Question creation support device, question creation support method, and program

Abstract

To provide a question creation support technique for supporting creation of questions according to the learning level of a learner.SOLUTION: An aspect of the present disclosure relates to a question creation support device having a user interface unit that receives the learning level of questions to be created, and a question creation unit that acquires questions according to the learning level and generates question paper data from the acquired questions.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a question creation support device, a question creation support method, and a program. [Background technology]

[0002] With the recent advances in information and communications technology, IT (Information Technology) and DX (Digital Transformation) are being introduced into a variety of industries and business processes.

[0003] For example, information and communication technology is being actively used in the field of education. Schools are beginning to use electronic whiteboards and tablets in lessons. In addition, teaching materials creation apps are being used by teachers to create teaching materials, promoting the efficiency of work. For example, Patent Document 1 describes an information processing system for creating question paper images. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-146667 A Summary of the Invention [Problem to be solved by the invention]

[0005] An object of the present disclosure is to provide a question creation support technology for supporting the creation of questions that correspond to the academic ability level of learners. [Means for solving the problem]

[0006] One aspect of the present disclosure relates to a question creation support device having a user interface unit that accepts the academic level of the question to be created, and a question creation unit that acquires questions corresponding to the academic level and generates question paper data from the acquired questions. Effect of the Invention

[0007] According to the present disclosure, it is possible to provide a question creation support technology for supporting the creation of questions corresponding to the academic ability level of learners. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram showing a question creation support process according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a schematic diagram showing questions created by a question creation support process according to an embodiment of the present disclosure. [Diagram 3] FIG. 3 is a block diagram illustrating a hardware configuration of a question creation support device according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a block diagram illustrating a functional configuration of a question creation support device according to an embodiment of the present disclosure. [Diagram 5] FIG. 5 is a diagram showing a user interface screen in the question creation support process according to an embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram showing a user interface screen in the question creation support process according to an embodiment of the present disclosure. [Figure 7] FIG. 7 is a diagram showing a user interface screen in the question creation support process according to an embodiment of the present disclosure. [Figure 8] FIG. 8 is a diagram showing a user interface screen in the question creation support process according to an embodiment of the present disclosure. [Figure 9] FIG. 9 is a diagram illustrating a question database according to one embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating problem candidates according to one embodiment of the present disclosure. [Figure 11] FIG. 11 is a diagram showing an example of calculation of the academic ability level of a question according to an embodiment of the present disclosure. [Figure 12] FIG. 12 is a diagram illustrating a question database according to one embodiment of the present disclosure. [Figure 13] FIG. 13 is a diagram illustrating a question database according to one embodiment of the present disclosure. [Figure 14] FIG. 14 is a diagram illustrating training data for a question generation model according to one embodiment of the present disclosure. [Figure 15] FIG. 15 is a diagram illustrating a question database according to one embodiment of the present disclosure. [Figure 16] FIG. 16 is a diagram illustrating training data for a question generation model according to one embodiment of the present disclosure. [Figure 17] FIG. 17 is a diagram illustrating a learner information database according to one embodiment of the present disclosure. [Figure 18] FIG. 18 is a flowchart showing a question creation support process according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0010] In the following embodiment, a question creation support device for creating questions to be distributed to learners is disclosed.

[0011] [Summary of the Disclosure] In an embodiment described later, as shown in Fig. 1, when the academic ability level of a question to be generated is received from a user terminal 20 operated by a teacher or the like, the question creation support device 100 acquires questions corresponding to the academic ability level from a question generation model 10 and / or a question database (DB) 20, and generates question paper data such as a question paper image using the acquired questions. Here, the question paper data may have a layout configuration as shown in Fig. 2, for example, and answer data corresponding to the question paper data can also be generated.

[0012] Generally, the academic ability levels of learners vary, and if a learner learns using questions that are not suited to his / her own academic ability level, the learner may not be able to obtain a good learning effect. It is desirable to provide low-difficulty questions to learners with low academic ability levels, and high-difficulty questions to learners with high academic ability levels. On the other hand, creating questions corresponding to the academic ability levels of each learner may increase the burden on instructors such as teachers. According to the problem creation support device 100 of the following embodiment, it is possible to create questions corresponding to the academic ability level specified by a user such as an instructor, and to distribute the created questions to the learners. This allows a user such as an instructor to efficiently create questions corresponding to the academic ability level by using the problem creation support device 100.

