JP7779140B2 - Information processing device and program - Google Patents

Description

The present invention relates to technology for outputting information related to learning.

Systems that store test results administered to students in a database and enable them to be viewed on a computer have been known for some time. Patent Document 1 discloses an educational support system that has a performance summary database that compiles learners' test scores and is configured so that the database can be accessed via a tablet terminal device.

JP 2016-65987 A

However, the invention described in Patent Document 1 only allows users to check test results, which are learning histories, and does not allow users to check students' learning trends.

The present invention has been made to solve the above-mentioned problems, for example, and aims to provide an information processing device that analyzes and outputs a learner's learning tendencies for similar questions.

In one aspect of the present invention, an information processing device communicably connected to a terminal device used by a subject who is a specific learner includes a problem storage unit that stores problem information classified into learning elements that subdivide learning content , a learning history storage unit that stores answer information regarding answers given to problems by the learner, a similarity calculation unit that calculates the similarity of the problems based on at least one of the problem information and the answer information, a similar problem group classification unit that classifies a 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, and a learning history storage unit that stores answer information regarding answers given to problems by the learner based on the similarity of the problems. The system comprises a similar academic ability group classification unit that classifies learners into a plurality of similar academic ability groups further subdivided by academic ability; an input information acquisition unit that acquires input information from the terminal device including information on target questions that are questions entered by the subject; a learning element identification unit that refers to the question memory unit and identifies the learning element to which the target question 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, acquires the subject's academic ability based on the input information, and identifies the similar academic ability group to which the subject belongs; and 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 .

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.

In one aspect of the information processing device, the graph creation unit creates a graph corresponding to the similar academic ability group to which the subject belongs, outputting the subject's position based on the subject's answer information for the target question. According to this aspect, the learner can easily confirm their own position on the graph.

In one aspect of the above 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 target student, and creates a graph that simultaneously outputs the average value of the answers to the problems by the learners and the value of the answers to the target problem by the target student 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.

In one aspect of the above information processing device, the graph creation unit creates a graph that simultaneously outputs the trend in the average value for each similar question group and the trend in the value for each similar question group. According to this aspect, learners can check their own learning results and learning trends as well as those of other learners with similar academic ability by not only looking at the values on the graph but also at the trends.

In another aspect of the above information processing device, a comment storage unit is provided that stores, as a learning trend, the amount of deviation between the change in the average value of the learner's answers to the questions and the change in the value of the subject's answers in association with comments to the learner, and the graph creation unit calculates the amount of 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 amount of deviation. According to this aspect, the information processing device can provide the learner with advice on learning strategies, etc., in the form of comments, depending on the deviation in the trends.

In another aspect of the above 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 learners' learning results and learning tendencies based on the difficulty level of the questions.

In another aspect of the above information processing device, the similarity is the 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 learners' learning results and learning tendencies based on the text similarity of the questions.

In another aspect of the present invention, there is provided a program executed by an information processing device that is communicably connected to a terminal device used by a target person who is a specific learner and that is equipped with a computer, the program including: a question storage unit that stores question information classified into learning elements that subdivide learning content ; a learning history storage unit that stores answer information regarding answers given to questions by the learner; a similarity calculation unit that calculates the similarity of the questions based on at least one of the question information and the answer information; a similar question group classification unit that classifies a plurality of questions having the same learning element into further subdivided similar question groups based on the similarity of the questions; an academic ability calculation unit that calculates the academic ability of the learner based on the answer information; and a graph creation unit that creates a graph corresponding to the plurality of similar academic ability groups, including the similar academic ability group to which the subject belongs. By installing and running this program on a computer, an information processing device according to the present invention can be configured.

The information processing device according to the present invention can analyze and output a learner's learning tendencies for similar questions.

