklist or answer to a questionnaire for analyzing various characteristics (e.g., strength area/security area, and creative problem solving ability and self-esteem) from the secondary diagnosis information. And, you can score the extracted answers. The scoring may be directly performed by an operator who operates the server 100, or, like the first diagnosis, a score for each characteristic of a learner may be calculated based on information for scoring previously stored. On the other hand, the server 100 is the most recent one in which an experience activity for answer information currently being scored is performed among a plurality of experience activities performed at a specified period, and an experience activity similar to the experience activity for answer information is 2 If it is performed more than once, the score calculated for the characteristic based on the answer information may be given a lower value. The degree of similarity for each of the experience activities is stored in advance, and the degree of similarity may be set based on the characteristics of the experience activity. In consideration of the learner's adaptation to experiential learning, a low score is given. In addition, the server 100 may generate comprehensive analysis information for learners based on the calculated scores. Information including values of scores for each characteristic and comprehensive analysis information on learners may be defined as secondary diagnosis information analysis data. The server 100 may create an interface by visualizing the secondary diagnosis information analysis data in a form that can be displayed on the electronic device 200 (eg, graphing scores), and an interface in which secondary diagnosis information analysis data is visualized. May be provided to the electronic device 200.

According to an embodiment, the server 100 may analyze the tertiary diagnosis information data in operation 506. In other words, the server 100 may obtain tertiary diagnosis information data by comprehensively analyzing primary diagnosis information data collected as a result of the first diagnosis and secondary diagnosis information data collected as a result of the second diagnosis. . For example, the server 100 (for example, the information analysis module 123) is performed over a long period of time as shown in FIG. Based on the learner's feedback information, comprehensive analysis (career direction analysis and developmental analysis) can be performed to generate tertiary diagnosis information analysis data for learners. The third diagnosis information analysis data may include values for characteristics such as career direction and developmentality for a learner. The server 100 may create an interface by visualizing the tertiary diagnosis information analysis data in a form that can be displayed on the electronic device 200 (eg, graphing scores), and an interface in which the third diagnosis information analysis data is visualized. May be provided to the electronic device 200. Accordingly, the learner and the educator can objectively check the result of smart diagnosis and education based on the smart diagnosis for the learner using the server 100. According to an embodiment, the server 100 includes big data and big data in operation 507. The recommended education content based on the machine learning model may be generated, and information on the recommended education content generated in operation 508 may be transmitted to the electronic device 200. For example, as shown in FIG. 8, the server 100 may use the first to third diagnosis information analysis data obtained based on the first to third diagnosis performed several times over a long period of time, as shown in FIG. 8, and the educational content recommendation module 124 ). The educational content recommendation model 124 includes characteristics (e.g., fluency, flexibility, sophistication, originality, imagination) included in the primary to secondary diagnostic information analysis data, creativity, language ability, and creative thinking ability (e.g., attention/observation ability). , Associative/shaping, categorization ability, analogy/reasoning ability, integrated thinking ability, etc.), strength area/security area, and creative problem-solving ability and self-esteem). The educational content recommendation model 124 inputs values for each of the extracted features into the machine learning model 330, and the machine learning model 330 is input based on information on weights for educational content for each of the preset features. In response to the values, a score may be assigned for each educational content. For example, the machine learning model 330 is pre-trained by assigning a first weight to the first educational content when the first characteristic (fluency) is the first score, and the first characteristic (fluency) is the first score. A first weight may be assigned to the first educational content based on the input of. In this way, the machine learning model 330 may perform an operation of sequentially assigning scores to a plurality of educational contents. As a result, the machine learning model 330 completes the scoring operation for a plurality of educational contents, and then the number of educational contents (first educational content and second educational content, 910) ( Example: Company A's textbook A, company B's play activity B) can be returned. The server 100 may visualize the educational contents and provide an interface including the visualized educational contents to the electronic device 200 to allow a learner to check recommended educational contents. The learner can proceed with learning by using the recommended educational contents. In this case, the learner requests the use of the recommended educational content through the server 100, and the server 100 may provide the content for which payment has been completed by making a payment to the external server 300.

