KR20230019807A - User customized learning service providing system using analysis of content provision criteria and method thereof - Google Patents

Abstract

A user-customized learning service providing system using analysis of content provision criteria and a method thereof are provided. The system comprises: a user terminal driven by at least one user; and a server for analyzing user learning information including a scoring result for a test problem received from a user terminal, predicting a learning ability of the user to generate customized learning information that includes a customized prediction problem for each difficulty level, and providing the customized learning information to the user terminal.

Description

User-customized learning service provision system and method through analysis of content provision criteria

The present invention relates to a system and method for providing a user-customized learning service through analysis of content provision criteria, and more particularly, to a customized prediction with sequential difficulty by analyzing the scoring result of a test problem and identifying the learning level and weak area. A system and method for providing a user-customized learning service through analysis of content provision criteria capable of providing a customized learning service suitable for a user's level of difficulty by creating a problem.

Recently, the concept of personalization has emerged in order to provide services that reflect users' preferences as much as possible on the Internet. For example, such a personalization system allows users to select and view information suitable for a user's style, including a function to edit and view a basic screen to suit the user's taste on a portal site on the Internet.

In addition, e-commerce companies are also providing functions to configure their own pages according to the user's personal taste and to receive product recommendations that match the user's purchase history and taste.

In general, when it comes to personalization, the term “website personalization” is used in connection with a website, and personalization on such a website is a series of value exchange processes. If provided, the website provides the most appropriate information to the user based on the data provided by the user.

Through this personalization, the website operator can obtain data about the user and obtain the user's continuous use or purchase, and the user can obtain the most suitable information for himself/herself in a convenient way.

In the existing personalized service, most Internet application service systems provide the same content to all users without considering the content use characteristics of individual users. After analyzing the user's content use characteristics using data mining technology, As the method of providing content suitable for users has evolved, user satisfaction has been improved.

In particular, the personalized service using the collaborative filtering method is adopted in most personalization service systems because it is easy to implement and has relatively high accuracy.

However, conventional recommendation algorithms including collaborative filtering methods are one-time recommendation methods, and end up recommending things or items that are considered to be suitable in a current state to a certain user in a list only once.

Therefore, when a user who wants to accumulate knowledge in a certain field continuously wants to be recommended learning problems suitable for this purpose, there is a limitation in recommending problems through the existing recommendation algorithm.

Republic of Korea Patent Publication No. 10-2019-0025871

The problem to be solved by the present invention is to provide a user-customized learning service providing system and method through analysis of content provision criteria.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

A user-customized learning service providing system through analysis of content provision criteria according to an embodiment of the present invention for solving the above problems includes a user terminal driven by at least one user; and predicting the learning ability of the user by analyzing the user learning information including the scoring result for the test problem received from the user terminal to generate customized learning information including a customized expected problem for each difficulty level, and converting the customized learning information to the above. A server provided to the user terminal; may include.

In one embodiment of the present invention, the server includes a first customized prediction problem having a first difficulty level through which 80% of users can pass by identifying a user's learning level and a weak area based on the user learning information. The customized learning information can be created.

In one embodiment of the present invention, when the user passes the first customized prediction problem having the first difficulty level, the server analyzes the user learning information for the first customized prediction problem to determine the first difficulty level. The customized learning information including a second customized prediction problem having a high second difficulty level may be generated.

In one embodiment of the present invention, when the user passes the second customized prediction problem and the user's learning level is determined to be the highest level, the server changes and sets the user's learning progress to the next unit, A test problem selected according to the changed learning progress may be provided to the user terminal.

In one embodiment of the present invention, the manager terminal for updating the customized learning information generated in response to the user learning information in real time; may further include.

