Information processing device and program

Abstract

To analyze and output a learning tendency of a learner to a similar question.SOLUTION: An information processing device includes a question storage part for storing question information including information of a group to which a question belongs, and a learning history storage part for storing answer information on an answer to the question by the learner. The information processing device calculates similarity of the question on the basis either one of the question information and the answer information. Then, the information processing device further classifies the question belonging to the same group to a fragmented similar question group on the basis of the similarity of the question. Further, the information processing device analyzes the question belonging to each similar question group on the basis of the question information and the answer information.SELECTED DRAWING: Figure 15

Description

[Technical Field]

[0001] The present invention relates to a technique for outputting information related to learning. [Background technology]

[0002] Systems have been known in the past that store test results administered to students in a database and enable them to be checked on a computer. Patent Document 1 discloses an education support system that has a performance summary database that summarizes the test scores of learners and is configured so that the database can be accessed using a tablet terminal device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-65987 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the invention of Patent Document 1 only allows checking test results, which are learning histories, and does not allow checking students' learning tendencies.

[0005] The present invention has been made to solve the above-mentioned problems, and has an object to provide an information processing device that analyzes and outputs a learner's learning tendency for similar questions. [Means for solving the problem]

[0006] In one aspect of the invention, The information processing device connected to the terminal device used by the target person who is a specific learner is capable of communicating with the learning content classified into learning elements. a question storage unit that stores question information; a learning history storage unit that stores answer information regarding answers given by learners to questions; and a similarity calculation unit that calculates a similarity of the questions based on at least one of the question information and the answer information; A plurality of learning elements each having the same learning elementa similar problem group classification unit that classifies the problems into further subdivided similar problem groups based on the similarity of the problems; an academic ability calculation unit that calculates the academic ability of the learner based on the answer information; a similar academic ability group classification unit that classifies learners who have tackled questions belonging to the same similar problem group into multiple similar academic ability groups that are further divided according to their academic ability; an input information acquisition unit that acquires input information including information on a target problem that is a question entered by the subject from the terminal device; a learning element identification unit that refers to the problem storage unit and identifies a learning element to which the target problem belongs; a similar academic ability group identification unit that identifies a similar problem group corresponding to the learning element to which the target problem belongs, obtains the subject's academic ability based on the input information, and identifies a similar academic ability group to which the subject belongs; and a graph creation unit that creates a graph corresponding to multiple similar academic ability groups including the similar academic ability group to which the subject belongs. Equipped with.

[0007] For example, the information processing device can obtain similar questions from other learning materials belonging to the same group for a question in a learning material, and further subdivide and classify the questions by similarity. Furthermore, the information processing device can compare the learner's learning results and learning trends for each level of question similarity by analyzing the learner's answer information. Furthermore, the information processing device can compare the learner's learning results and learning trends for each level of question similarity and for each learner's academic ability by analyzing the learner's answer information. Furthermore, the information processing device can identify an arbitrarily set group of similar academic ability for the subject. Furthermore, the information processing device creates a graph corresponding to each similar academic ability group, making it easy for the learner to visually check the learning results and learning trends for each level of question similarity and each learner's academic ability.

[0010] In one aspect of the information processing device, the graph creation unit creates a graph corresponding to the similar ability group to which the subject belongs, based on the answer information of the subject to the target question, so as to output the position of the subject. According to this aspect, the learner can easily check his / her position on the graph.

[0011] In one aspect of the information processing device, the graph creation unit creates a new graph based on answer information from learners who have tackled problems with the same learning element as the target problem and who have a similar level of academic ability to the subject, and creates a graph so that the average value of the answers to the problems by the learners and the value of the answers to the target problem by the subject are simultaneously output on the new graph. According to this aspect, the learner can easily compare their own value with the average value of other learners with a similar level of academic ability on the graph.

[0012] In one aspect of the information processing device, the graph creation unit creates a graph so as to simultaneously output the transition of the average value for each similar question group and the transition of the value for each similar question group. According to this aspect, a learner can check the learning results and learning tendencies of other learners with similar academic ability and his or her own by not only looking at the values ​​on the graph but also at the transitions.

[0013] In another aspect of the information processing device, the information processing device includes a comment storage unit that stores, as a learning trend, a deviation between the change in the average value of the answers to the questions by the learner and the change in the value of the answers to the questions by the subject, in association with comments to the learner, and the graph creation unit calculates the deviation between the change in the average value for each similar question group and the change in the value for each similar question group, and creates a graph to output comments extracted from the comment storage unit based on the calculated deviation. According to this aspect, the information processing device can provide the learner with advice on learning strategies through comments in accordance with the deviation in the trends.

[0014] In another aspect of the information processing device, the similarity is the difficulty level of the questions, the similarity calculation unit calculates the difficulty level of the questions based on the answer information, and the similar-question group classification unit classifies questions belonging to the same group based on the difficulty level of the questions. According to this aspect, the information processing device can compare the learning results and learning tendencies of learners based on the difficulty level of the questions.

[0015] In another aspect of the information processing device, the similarity is a text similarity of the questions, the similarity calculation unit calculates the text similarity based on the question information, and the similar-question group classification unit classifies questions belonging to the same group based on the text similarity. According to this aspect, the information processing device can compare the learning results and learning tendencies of learners based on the text similarity of the questions.

[0016] In another aspect of the invention, A terminal device used by a specific learner is communicably connected to the device, A program executed by an information processing device having a computer, The learning content is divided into detailed learning elements a question storage unit that stores question information; a learning history storage unit that stores answer information regarding answers given by learners to questions; and a similarity calculation unit that calculates a similarity of the questions based on at least one of the question information and the answer information; A plurality of learning elements each having the same learning element a similar problem group classification unit that classifies the problems into further subdivided similar problem groups based on the similarity of the problems; an academic ability calculation unit that calculates the academic ability of the learner based on the answer information; a similar academic ability group classification unit that classifies learners who have tackled problems belonging to the same similar problem group into multiple similar academic ability groups that are further divided according to their academic ability; an input information acquisition unit that acquires input information from the terminal device including information on a target problem that is a problem entered by the subject; a learning element identification unit that refers to the problem storage unit and identifies the learning element to which the target problem belongs; a similar academic ability group identification unit that identifies a similar problem group corresponding to the learning element to which the target problem belongs, obtains the subject's academic ability based on the input information, and identifies the similar academic ability group to which the subject belongs; a graph creation unit that creates a graph corresponding to multiple similar academic ability groups including the similar academic ability group to which the subject belongs;By installing this program in a computer and running it, an information processing device according to the present invention can be configured. [Effects of the Invention]

[0017] According to the information processing device of the present invention, it is possible to analyze and output the learning tendency of a learner with respect to similar questions. [Brief explanation of the drawings]

[0018] [Figure 1] 1 shows the configuration of a learning support system to which a server of the present invention is applied. [Figure 2] FIG. 2 is a block diagram showing the hardware configuration of a server. [Figure 3] 10 is an example of a data configuration of a learning element DB. [Figure 4] 10 is an example of the data structure of a question DB. [Figure 5] 10 is an example of a data configuration of a learning history DB. [Figure 6] FIG. 2 is a block diagram showing the functional configuration of a server in the first embodiment. [Figure 7] Here is an example of a problem with the same learning element. [Figure 8] FIG. 10 is a diagram illustrating a method for grouping based on feature amounts. [Figure 9] 1 is an example of a first graph showing a student's learning trends. [Figure 10] This is an example of a second graph showing students' learning trends. [Figure 11] 10 is an example of a first learning tendency screen in the first embodiment. [Figure 12] 10 is an example of a second learning tendency screen in the first embodiment. [Figure 13] FIG. 2 is a block diagram showing the hardware configuration of a student terminal. [Figure 14] 10 is a flowchart of a classification process. [Figure 15] 10 is a flowchart of an analysis process. [Figure 16] 10 is a flowchart of subject graph processing. [Figure 17] 10 shows an example of the configuration of a learning support system according to a third modified example. [Figure 18] FIG. 10 is a block diagram showing the functional configuration of a server in the second embodiment. [Figure 19] 10 is an example of a first learning tendency screen in the second embodiment. [Figure 20] 10 is an example of a second learning tendency screen in the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0019] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. First Embodiment [Overall configuration] Figure 1 shows the configuration of a learning support system to which the server of the present invention is applied. Learning support system 100 is a system that acquires questions that belong to the same group as a given question and the answers to the question, analyzes learning trends for each similarity, and outputs the results. Learning support system 100 is configured so that server 10, multiple student terminals 20, and multiple teacher terminals 30 can communicate with each other via network 5 such as the Internet.