3.2 Second Example <Operation of selecting and providing a specified number of experience activities when selecting an experience activity>

Since the operations of the above-described smart education system may be applied mutatis mutandis to the second embodiment, redundant descriptions will be omitted.

According to an embodiment, the server 100 may use first diagnosis information analysis data when selecting an experience activity for a second diagnosis. In addition, the server 100 may select a specified number of experience activities based on the execution period of the experience activities, since the experience activities must be performed at a specified period during a specified period.

10 is a flowchart illustrating another example of the operation of the smart education system according to an embodiment of the present application. According to various embodiments, the operation of the smart education system is not limited to the order of operations illustrated in FIG. 10, and may be performed in a different order from the illustrated order. In addition, according to various embodiments, more operations may be performed, or at least one operation less than that of the smart education system illustrated in FIG. 10 may be performed. Hereinafter, FIG. 10 will be described with reference to FIGS. 11 to 12.

11 is a diagram for explaining an example of an operation of selecting an experience activity for secondary diagnosis by the server 100 according to an embodiment of the present application. 12 is a view for explaining an example of an operation of combining experience activities when selecting an experience activity for secondary diagnosis by the server 100 according to an embodiment of the present application.

According to an embodiment, the server 100 may acquire pre-test data in operation 1001 and acquire primary diagnosis information analysis data. For example, when the electronic device 100 is connected, the server 100 performs a guardian and/or personality type test (MBTI) and a parenting and disposition test, which are neighbors of the learner, and the personality type test result data and parenting and disposition. Pre-test data including test result data may be acquired and stored. In addition, for example, the server 100 is divided into areas (eg, fluency, flexibility, sophistication, originality, imagination) creativity, language ability, and creative thinking ability (eg, attention/observation ability, association/shaping ability, categorization ability, analogy/ An interface for diagnosing characteristics such as reasoning ability, integrated thinking ability, etc.) may be provided, and response information may be received and analyzed to generate primary diagnosis information analysis data including values for characteristics. Since the operation of acquiring the pre-test data of the server 100 and the operation of acquiring the primary diagnostic information analysis data has been described above, a redundant description is omitted.

According to an embodiment, the server 100 selects an experience activity based on the first diagnosis information analysis data in operation 1002 and the time required for experiential learning, and transmits information on the experience activity selected in operation 1003 to the electronic device. It can be provided as (200). For example, the server 100 may pre-store a plurality of experience activities for secondary diagnosis. The plurality of experiential activities are of various fields (eg, art, physical education, music, interpersonal, etc.) to determine characteristics (strength area/security area, and creative problem-solving ability and self-esteem) to be analyzed during the second diagnosis. May include experiential activities. The server 100 includes experiential activities 1110 corresponding to the primary diagnosis information analysis data analyzed by the information analysis module 123 among a plurality of experiential activities, as shown in 1101 of FIG. Experience activity and second experience activity) can be selected. For example, the server 100 includes characteristics included in the primary diagnostic information analysis data (eg, by domain (eg fluency, flexibility, sophistication, originality, imagination) creativity, language ability, and creative thinking ability (eg: A specified number of characteristics having a high value among attention/observation, association/shaping, categorization ability, analogy/reasoning ability, integrated thinking ability, etc. The server 100 may identify a plurality of experiential activities and identified designated designated features. By calculating the degree of correlation of the number of characteristics, the designated number of experience activities 1110 (eg, a first experience activity and a second experience activity) may be selected in the order of a high degree of correlation. In the case of experiential activities, it may be defined as an experiential activity with a high priority, in this case, the designated number may be determined by the period during which the secondary diagnosis is performed, the period required for each experiential activity, and/or difficulty level. , The server 100 may set (eg, set to 3 months) a period during which the secondary diagnosis is performed based on the learner's personal information (eg, age group and gender). Experience activity sets to be performed during a specified period may be generated by arranging activity activities having a high priority (or relevance) among activities in order. First, a first experience activity having the highest priority may be placed. The server 100 identifies a required period and/or difficulty level of the deployed first experience activity, and provides a system based on the identified required period and/or difficulty level. 1 After performing the experience activity, it is possible to set a pause period t1 until the next experience activity is performed.The server 100 may set the first experience activity after the set pause period t1 from the time when the first experience activity is performed. A second experience activity of the next priority may be placed: Subsequently, the server 100 identifies a rest period corresponding to the second experience activity, and performs a third experience activity of the next priority after the identified rest period. Can be deployed. At this time, the server 10 0) identifies the experiential activity available period in which the experiential activity can be placed during the specified period, and no longer occurs when the experiential activity possible period falls below a preset threshold period (e.g., a period that is 1/3 of the period in which the experiential activity is performed) Experiential activities may not be arranged. As a result, the set of experiential activities to be performed during a specified period may be composed of experiential activities and a rest period based on a required period and/or difficulty level of each experiential activity. Meanwhile, the server 100 may adjust the threshold period based on the learner's personal information (eg, age group and gender). For example, when the sex of the learner is male and the age of the learner is 6 years or older, the server 100 may reduce the threshold period by setting the threshold period to a period of 1/4 of the period during which the experiential activity is performed. That is, as the sex of the learner is male and the age of the learner increases, the server 100 may decrease the critical period so that more experiential activities are performed.