In addition, a user-customized learning service providing method through analysis of content provision criteria according to another embodiment of the present invention for solving the above problems is a user-customized learning service through analysis of content provision criteria performed by a server. A method for providing, comprising: providing a test problem selected according to a user's learning progress to a user terminal; checking whether the answer to the test question is correct, and scoring the test question; Analyzing the learning level and weak areas of the user through the test scoring result of the test problem; generating a first customized prediction problem having a first difficulty level by predicting the user's learning ability based on the analysis result of the user's learning level and weak areas; performing a first scoring on the first customized prediction problem having the first difficulty by checking whether an answer to the first customized prediction problem having the first difficulty is correct; generating a second customized prediction problem having a second difficulty level higher than the first difficulty level when the first customized prediction problem having the first difficulty level is passed through the first scoring result; and checking whether an answer to the second customized prediction problem having the second difficulty level is correct, and performing a second scoring on the second customized prediction problem having the second difficulty level. In the step of generating the first customized expected problem, the user's learning level and weak area may be identified based on the user's learning information, and a problem that the user can pass 80% of the time may be generated.

In one embodiment of the present invention, the generating of the first customized expected problem may include classifying a problem that a user can pass as a first problem; classifying a problem that the user cannot pass as a second problem; and mixing the first problem and the second problem at a ratio of 80:20.

In one embodiment of the present invention, generating the second customized prediction problem may include mixing the first problem and the second problem in a ratio of 60:40.

In one embodiment of the present invention, when the user passes the second customized prediction problem having the second difficulty through the second scoring result, the second scoring result is analyzed to predict the user's learning ability mixing the first problem and the second problem in a ratio of 0:100 to generate a third customized prediction problem of a third difficulty; but, when the user passes the third customized prediction problem, the user's When the learning level is determined to be the highest level, the server may change and set the user's learning progress to the next unit, and provide a test problem selected according to the changed learning progress to the user terminal.

The program according to an embodiment of the present invention is combined with a computer, which is hardware, and stored in a computer-readable recording medium to perform a user-customized learning service providing method through analysis of the content provision criteria.

Other specific details of the invention are included in the detailed description and drawings.

According to one embodiment of the present invention, a customized learning service suitable for a user's difficulty level can be provided by analyzing the scoring result of a test problem to identify a learning level and a weak area and creating a customized problem having a sequential difficulty level.

According to one embodiment of the present invention, the user's learning ability can be improved by analyzing the scoring result of the test problem to predict the user's learning ability and providing a learning service corresponding to the predicted learning ability.

According to one embodiment of the present invention, the user's learning result can be further improved by providing customized learning suitable for the user's level of difficulty.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram for explaining the configuration of a user-customized learning service providing system through analysis of content provision criteria according to an embodiment of the present invention.
FIG. 2 is a diagram for explaining a detailed configuration of the server shown in FIG. 1 .
FIG. 3 is a diagram for explaining a detailed configuration of a user terminal shown in FIG. 1 .
4 is a diagram for explaining a method of providing a user-customized learning service through analysis of content provision criteria according to an embodiment of the present invention.
FIG. 5 is a diagram for explaining a step of generating a first tailored prediction problem of a first difficulty shown in FIG. 4 .
FIG. 6 is a diagram for explaining a step of generating a second customized prediction problem of a second difficulty shown in FIG. 4 .
FIG. 7 is a diagram for explaining a step of generating a third customized prediction problem of a third difficulty shown in FIG. 4 .

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, only these embodiments are intended to complete the disclosure of the present invention, and are common in the art to which the present invention belongs. It is provided to fully inform the person skilled in the art of the scope of the invention, and the invention is only defined by the scope of the claims.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first element mentioned below may also be the second element within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram for explaining the configuration of a user-customized learning service providing system through analysis of content provision criteria according to an embodiment of the present invention, and FIG. 2 is a diagram for explaining the detailed configuration of the server shown in FIG. 1 3 is a diagram for explaining a detailed configuration of the user terminal shown in FIG. 1 .

As shown in FIG. 1 , a user-customized learning service providing system through analysis of content provision criteria, which is an embodiment of the present invention, may include a server 100 and a user terminal 200 .