1 shows the configuration of a learning support system to which a server of the present invention is applied. FIG. 2 is a block diagram showing the hardware configuration of a server. 10 is an example of the data configuration of a learning element DB. 10 is an example of a data structure of a question DB. 10 is an example of a data configuration of a learning history DB. FIG. 2 is a block diagram showing the functional configuration of a server according to the first embodiment. Here is an example of a problem with the same learning element. FIG. 10 is a diagram illustrating a method for grouping based on feature amounts. 1 is an example of a first graph showing a student's learning tendency. 10 is an example of a second graph showing a student's learning tendency. 10 is an example of a first learning tendency screen in the first embodiment. 10 is an example of a second learning tendency screen in the first embodiment. FIG. 2 is a block diagram showing the hardware configuration of a student terminal. 10 is a flowchart of a classification process. 10 is a flowchart of an analysis process. 10 is a flowchart of subject graph processing. 10 shows an example of the configuration of a learning support system according to a third modified example. FIG. 10 is a block diagram showing the functional configuration of a server according to a second embodiment. 10 is an example of a first learning tendency screen in the second embodiment. 10 is an example of a second learning tendency screen in the second embodiment.

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

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

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

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 learning trend screens, etc.

[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.

Note that the server 10 may be run on a single computer, distributed across multiple computers, or distributed across virtual machines.

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 sends learning trend screens to the student terminal 20 and the teacher terminal 30.

The control unit 12 includes processing units such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), and GPU (Graphics Processing Unit), and performs various information processing, control processing, and other operations related to the server 10 by reading and executing programs stored in the memory unit 13. The programs can be deployed to run on a single computer, at a single site, or distributed across multiple sites and on multiple computers interconnected by a communications network. While Figure 2 illustrates the control unit 12 as a single processor, it may also be a multi-processor.

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

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

The display unit 15 is a liquid crystal display or organic EL (electroluminescence) display, etc., and displays various information according to instructions from the control unit 12. The input unit 16 is an input device such as a mouse, keyboard, touch panel, or buttons, and outputs received operation information to the control unit 12.

The learning element DB41 stores information about learning elements, which are subdivisions of learning content. Here, learning elements are learning content and textbook explanations that have been subdivided to an optimal level of granularity, taking into account learning groups such as units, for purposes such as linking textbooks and teaching materials, understanding learning progress, and creating lesson plans. In other words, questions with the same learning element can be said to belong to the same group. Furthermore, a unit is a group of learning activities centered around a specific theme, is set for each subject such as "Mathematics" or "Japanese," and is composed of one or more learning elements.

Figure 3 is an example of the data structure of the learning element DB41. As shown, the learning element DB41 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, which is set for each subject, such as "Differentiation." The unit is the name of the unit, which is 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, which is set for each unit, such as "log + linear expression" or "log + quadratic expression." The learning element ID is identification information for the learning element.

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 each set in advance. The data structure of the learning element DB41 shown in Figure 3 is an example, and the present invention is not limited to this. The data structure of the learning element DB41 can be set arbitrarily as long as it stores information related to the identification of learning elements.

Question DB 42 stores question information about questions that students work on, in association with question IDs that identify the questions. Figure 4 shows an example of the data structure of question DB 42. As shown in the figure, question DB 42 stores information such as question IDs, question data, learning element IDs, learning material names, pages, and difficulty levels. Question data is data about the question indicated by the question ID. Learning element ID is identification information for the learning element to which the question indicated by the question ID belongs. 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 page is the page and question number on which the problem appears in the learning material.

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 correct answer rate, 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 Figure 4, the difficulty level may be stored in the question DB 42 and extracted when needed, or it may not be stored in the question DB 42 and instead be calculated based on the answer information each time it is needed.

Note that which learning element a question belongs to is set in advance. Furthermore, the data structure of question DB42 shown in Figure 4 is an example, and the present invention is not limited to this. Question DB42 can have any data structure as long as it stores information linking questions to learning elements.

The learning history DB43 stores answer information related to the answers to questions that students have worked on, in association with a student ID that identifies the student. Figure 5 shows an example of the data structure of the learning history DB43. As shown in the figure, the learning history DB43 stores information such as the student ID, question ID, correct/incorrect answer, answer time, and number of characters in the answer. The question ID is identification information for the question that the student identified by the student ID worked on. The correct/incorrect answer, answer time, and number of characters in the answer are respectively the correct/incorrect answer to the question 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.