[0013] In the illustrated embodiment, the question creation support device 100 and the user terminal 30 are shown to be realized by separate devices, but the present disclosure is not limited to this, and for example, some or all of the functions provided by the question creation support device 100 may be realized by the user terminal 30. In addition, the question generation model 10 and / or the question DB 20 may be provided within the question creation support device 100, or may be stored and / or realized on a server separate from the question creation support device 100.

[0014] Here, question creation support device 100 may be realized by a computing device such as a server, a personal computer (PC), a smartphone, a tablet, etc., and may have a hardware configuration such as that shown in Fig. 3. That is, question creation support device 100 has a drive device 101, a storage device 102, a memory device 103, a processor 104, a user interface (UI) device 105, and a communication device 106, which are interconnected via a bus B.

[0015] The programs or instructions for implementing the various functions and processes of the question creation support device 100 may be stored in a removable storage medium such as a CD-ROM (Compact Disk-Read Only Memory) or a flash memory. When the storage medium is set in the drive device 101, the programs or instructions are installed from the storage medium via the drive device 101 into the storage device 102 or the memory device 103. However, the programs or instructions do not necessarily have to be installed from the storage medium, and may be downloaded from any external device via a network or the like.

[0016] The storage device 102 is realized by a hard disk drive or the like, and stores installed programs or instructions as well as files, data, etc. used in executing the programs or instructions.

[0017] The memory device 103 is realized by a random access memory, a static memory, or the like, and when a program or an instruction is activated, reads and stores the program or instruction, data, or the like from the storage device 102. The storage device 102, the memory device 103, and the removable storage medium may be collectively referred to as a non-transitory storage medium.

[0018] The processor 104 may be realized by one or more CPUs (Central Processing Units), GPUs (Graphics Processing Units), processing circuitry, etc., which may be composed of one or more processor cores, and performs various functions and processing of the question creation support device 100 in accordance with programs, instructions, data such as parameters necessary to execute the programs or instructions, etc. stored in the memory device 103.

[0019] User interface (UI) device 105 may be composed of input devices such as a keyboard, mouse, camera, microphone, etc., output devices such as a display, speaker, headset, printer, etc., and input / output devices such as a touch panel, and realizes an interface between a user and question creation support device 100. For example, a user may operate question creation support device 100 by operating a GUI (Graphical User Interface) displayed on a display or touch panel using a keyboard, mouse, etc.

[0020] The communication device 106 is realized by various communication circuits that execute wired and / or wireless communication processing with an external device, the Internet, a LAN (Local Area Network), a cellular network, or other communication network.

[0021] However, the above-described hardware configuration is merely an example, and the question creation support device 100 according to the present disclosure may be realized by any other appropriate hardware configuration.

[0022] [Question Creation Support Device] Next, a question creation support device 100 according to an embodiment of the present disclosure will be described. Fig. 4 is a block diagram showing a functional configuration of question creation support device 100 according to an embodiment of the present disclosure. As shown in Fig. 4, question creation support device 100 has a user interface unit 110 and a question creation unit 120. Each functional unit of user interface unit 110 and question creation unit 120 may be realized by processor 104 executing a computer program stored in memory device 103 of question creation support device 100.

[0023] The user interface unit 110 accepts the academic level of the problem to be generated. For example, the academic level here may be indicated by LRT (Latent Rank Theory), a deviation value, difficulty level, or the like. The problem to be generated may be composed of a question sentence and an answer. Depending on the nature of the question, the question may further include a figure related to the question sentence. For example, when the user specifies the academic level of the problem to be generated on the user terminal 30, the user interface unit 110 accepts the academic level specified by the user from the user terminal 30.