Here, the server 100 and the user terminal 200 may be synchronized in real time using the communication network 300 to transmit and receive data. The communication network may support various telecommunication methods, for example, wireless LAN (WLAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband: Wibro), WiMAX (World Interoperability for Microwave Access: Wimax) , GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), High Speed Downlink Packet Access (HSDPA), High Speed Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTEA), Wireless Mobile Broadband Service: Various communication methods such as WMBS), BLE (Bluetooth Low Energy), Zigbee, RF (Radio Frequency), and LoRa (Long Range) may be applied, but are not limited thereto, and various widely known wireless or mobile communication methods this may apply.

First, the server 100 may include a communication module 110, a memory 120, a processor 130, and a database 140, as shown in FIG.

The communication module 110 interworks with the communication network 300 to provide a communication interface necessary to provide a transmission/reception signal between the server 100 and the user terminal 200 in the form of packet data. Furthermore, the communication module 110 may serve to receive a data request from the user terminal 200 and transmit data as a response thereto.

For example, the communication module 110 may receive user learning information including answer information on a test problem from the user terminal 200 and transmit a scoring result of the test problem to the user terminal 200 as a response thereto. there is. In addition, the communication module 110 receives user learning information including answer information on the customized expected problem for each difficulty level from the user terminal 200, and as a response thereto, the user terminal 200 scores the customized expected problem for each difficulty level. ) can be transmitted.

The communication module 110 may be a device including hardware and software necessary for transmitting and receiving signals such as control signals or data signals with other network devices through wired or wireless connections.

A program for performing a method of providing a user-customized learning service may be recorded in the memory 120 .

The memory 120 may temporarily or permanently store data processed by the processor 130 . Here, the memory 120 may include magnetic storage media or flash storage media, but the scope of the present invention is not limited thereto.

The processor 130, as a kind of central processing unit, can control the entire process of providing a user-customized learning service. Each step performed by the processor 130 will be described later with reference to FIGS. 4 to 7 .

Here, the processor 130 may include all types of devices capable of processing data, such as a processor. Here, a 'processor' may refer to a data processing device embedded in hardware having a physically structured circuit to perform functions expressed by codes or instructions included in a program, for example. As an example of such a data processing device built into hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated (ASIC) circuit), field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

The database 140 may store information of users who use learning services, such as the user's age, grade, learning progress, current learning level, and areas of weakness, by classifying them for each user. In addition, the database 140 may classify and store information on problems provided for learning services, such as learning progress, learning level, and weak areas of problems to be provided to users by problem.

The database 140 may store a plurality of application programs (application programs or applications) running in the server 100, data for operation of the server 100, and commands. At least some of these application programs may be downloaded from an external server through wireless communication.

The server 100 having such a configuration may select a test problem according to the learning progress of the user and provide the selected test problem to the user terminal 200 .

In addition, the server 100 may generate a user-customized prediction problem through the scoring result for the test problem, and provide the generated customized prediction problem to the user terminal 200 .

Specifically, the server 100 analyzes the user learning information received from the user terminal 200 to identify the user's learning level and weak area, predict the user's learning ability, and generate customized learning information.

At this time, the user learning information may include the information of the user using the learning service, such as the user's age, grade, learning progress, current learning level, and weak areas, scoring results for test problems, and scoring results for customized expected problems by difficulty. However, it is not limited thereto.

In addition, the customized learning information may include, but is not limited to, problem information provided for the learning service, such as learning progress, learning level, and weak area of the problem to be provided to the user, and customized expected problems by difficulty level.

For example, the server 100 identifies the user's learning level and weak areas based on user learning information according to the test scoring result, and includes a first customized prediction problem having a first difficulty level that 80% of users can pass. Customized learning information can be created. At this time, if the server 100 does not pass the first customized prediction problem having the first difficulty that 80% of users can pass, the first customized prediction problem having the first difficulty already created based on the user learning information Alternatively, a new first customized prediction problem having a difficulty lower than the first difficulty may be generated.