In this embodiment, as an example, the student terminal 20 is pre-linked to the student ID of the student using 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. Furthermore, 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. 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.

Comment DB44, which will be described in more detail below, stores comment information that links students' learning tendencies in terms of answer time and number of characters in their answers with comments to the students.

Note that the storage format of each DB described above is an example, and other storage formats are possible as long as the relationships between data are maintained. Each DB is implemented using a recording medium such as an HDD (Hard Disk Drive) or SSD (Solid State Drive). 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 also be external storage devices connected to the server 10, and the configuration can be set as desired.

Figure 6 is a block diagram showing the functional configuration of the server. 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.

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

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, similarity refers to, for example, the difficulty of the question and 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, as another example of similarity, the similarity calculation unit 45 uses cosine similarity to calculate the similarity of the question text (hereinafter also referred to as "text similarity") as a numerical value. Details of text similarity will be described later, but in feature space, the closer the question is to the question, the higher the similarity, with the numerical value approaching 1, and the farther the question is to the question, the lower the similarity, with the numerical value approaching 0.

The similar question group classification unit 46 extracts questions with the same learning elements from the question DB 42 and classifies the extracted questions into further subdivided similar question groups based on their similarity.

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

In this embodiment, multiple questions with the same learning elements are classified into three groups: similar question group A with a difficulty level of "0.0 to 1.0," similar question group B with a difficulty level of "1.1 to 2.0," and similar question group C with a difficulty level of "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.

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 difficulty level.

Next, we will explain a method for classifying multiple questions with the same learning element based on text similarity. Figure 8 is a diagram illustrating a method for grouping questions based on features. As shown in Figure 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 using a machine learning technique capable of processing time-series information in text, such as LSTM (Long Short Term Memory). The similar problem group classification unit 46 quantifies the features of all questions with the same learning element and plots them in feature space, as shown in Figure 8(b). Then, as shown in Figure 8(c), the similar problem group classification unit 46 groups all questions with the same learning element into similar problem group A, similar problem group B, and similar problem group C by clustering. Text similarity is higher for questions closer to each other in the feature space, and lower for questions farther apart. Therefore, it can be said that the similar question group classification unit 46 classifies multiple questions with the same learning element based on text similarity.

In this embodiment, the questions are mathematical formulas, but the present invention is not limited to this. For example, the questions may be written questions that require a descriptive answer. In other words, the questions can be set arbitrarily.

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 for each degree of question similarity and student academic ability based on the question information stored in the question DB 42 and the answer information stored in the learning history DB 43.

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.

The academic ability assessment unit 51 calculates each student's academic ability level (hereinafter simply referred to as "academic ability") 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 each student's answer information to calculate a numerical academic ability level. 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 student's answer information, but it may be stored in the memory unit 13 in association with the student ID and extracted when needed, or it may not be stored in the memory unit 13 and instead be calculated based on the answer information each time it is needed.

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

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

The input information acquisition unit 53 acquires input information from the student terminal 20, including a student ID and information regarding the question for which the student's learning tendency is to be checked (hereinafter also referred to as the "target question"). When a student wants to check their own learning tendency, they use the student terminal 20 to input a specific question as the target question and send 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.

The learning element identification unit 54 references the question DB 42 and identifies the learning elements of the target question included in the input information. Specifically, the learning element identification unit 54 references the question DB 42 and identifies the question ID of the question included in the input information and the learning element ID of that question.

The extraction unit 55 extracts the subject's answer information from the learning result DB 43 based on the student ID included in the input information.

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 obtains 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.

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 trends based on the question information and answer information. The graph creation unit 57 then creates a learning trend screen including the created graph and transmits it to the student's device 20.

The position identification unit 61 and the transition identification unit 62 are realized by the control unit 12 executing a program.