[0020] The server 10 is an information processing device that processes, stores, and transmits / receives various types of information, and is, for example, a server device, a personal computer, or a general-purpose tablet PC (personal computer).

[0021] The student terminal 20 is used by learners such as students and their parents, and is an information processing device such as a smartphone, a mobile phone, a wearable device such as an Apple Watch (registered trademark), a tablet, a personal computer terminal, etc. Specifically, the student terminal 20 transmits learning history information and input information, receives and displays learning trend screens, etc.

[0022] The teacher terminal 30 is used by a learning supporter such as a teacher, and is, for example, an information processing device such as a tablet or personal computer terminal. Specifically, the teacher terminal 30 transmits input information, receives and displays a learning trend screen, etc.

[0023] [Server Configuration] 2 is a block diagram showing the hardware configuration of server 10. Server 10 includes a communication unit 11, a control unit 12, a storage unit 13, a recording medium 14, a display unit 15, and an input unit 16. These components, a learning element database (hereinafter, "database" will be referred to as "DB") 41, a question DB 42, a learning history DB 43, and a comment DB 44 are interconnected via a bus 19.

[0024] The server 10 may be executed by a single computer, or may be executed by a plurality of computers in a distributed manner, or may be executed by a virtual machine in a distributed manner.

[0025] The communication unit 11 is a communication unit for communicating with the student terminal 20 and the teacher terminal 30 via the network 5. Specifically, the communication unit 11 receives input information from the student terminal 20 and the teacher terminal 30, and transmits a learning trend screen to the student terminal 20 and the teacher terminal 30.

[0026] The control unit 12 includes a central processing unit (CPU), a micro-processing unit (MPU), a graphics processing unit (GPU), and other arithmetic processing devices, and performs various information processing, control processing, and the like related to the server 10 by reading and executing programs stored in the storage unit 13. The programs can be deployed so that they are executed on a single computer, located at one site, or distributed across multiple sites and on multiple computers interconnected by a communications network. Although the control unit 12 is described in FIG. 2 as being a single processor, it may also be a multi-processor.

[0027] The storage unit 13 includes memory elements such as RAM (Random Access Memory) and ROM (Read Only Memory), and stores programs, data, etc. required for the control unit 12 to execute processing. The storage unit 13 also temporarily stores data, etc. required for the control unit 12 to execute arithmetic processing.

[0028] The recording medium 14 is a non-volatile, non-temporary recording medium such as a disk-shaped recording medium or a semiconductor memory, and is configured to be detachable from the server 10. The recording medium 14 records various programs executed by the control unit 12. When the server 10 executes classification processing or analysis processing, the programs recorded on the recording medium 14 are loaded into the memory unit 13 and executed by the control unit 12.

[0029] The display unit 15 is a liquid crystal display, an organic EL (electroluminescence) display, or the like, and displays various information in accordance with instructions from the control unit 12. The input unit 16 is an input device such as a mouse, keyboard, touch panel, or button, and outputs received operation information to the control unit 12.

[0030] The learning element DB 41 stores information about learning elements, which are subdivisions of learning content. Here, learning elements refer to learning content and textbook explanations that have been sub-divided into optimal granularity, based on learning groups such as units, for purposes such as linking textbooks and teaching materials, understanding learning progress, and creating lesson plans. In other words, problems with the same learning element can be said to belong to the same group. Furthermore, a unit is a group of learning activities centered on a specific theme, and is set for each subject, such as "mathematics" or "Japanese," and is composed of one or more learning elements.

[0031] FIG. 3 is an example of the data structure of the learning element DB 41. As shown in the figure, the learning element DB 41 stores information on subjects, fields, units, learning elements, and learning element IDs. The subject is the name of the subject, such as "Mathematics" or "Japanese." The field is the name of the field, set for each subject, such as "Differentiation." The unit is the name of the unit, set for each field, such as "Differentiation of a Composite Function." The learning element is information indicating the learning content that the learning element targets, set for each unit, such as "log+linear equation," "log+quadratic equation," etc. The learning element ID is identification information for the learning element.

[0032] It is assumed that the fields that make up a subject, the units that make up a field, and the learning elements that make up a unit are all set in advance. The data structure of the learning element DB 41 shown in Figure 3 is an example, and the present invention is not limited to this. The data structure of the learning element DB 41 can be set arbitrarily as long as it stores information related to the identification of learning elements.

[0033] The question DB 42 stores question information about the questions that students tackle, in association with a question ID that identifies the question. Figure 4 is an example of the data structure of the question DB 42. As shown in the figure, the question DB 42 stores information such as a question ID, question data, learning element ID, learning material name, page, and difficulty level. The question data is data about the question indicated by the question ID. The learning element ID is identification information for the learning element to which the problem indicated by the question ID belongs. The learning material name is the name of the learning material, such as a reference book or textbook, that contains the problem indicated by the question ID, and the page is the page and question number on which the problem is written in the learning material.

[0034] The difficulty level is a numerical value indicating the difficulty of the question indicated by the question ID. Here, the question difficulty level (hereinafter simply referred to as "difficulty level") is based on any concept, such as the difficulty level of the question or the rate of correct answers, and may be set by evaluating each question using Item Response Theory (IRT) or the like, or may be set artificially in advance. Specifically, in this embodiment, the difficulty level is calculated based on the student's answer information, which will be described later. However, as shown in FIG. 4, the difficulty level may be stored in the question DB 42 and extracted when needed, or may not be stored in the question DB 42 and may be calculated based on the answer information each time needed.

[0035] It should be noted that which learning element a question belongs to is set in advance. Also, the data structure of the question DB 42 shown in Figure 4 is an example, and the present invention is not limited to this, and the data structure of the question DB 42 can be set arbitrarily as long as it stores information linking questions to learning elements.

[0036] The learning history DB 43 stores answer information related to the answers to problems that students have worked on, in association with a student ID that identifies the student. FIG. 5 is an example of the data structure of the learning history DB 43. As shown in the figure, the learning history DB 43 stores information such as a student ID, a problem ID, correct / incorrect answers, the answer time, and the number of characters in the answer. The problem ID is identification information for the problem that the student identified by the student ID worked on. The correct / incorrect answers, the answer time, and the number of characters in the answer are respectively the correct / incorrect answers to the problems that the student identified by the student ID worked on, the time taken to answer the answer, and the number of characters in the answer.

[0037] In this embodiment, as an example, the student terminal 20 is linked in advance with the student ID of the student who uses it, and answer information regarding answers to questions that the student has worked on using the student terminal 20 is automatically stored in the learning history DB 43 of the server 10. Also, the data structure of the learning history DB 43 shown in Fig. 5 is an example, and the present invention is not limited to this, and the learning history DB 43 stores information regarding the learning that the student has worked on using the student terminal 20, and the data structure can be set as desired.