Depending on the embodiment, user patterns and keywords may be extracted from user learning information in order to identify the user's learning level and weak areas.

For example, customized learning including the first customized prediction problem having the first difficulty that 80% of users can pass by identifying the user's learning level and weak areas based on user learning information using user patterns and keywords information can be generated.

Depending on the embodiment, user learning information may be pre-processed.

For example, if the user learning information is text, the server 100 may perform preprocessing by sequentially performing a tokenization operation, a cleaning operation, and a normalization operation. That is, the server 100 performs a tokenization operation of filtering the requested data made of text, and a refinement operation of removing noise data included in the tokenized data, and then the refinement operation is performed. Normalized data can be preprocessed.

In other words, the server 100 performs a tokenization operation using a space removal filter and a special character removal filter so that words included in the text are divided into minimum units of meaningful words, and then appears in the tokenized data. Refinement may be performed to emphasize the meaning of the remaining words by removing noise data for words with low frequency or multiple repetitions, and then the refined data may be normalized and preprocessed.

At this time, the server 100 may digitize the noise data and determine whether or not to delete the noise data in response to the user learning information.

Depending on the embodiment, the server 100 may automatically check and convert typos included in the text or automatically remove redundant data.

In addition, the server 100 analyzes the first scoring result for the first customized prediction problem having the first difficulty based on the user learning information according to the first scoring result, identifies the user's learning level and weak area, and determines the user's Customized learning information including a second customized prediction problem having a second difficulty that can pass 60% may be generated. At this time, if the server 100 does not pass the second customized prediction problem having a second difficulty that 60% of users can pass, the second customized prediction problem having a second difficulty already created based on the user learning information Alternatively, a new second customized prediction problem having a difficulty lower than the second difficulty may be created. Alternatively, the server 100 may generate a first customized prediction problem having a pre-generated first difficulty based on the user learning information or a new first customized prediction problem having a difficulty lower than the first difficulty.

In addition, the server 100 analyzes the second scoring result for the second customized prediction problem having the second difficulty based on the user learning information according to the second scoring result, identifies the user's learning level and weak area, and determines the user's Customized learning information including a third customized prediction problem having a third degree of difficulty that can pass 0% may be generated. At this time, the server 100 may change and set the user's learning progress to the next unit when the third customized prediction problem having a third degree of difficulty that can be passed by 0% of the user has passed. On the other hand, if the server 100 does not pass the third customized expected problem having a third difficulty that 0% of the user can pass, the first customized expected problem having a first difficulty or the first customized expected problem based on the user learning information A second customized prediction problem having a level of difficulty of 2 may be created.

In this embodiment, 80% of users can pass the first customized prediction problem having a first difficulty level, 60% of users can pass a second customized prediction problem having a second difficulty level, and a third difficulty level. The third customized prediction problem with 0% of users started to be able to pass, but is not limited thereto, and the customized prediction problem can be generated by sequentially adjusting the difficulty by identifying the user's learning level and weak areas. .

According to an embodiment, the server 100 may update customized learning information generated in response to user learning information in real time.

Such a server 100 may be implemented by hardware circuitry (eg, CMOS-based logic circuitry), firmware, software, or a combination thereof. For example, it may be implemented using transistors, logic gates, and electronic circuits in the form of various electrical structures.

As shown in FIG. 3 , the user terminal 200 may include a communication module 210 , a memory 220 , a processor 230 , a display module 240 and a camera module 250 .

First, in the description of the communication module 210, the memory 220 and the processor 230, the description of the communication module 110, the memory 120 and the processor 130 described above with reference to FIG. 2 is duplicated. description is omitted.