Figure 9 is an example of a first graph showing a student's learning tendency. Figure 9 includes a question item 84 displaying questions whose learning element is (log + linear expression), and a graph 85 showing the student's learning tendency. The question item 84 includes questions 84a to 84d whose learning element is (log + linear expression) extracted from question DB 42.

Graph 85 has nine graphs 85a-85i, with similar question group A, similar question group B, and similar question group C on the vertical axis and academic ability level 1, academic ability level 2, and academic ability level 3 on the horizontal axis. Specifically, if similarity is the difficulty of the question, then for questions in question item 84, for example, similar question group A is a question with a difficulty level of "0.0-1.0," similar question group B is a question with a difficulty level of "1.1-2.0," and similar question group C is a question with a difficulty level of "2.1-3.0." Furthermore, if similarity is the text similarity of the question, then for questions in question item 84, for example, similar question group A is a question with an integer (log + linear expression), similar question group B is a question with a decimal (log + linear expression), and similar question group C is a question with a fraction (log + linear expression).

Graph 85a is a graph created based on the answer information of students at academic ability level 1 who tackled 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 problems belonging to similar problem group A.

As shown in FIG. 9, graph 85a has answer time on the vertical axis and the number of characters in the answer 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 extracts all of the answer information for each student corresponding to 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 for each student corresponding to questions belonging to similar question group A. Then, graph creation unit 57 creates graph 85a by placing each student's icon in the position indicated by each student's average answer time and average number of characters in the answer.

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 placing 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 placing Student B's icon 87b.

The graph creation unit 57 then groups groups of students with similar tendencies in the created graph 85a. Examples of grouping methods include 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.

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.

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.

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.

As such, the nine graphs 85a-85i of graph 85 are graphs created based on the answer information of students belonging to each similar academic ability group. In other words, graph creation unit 57 graphs students' learning trends for questions with the same learning element, for each student's academic ability level and similar problem group. This makes it possible to confirm learning trends such as, for example, "students with low academic ability levels take a long time to answer questions even when the question difficulty is low, but students with high academic ability levels take a short time to answer questions even when the question difficulty is medium." It is also possible to confirm learning trends such as, for example, "students with low academic ability levels take a relatively short time to answer questions with integers (log + linear equations), but take a long time to answer questions with fractions (log + linear equations)."

Figure 10 is an example of a second graph showing a student's learning tendency. Figure 10 shows a question item 84 whose learning element is (log + linear expression) and a graph 88 showing the student's learning tendency. The question item 84 includes questions 84a to 84d whose learning element is (log + linear expression) extracted from question DB 42.

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.

Graph 88a is created based on the answer information of students at 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 for each student at academic ability level 1 who tackled problems belonging to similar problem group A. Then, graph creation unit 57 calculates the average answer time for 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 placing 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.

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 each student's icon at a position indicating each student's average answer time 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. This makes it possible to output on graph 88a the change in the answer time values for each student for each similar question group. In addition, the graph creation unit 57 can calculate the average value of the answer time values for all students at academic ability level 1 for each similar question group, and output the change in the average value on graph 88a.

For example, if Student A is at academic ability level 1, the 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 places Student A's icon 89a. The 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 places Student A's icon 89b. The 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 places Student A's icon 89c. The graph creation unit 57 then connects Student A's icons 89a to 89c with lines to create graph 88a that can output the transition in Student A's answer time values for each similar problem group.

Similar to graph 88a, the graph creation unit 57 creates graph 88c, which shows the change in the answer time values for each student in each similar question group, based on the answer information of students at academic ability level 2 who tackled problem item 84. Furthermore, the graph creation unit 57 creates graph 88e, which shows the change in the answer time values for each student in each similar question group, based on the answer information of students at academic ability level 3 who tackled problem item 84.

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 for 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 each student's answer corresponding to questions in similar question group A based on the extracted answer information. Then, graph creation unit 57 creates graph 88b by placing each student's icon at a position that indicates each student's average number of characters in their answer within the range of each similar question group set on the horizontal axis.