[0024] The user interface unit 110 may also receive learning contents such as learning elements, learning element IDs, or keywords for the problem to be generated. Here, the learning elements are those that have been developed mainly by the Japan Association for Promotion of Educational Information Technology, and are elements that are subdivided at an optimal granularity in order to clearly classify the learning contents in textbooks and teaching materials (for example, see https: / / www.mext.go.jp / a_menu / shotou / zyouhou / detail / __icsFiles / afieldfile / 2018 / 11 / 13 / 1410959_001_1_1.pdf, etc.). Each learning element is specified by a learning element name and identified by a learning element ID (consisting of six digits A to Z, 0 to 9). For example, there is a learning element name of "area of ​​a triangle (formula: the height is inside the figure)", and "T1SUEK" is assigned as the learning element ID of the learning element name. Note that the content of the problem to be generated is not limited to learning elements, and may be other descriptions / explanations such as keywords indicating the learning contents. The user interface unit 110 may also receive the number of questions to be generated, the number of questions included on one page of a question paper, and the like from the user terminal 20. The user interface unit 110 passes the received generation conditions, such as the academic ability level and learning elements, to the question creation unit 120.

[0025] The user interface unit 110 may display, for example, an interactive user interface screen such as those shown in FIGS. 5 to 8 on the user terminal 30, and obtain the academic ability level, learning elements, and the like based on the user input on the user interface screen.

[0026] For example, in the user interface screen shown in FIG. 5, the user interface unit 110 first prompts the user to input a learning element ID, a learning element name, or a keyword of the problem to be generated. In the illustrated example, the user inputs a learning element name of "area of ​​triangle (formula: height is inside the figure)". Next, the user interface unit 110 prompts the user to input an academic ability level of the problem to be generated. In the illustrated example, the user inputs an LRT academic ability level of "0.0 to 1.0". Next, the user interface unit 110 prompts the user to input the number of problems to be created. In the illustrated example, the user inputs the number of problems "4". Furthermore, the user interface unit 110 prompts the user to specify the number of pages of the question paper image. In the illustrated example, the user inputs the number of pages "1".

[0027] The question creation unit 120 acquires questions corresponding to the academic level and generates question paper data from the acquired questions. That is, when the academic level is acquired from the user interface unit 110, the question creation unit 120 may acquire questions corresponding to the academic level from the question generation model 10 and / or the question database 20, which will be described in detail below.

[0028] For example, when generation conditions such as academic ability level and learning element are accepted via the user interface screen shown in FIG. 5, the question creation unit 120 may acquire questions corresponding to the learning element "area of ​​triangle (formula: height is inside the figure)" and the academic ability level "0.0 to 1.0" as shown in FIG. 6, and generate question paper data from the acquired questions. Here, the question creation unit 120 generates a question paper image including four questions on one page as shown in the figure, since the number of questions and the number of pages specified by the user are "4" and "1", respectively. The user interface unit 110 may display the generated question paper data and the answers to the questions on the user terminal 30, and allow the user to confirm the question paper data and the answers to the questions. In the illustrated example, the user approves the displayed question paper data and the answers to the questions.

[0029] The question paper data approved by the user may be distributed to the learners. For example, the user interface unit 110 may distribute the question paper data to the learners corresponding to the academic ability level. Specifically, as shown in FIG. 7, the user interface unit 110 may display a list of learners corresponding to the specified academic ability level "0.0 to 1.0" on the user terminal 30. In the illustrated example, the user instructs that the question paper data be distributed to the learner of "5th grade, class 1" from the displayed list. Upon receiving the instruction, the user interface unit 110 distributes the question paper data to the specified learner.

[0030] The designation of the generation conditions such as academic ability level and learning elements is not limited to the format of inputting for each generation condition as described above, and for example, as shown in Fig. 8, the user interface unit 110 may accept user instructions by free description such as "Please create a one-page test consisting of four questions regarding the area of ​​a triangle (formula: the height is the inside of the figure) for learners with academic ability levels of 0.0 to 1.0." In this case, the question creation unit 120 can generate question paper data similar to that of Fig. 6.

[0031] The question creation unit 120 may use the question generation model 10 and / or the question database 20 to obtain questions corresponding to the above-mentioned academic ability level. In one embodiment, the question creation unit 120 may obtain question candidates from the question database 20 based on the learning element name, learning element ID, or keyword related to the problem to be generated, and extract questions corresponding to the academic ability level from the question candidates. For example, it is assumed that the question database 20 stores in advance a question set consisting of learning elements, question sentences, figures, and answers as shown in FIG. 9. If the learning element of the problem to be generated is specified as "area of ​​a triangle (formula: height is inside the figure)", the question creation unit 120 may extract questions corresponding to the learning element of "area of ​​a triangle (formula: height is inside the figure)" from the question database 20, and select the extracted questions as question candidates.