[0038] The comment DB 44, the details of which will be described later, stores comment information that links the student's learning tendency in terms of answer time and number of characters in the answer with comments to the student.

[0039] The storage format of each DB described above is an example, and other storage formats may be used as long as the relationships between the data are maintained. Each DB is realized by a recording medium such as a hard disk drive (HDD) or a solid state drive (SSD). In this embodiment, the storage unit 13 and the various DBs may be configured as an integrated storage device, or may be separate storage devices. The various DBs may be external storage devices connected to the server 10, and the configuration thereof may be set arbitrarily.

[0040] 6 is a block diagram showing the functional configuration of the server 10. Functionally, the server 10 includes a learning element DB 41, a question DB 42, a learning history DB 43, a comment DB 44, a similarity calculation unit 45, a similar question group classification unit 46, and an analysis unit 47.

[0041] The similarity calculation unit 45, the similar problem group classification unit 46, and the analysis unit 47 are realized by the control unit 12 executing a program.

[0042] The similarity calculation unit 45 calculates the similarity of questions based on one or more of the question information stored in the question DB 42 and the answer information stored in the learning history DB 43. Here, the similarity may refer to, for example, the difficulty of the question or the text similarity of the question. Specifically, the similarity calculation unit 45 uses IRT as an example of similarity to calculate the difficulty of each question as a numerical value. The lower the numerical value, the easier the question, and the higher the numerical value, the more difficult the question. Furthermore, the similarity calculation unit 45 uses cosine similarity as another example of similarity to calculate the similarity of the text of the question (hereinafter also referred to as "text similarity") as a numerical value. As will be described in detail later, in feature space, the closer the question is to a question, the higher the similarity, and the closer the numerical value, the closer the question is to a question. On the other hand, the farther the question is to a question, the lower the similarity, and the closer the numerical value, the closer the text similarity is to a question.

[0043] The similar question group classification unit 46 extracts questions with the same learning element from the question DB 42, and classifies the extracted questions into further subdivided similar question groups based on the degree of similarity.

[0044] Specifically, the classification method by the similar problem group classification unit 46 will be described. First, a method will be described in which the similarity is the difficulty of the problem and multiple problems with the same learning element are classified based on the difficulty. Figure 7 is an example of problems with the same learning element. As shown in Figure 7, a problem with a learning element of (log + 1 order equation) has Formula 81, Formula 82, and Formula 83.

[0045] In this embodiment, multiple questions with the same learning element are classified into three groups: similar question group A with difficulty level "0.0 to 1.0", similar question group B with difficulty level "1.1 to 2.0", and similar question group C with difficulty level "2.1 to 3.0". The difficulty level used as the classification standard and the number of similar question groups into which the questions are classified can be set arbitrarily.

[0046] As shown in FIG. 7, the difficulty level of the problem for Formula 81 is "0.8," so the similar problem group classification unit 46 classifies Formula 81 into similar problem group A, which has a difficulty level of "0.0 to 1.0." Furthermore, the difficulty level of the problem for Formula 82 is "1.3," so the similar problem group classification unit 46 classifies Formula 82 into similar problem group B, which has a difficulty level of "1.1 to 2.0." Furthermore, the difficulty level of the problem for Formula 83 is "2.6," so the similar problem group classification unit 46 classifies Formula 83 into similar problem group C, which has a difficulty level of "2.1 to 3.0." In this way, the similar problem group classification unit 46 classifies problems of similar difficulty into the same similar problem group based on the difficulty level.

[0047] Next, a method for classifying multiple problems with the same learning element based on text similarity, where the similarity is text similarity, will be described. FIG. 8 is a diagram illustrating a method for grouping problems based on features. As shown in FIG. 8(a), the similar problem group classification unit 46 treats each character of a problem with Formula 81 as text, such as "y" and "=", and quantifies and extracts the features of the problem with Formula 81 by using a machine learning technique capable of processing time-series information as text, such as Long Short Term Memory (LSTM). The similar problem group classification unit 46 quantifies the features of all problems with the same learning element and plots them in a feature space, as shown in FIG. 8(b). Then, as shown in FIG. 8(c), the similar problem group classification unit 46 groups all problems with the same learning element into similar problem group A, similar problem group B, and similar problem group C by clustering. The closer the problems are in the feature space, the higher the text similarity, and the farther the problems are in the feature space, the lower the text similarity. Therefore, it can be said that the similar question group classification unit 46 classifies a plurality of questions having the same learning element based on the degree of text similarity.

[0048] In this embodiment, the questions are mathematical expressions, but the present invention is not limited to this, and the questions may be, for example, written questions that require a written answer. In other words, the questions can be set arbitrarily.

[0049] The analysis unit 47 includes an academic ability assessment unit 51, a similar academic ability group classification unit 52, an input information acquisition unit 53, a learning element identification unit 54, an extraction unit 55, a similar academic ability group identification unit 56, and a graph creation unit 57, and analyzes questions belonging to similar question groups based on the question information stored in the question DB 42 and the answer information stored in the learning history DB 43, for each degree of similarity of the question and the student's academic ability.

[0050] The academic ability assessment unit 51, similar academic ability group classification unit 52, input information acquisition unit 53, learning element identification unit 54, extraction unit 55, similar academic ability group identification unit 56 and graph creation unit 57 are realized by the control unit 12 executing a program.

[0051] The academic ability assessment unit 51 calculates the academic ability level (hereinafter simply referred to as "academic ability") of each student based on the answer information stored in the learning history DB 43. Specifically, the academic ability assessment unit 51 evaluates each student using Latent Rank Theory (LRT) or the like based on the answer information of each student to calculate the academic ability level as a numerical value. The lower the numerical value of the academic ability level, the lower the student's learning ability, and the higher the numerical value, the higher the student's learning ability. In this way, the academic ability level is calculated based on the answer information of the student, but it may be stored in the storage unit 13 in association with the student ID and extracted when needed, or it may not be stored in the storage unit 13 and may be calculated based on the answer information whenever needed.

[0052] In this embodiment, the academic ability level is calculated based on answer information, but the present invention is not limited to this, and it may also be calculated as a deviation value or the like and stored in advance in association with the student ID.

[0053] The similar academic ability group classification unit 52 classifies students who have worked on problems belonging to a predetermined similar problem group into further subdivided similar academic ability groups by academic ability level. The analysis unit 47 analyzes the problems worked by students belonging to each similar academic ability group based on the problem information and answer information.

[0054] The input information acquisition unit 53 acquires input information including a student ID and information related to a question (hereinafter also referred to as a "target question") for which the student will check their learning tendency from the student terminal 20. When a student wants to check their own learning tendency, the student uses the student terminal 20 to input a predetermined question as the target question and transmits the input information to the server 10. The input information acquisition unit 53 acquires the input information from the student terminal 20 and sets the student as the target of analysis.

[0055] The learning element identification unit 54 identifies the learning element of the target question included in the input information by referring to the question DB 42. Specifically, the learning element identification unit 54 identifies the question ID of the question included in the input information and the learning element ID of the question by referring to the question DB 42.

[0056] The extraction unit 55 extracts answer information of the subject from the learning result DB 43 based on the student ID included in the input information.

[0057] The similar academic ability group identification unit 56 identifies the similar academic ability group to which the subject belongs based on the learning elements of the target question, the similarity of the target question, and the subject's academic ability level. Specifically, the similar academic ability group identification unit 56 acquires the learning elements of the target question identified by the learning element identification unit 54, the similarity of the target question calculated by the similarity calculation unit 45, and the academic ability level calculated by the academic ability assessment unit 51 based on the subject's answer information, and identifies the similar academic ability group to which the subject belongs.