According to another embodiment, the server 100 may perform at least a portion of a plurality of experiential activities 1110 (eg, a first experiential activity and a second experiential activity) constituting an experiential activity set as shown in FIG. 12. Can be combined and merged. For example, the server 100 may identify a degree of similarity of some experiential activities constituting the plurality of experiential activities 1110, and when the identified similarity is greater than or equal to a preset threshold similarity, may combine some of the experiential activities. For example, when the first experiential activity constituting the experiential activity set is a "physical activity" and the second experiential activity is an "art" activity, the server 100 calculates a high degree of similarity (u) between each experiential activity. In addition, the first experience activity and the second experience activity can be combined so that they are performed together on the same day (the first experience activity + the second experience activity). Thereafter, the server 100 arranges the next priority third experience activity to be performed after the rest period based on the first experience activity and the second experience activity from the day the first experience activity and the second experience activity are performed (1111). )can do. Meanwhile, the threshold similarity may be determined according to the number of experiential activities included in the experiential activity set. For example, the server 100 may increase a threshold similarity as the number of experience activities included in the experience activity set increases, so that the experience activities are not combined. Accordingly, a large number of experiential activities can be efficiently performed so that learners can be diagnosed more accurately.

According to an embodiment, the electronic device 200 may acquire secondary diagnosis information during an experience activity selected in operation 1004 and transmit the secondary diagnosis information to the server 100 in operation 1005. For example, as shown in 1102 of FIG. 11, the electronic device 200 provides the received information on the first experience activity and the information on the second experience activity to the educator, and the educator provides each Experiential activities can be carried out. The educator fills in the answer information to the questionnaires included in the interface for secondary diagnosis while each experiential activity is performed for a specified period, and sends the secondary diagnosis information 1120 to the server 100 through the electronic device 200. ) Can be provided. Since the operation of providing the secondary diagnosis information has been described above in operations 504 and 505, a redundant description will be omitted.

According to an embodiment, the server 100 may process secondary diagnostic information and analyze data in operation 1006. For example, the server 100 extracts and extracts a checklist or answer to a questionnaire for analyzing various characteristics (eg, strength area/security area, and creative problem solving ability and self-esteem) from the secondary diagnosis information. Answers can be scored as values for each feature. In this case, the server 100 may score the extracted answers as values for each characteristic based on the priority of the experience activity. For example, the server 100 may assign a higher score when scoring as values for characteristics based on answer information obtained during execution of an experience activity having a high priority. The server 100 may create an interface by visualizing the secondary diagnosis information analysis data in a form that can be displayed on the electronic device 200 (eg, graphing scores), and an interface in which secondary diagnosis information analysis data is visualized. May be provided to the electronic device 200. In addition, since operation 1006 of the server 100 may be performed in the same manner as operation 505 of the server 100 described above, a redundant description will be omitted.