More specifically, the communication module 210 may provide a communication interface necessary to provide a transmission/reception signal between the server 100 and the user terminal 200 in the form of packet data in conjunction with the communication network 300 . Furthermore, the communication module 210 may serve to transmit a data request to the server 100 and receive data in response thereto.

For example, the communication module 210 may receive a test question provided from the server 100 and transmit answer information on the test question to the server 100 as a response thereto.

A program for performing a method of providing a user-customized learning service may be recorded in the memory 220 . In addition, it may perform a function of temporarily or permanently storing data processed by the processor 230 . At this time, the memory 120 and the program for performing the method of providing the user-customized learning service recorded in the memory 220 may be different for the terminal and for the server.

The processor 230, as a kind of central processing unit, can control the entire process of providing a user-customized learning service. The processor 230 may perform a process of providing a user-customized learning service by itself, but preferably, may perform a process of providing a user-customized learning service through the server 100 .

The display module 240 performs a function of displaying an application execution screen for a method of providing a user-customized learning service, and performs a function of displaying test problems, customized prediction problems, and scoring results for each problem through the application. can

The camera module 250 is a device for photographing a specific object, and may generate learning information, image information, etc. of interest to the user.

For example, the camera module 250 may photograph a problem in a problem book implemented as a book, and the photographed problem may be analyzed and used to construct a customized expected problem later.

The user terminal 200 having such a configuration may receive a test problem, a customized expected problem, etc. from the server 100, display the received problem on the screen, and include answer information and user information for each problem. User learning information may be transmitted to the server 100 .

Such a user terminal 200 may refer to a communication terminal capable of using an application in a wired/wireless communication environment, and may be, for example, a portable terminal. User terminal 200 may include any type of handheld computing device (eg, PDA, email client, etc.), cell phone, or other type of computing or communication platform, although the present invention does not It is not limited, and as described above, the terminal capable of loading the application may be borrowed without limitation. At this time, the user terminal 200 may operate using an application program (application program or application) in the present disclosure, and such an application program is downloaded from an external server or a local control management server 20 through wireless communication. It can be.

Depending on the embodiment, the user-customized learning service providing system through the analysis of content provision criteria may further include an administrator terminal (not shown).

The manager terminal may transmit/receive data by being synchronized with the server 100 and the user terminal 200 in real time using a wireless communication network.

Depending on the embodiment, the manager terminal may monitor data transmitted and received between the server 100 and the user terminal 200 and the manager terminal through a screen.

Depending on the embodiment, the manager terminal may generate customized learning information using the user learning information received from the user terminal 200 .

Depending on the embodiment, the manager terminal may generate customized learning information using the user learning information received from the server 100 .

Depending on the embodiment, the manager terminal may update customized learning information generated in response to user learning information in real time.

Such an administrator terminal can control the operation of the user terminal 200 in the manager terminal using an application program (application program or application), and this application program can control the operation of the external server or server 100 through wireless communication. can be downloaded from

The operation of the user-customized learning service providing method through the analysis of content provision criteria according to an embodiment of the present invention having such a structure is as follows. 4 is a diagram for explaining a method of providing a user-customized learning service through analysis of content provision criteria according to an embodiment of the present invention, and FIG. 5 generates a first customized prediction problem of the first difficulty shown in FIG. 4 FIG. 6 is a diagram for explaining the step of generating a second customized prediction problem of the second difficulty shown in FIG. 4, and FIG. 3 It is a diagram for explaining the steps of creating a customized prediction problem.

First, as shown in FIG. 4 , the server 100 may provide the user terminal 200 with a test problem selected according to the user's learning progress (S10).

Specifically, the server 100 may check the user's age, grade, etc. through user information, predict the user's learning progress in consideration of the current time, select a test problem according to the user's learning progress, and select the selected A test problem may be provided to the user terminal 200 .

For example, if the user is in the third year of middle school and the current date is confirmed as March, the server 100 may predict the user's learning progress as the beginning of the first semester of the third year of middle school, and start the first semester of the third year of middle school. A test problem may be selected with necessary content, and the selected test problem may be provided to the user terminal 200 .