[0058] The graph creation unit 57 includes a position identification unit 61 and a transition identification unit 62, and creates a graph representing the student's learning tendency based on the question information and answer information. The graph creation unit 57 then creates a learning tendency screen including the created graph, and transmits it to the student terminal 20 of the target person.

[0059] The position specifying unit 61 and the transition specifying unit 62 are realized by the control unit 12 executing a program.

[0060] Fig. 9 is an example of a first graph showing a student's learning tendency. Fig. 9 has question items 84 displaying questions whose learning element is (log+1 degree equation), and a graph 85 showing the student's learning tendency. Question items 84 include questions 84a to 84d whose learning element is (log+1 degree equation) extracted from question DB 42.

[0061] Graph 85 has nine graphs 85a to 85i, with similar question group A, similar question group B, and similar question group C set on the vertical axis and academic ability level 1, academic ability level 2, and academic ability level 3 set on the horizontal axis. Specifically, if similarity is the difficulty of the question, for example, similar question group A is a question with a difficulty level of "0.0 to 1.0," similar question group B is a question with a difficulty level of "1.1 to 2.0," and similar question group C is a question with a difficulty level of "2.1 to 3.0." Also, if similarity is the text similarity of the question, for example, similar question group A is a question with an integer (log+1 degree equation), similar question group B is a question with a decimal (log+1 degree equation), and similar question group C is a question with a fraction (log+1 degree equation).

[0062] Graph 85a is a graph created based on the answer information of students at academic ability level 1 who tackled the problems belonging to similar problem group A. In other words, graph 85a is a graph corresponding to the similar academic ability group to which students at academic ability level 1 belong who tackled the problems belonging to similar problem group A.

[0063] 9, graph 85a has answer time on the vertical axis and the number of characters in the answer on the horizontal axis, and an icon for each student is arranged based on the answer information of each student. Specifically, graph creation unit 57 first refers to question DB 42 and extracts all of the answer information of each student corresponding to the questions belonging to similar question group A from learning history DB 43. Then, based on the extracted answer information, graph creation unit 57 calculates the average answer time and average number of characters in the answer of each student corresponding to the questions belonging to similar question group A. Then, graph creation unit 57 creates graph 85a by arranging the icon of each student at the position indicated by the average answer time and average number of characters in the answer of each student.

[0064] For example, if Student A has worked on "100 questions" belonging to Similar Question Group A, the graph creation unit 57 calculates Student A's average answer time and average number of characters in the answer based on the answer information for all 100 questions, and creates graph 85a by arranging Student A's icon 87a. Also, if Student B has worked on only "two questions" belonging to Similar Question Group A, the graph creation unit 57 calculates Student B's average answer time and average number of characters in the answer based on the answer information for the two questions, and creates graph 85a by arranging Student B's icon 87b.

[0065] Then, the graph creation unit 57 groups groups of students with similar tendencies in the created graph 85a. Examples of grouping methods include grouping using a combination of RANSAC (Random Sample Consensus) and k-means. Specifically, as shown in Fig. 9, the graph creation unit 57 groups the student icons arranged in the graph 85a into similar tendency groups 86a, 86b, and 86c by clustering. Students belonging to the same similar tendency group can be said to have the same learning tendencies.

[0066] Like graph 85a, graph 85b is a graph corresponding to the similar academic ability group to which students at academic ability level 2 belong among students who worked on problems belonging to similar problem group A. Graph 85c is a graph corresponding to the similar academic ability group to which students at academic ability level 3 belong among students who worked on problems belonging to similar problem group A.

[0067] Graph 85d is a graph corresponding to the similar academic ability group to which students at academic ability level 1 belong among students who worked on problems belonging to similar problem group B. Graph 85e is a graph corresponding to the similar academic ability group to which students at academic ability level 2 belong among students who worked on problems belonging to similar problem group B. Graph 85f is a graph corresponding to the similar academic ability group to which students at academic ability level 3 belong among students who worked on problems belonging to similar problem group B.

[0068] Graph 85g is a graph corresponding to the similar academic ability group to which students at academic ability level 1 belong among students who worked on problems belonging to similar problem group C. Graph 85h is a graph corresponding to the similar academic ability group to which students at academic ability level 2 belong among students who worked on problems belonging to similar problem group C. Graph 85i is a graph corresponding to the similar academic ability group to which students at academic ability level 3 belong among students who worked on problems belonging to similar problem group C.

[0069] As described above, the nine graphs 85a to 85i of the graph 85 are graphs created based on the answer information of students belonging to each similar academic ability group. That is, the graph creation unit 57 graphs the learning tendencies of students for questions of the same learning element for each student's academic ability level and similar question group. This allows for confirmation of learning tendencies such as, for example, "students with low academic ability levels take a long time to answer questions even when the question difficulty is low, while students with high academic ability levels take a short time to answer questions even when the question difficulty is medium." Furthermore, it allows for confirmation of learning tendencies such as, for example, "students with low academic ability levels take a relatively short time to answer questions with integers (log+1 degree equations), but take a long time to answer questions with fractions (log+1 degree equations)."

[0070] Fig. 10 is an example of a second graph showing a student's learning tendency. Fig. 10 shows a question item 84 whose learning element is (log+1 degree equation) and a graph 88 showing the student's learning tendency. The question item 84 includes questions 84a to 84d whose learning element is (log+1 degree equation) extracted from the question DB 42.

[0071] The graph 88 includes graphs 88a and 88b for academic ability level 1, graphs 88c and 88d for academic ability level 2, and graphs 88e and 88f for academic ability level 3.

[0072] Graph 88a is created based on the answer information of students of academic ability level 1 who tackled the problem in question item 84. As shown in FIG. 10 , graph 88a has answer time set on the vertical axis and similar problem group set on the horizontal axis, with each student's icon arranged based on their answer information. Specifically, graph creation unit 57 first references question DB 42 and learning history DB 43 and extracts answer information of each student of academic ability level 1 who tackled the problems belonging to similar problem group A. Then, graph creation unit 57 calculates the average answer time of each student corresponding to the problems belonging to similar problem group A based on the extracted answer information. Then, graph creation unit 57 creates graph 88a by arranging each student's icon at a position indicating each student's average answer time within the range of similar problem group A set on the horizontal axis.

[0073] In this way, the graph creation unit 57 calculates the average answer time for each student corresponding to the questions belonging to similar question groups A to C. Then, the graph creation unit 57 places the icon of each student at a position indicating the average answer time for each student within the range of each similar question group set on the horizontal axis, and creates graph 88a by connecting icons of the same student with a line. In this way, it is possible to output the transition of the answer time values ​​of each student for each similar question group on graph 88a. Furthermore, the graph creation unit 57 can calculate the average value of the answer time values ​​of all students at academic ability level 1 for each similar question group, and output the transition of the average value on graph 88a.

[0074] For example, if student A is at academic ability level 1, graph creation unit 57 calculates student A's average answer time based on the answer information for questions belonging to similar problem group A that student A worked on, and arranges student A's icon 89a. Graph creation unit 57 also calculates student A's average answer time based on the answer information for questions belonging to similar problem group B that student A worked on, and arranges student A's icon 89b. Graph creation unit 57 also calculates student A's average answer time based on the answer information for questions belonging to similar problem group C that student A worked on, and arranges student A's icon 89c. Graph creation unit 57 then connects student A's icons 89a to 89c with lines to create graph 88a that can output the transition of student A's answer time values ​​for each similar problem group.