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 that indicates 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 trend in the value of the number of characters in each student's answer for each similar question group. In addition, the graph creation unit 57 can calculate the average value of the value of the number of characters in each student's answer for all students at academic ability level 1 for each similar question group, and output the trend in this average value on graph 88b.

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 tackled, and places 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 tackled, and places 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 tackled, and places 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 in the number of characters in Student A's answers for each similar problem group.

Similar to graph 88b, the graph creation unit 57 creates graph 88d, which shows the change in the number of characters in the answers of each student for each similar question group, based on the answer information of students at academic ability level 2 who tackled problem item 84. The graph creation unit 57 also creates graph 88f, which shows the change in the number of characters in the answers of each student for each similar question group, based on the answer information of students at academic ability level 3 who tackled problem item 84.

As such, the six graphs 88a to 88f in graph 88 are graphs for each academic level of the students who tackled the questions in question item 84. In other words, the graph creation unit 57 graphs each student's learning tendencies for each student's academic level. This makes it possible to see at a glance the changes in each student's answer time and number of characters in their answers for each similar question group.

Here, we will explain the first learning trend screen, which includes a first graph that represents the student's learning trends. Figure 11 is an example of the first learning trend screen. The learning trend screen is created based on question information and answer information, and includes a first graph created by the graph creation unit 57, and is sent to the student device 20 of the subject. The subject can check their own learning trends by displaying the learning trend screen received from the server 10 using the student device 20.

As shown in Figure 11, the learning tendency screen has a target person 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.

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 a 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 enter the target question in 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 given 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.

Question item 84 displays questions that have the same learning element as the target question identified by learning element identification unit 54. Specifically, if the learning element of the target question is (log + linear expression), then all questions with the learning element (log + linear expression) extracted from question DB 42 are displayed. Graph 70 is a graph that shows the student's learning tendency. Specifically, graph 70 has similar question groups on the vertical axis and academic ability levels 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 target student has been overwritten on graph 85 shown in Figure 9.

The position identification 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 identification unit 61 first identifies the graph of the similar academic ability group to which the subject belongs, identified by the similar academic ability group identification unit 56, in 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 identification unit 61 identifies the subject's position on graph 85e based on the subject's answer information. The graph creation unit 57 creates graph 70e and graph 70 shown in FIG. 11 by placing the subject's icon on graph 85e at the position identified by the position identification unit 61. This makes it possible to display the subject's position on graph 70e using an icon.

At this time, the graph creation unit 57 may group the students whose icons are placed on 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 on 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. This makes it possible to display the subject's icon 99 and an arrow indicating the learning tendency group to which the subject belongs on the graph 70e, as shown in FIG. 11. The average answer time and average number of characters in the answer may also 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.

Next, we will explain the second learning trend screen, which includes a second graph showing the student's learning trend. Figure 12 is an example of the second learning trend screen. As shown in Figure 12, it 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 level item 97, a question item 84, a graph 71, and advice 72. Note that, apart from the graph 71 and advice 72, the screen is the same as the first learning trend screen shown in Figure 11, and therefore a description thereof will be omitted for simplicity's sake.

Graph 71 is a graph that shows a student's learning tendency. It is assumed that the subject's academic ability level 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 Figure 10, which only outputs the trend in average values. 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 Figure 10, which only outputs the trend in average values.

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 question item 84. The transition identification unit 62 then 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 values and their transitions. As a result, the transition of the student's average value and the transition of the subject's value can be displayed on graph 71a, as shown in FIG. 12.

Furthermore, the trend identification unit 62 identifies the trend of the value indicating the subject's average number of characters in their 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 trend. As a result, as shown in FIG. 12, it is possible to display the trend of the students' average value and the trend of the subject's value on graph 71b.

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 trend in the student's average value and the trend in the subject's value in the graph 71, the graph creation unit 57 calculates the amount of deviation between the trend in the student's average value and the trend in the subject's value as the learning tendency. In this case, the comment DB 44 stores comment information that links the amount of deviation, 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 deviation, and creates and displays advice.