The user's learning progress may be predicted by the server 100 and set automatically, or may be directly selected from the user terminal 200 and set manually.

The user terminal 200 may display the test questions provided from the server 100 on the screen, and may further display an interface for selecting an answer to the question on the screen.

When an answer to the test question is input to the user terminal 200, the user terminal 200 may transmit the input answer information to the server 100.

Next, the server 100 may score the test question based on the answer information on the test question received from the user terminal 200 and analyze the test scoring result (S12). That is, the server 100 can check whether the answer to the test question is correct, and can score the test question through the result of checking the correct answer.

Accordingly, the server 100 may analyze the learning level and weak areas of the user through the scoring result of the test problem.

Specifically, the server 100 may compare the scoring result of the test problem with a preset reference value for each level, and analyze the level of the user's learning level.

For example, if the scoring result of the test problem is 90 points or more, the server 100 may analyze the user's learning level and weak area as 1st grade, and if the scoring result of the test problem is 80 points or more, the user's learning level The level and weak areas can be analyzed as 2 grades, and if the scoring result of the test problem is 70 points or more, the user's learning level and weak areas can be analyzed as 3 grades.

Next, the server 100 may generate a first customized prediction problem having a first difficulty level by predicting the user's learning ability based on the analysis result of the user's learning level and weak areas (S14).

Specifically, referring to FIG. 5 , the server 100 classifies a problem that 80% of users can pass as a first problem based on the analysis result of the user's learning level and weak area (S100). (S110).

Next, when the number of classified first problems is greater than the predetermined number (S120), the server 100 may select 80% of the classified first problems (S130).

Meanwhile, when the number of classified first problems is smaller than the predetermined number (S120), the server 100 may classify a problem that 80% of users can pass as the first problem again.

In addition, the server 100 may classify a problem that 20% of users cannot pass as a second problem based on the analysis result of the user's learning level and weak area (S100).

Next, when the number of classified second problems is greater than the predetermined number (S150), the server 100 may select 20% of the classified second problems (S160).

Meanwhile, when the number of classified second problems is smaller than the preset number of problems (S150), the server 100 may classify a problem that 20% of users can pass as a second problem again.

In contrast, the step of classifying a problem that 20% of users cannot pass as a second problem (S140) is performed before or simultaneously with the step of classifying a problem that 80% of users pass as a first problem (S110). It can be.

Next, the server 100 may generate a first customized prediction problem having a first difficulty level using the selected first and second problems. In this case, the first customized prediction problem having the first difficulty may be higher than the difficulty of the test problem, but is not limited thereto.

For example, the server 100 may generate a first customized prediction problem by integrating both the re-selected first and second problems at a ratio of 80:20 and removing only duplicate problems from the integrated problems.

Next, the server 100 may provide the user terminal 200 with the first customized prediction problem having the generated first difficulty level.

The user terminal 200 may display the first customized prediction problem provided from the server 100 on the screen, and may further display an interface for selecting an answer to the first customized prediction problem on the screen.

When an answer to the first customized prediction problem is input to the user terminal 200, the user terminal 200 may transmit the input answer information to the server 100.

Next, the server 100 scores the first customized prediction problem having the first difficulty based on the answer information on the first customized prediction problem having the first difficulty received from the user terminal 200, and scoring the first prediction problem. The results can be analyzed (S16). That is, the server 100 may check whether the answer to the first customized prediction problem having the first difficulty is correct, and score the first customized prediction problem having the first difficulty through the correct answer confirmation result. there is.

Next, when the first customized prediction problem having a first difficulty level is passed through the first scoring result (S18), the server 100 determines a second difficulty level higher than the first difficulty level based on the first scoring result. It is possible to generate a second customized prediction problem having (S20).