[0075] Similar to graph 88a, graph creation unit 57 creates graph 88c, which represents the transition of the answer time values ​​of each student for each similar question group, based on the answer information of students of academic ability level 2 who tackled the problem in question item 84. In addition, graph creation unit 57 creates graph 88e, which represents the transition of the answer time values ​​of each student for each similar question group, based on the answer information of students of academic ability level 3 who tackled the problem in question item 84.

[0076] Graph 88b is created based on the answer information of students at academic ability level 1 who tackled questions belonging to question item 84. As shown in FIG. 10 , graph 88b has the number of characters in the answer set on the vertical axis and the similar question group set on the horizontal axis, with each student's icon arranged based on their answer information. Specifically, graph creation unit 57 first references question DB 42 and learning history DB 43 and extracts answer information of each student at academic ability level 1 who tackled questions belonging to similar question group A. Then, graph creation unit 57 calculates the average number of characters in the answer of each student corresponding to questions that conform to similar question group A based on the extracted answer information. Then, graph creation unit 57 creates graph 88b by arranging each student's icon at a position that indicates each student's average number of characters in the answer within the range of each similar question group set on the horizontal axis.

[0077] In this way, the graph creation unit 57 calculates the average number of characters in each student's answer corresponding to the questions belonging to similar question groups A to C. Then, the graph creation unit 57 places each student's icon at a position indicating the average number of characters in each student's answer within the range of each similar question group set on the horizontal axis, and creates graph 88b by connecting icons of the same student with a line. This makes it possible to output on graph 88b the transition of the value of the number of characters in each student's answer for each similar question group. Furthermore, the graph creation unit 57 can calculate the average value of the value of the number of characters in each student's answer for each similar question group at academic ability level 1, and output the transition of the average value on graph 88b.

[0078] For example, if Student A is at academic ability level 1, the graph creation unit 57 calculates the average number of characters in Student A's answers based on the answer information for questions belonging to similar problem group A that Student A has worked on, and arranges Student A's icon 90a. The graph creation unit 57 also calculates the average number of characters in Student A's answers based on the answer information for questions belonging to similar problem group B that Student A has worked on, and arranges Student A's icon 90b. The graph creation unit 57 also calculates the average number of characters in Student A's answers based on the answer information for questions belonging to similar problem group C that Student A has worked on, and arranges Student A's icon 90c. The graph creation unit 57 then connects Student A's icons 90a to 90c with lines to create a graph 88b that can output the transition of Student A's answer character length for each similar problem group.

[0079] Similar to graph 88b, graph creation unit 57 creates graph 88d, which represents a transition in the value of the number of characters in an answer for each student in each similar question group, based on the answer information of students at academic ability level 2 who tackled the problem in question item 84. In addition, graph creation unit 57 creates graph 88f, which represents a transition in the value of the number of characters in an answer for each student in each similar question group, based on the answer information of students at academic ability level 3 who tackled the problem in question item 84.

[0080] In this way, the six graphs 88a to 88f of the graph 88 are graphs for each academic level of the students who tackled the problems in the question item 84. In other words, the graph creation unit 57 graphs the learning tendency of each student for each academic level of the student. This makes it possible to check at a glance the changes in the answer time and number of characters in the answer of each student for each similar question group.

[0081] Here, we will explain the first learning trend screen, which includes a first graph showing the student's learning trend. FIG. 11 is an example of the first learning trend screen. The learning trend screen is created based on question information and answer information, and is a screen including a first graph created by the graph creation unit 57, and is transmitted to the student terminal 20 of the subject. The subject can check his or her own learning trend by displaying the learning trend screen received from the server 10 using the student terminal 20.

[0082] As shown in Figure 11, the learning tendency screen has a target item 91, a target question item 92, an answer item 93, a correct / incorrect item 94, an answer time item 95, an answer character count item 96, an academic ability level item 97, a question item 84, and a graph 70.

[0083] The target student item 91 displays the student ID of the target student. The target question item 92 is an item that displays the target question. Note that the student may use the student terminal 20 to perform a predetermined operation to display a learning trend screen on which the question item 84 and graph 70 are not yet displayed, and input the target question into the target question item 92, thereby transmitting input information including the student ID and information about the target question to the server 10. The answer item 93 displays the answer by the target student to the target question. The correct / incorrect item 94, answer time item 95, and answer character count item 96 display the correct / incorrect status of the target question, the answer time for the target question, and the number of characters in the answer for the target question, respectively. The academic ability level item 97 displays the academic ability level of the target student.

[0084] Question item 84 displays questions that have the same learning element as the learning element of the target question identified by learning element identification unit 54. Specifically, if the learning element of the target question is (log+1 degree equation), all questions whose learning element extracted from question DB 42 is (log+1 degree equation) are displayed. Graph 70 is a graph that shows the student's learning tendency. Specifically, graph 70 has similar question group on the vertical axis and academic ability level on the horizontal axis, and has nine graphs corresponding to each similar academic ability group, and is a graph in which the position of the subject is overwritten on graph 85 shown in Figure 9.

[0085] The position identifying unit 61 identifies the position of the subject on a graph corresponding to the similar academic ability group to which the subject belongs, based on the subject's answer information. Specifically, the position identifying unit 61 first identifies the graph of the similar academic ability group to which the subject belongs, identified by the similar academic ability group identifying unit 56, in the graph 85 shown in FIG. 9. For example, if the graph of the similar academic ability group to which the subject belongs is graph 85e, the position identifying unit 61 identifies the position of the subject on graph 85e based on the subject's answer information. The graph creating unit 57 places the subject's icon on graph 85e at the position identified by the position identifying unit 61, thereby creating graph 70e and graph 70 shown in FIG. 11. This makes it possible to display the subject's position on graph 70e using an icon.

[0086] At this time, the graph creation unit 57 may group the students whose icons are arranged in the graph 70e into, for example, similar tendency groups 98a, 98b, and 98c by clustering. Furthermore, the position identification unit 61 may identify the similar tendency group to which the subject belongs in the graph 70e. In this case, the graph creation unit 57 creates a graph 70 in which the subject's icon 99 and an arrow are arranged to indicate the similar tendency group identified by the position identification unit 61. As a result, as shown in FIG. 11, the subject's icon 99 and an arrow indicating the learning tendency group to which the subject belongs can be displayed in the graph 70e. The average answer time and the average number of characters in the answer may be calculated based on the answer information of other students in the similar tendency group to which the subject belongs, and displayed at the bottom of the learning tendency screen, as shown in FIG. 11.

[0087] Next, a second learning tendency screen including a second graph showing the student's learning tendency will be described. FIG. 12 is an example of the second learning tendency screen. As shown in FIG. 12, the second learning tendency screen includes a target item 91, a target question item 92, an answer item 93, a correct / incorrect item 94, an answer time item 95, an answer character count item 96, an academic ability level item 97, a question item 84, a graph 71, and advice 72. Note that, since the elements other than the graph 71 and the advice 72 are the same as those in the first learning tendency screen shown in FIG. 11, a description thereof will be omitted for the sake of brevity.

[0088] Graph 71 is a graph showing the learning tendency of a student. It is assumed that the academic ability level of the subject in graph 71 is "2." Specifically, graph 71 has graphs 71a and 71b. Graph 71a has answer time on the vertical axis and similar question group on the horizontal axis, and is similar to graph 88c for academic ability level 2 shown in FIG. 10, which only outputs the trend in the average value. Graph 71b has the number of characters in the answer on the vertical axis and similar question group on the horizontal axis, and is similar to graph 88d shown in FIG. 10, which only outputs the trend in the average value.