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 level 0.0 to 1.0," similar question group B is "questions of difficulty level 1.1 to 2.0," and similar question group C is "questions of difficulty level 2.1 to 3.0." Based on graph 71a, graph creation unit 57 compares the subject's answer time trends with those of other students, and displays advice such as, "Your answer time for questions of difficulty level 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 level 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 trend in the number of characters in the answers of the subject with the trend in 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 using 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 answer time, try eliminating unnecessary intermediate steps." may be displayed.

In this embodiment, the second learning trend screen displays, in graph 71, the progress of the subject's value, the progress of the average value of students at the same academic level as the subject, and advice; however, the present invention is not limited to this, and it is also possible to display the progress of the subject's value, the progress of the average value of students at a higher academic level than the subject, and advice. This allows the subject to compare their own progress with the progress of the average value of students at a higher academic level than themselves, which can be useful for future studies.

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 assessment 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.

[Student Device Configuration]
13 is a block diagram showing the hardware configuration of the student terminal 20. The 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 connected to each other via a bus 29.

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

The control unit 22 includes a processing unit such as a CPU, MPU, or GPU, and performs various information processing, control processing, and the like related to the student terminal 20 by reading and executing programs stored in the memory unit 23. Note that while Figure 13 describes the control unit 22 as a single processor, it may also be a multi-processor.

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

The display unit 25 is a liquid crystal display, organic EL display, or the like, and displays various information according to 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.

[Classification process]
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 degree of 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.

The 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 references the question DB 42 and identifies the learning elements of the target question contained 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 smaller similar question groups based on the similarity (step S104). This completes the classification process for the server 10.

[Analysis processing]
Next, we will explain the analysis process for analyzing similar questions based on the question information and answer information, taking into account the degree of similarity of the questions and the academic ability of the students. Figure 15 is a flowchart of the analysis process performed by the server 10. This process is realized by the server 10 executing a program prepared in advance.

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

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

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

Figure 16 is a flowchart of subject graph processing by server 10. This processing is realized by server 10 executing a program prepared in advance. Server 10 identifies the target student based on the student ID included in the input information (step S301). Then, server 10 references learning history DB 43 and extracts the subject's answer information (step S302). Furthermore, server 10 calculates the subject's academic ability level based on the subject's answer information (step S303). Also, server 10 references question DB 42 and identifies the learning elements and similarity of the target question included in the input information (step S304). Then, 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, server 10 calculates the subject's position on the graph corresponding to the identified similar academic ability group based on the subject's answer information (step S306). The server 10 then updates and creates the graph to output the subject's position on the graph (step S307). This causes the server 10 to end the subject graph processing and proceed to step S208 of the analysis processing shown in FIG. 15.

The server 10 creates a learning trend screen including the created graph and transmits it to the student's device 20 (step S208). This marks the end of the analysis process for the server 10.

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

In addition, in the above embodiment, students use student terminals 20 to send input information to server 10 and view the learning trend screen obtained from server 10, but the present invention is not limited to this. A teacher may use teacher terminal 30 to send input information including the student ID of the target student and information about the target question to server 10, and view the learning trend screen obtained from server 10. In this case, server 10 performs classification and analysis processes based on the input information received from teacher terminal 30, and sends a learning trend confirmation screen to teacher terminal 30.

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 guidelines code established by the Ministry of Education, Culture, Sports, Science and Technology.

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 learner's answer information, the learning support system 100 can compare the learner's learning results and learning tendencies by question similarity and by the learner's academic ability.

Specifically, the server 10 creates graphs of question similarity and learning trends for each academic level, allowing learners to quantitatively compare their own answer trends with those of learners with similar academic abilities. 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, etc.

Furthermore, by having the server 10 create a graph that shows the learner's learning tendencies based on the similarity of questions with the same learning elements, the learner can compare the progress of their own learning tendencies by similarity with the progress of the learning tendencies by similarity of learners with similar academic ability. For example, the learner can check the progress of their learning tendencies, such as answer time and number of characters in answers, on a learning trend screen that includes a graph. Furthermore, the server 10 can provide the learner with advice on their learning strategy depending on any discrepancies in the progress.