Specifically, referring to FIG. 6 , the server 100 may classify a problem that 60% of users can pass as a first problem based on the first scoring result (S200).

Next, when the number of classified first problems is greater than the predetermined number (S220), the server 100 may select 60% of the classified first problems (S230).

Meanwhile, when the number of classified first problems is smaller than the predetermined number (S220), the server 100 may classify a problem that 60% of users can pass as the first problem again.

In addition, the server 100 may classify a problem that 40% of users cannot pass as a second problem based on the first scoring result (S200).

Next, when the number of classified second problems is greater than the predetermined number (S250), the server 100 may select 40% of the classified second problems (S260).

Meanwhile, when the number of classified second problems is smaller than the preset number of problems (S250), the server 100 may classify a problem that 40% of users can pass as a second problem again.

In contrast, the step of classifying a problem that 40% of users cannot pass as a second problem (S240) is performed before or simultaneously with the step of classifying a problem that 60% of users pass as a first problem (S210). It can be.

Next, the server 100 may generate a second customized prediction problem having a second difficulty level by using the selected first and second problems. In this case, the second customized prediction problem having the second difficulty may have higher difficulty than the test problem and the first customized prediction problem having the first difficulty, but is not limited thereto.

For example, the server 100 may generate a second customized prediction problem by integrating both the re-selected first and second problems at a ratio of 60:40 and removing only duplicate problems from the integrated problems.

Next, the server 100 may provide the generated second customized prediction problem having a second difficulty to the user terminal 200 .

The user terminal 200 may display the second customized prediction problem provided from the server 100 on the screen, and may further display an interface for selecting an answer to the second customized prediction problem on the screen.

When an answer to the second customized prediction problem is input to the user terminal 200, the user terminal 200 may transmit the input answer information to the server 100.

Next, the server 100 scores the second customized prediction problem having the second difficulty based on the answer information for the second customized prediction problem having the second difficulty received from the user terminal 200, and the second scoring The result can be analyzed (S22). That is, the server 100 may check whether the answer to the second customized prediction problem having the second difficulty is correct, and score the second customized prediction problem having the second difficulty through the correct answer confirmation result. there is.

Next, when the second customized prediction problem having a second difficulty level is passed through the second scoring result (S24), the server 100 determines a third difficulty level higher than the second difficulty level based on the second scoring result. It is possible to generate a third customized prediction problem having (S26).

Specifically, referring to FIG. 7 , the server 100 may classify a problem that 0% of users can pass as a first problem based on the second scoring result (S300).

Next, when the number of classified first problems is greater than the predetermined number (S320), the server 100 may select 0% problems from among the classified first problems (S330).

Meanwhile, when the number of classified first problems is smaller than the predetermined number (S320), the server 100 may classify a problem that 0% of users can pass as the first problem again.

In addition, the server 100 may classify a problem that 100% of users cannot pass as a second problem based on the second scoring result (S300).

Next, when the number of classified second problems is greater than the predetermined number (S350), the server 100 may select 100% of the classified second problems (S360).

Meanwhile, when the number of classified second problems is smaller than the predetermined number of problems (S350), the server 100 may classify a problem that 100% of users can pass as a second problem again.

In contrast, the step of classifying a problem that 100% of users cannot pass as a second problem (S340) is performed before or simultaneously with the step of classifying a problem that 0% of users pass as a first problem (S310). It can be.

Next, the server 100 may generate a third customized prediction problem having a third difficulty level by using the selected first and second problems. In this case, the third customized prediction problem having a third difficulty may have higher difficulty than the test problem, the first customized prediction problem having a first difficulty, and the second customized prediction problem having a second difficulty, but is not limited thereto.

For example, the server 100 may generate a third customized prediction problem by integrating all of the re-selected first and second problems at a ratio of 0:100 and removing only duplicate problems from the integrated problems.

Next, the server 100 may provide the user terminal 200 with a third customized prediction problem having a third difficulty level.