[0089] The transition identification unit 62 identifies the transition of the subject's value on a second graph representing the student's learning tendency based on the subject's answer information. Specifically, the transition identification unit 62 first calculates the subject's average answer time and average number of characters in the answer for each similar question group based on the subject's answer information for all questions in the question item 84. Then, the transition identification unit 62 identifies the transition of the value indicating the subject's average answer time for each similar question group on graph 88c shown in FIG. 10, and the graph creation unit 57 creates graph 71a to output the identified value and its transition. As a result, as shown in FIG. 12, the transition of the student's average value and the transition of the subject's value can be displayed on graph 71a.

[0090] Furthermore, the transition identification unit 62 identifies the transition of the value indicating the subject's average number of characters in answers for each similar question group on graph 88d shown in Fig. 10, and the graph creation unit 57 creates graph 71b to output the identified value and its transition. As a result, as shown in Fig. 12, it is possible to display the transition of the students' average value and the transition of the subject's value on graph 71b.

[0091] The advice 72 displays advice on a study policy based on the results of comparing the learning tendencies of the subject with those of other students based on the graph 71, and on comments linked to the learning tendencies of the subject extracted from the comment DB 44. For example, if there is a discrepancy between the change in the student's average value and the change in the subject's value in the graph 71, the graph creation unit 57 calculates the amount of discrepancy between the change in the student's average value and the change in the subject's value as the learning tendency. In this case, the comment DB 44 stores comment information that links the amount of discrepancy, which is the student's learning tendency, with comments to the student. Then, the graph creation unit 57 extracts comments to the student from the comment DB 44 based on the calculated amount of discrepancy, and creates and displays advice.

[0092] Specifically, advice when the similarity is the difficulty of the questions will be described. In this case, similar question group A is "questions of difficulty 0.0 to 1.0," similar question group B is "questions of difficulty 1.1 to 2.0," and similar question group C is "questions of difficulty 2.1 to 3.0." Based on graph 71a, graph creation unit 57 compares the answer time trends of the subject with those of other students, and displays advice such as, "Your answer time for questions of difficulty 0.0 to 1.0 is 7 seconds faster. Take a little more time to avoid careless mistakes," as shown in FIG. 12. If the answer time is slow, advice such as, "Your answer time for questions of difficulty 0.0 to 1.0 is 10 seconds slower. Try to solve them a little faster so you can allocate time to other questions," may be displayed. Furthermore, the graph creation unit 57 compares the tendency of the number of characters in the answers of the subject with the tendency of the number of characters in the answers of other students based on the graph 71b, and displays advice such as "The number of characters in the answers for questions of difficulty level 0.0 to 1.0 is 20 characters short. To prevent careless mistakes, try to use intermediate steps.", as shown in Fig. 12. In this case, if the number of characters in the answers is large, advice such as "The number of characters in the answers for questions of difficulty level 0.0 to 1.0 is 10 characters too many. To shorten the answering time, try to eliminate unnecessary intermediate steps." may be displayed.

[0093] In the present embodiment, the second learning tendency screen displays, in graph 71, the change in the subject's value, the change in the average value of students with the same academic ability level as the subject, and advice, but the present invention is not limited to this, and the change in the subject's value, the change in the average value of students with a higher academic ability level than the subject, and advice may be displayed. This allows the subject to compare their own change with the change in the average value of students with a higher academic ability level than themselves, which can be useful for future studies.

[0094] In the above configuration, the question DB 42, learning history DB 43, and comment DB 44 of the server 10 are examples of the question storage unit, learning history storage unit, and comment storage unit of the present invention, respectively. Also, in the above configuration, the similarity calculation unit 45, similar question group classification unit 46, analysis unit 47, academic ability determination unit 51, similar academic ability group classification unit 52, input information acquisition unit 53, learning element identification unit 54, similar academic ability group identification unit 56, and graph creation unit 57 of the server 10 are examples of the similarity calculation unit, similar question group classification unit, analysis unit, academic ability calculation unit, similar academic ability group classification unit, input information acquisition unit, learning element identification unit, similar academic ability group identification unit, and graph creation unit, respectively.

[0095] [Student Device Configuration] 13 is a block diagram showing the hardware configuration of student terminal 20. Student terminal 20 includes a communication unit 21, a control unit 22, a storage unit 23, a display unit 25, and an input unit 26. These components are interconnected via a bus 29.

[0096] The communication unit 21 is a communication unit for communicating with the server 10 via the network 5. Specifically, the communication unit 21 transmits answer information and input information to the server 10, and receives a learning trend screen from the server 10.

[0097] The control unit 22 includes an arithmetic processing unit such as a CPU, an MPU, a GPU, etc., and reads and executes programs stored in the storage unit 23 to perform various information processing, control processing, etc. related to the student terminal 20. Note that although the control unit 22 is described as a single processor in Fig. 13, it may be a multiprocessor.

[0098] The storage unit 23 includes memory elements such as RAM and ROM, and stores programs, data, etc. required for the control unit 22 to execute processing. The storage unit 23 also temporarily stores data, etc. required for the control unit 22 to execute arithmetic processing.

[0099] The display unit 25 is a liquid crystal display, an organic EL display, or the like, and displays various information in accordance with instructions from the control unit 22. The input unit 26 is an input device such as a mouse, keyboard, touch panel, or button, and outputs received operation information to the control unit 22.

[0100] [Classification Processing] Next, we will explain the process of extracting questions with the same learning elements as the target question and classifying the questions into similar question groups based on the similarity. Figure 14 is a flowchart of the classification process performed by the server 10. This process is realized by the server 10 executing a program prepared in advance.

[0101] A target student uses the student terminal 20 to send input information including a student ID and information about the target question to the server 10. The server 10 acquires the input information from the student terminal 20 (step S101). The server 10 then refers to the question DB 42 and identifies the learning elements of the target question included in the input information (step S102). The server 10 then extracts questions with the same learning elements as the target question from the question DB 42 (step S103). The server 10 then calculates the similarity of the extracted questions and classifies the questions into a similar question group subdivided based on the similarity (step S104). This completes the classification process for the server 10.

[0102] [Analysis processing] Next, an analysis process will be described in which similar questions are analyzed for each degree of similarity of the questions and the academic ability of the students based on the question information and answer information. Figure 15 is a flowchart of the analysis process by the server 10. This process is realized by the server 10 executing a program prepared in advance.

[0103] The server 10 acquires information about the similar question groups classified by the classification process (step S201). Then, the server 10 refers to the learning history DB 43 and extracts all answer information for questions belonging to a predetermined similar question group (step S202). Furthermore, the server 10 calculates the academic ability levels of students who have tackled the questions belonging to the similar question group based on the extracted answer information (step S203). Then, the server 10 classifies the students who have tackled the questions belonging to the similar question group into similar ability groups that are further divided by academic ability level (step S204). Then, the server 10 creates a graph corresponding to each similar academic ability group based on the answer information of students belonging to the predetermined similar academic ability group (step S205).

[0104] Then, the server 10 determines whether there are any groups of similar academic ability for which graphs have not yet been created (step S206). If it is determined that there are any groups of similar academic ability for which graphs have not yet been created (step S206; Yes), the server 10 repeats the processes of steps S202 to S205 to create graphs corresponding to all of the classified groups of similar academic ability.

[0105] If it is determined that there are no similar academic ability groups for which graphs have not been created, that is, that graphs corresponding to all similar academic ability groups have been created (step S206; No), the server 10 proceeds to subject graph processing (step S207).