[0032] Alternatively, if a question generation model 10 trained to generate questions based on a learning element name, learning element ID, or keyword related to the question to be generated is available, the question creation unit 120 may obtain question candidates from the question generation model 10 and extract questions corresponding to the academic level from the question candidates. For example, if the learning element of the question to be generated is specified as "area of ​​a triangle (formula: height is inside the figure)", the question creation unit 120 may input the learning element or the corresponding learning element ID to the question generation model 10 and obtain question candidates consisting of a question sentence, a figure, and an answer from the question generation model 10. For example, the question generation model 10 may generate question candidates as shown in FIG. 10. Note that such a question generation model 10 may be realized as any type of machine learning model, such as a language processing model, an image processing model, a video processing model, an audio processing model, and / or a combination thereof. The question generation model 10 may be realized as a machine learning model trained by training data consisting of pairs of input data indicating learning contents such as learning elements and correct answer data (question text, answer, diagram, etc.), or may be realized as one or more well-known machine learning models and / or any combination thereof. For example, the question generation model 10 may be realized by combining a GPT-based general-purpose language model used in ChatGPT and the like with an image generation model such as DALL-E.

[0033] The question creation unit 120 may estimate the academic ability level of each question candidate obtained from the question generation model 10 and / or the question database 20 in this manner by comparing it with questions in a question set prepared in advance for which the academic ability level has been estimated. For example, if such a question set is as shown in Fig. 11, the question creation unit 120 may detect questions from the question set that have the same learning element as the question candidate and similar question text, and set the academic ability level of the question detected from the question set as the academic ability level of the question candidate.

[0034] Here, each problem in the problem set is answered by a learner whose academic ability level is known in advance, and statistical results regarding the academic ability levels of those who answered correctly are obtained. In the illustrated example, the academic ability levels of those who answered correctly for the problem "Find the area of ​​an equilateral triangle with one side measuring 4 cm" are graphed. In order to exclude cases where the answer was given correctly by chance, a threshold value for the number of people who answered correctly as shown in the figure may be set, and the academic ability level of the lowest correct answerer above the threshold (minimum required LRT = 0.5) may be set as the academic ability level of this problem. In the same way, the academic ability level of the problem "Find the area of ​​an equilateral triangle with one side measuring 12 cm" may be estimated as 0.7. Note that the setting of the academic ability level of the problem is not limited to the academic ability level of the lowest correct answerer above the above-mentioned threshold, and may be any other level, such as the average academic ability level above the threshold. It may be set to an appropriate value.

[0035] For example, if the question candidate is "Find the area of ​​an equilateral triangle with one side being 6 cm," the question creation unit 120 may select the above-mentioned two questions, "Find the area of ​​an equilateral triangle with one side being 4 cm," and "Find the area of ​​an equilateral triangle with one side being 12 cm," as questions similar to the question candidate. In this case, the question creation unit 120 may estimate the academic ability level of the question candidate as the average academic ability level of the two similar questions, "0.6." In this way, the question creation unit 120 may estimate the academic ability level of each question candidate as shown in FIG. 12, and select a question corresponding to the specified academic ability level "0.0 to 1.0." However, the estimation of the academic ability level for each question described above is merely an example, and any other appropriate estimation method may be used.

[0036] The above-mentioned problem acquisition involves acquiring problem candidates from the problem generation model 10 and / or the problem database 20 and estimating the academic level of each problem candidate, but the present disclosure is not limited thereto. In another embodiment, the problem creation unit 120 may acquire problems whose academic level has already been estimated from the problem generation model 10 and / or the problem database 20. For example, the problem creation unit 120 may extract problems corresponding to the academic level from the problem database 20 based on the learning element name, learning element ID, or keyword related to the problem to be generated and the academic level. Specifically, the problem database 20 is assumed to have stored in advance a problem set consisting of a learning element, a problem statement, a figure, an answer, and a problem difficulty level as shown in FIG. 13. If the learning element of the problem to be generated is "area of ​​a triangle (formula: height is inside the figure)" and the academic level is specified as "low difficulty", the problem creation unit 120 may extract problems corresponding to the learning element of "area of ​​a triangle (formula: height is inside the figure)" and the problem difficulty level of "low" from the problem database 20. Here, both question difficulty and LRT are indicators of academic ability level and may be used interchangeably. For example, question difficulty levels of "low", "medium" and "high" may be associated with LRTs of, without limitation, "0.5", "1.5" and "2.5", respectively.