The user terminal 200 may display the third customized prediction problem provided from the server 100 on the screen, and may further display an interface for selecting an answer to the third customized prediction problem on the screen.

When an answer to the third customized prediction problem is input to the user terminal 200 , the user terminal 200 may transmit input answer information to the server 100 .

Next, the server 100 scores the third customized prediction problem having the third difficulty based on the answer information for the third customized prediction problem having the third difficulty received from the user terminal 200, and the third scoring. The result can be analyzed (S28). That is, the server 100 may check whether the answer to the third customized prediction problem having the third difficulty level is correct, and score the third customized prediction problem having the third difficulty level through the correct answer confirmation result. there is.

Next, when the third customized prediction problem having the third difficulty level is passed through the third scoring result (S30), the server 100 determines whether the user's learning level is the highest grade. It can (S32).

For example, if the learning level is classified into 10 grades and the highest grade is set to 1 grade, the server 100 may determine whether the user's learning level is currently set to 1 grade. there is.

Next, when the user's learning level is determined to be the highest level through the third scoring result, the server 100 may change and set the user's learning progress to the next unit (S34).

For example, if the user's learning progress is previously set to Unit 1, the server 100 may change and set the learning progress from Unit 1 to Unit 2 when the third customized prediction problem set to the highest level is passed. there is.

When the learning progress is changed to the next unit and set, the server 100 may select a test problem according to the changed learning progress and provide the selected test problem to the user terminal 200 .

On the other hand, if it is determined that the user's learning level is not the highest level (S32), the user's learning level is changed to one higher level by returning to the step of generating a third customized prediction problem having a third difficulty level (S28). That is, steps S26 to S32 may be repeatedly performed until the user's learning level is changed to the highest level.

In addition, when the first customized prediction problem having the first difficulty level is not passed through the first scoring result (S18), the server 100 returns to the step of generating the first customized prediction problem having the first difficulty level (S14). ) may regenerate the first customized prediction problem and provide it to the user terminal 200 . That is, the server 100 may provide various types of first customized prediction problems to the user terminal 200 until the first customized prediction problem passes.

In addition, if the second customized prediction problem having a second difficulty level is not passed through the second scoring result (S24), the server 100 returns to the step of generating a second customized prediction problem having a second difficulty level (S20). ) may regenerate the second customized prediction problem and provide it to the user terminal 200 . That is, the server 100 may provide various types of second customized prediction problems to the user terminal 200 until the second customized prediction problem passes.

According to the embodiment, if the second customized prediction problem having a second difficulty level is not passed through the second scoring result (S24), the process returns to generating a first customized prediction problem having a first difficulty level (S14). The first customized prediction problem may be regenerated and provided to the user terminal 200 .

Then, if the third customized prediction problem having a third difficulty level is not passed through the third scoring result (S30), the server 100 returns to the step of generating a third customized prediction problem having a third difficulty level (S26). ) may generate a third customized prediction problem again and provide it to the user terminal 200 . That is, the server 100 may provide various types of third customized prediction problems to the user terminal 200 until the third customized prediction problem passes.

According to the embodiment, if the third customized prediction problem having a third difficulty level is not passed through the third scoring result (S30), the process returns to the step of generating a first customized prediction problem having a first difficulty level (S14). The first customized prediction problem is regenerated and provided to the user terminal 200, or the second customized prediction problem having the second difficulty is generated (S20) and the second customized prediction problem is regenerated to the user terminal ( 200) can be provided.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the invention pertains.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

100: server
200: user terminal
300: communication network

Claims (1)

a user terminal driven by at least one user; and
The user learning information including the scoring result of the test problem received from the user terminal is analyzed to predict the user's learning ability, and customized learning information including a customized expected problem for each difficulty level is generated, and the customized learning information is transmitted to the user. Server provided to the terminal; user-customized learning service providing system through analysis of content provision criteria, including a.

Images