According to an embodiment, the server 100 may generate recommended education content based on data and a machine learning model in operation 1007 and provide the recommended education content to the electronic device 200 in operation 1008. For example, the server 100 inputs the first to third diagnosis information analysis data acquired based on the first to third diagnosis performed several times over a long period of time into the machine learning model 330, and The model 330 may assign a weight for each educational content in response to input values based on information on a weight for educational content according to preset characteristics. As a result, the machine learning model 330 completes the weighting operation for a plurality of educational contents, and then a specified number of educational contents (first education content and second education content, 910) in order of higher weights ( Example: Company A's textbook A, company B's play activity B) can be returned. Since operations 1007 to 1008 of the server 100 may be performed as operations 506 to 507 of the server 100 described above, a redundant description will be omitted.

3.3. Third Embodiment <Operation of Reconfiguring Recommended Educational Content>

Since the operations of the above-described smart education system may be applied mutatis mutandis to the third embodiment, redundant descriptions will be omitted.

According to an embodiment, the server 100 receives feedback information on recommended educational content (eg, education is not well performed) from the electronic device 200 and rearranges the priorities for the educational content based on this. Recommend educational content.

13 is a flowchart illustrating another example of the operation of the smart education system according to an embodiment of the present application. According to various embodiments, the operation of the smart education system is not limited to the order of operations illustrated in FIG. 13, and may be performed in a different order from the illustrated order. In addition, according to various embodiments, more operations may be performed, or at least one operation less than that of the smart education system illustrated in FIG. 13 may be performed. Hereinafter, FIG. 13 will be described with reference to FIG. 14.

14 is a diagram for explaining an example of an operation of re-recommending educational content of a smart education system according to an embodiment of the present application.

According to an embodiment, the server 100 may generate recommended education content based on big data and a machine learning model in operation 1301 and provide the recommended education content in operation 1302. For example, the educational content recommendation module 124 of the server 100 uses the first to second diagnosis information analysis data obtained based on the first diagnosis and the second diagnosis performed several times over a long period of time in a machine learning model ( Educational content input to 330 and returned from the machine learning model 330 (eg, first education data and second education data) may be obtained. The server 100 may visualize educational contents (eg, first education data and second education data) and provide them as shown in 1401 of FIG. 140. For example, the first educational content may indicate a textbook A of Company A, and the second education content may indicate a B education image of Company B.

According to an embodiment, the server 100 may receive feedback on the recommended educational content in operation 1303 and reconfigure the recommended educational content in operation 1304. For example, whenever learning based on educational contents is performed, the server 100 may conduct a survey on learning from a learner and/or an educator of the electronic device 200. The server 100 may calculate a satisfaction score for the first education content and the second education content from the answer to the survey, and start reconfiguring the education contents when the calculated satisfaction score is lower than a preset value. . A preset value to be compared with the satisfaction score may be determined based on a value for a characteristic of the learner. For example, the preset value is set higher as the value of one characteristic of the learner having the highest correlation with the educational contents is higher, so that reconstruction of educational contents more sensitive to user feedback is initiated. I can. As shown in 1402 of FIG. 14, the server 100 includes educational contents other than the first educational content and the second educational content (eg, third educational content, fourth educational content, fifth educational content,? The priorities of ,) may be rearranged, and based on the rearranged priority, educational contents having the highest priority may be selected (eg, fifth educational content and fourth educational content) as many as a specified number and provided. The rearrangement of the priority is based on the similarity between the excluded first and second education contents and the remaining education contents (eg, third education content, fourth education content, fifth education content, ??,). Based on this, the lower the similarity, the higher the priority may be set.

According to an embodiment, the server 100 may provide the recommended educational content reconstructed in operation 1305. For example, as shown in 1402 of FIG. 14, the server 100 selects the highest priority educational content as many as a specified number (eg, the fifth education content and the fourth education content) and visualizes the electronic device ( 200) can be provided. For example, the fifth educational content may represent the C toy of the company C, and the fourth educational content may represent the D education video of the D company.