[0037] Alternatively, if a question generation model 10 trained to generate questions based on a learning element name, learning element ID, or keyword related to the question to be generated and an academic level is available, the question creation unit 120 may obtain a question from the question generation model 10. For example, if the learning element of the question to be generated is "area of ​​triangle (formula: height is inside the figure)" and the question difficulty is specified as "low", the question creation unit 120 may input the learning element or the corresponding learning element ID and the question difficulty "low" to the question generation model 10 and obtain a question consisting of a question text, a figure, and an answer from the question generation model 10. For example, the question generation model 10 may generate a question as shown in FIG. 14. Note that such a question generation model 10 may be realized as any type of machine learning model, such as a language processing model, an image processing model, a video processing model, an audio processing model, and / or a combination thereof. The question generation model 10 may be realized as a machine learning model trained by training data consisting of pairs of input data indicating learning contents such as learning elements and difficulty levels and correct answer data (question text, answer, diagram, question difficulty level, etc.), or may be realized as one or more well-known machine learning models and / or any combination thereof. For example, the question generation model 10 may be realized by combining a GPT-based general-purpose language model used in ChatGPT and the like with an image generation model such as DALL-E.

[0038] Although the above-mentioned questions are obtained corresponding to the learning elements, the present disclosure is not limited thereto. For example, past questions that have been asked in the entrance examinations of each school may be extracted as questions. In one embodiment, the question creation unit 120 may extract questions corresponding to the academic level from the question database 20 based on the question source and the subject. For example, the question creation unit 120 may acquire corresponding questions from the question database 20 based on the school and subject that sets the question to be generated and the academic level (difficulty). Specifically, it is assumed that the question database 20 stores past questions indicating the subject, question text, answer, and university name as shown in FIG. 15. If the subject of the question to be generated is "Mathematics" and the university is specified as "University of Tokyo", the question creation unit 120 may extract questions corresponding to the subject "Mathematics" and the university name "University of Tokyo" from the question database 20 and select the extracted questions as question candidates.

[0039] Alternatively, if a question generation model 10 trained to generate questions based on a question source and a subject related to the question to be generated is available, the question creation unit 120 may obtain question candidates from the question generation model 10 and extract questions corresponding to the academic level from the question candidates. For example, if the subject of the question to be generated is "mathematics" and the university is specified as "University of Tokyo", the question creation unit 120 may input the subject and the name of the university to the question generation model 10 and obtain past question candidates from the question generation model 10. For example, the question generation model 10 may generate question candidates as shown in FIG. 16. Note that such a question generation model 10 may be realized as any type of machine learning model, such as a language processing model, an image processing model, a video processing model, an audio processing model, and / or a combination thereof. The question generation model 10 may be realized as a machine learning model trained by training data consisting of pairs of input data indicating learning contents such as learning elements and university names and correct answer data (question text, answer, diagram, etc.), or may be realized as one or more well-known machine learning models and / or any combination thereof. For example, the question generation model 10 may be realized by combining a GPT-based general-purpose language model used in ChatGPT and the like with an image generation model such as DALL-E.

[0040] In this way, the question creation unit 120 may extract questions corresponding to the specified academic ability level from the question candidates acquired from the question generation model 10 and / or the question database 20. The academic ability level of each question candidate may be estimated by the estimation method described above or any other appropriate estimation method.

[0041] The learner information may be managed by a learner information database as shown in FIG. 17. In the learner information shown in FIG. 17, questions that have been correctly answered in the past may be stored in addition to the grade and name of each learner. The highest academic ability level among the questions that have been correctly answered in the past may be set as the academic ability level of the learner. Furthermore, the learner information database may be appropriately updated to appropriately reflect the current academic ability level of each learner. In this way, even if the academic ability level of the learner rises, the learning level of each learner can be dynamically estimated, and the discrepancy between the question to be generated and the current academic ability level of the learner can be reduced.