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

(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 the 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.

This allows teachers to easily visually confirm each student's learning trends by viewing the learning trend screen including graph 88. Furthermore, the advice 72 displayed on the second learning trend screen shown in FIG. 12 is automatically created based on the results of the learning trend comparison and comments extracted from comment DB 44, but advice 72 may also be entered directly by a teacher viewing graph 88, for example.

Furthermore, by viewing the learning trend screen including 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, server 10 updates graph 88 and creates a new graph so that the trend of the subject's values is output on graph 88. This makes it possible to display the trend of the subject student and the trend of many other students on the new graph 88.

(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.

As an example, the server 10 first calculates the features 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.

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

(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 that has 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).

Figure 17 shows an example configuration of a learning support system 200 in this case. As shown, the learning support system 200 is configured to enable communication between a teacher terminal 75 and multiple student terminals 20 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 subdivided 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 by 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.

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.

First, the functional configuration of the server in the second embodiment will be described. Figure 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, similar academic ability group identification unit 56, and subject average value calculation unit 64 will be described in detail.

The input information acquisition unit 53 acquires input information from the student terminal 20, including the student ID and information regarding the specified learning elements and difficulty level entered by the student. When a student wants to check their own learning trends, they use the student terminal 20 to set the specified learning elements and difficulty level and send 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 the target of the learning trend screen. Note that in the second embodiment, since the input information includes information regarding the learning elements and difficulty level, the learning element identification unit 54 of the first embodiment is not necessary.

The similar academic ability group identification unit 56 identifies the 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.

The subject average value calculation unit 64 first references the question DB 42 and extracts the learning elements and questions of difficulty contained in the input information. The subject average value calculation unit 64 then calculates the subject average value based on the answer information of the subject corresponding to the extracted questions. Specifically, the subject average value 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 value.

Next, the learning trend screen in the second embodiment will be described. Figure 19 is an example of a first learning trend screen in the second embodiment. Figure 20 is an example of a second learning trend screen in the second embodiment. For the sake of simplicity, explanations similar to those in the first embodiment will be omitted, and only the learning element item 65, difficulty level item 66, question selection item 67, answer item 93x, correct/incorrect item 94x, answer time item 95x, and answer character count item 96x will be described in detail.

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 difficulty level item 66 are items that display the specific learning element and difficulty level for which the student wishes to check the learning trend, respectively. As in the first embodiment, a student can use the student device 20 to perform a specific operation to display a learning trend screen that does not display graphs, etc., and set the specific learning element and difficulty level in the learning element item 65 and 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.

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.

The position identification unit 61 of the graph creation unit 57 may identify the subject's position on the first graph of 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 calculation unit 64, or based on the answer time and number of characters of the question selected in the question selection item 67. The graph creation 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 level set by the student.

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 that the transition of the identified values is output as the transition of the subject's values. In this way, the server 10x in the second embodiment creates a second learning trend screen such as that shown in FIG. 20 based on input information including information on the learning elements and difficulty level set by the student.

5 Network 10, 10x Server 20 Student terminal 30, 75 Teacher terminal 41, 76 Learning element DB
42, 77 Problem DB
43, 78 Learning history DB
44, 79 Comment DB
45 Similarity calculation unit 46 Similar question group classification unit 47 Analysis unit 51 Academic ability determination unit 52 Similar academic ability group classification unit 53 Input information acquisition unit 54 Learning element identification unit 55 Extraction unit 56 Similar academic ability group identification unit 57 Graph creation unit 100, 200 Learning support system

Claims (8)

An information processing device communicably connected to a terminal device used by a target person who is 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: 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. 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. 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. 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. 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. 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. A program executed by an information processing device having a computer , which is communicably connected to a terminal device used by a target person who is a specific learner ,
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