[0106] FIG. 16 is a flowchart of subject graph processing by the server 10. This processing is realized by the server 10 executing a program prepared in advance. The server 10 identifies the subject student based on the student ID included in the input information (step S301). Then, the server 10 refers to the learning history DB 43 and extracts the subject's answer information (step S302). Furthermore, the server 10 calculates the subject's academic ability level based on the subject's answer information (step S303). The server 10 also refers to the question DB 42 and identifies the learning elements and similarity of the target question included in the input information (step S304). Then, the server 10 identifies the similar academic ability group to which the subject belongs based on the subject's academic ability level, the learning elements of the target question, and the similarity of the target question (step S305). Furthermore, the server 10 calculates the subject's position in the graph corresponding to the identified similar academic ability group based on the subject's answer information (step S306). Then, the server 10 updates and creates the graph so as to output the position of the subject on the graph (step S307). As a result, the server 10 ends the subject graph processing, and proceeds to step S208 of the analysis processing shown in FIG.

[0107] The server 10 creates a learning tendency screen including the created graph and transmits it to the student terminal 20 of the subject (step S208). Then, the server 10 ends the analysis process.

[0108] In the above analysis process, it is assumed that a graph of the student's academic ability level and the student's learning tendency for each similar question group is created, and a first learning tendency screen as shown in Fig. 11 is created, but the present invention is not limited to this. The server 10 may also create a graph showing the student's learning tendency based on the similarity of the questions through the analysis process, and create a second learning tendency screen as shown in Fig. 12.

[0109] Furthermore, in the above embodiment, the student uses the student terminal 20 to send input information to the server 10 and then views the learning trend screen obtained from the server 10, but the present invention is not limited to this, and the teacher may use the teacher terminal 30 to send input information including the student ID of the target student and information about the target question to the server 10 and view the learning trend screen obtained from the server 10. In this case, the server 10 performs classification processing and analysis processing based on the input information received from the teacher terminal 30, and sends a learning trend confirmation screen to the teacher terminal 30.

[0110] Furthermore, in the above embodiment, learning elements are used to extract questions with the same learning elements as the target question from question DB42, but the present invention is not limited to this, and any standard may be used, for example, the curriculum code established by the Ministry of Education, Culture, Sports, Science and Technology.

[0111] The learning support system 100 of this embodiment can use learning elements to obtain questions with the same learning elements from other learning materials for questions in learning materials, and further subdivide and classify the questions by similarity. Furthermore, by analyzing the answer information of the learner, the learning support system 100 can compare the learning results and learning tendencies of the learner by the similarity of the questions and the academic ability of the learner.

[0112] Specifically, the server 10 creates graphs of the similarity of questions and learning trends for each academic level, allowing learners to quantitatively compare their own answer trends with those of learners with similar academic levels. For example, learners can check their learning results and learning trends, such as answer time and number of characters in their answers, on a learning trend screen that includes graphs. Learners can also compare a target question with multiple similar questions in a unified manner. This can be used to determine the learner's future learning strategy.

[0113] Furthermore, the server 10 creates a graph showing the learner's learning tendency based on the similarity of questions with the same learning element, allowing the learner to compare the progress of their own learning tendency for each similarity with the progress of the learning tendency for each similarity of learners with similar academic ability. For example, the learner can check the progress of their learning tendency, such as answer time and number of characters in the answer, on the learning tendency screen including the graph. Furthermore, the server 10 can provide the learner with advice on their learning strategy depending on the deviation in progress.

[0114] <Modification> Next, a description will be given of modifications of the first embodiment. The following modifications can be applied to the first embodiment and the second embodiment described later in appropriate combination.

[0115] (First Modification) In the first embodiment described above, the graph 70 shown in Fig. 11 and the graph 71 shown in Fig. 12 are included in the learning tendency screen and can be viewed by students and teachers, but the present invention is not limited to this, and the learning tendency screen may also include a graph 88 shown in Fig. 10. Graph 88 graphs the progress of each student's answer time or number of characters in their answer as a learning tendency for each student's academic ability level.

[0116] This makes it easy for teachers to visually check the learning trends of each student by viewing the learning trend screen including graph 88. Furthermore, advice 72 displayed on the second learning trend screen shown in Fig. 12 is automatically created based on the results of the comparison of learning trends and comments extracted from comment DB 44, but advice 72 may also be entered directly by a teacher who views graph 88, for example.

[0117] Furthermore, by viewing the learning trend screen including the graph 88, students can compare their own learning trends with those of many other students, which can be useful for future studies. In this case, the server 10 updates the graph 88 and creates a new graph so as to output the transition of the subject's values ​​on the graph 88. This makes it possible to display the transition of the subject student and the transitions of many other students on the new graph 88.

[0118] (Second Modification) In the first embodiment described above, the difficulty of the question and the text similarity of the question are given as examples of similarity, but the present invention is not limited to this, and for example, the similarity may be a combination of the difficulty of the question and the text similarity.

[0119] As an example, the server 10 first calculates the feature values ​​of all questions with the same learning element and groups the questions based on text similarity. The server 10 then calculates the average difficulty of the questions in each group. As a result, the server 10 may classify questions with the same learning element into similar question groups subdivided by difficulty level.

[0120] As another example, the server 10 first groups all questions with the same learning element by difficulty level. Then, the server 10 calculates the feature quantities of the questions belonging to each group. As a result, the server 10 may classify the questions with the same learning element into smaller similar question groups based on text similarity.

[0121] (Third Modification) In the first embodiment described above, the teacher uses the teacher terminal 30, but the present invention is not limited to this, and the teacher may use a teacher terminal 75 having the functions of the server 10. In this case, the student terminals 20 are used by students, their parents, etc. The teacher terminal 75, like the server 10, is, for example, a personal computer or a general-purpose tablet PC (personal computer).

[0122] FIG. 17 shows an example configuration of a learning support system 200 in this case. As shown in the figure, the learning support system 200 is configured so that a teacher terminal 75 and multiple student terminals 20 can communicate with each other via a network 5. The teacher terminal 75 is connected to a learning element DB 76, a question DB 77, a learning history DB 78, and a comment DB 79. The teacher terminal 75 executes the classification process previously performed by the server 10 to extract questions with the same learning element as the target question and classify the questions into similar question groups based on similarity. The teacher terminal 75 also executes the analysis process previously performed by the server 10 to analyze questions belonging to similar question groups based on question similarity and student academic ability. This allows the teacher terminal 75 to create a learning trend screen, send it to the student terminals 20, or display it on its own display. In this case, the teacher terminal 75 is an example of an information processing device of the present invention.

[0123] Second Embodiment In the first embodiment, the input information includes the student ID of the target student and information about the target question, but the present invention is not limited to this, and may include information about the learning elements and difficulty level set by the target student instead of the target question. In this case, the similarity is the difficulty level of the question.

[0124] First, the functional configuration of the server in the second embodiment will be described. Fig. 18 is a block diagram showing the functional configuration of the server in the second embodiment. For the sake of convenience, explanations similar to those in the first embodiment will be omitted, and the input information acquisition unit 53, the similar academic ability group identification unit 56, and the subject average value calculation unit 64 will be described in detail.

[0125] The input information acquisition unit 53 acquires input information from the student terminal 20, including a student ID and information related to the predetermined learning element and difficulty level input by the student. When a student wants to check his or her own learning trends, the student sets the predetermined learning element and difficulty level using the student terminal 20 and transmits this as input information to the server 10x. The input information acquisition unit 53 acquires the input information from the student terminal 20 and sets the student as a target for the learning trend screen. In the second embodiment, the input information includes information related to the learning element and difficulty level, and therefore the learning element identification unit 54 of the first embodiment is not necessary.

[0126] The similar academic ability group specifying unit 56 specifies a similar academic ability group to which the subject belongs based on the learning elements and difficulty levels included in the input information and the subject's academic ability level.