[0042] [Question creation support process] Next, a question creation support process according to an embodiment of the present disclosure will be described. Fig. 18 is a flowchart showing the question creation support process according to an embodiment of the present disclosure. The question creation support process may be executed by, for example, the question creation support device 100, and more specifically, may be realized by the processor 104 of the question creation support device 100 executing a computer program or instructions stored in the memory device 103.

[0043] In step S101, the question creation support device 100 accepts the academic ability level of the question to be generated. Specifically, the question creation support device 100 may acquire any information related to the generation of the question, such as the content of the question to be generated, the academic ability level, and the configuration of the question paper image, as a generation condition from the user terminal 30 of a user such as a teacher.

[0044] For example, the question creation support device 100 may acquire the generation conditions from the user terminal 30 via a question creation support app that provides a question-and-answer style user interface screen as shown in Figures 5 to 8. Such a question creation support app may be pre-installed in the user terminal 30. Alternatively, the user terminal 30 may access a question creation support website and operate a user interface screen as shown in the drawings that is provided by the question creation support website.

[0045] In step S102, the question creation support device 100 acquires questions corresponding to the academic ability level. For example, when the learning element is "area of ​​triangle (formula: height is inside the figure)" and the academic ability level is "0.0 to 1.0", the question creation support device 100 may acquire question candidates corresponding to the learning element from the question generation model 10 and / or question database 20, and select a question corresponding to the academic ability level from the acquired question candidates.

[0046] In step S103, the question creation support device 100 generates question paper data from the acquired questions. For example, the question creation support device 100 may generate a question paper image as shown in Fig. 2. The question creation support device 100 may also distribute the generated question paper image to learners who correspond to the academic ability level.

[0047] According to the above-described embodiment, it becomes possible to automatically generate questions that correspond to the academic level specified by the user, and users such as teachers can use the question creation support device 100 to efficiently create question sheets that correspond to the academic level.

[0048] Although the examples of the present disclosure have been described in detail above, the present disclosure is not limited to the specific embodiments described above, and various modifications and variations are possible within the scope of the gist of the present disclosure described in the claims. [Explanation of symbols]

[0049] 10 Problem Generation Model 20 Problem Database 30 User terminal 100 Question Creation Support Device 110 User Interface Section 120 Question Creation Department

Claims

1. a user interface unit that accepts the academic ability level of a question to be generated; a question creation unit that acquires questions corresponding to the academic ability level and generates question paper data from the acquired questions; A problem creation support device having the above structure.

2. The question creation support device of claim 1, wherein the question creation unit obtains question candidates from a first question database based on a learning element name, learning element ID, or keyword related to the question to be generated, and extracts questions corresponding to the academic ability level from the question candidates.

3. The question creation support device of claim 1, wherein the question creation unit obtains question candidates from a first question generation model trained to generate questions based on a learning element name, learning element ID, or keyword related to the question to be generated, and extracts questions corresponding to the academic ability level from the question candidates.

4. The question creation support device of claim 1, wherein the question creation unit extracts questions corresponding to the academic ability level from a second question database based on a learning element name, learning element ID or keyword related to the question to be generated and the academic ability level.

5. The question creation support device of claim 1, wherein the question creation unit obtains questions corresponding to the academic ability level from a second question generation model trained to generate questions based on a learning element name, learning element ID or keyword related to the question to be generated and the academic ability level.

6. 2. The question creation support device according to claim 1, wherein the question creation unit extracts questions corresponding to the academic ability level from a third question database based on a question source and a subject.

7. The question creation support device according to claim 1 , wherein the question creation unit obtains questions corresponding to the academic ability level from a third question generation model trained to generate questions based on a question source and a subject.

8. The problem creation support device according to claim 1 , wherein the problem includes a problem statement, an answer, and a diagram.

9. 2. The question creation support device according to claim 1, wherein the question creation section generates a question paper image from the acquired questions based on the number of questions included on one page of the question paper.

10. 2. The question creation support device according to claim 1, wherein the user interface unit distributes the question paper data to learners corresponding to the academic ability level.

11. Accepting the academic level of the problem to be generated; Obtaining questions corresponding to the academic ability level and generating question paper data from the obtained questions; A problem creation assistance method implemented by a computer.

12. Accepting the academic level of the problem to be generated; Obtaining questions corresponding to the academic ability level and generating question paper data from the obtained questions; A program that causes a computer to execute the following.

Images