Claims (5)

As a method of operating the server,
Receiving a plurality of educational content from an external server; Including, wherein the plurality of educational content includes content for education sold or distributed by a plurality of companies,
Generating a machine learning model by using a plurality of diagnostic information analysis data and a plurality of educational contents accumulated in the server as training data, wherein the plurality of diagnosis information analysis data are learners Including values for a plurality of first characteristics, a plurality of second characteristics, and a plurality of third characteristics of, wherein the machine learning model provides at least one educational content when diagnostic information analysis data for the learner is input. Is set to output,
Identifying a connection of an electronic device associated with a first learner to the server;
A first interface for diagnosing the plurality of first characteristics for the first learner is provided to the connected electronic device, and a first value for the plurality of first characteristics is determined based on the provision of the first interface. Acquiring the first diagnostic information analysis data to be included;
After the acquisition of the first diagnosis information analysis data, a plurality of second interfaces for diagnosis of the plurality of second characteristics for the first learner are provided, and the plurality of second interfaces are provided based on the provision of the plurality of second interfaces. Acquiring second diagnostic information analysis data including a second value for a second characteristic; including, wherein each of the plurality of second interfaces includes a plurality of experiential learnings for analyzing the plurality of second characteristics. Provided to the electronic device corresponding to each,
Acquiring third diagnosis information analysis data including third values for the plurality of third characteristics based on the first diagnosis information analysis data and the second diagnosis information analysis data; And
At least one education recommended to the first learner among the plurality of education contents by inputting the first diagnosis information analysis data, the second diagnosis information analysis data, and the third diagnosis information analysis data into the machine learning model Acquiring content and providing the obtained at least one educational content to the electronic device; Including,
Pre-storing a plurality of first experiential activities for diagnosis of the second characteristic;
Identifying values representing the first characteristics from the first diagnostic information analysis data, and identifying a specified number of characteristics from a highest value in descending order based on the identification;
Selecting a plurality of experiential activities of the specified number corresponding to the identified characteristics of the specified number of the plurality of first experiential activities;
Generating and providing the second interface including at least one of information on checklists to be filled out of the selected plurality of experience activities or information on questionnaires;
Obtaining personal information on the first learner and setting a period in which the second diagnosis will be performed based on the obtained personal information; And
Identifying the specified number based on the set period among the plurality of pre-stored first experience activities, and sequentially selecting a plurality of experience activities as many as the specified number; Including,
Identifying the specified number based on the set period of the plurality of pre-stored first experiential activities, and sequentially selecting a plurality of experiential activities as many as the specified number:
Selecting a first experience activity having a highest priority;
When the first experiential activity is selected, identifying a first rest period associated with the first experiential activity based on a duration or difficulty of the first experiential activity;
Selecting a second experience activity to be performed after the first pause period, and identifying a second pause period associated with the second experience activity based on a required period or difficulty level of the second experience activity;
If a period in which the experience activity can be performed based on the second pause period is less than a preset threshold period, stopping the operation of selecting the plurality of experience activities; further comprising,
The critical period is set based on the personal information of the first learner, and the critical period is set to decrease as the age of the first learner increases,
Identifying a degree of similarity between the selected plurality of experiential activities; And
Deriving one experiential activity by combining at least two experiential activities whose similarity is equal to or greater than a preset value among the selected plurality of experiential activities, and including the derived one experiential activity in the plurality of experiential activities; Including more,
When the derived one experiential activity is selected, a rest period associated with the derived one experiential activity is identified based on rest periods associated with each of the combined two or more experiential activities,
Receiving feedback information on the provided at least one educational data from the electronic device; And
Reconfiguring the at least one educational data based on the feedback information; including,
How it works. The method of claim 1,
The first value for the plurality of first characteristics includes a value for creativity for each area, a value for language ability, and a value for creative thinking ability, and the value for creativity for each area includes fluency, flexibility, sophistication, Including values for originality, and imagination, and the values for creative thinking ability include values for attention/observation, associative/shaping, categorizing ability, analogy/reasoning ability, and integrated thinking ability,
The second value for the plurality of second characteristics includes a value for a strength area/security area and a value for creative problem solving ability and self-esteem,
How it works. The method of claim 2,
The first interface includes an interface for receiving a questionnaire and an answer for diagnosis of the first characteristic, and the plurality of second interfaces includes information or questionnaires on checklists to be filled out of the plurality of experience activities Including at least one of the information about,
How it works. delete delete

Images