[0127] The subject average calculation unit 64 first refers to the question DB 42 and extracts questions of learning elements and difficulty levels included in the input information. Then, the subject average calculation unit 64 calculates the subject average based on the answer information of the subjects corresponding to the extracted questions. Specifically, the subject average calculation unit 64 calculates the subject's correct answer rate, average answer time, and average number of characters for the extracted questions as the subject average.

[0128] Next, the learning tendency screen in the second embodiment will be described. Fig. 19 is an example of a first learning tendency screen in the second embodiment. Fig. 20 is an example of a second learning tendency screen in the second embodiment. For the sake of convenience, explanations similar to those in the first embodiment will be omitted, and therefore the learning element items 65, difficulty level items 66, question selection items 67, answer items 93x, correct / incorrect items 94x, answer time items 95x, and answer character count items 96x will be described in detail.

[0129] The learning trend screen shown in Figures 19 and 20 has a learning element item 65 and a difficulty level item 66 instead of the target question item 92 in the first embodiment. The learning element item 65 and the difficulty level item 66 are items that display a specific learning element and difficulty level for which the student wishes to check the learning trend, respectively. As in the first embodiment, a student may use the student terminal 20 to perform a specific operation to display a learning trend screen that does not display graphs, etc., and set a specific learning element and difficulty level in the learning element item 65 and the difficulty level item 66, thereby transmitting input information including the student ID and information regarding the set learning element and difficulty level to the server 10x.

[0130] The question selection item 67 displays questions of the learning elements and difficulty levels displayed in the learning element item 65 and difficulty level item 66. The subject may be able to select one question from the questions displayed in the question selection item 67. The answer item 93x displays the subject's answer to the question displayed in the question selection item 67. When the subject selects one question in the question selection item 67, the answer item 93x displays the subject's answer to the selected question so that it can be viewed without scrolling. The correct / incorrect item 94x, answer time item 95x, and answer character count item 96x respectively display the correct answer rate, average answer time, and average number of characters calculated by the subject average value calculation unit 64.

[0131] The position identifying unit 61 included in the graph creating unit 57 may identify the position of the subject on the first graph included in the first learning trend screen shown in Fig. 19 based on the average answer time and average number of characters calculated by the subject average value calculating unit 64, or based on the answer time and number of characters of the question selected in the question selection item 67. The graph creating unit 57 then creates the graph in the same manner as in the first embodiment. In this way, the server 10x in the second embodiment creates the first learning trend screen as shown in Fig. 19 based on input information including information on the learning elements and difficulty levels set by the student.

[0132] Furthermore, the transition identification unit 62 included in the graph creation unit 57 identifies the transition of values ​​indicating the subject's average answer time or average number of characters in answers for each similar question group on the second graph included in the second learning trend screen shown in Fig. 20, and the graph creation unit 57 creates the graph so as to output the transition of the identified values ​​as the transition of the subject's values. In this way, the server 10x in the second embodiment creates the second learning trend screen as shown in Fig. 20 based on input information including information on the learning elements and difficulty levels set by the student. [Explanation of symbols]

[0133] 5. Network 10, 10x servers 20 Student devices 30, 75 Teacher's terminals 41, 76 Learning element DB 42, 77 Problem DB 43, 78 Learning history DB 44, 79 Comment DB 45 Similarity calculation part 46 Similar Problem Group Classification Unit 47 Analysis Department 51 Academic Ability Judgment Department 52 Similar Academic Ability Group Classification Section 53 Input information acquisition unit 54 Learning element identification section 55 Extraction part 56 Similar Academic Ability Group Identification Department 57 Graph Creation Department 100, 200 Learning Support System

Claims

1. An information processing device communicably connected to a terminal device used by a specific learner, a question storage unit that stores question information classified into learning elements obtained by subdividing learning content; a learning history storage unit that stores answer information regarding answers to questions by learners; a similarity calculation unit that calculates a similarity of the question based on at least one of the question information and the answer information; a similar problem group classification unit that classifies the plurality of problems having the same learning element into further subdivided similar problem groups based on the similarity of the problems; an academic ability calculation unit that calculates the academic ability of the learner based on the answer information; a similar ability group classification unit that classifies learners who have tackled problems belonging to the same similar problem group into a plurality of similar ability groups that are further subdivided according to the academic ability; an input information acquisition unit that acquires input information including information on a target question that is a question input by the subject from the terminal device; a learning element identification unit that refers to the problem storage unit and identifies a learning element to which the target problem belongs; a similar ability group identification unit that identifies a similar problem group corresponding to the learning element to which the target problem belongs, acquires the academic ability of the subject based on the input information, and identifies a similar academic ability group to which the subject belongs; a graph creation unit that creates a graph corresponding to a plurality of similar academic ability groups including the similar academic ability group to which the subject belongs; An information processing device comprising:

2. The information processing device according to claim 1 , wherein the graph creation unit creates a graph on a graph corresponding to a similar academic ability group to which the subject belongs, so as to output the position of the subject based on answer information of the subject to the target question.

3. 3. The information processing device of claim 1, wherein the graph creation unit creates a new graph based on answer information from a learner who has tackled a problem with the same learning element as the target problem and has a similar level of academic ability to the subject, and creates a graph so that the average value of the answers to the problems by the learner and the value of the answer to the target problem by the subject are simultaneously output on the new graph.

4. The information processing apparatus according to claim 3 , wherein the graph creation unit creates a graph so as to simultaneously output the transition of the average value for each of the similar problem groups and the transition of the value for each of the similar problem groups.

5. a comment storage unit that stores a deviation amount between a change in an average value of answers given by the learner and a change in a value of answers given by the subject as a learning tendency, and associates the deviation amount with a comment to the learner; 5. The information processing device according to claim 4, wherein the graph creation unit calculates the deviation between the trend of the average value for each of the similar problem groups and the trend of the value for each of the similar problem groups, and creates a graph to output comments extracted from the comment storage unit based on the calculated deviation.

6. The similarity is the difficulty of the question, the similarity calculation unit calculates the difficulty level of the question based on the answer information; The information processing device according to claim 1 , wherein the similar-question group classification unit classifies questions belonging to the same group based on the difficulty level of the questions.

7. The similarity is a text similarity of the question, the similarity calculation unit calculates a text similarity based on the question information; The information processing device according to claim 1 , wherein the similar question group classification unit classifies questions belonging to the same group based on the text similarity.

8. A program executed by an information processing device that is communicably connected to a terminal device used by a specific learner, the information processing device including a computer, a question storage unit that stores question information classified into learning elements obtained by subdividing the learning content; a learning history storage unit that stores answer information regarding answers to questions by learners; a similarity calculation unit that calculates a similarity of the question based on at least one of the question information and the answer information; a similar problem group classification unit that classifies the plurality of problems having the same learning element into further subdivided similar problem groups based on the similarity of the problems; an academic ability calculation unit that calculates the academic ability of the learner based on the answer information; a similar academic ability group classification unit that classifies learners who have tackled problems belonging to the same similar problem group into a plurality of similar academic ability groups that are further subdivided according to the academic ability; an input information acquisition unit that acquires, from the terminal device, input information including information on a target question that is a question input by the subject; a learning element identification unit that refers to the problem storage unit and identifies a learning element to which the target problem belongs; a similar academic ability group identification unit that identifies a similar question group corresponding to the learning element to which the target question belongs, obtains the academic ability of the subject based on the input information, and identifies a similar academic ability group to which the subject belongs; a graph creation unit that creates a graph corresponding to a plurality of similar academic ability groups including the similar academic ability group to which the subject belongs; A program that causes the computer to function as a

Images